pandas

July 28, 2024

0.0.1 What is Pandas

Pandas is a fast, powerful, flexible and easy to use open source data analysis and manipulation
tool, built on top of the Python programming language.
https://pandas.pydata.org/about/index.html

0.1 Importing Pandas

[29]: import pandas as pd
import numpy as np

0.2 Pandas Series

A Pandas Series is like a column in a table. It is a 1-D array holding data of any type. Since we did
not specify an index for the data, a default one consisting of the integers 0 through N - 1 (where N
is the length of the data) is created.

0.2.1 Series from lists

[30]: # string datatype
countries = ['India', 'Nepal', 'Bhutan', 'Russia']

c = pd.Series(countries)
c

[30]: 0 India
1 Nepal
2 Bhutan
3 Russia
dtype: object

[31]: # numeric datatype

runs = [87, 69, 92, 79, 84]

runs_ser = pd.Series(runs)
runs_ser

1
[31]: 0 87
1 69
2 92
3 79
4 84
dtype: int64

ser.array returns numpy array containing all the values.

[32]: runs_ser.array

[32]: <NumpyExtensionArray>
[87, 69, 92, 79, 84]
Length: 5, dtype: int64

[33]: runs_ser.index

[33]: RangeIndex(start=0, stop=5, step=1)

0.2.2 Series with custom indexing

• We can create series with custom indexing but the size should be equal.
[34]: marks = [89, 78, 93, 91]
subjcets = ['maths', 'english', 'science', 'hindi']

marks_subjects = pd.Series(marks, index=subjcets)

marks_subjects

[34]: maths 89
english 78
science 93
hindi 91
dtype: int64

0.2.3 Naming the Series

[35]: # Dictionary
marks_dict = {
'maths':84,
'english':57,
'science':89,
'hindi':97
}

marks = pd.Series(marks_dict, name='Dilkhush\'s marks')

marks

2
[35]: maths 84
english 57
science 89
hindi 97
Name: Dilkhush's marks, dtype: int64

0.3 Series Attributes

0.3.1 ser.size
• returns total number of non-Nan values in the series.
[36]: marks

[36]: maths 84
english 57
science 89
hindi 97
Name: Dilkhush's marks, dtype: int64

[37]: marks.size

[37]: 4

0.3.2 ser.dtype
• returns the datatype of series
• datatype of series can be altered during creation.
[38]: marks.dtype

[38]: dtype('int64')

[39]: marks = pd.Series(marks_dict, name='Dilkhush\'s Marks', dtype=int)

[40]: marks.dtype

[40]: dtype('int32')

[41]: temp = pd.Series([1, 2, "Hello", 4.3])

[42]: temp.dtype

[42]: dtype('O')

[43]: print(type(temp[0]))
print(type(temp[1]))
print(type(temp[2]))

3
 print(type(temp[3]))

<class 'int'>
<class 'int'>
<class 'str'>
<class 'float'>
Note - NumPy Array contains values of one data type but Pandas series can contain values of
different datatypes.

0.3.3 ser.name
• returns name of series
[44]: marks.name

[44]: "Dilkhush's Marks"

[45]: temp.name

0.3.4 ser.index
• if the name of the index follows the python rules for variable naming then we can extract the
values using ser.index
[46]: marks_subjects

[46]: maths 89
english 78
science 93
hindi 91
dtype: int64

[47]: marks_subjects.maths

[47]: 89

0.3.5 ser.index
• return Index object containing indices of series in case of indexes are strings,
• if indices are numbers, RangeIndex is returned
[48]: marks.index

[48]: Index(['maths', 'english', 'science', 'hindi'], dtype='object')

[49]: temp.index

[49]: RangeIndex(start=0, stop=4, step=1)

4
 0.3.6 ser.values
• returns ndarray containing values
[50]: marks.values

[50]: array([84, 57, 89, 97])

0.4 Reading Data

• We can read data using pandas inbuilt function, read_csv()
• read_csv() by default create DataFrame object, we can transform it into Series using squeeze
function
Text and binary data loading functions in pandas | Function | Description | |——————|—
——————————————————————————————————| | read_csv | Load
delimited data from a file, URL, or file-like object; use comma as default delimiter | | read_fwf
| Read data in fixed-width column format (i.e., no delimiters) | | read_clipboard | Variation of
read_csv that reads data from the clipboard; useful for converting tables from web pages | |
read_excel | Read tabular data from an Excel XLS or XLSX file | | read_hdf | Read HDF5 files
written by pandas | | read_html | Read all tables found in the given HTML document | | read_json
| Read data from a JSON (JavaScript Object Notation) string representation, file, URL, or file-like
object | | read_feather | Read the Feather binary file format | | read_orc | Read the Apache ORC
binary file format | | read_parquet | Read the Apache Parquet binary file format | | read_pickle |
Read an object stored by pandas using the Python pickle format | | read_sas | Read a SAS dataset
stored in one of the SAS system’s custom storage formats | | read_spss | Read a data file created
by SPSS | | read_sql | Read the results of a SQL query (using SQLAlchemy) | | read_sql_table |
Read a whole SQL table (using SQLAlchemy); equivalent to using a query that selects everything
in that table using read_sql | | read_stata | Read a dataset from Stata file format | | read_xml |
Read a table of data from an XML file |

[51]: subs = pd.read_csv('subs.csv')

type(subs)

[51]: pandas.core.frame.DataFrame

Note - pd.read_csv() directly reads the data into DataFrame but on that squeeze() function can
be used to convert to Series
[52]: subs = subs.squeeze()

[53]: type(subs)

[53]: pandas.core.series.Series

[54]: subs

[54]: 0 48
1 57

5
 2 40
3 43
4 44
…
360 231
361 226
362 155
363 144
364 172
Name: Subscribers gained, Length: 365, dtype: int64

[55]: vk = pd.read_csv('kohli_ipl.csv', index_col='match_no', dtype=int)

vk = vk.squeeze()
vk

[55]: match_no
1 1
2 23
3 13
4 12
5 1
..
211 0
212 20
213 73
214 25
215 7
Name: runs, Length: 215, dtype: int32

[56]: movies = pd.read_csv('bollywood.csv', index_col='movie')

movies = movies.squeeze()
movies

[56]: movie
Uri: The Surgical Strike Vicky Kaushal
Battalion 609 Vicky Ahuja
The Accidental Prime Minister (film) Anupam Kher
Why Cheat India Emraan Hashmi
Evening Shadows Mona Ambegaonkar
…
Hum Tumhare Hain Sanam Shah Rukh Khan
Aankhen (2002 film) Amitabh Bachchan
Saathiya (film) Vivek Oberoi
Company (film) Ajay Devgn
Awara Paagal Deewana Akshay Kumar
Name: lead, Length: 1500, dtype: object

6
 0.5 Series Methods
0.5.1 ser.head(n) or ser.tail(n)
• Return top or bottom n values from the series
• if n is not provided then by default n is 5
[57]: subs.head()

[57]: 0 48
1 57
2 40
3 43
4 44
Name: Subscribers gained, dtype: int64

[58]: vk.head(3)

[58]: match_no
1 1
2 23
3 13
Name: runs, dtype: int32

[59]: movies.tail(4)

[59]: movie
Aankhen (2002 film) Amitabh Bachchan
Saathiya (film) Vivek Oberoi
Company (film) Ajay Devgn
Awara Paagal Deewana Akshay Kumar
Name: lead, dtype: object

0.5.2 ser.sample(n)
• returns randomly sampled n values.
• by default n is 1
[60]: movies.sample()

[60]: movie
Dhadak Ishaan Khattar
Name: lead, dtype: object

[61]: movies.sample(3)

[61]: movie
Mad About Dance Saahil Prem
Hotel Salvation Adil Hussain

7
 Why Cheat India Emraan Hashmi
Name: lead, dtype: object

0.5.3 ser.value_counts()
• returns series of count of values
[62]: movies.value_counts()

[62]: lead
Akshay Kumar 48
Amitabh Bachchan 45
Ajay Devgn 38
Salman Khan 31
Sanjay Dutt 26
..
Diganth 1
Parveen Kaur 1
Seema Azmi 1
Akanksha Puri 1
Edwin Fernandes 1
Name: count, Length: 566, dtype: int64

[63]: vk.value_counts()

[63]: runs
0 9
1 8
12 8
9 7
35 6
..
36 1
45 1
71 1
37 1
53 1
Name: count, Length: 78, dtype: int64

0.5.4 ser.sort_values(ascending = True, inplace = False)

• return sorted array on the basis of values.
• no change into original series.
• by default sort in ascencing order
• inplace is used to make permanent changes into original series
[64]: vk.sort_values(ascending=False)

8
[64]: match_no
128 113
126 109
123 108
164 100
120 100
…
93 0
211 0
130 0
8 0
135 0
Name: runs, Length: 215, dtype: int32

[65]: movies.sort_values() # Alphabetically in case of string

[65]: movie
Qaidi Band Aadar Jain
Roar: Tigers of the Sundarbans Aadil Chahal
Lipstick Under My Burkha Aahana Kumra
Raat Gayi Baat Gayi? Aamir Bashir
Talaash: The Answer Lies Within Aamir Khan
…
Dil Toh Deewana Hai Zeenat Aman
Sallu Ki Shaadi Zeenat Aman
Strings of Passion Zeenat Aman
Dunno Y… Na Jaane Kyon Zeenat Aman
Taj Mahal: An Eternal Love Story Zulfi Sayed
Name: lead, Length: 1500, dtype: object

0.5.5 ser.sort_index(ascending = True, inplace = False)

• works same as sort_values() but on index
• inplace parameter is used for making permanent changes into series
[66]: movies.sort_index()

[66]: movie
1920 (film) Rajniesh Duggall
1920: London Sharman Joshi
1920: The Evil Returns Vicky Ahuja
1971 (2007 film) Manoj Bajpayee
2 States (2014 film) Arjun Kapoor
…
Zindagi 50-50 Veena Malik
Zindagi Na Milegi Dobara Hrithik Roshan
Zindagi Tere Naam Mithun Chakraborty

9
 Zokkomon Darsheel Safary
Zor Lagaa Ke…Haiya! Meghan Jadhav
Name: lead, Length: 1500, dtype: object

0.6 Mathematical Operations on Series

0.6.1 ser.count()
Note - count - only count all the values excluding missing values while size counts all
[67]: vk.count() # total matches played by vk

[67]: 215

0.6.2 ser.sum()
• sum of all elements of series
[68]: subs.sum() # total subscriber gained in last 365 days

[68]: 49510

0.6.3 ser.product()
• product of all elements of the series
[69]: vk.prod()

[69]: 0

[70]: vk.product()

[70]: 0

0.6.4 ser.mean()/median()/mode()/std()/var()
• apply stastical operations on series
[71]: subs.mean() # average subscribers gain every day

[71]: 135.64383561643837

[72]: vk.median() # median score

[72]: 24.0

[73]: movies.mode() # frequent lead in movies

10
[73]: 0 Akshay Kumar
Name: lead, dtype: object

[74]: subs.std()

[74]: 62.6750230372527

[75]: vk.var()

[75]: 688.0024777222343

0.6.5 ser.min()/max()
• returns minimum or maximum element from the series
[76]: subs.max()

[76]: 396

[77]: vk.min()

[77]: 0

0.6.6 ser.describe()
• return series containing count, mean, std, min, 25%, 50%, 75% and max
[78]: subs.describe()

[78]: count 365.000000

mean 135.643836
std 62.675023
min 33.000000
25% 88.000000
50% 123.000000
75% 177.000000
max 396.000000
Name: Subscribers gained, dtype: float64

0.7 Indexing
• Values can be fetched using positional indexing or keyword indexing.
• Negative indexing only works if data type of index is string(object)

[79]: x = pd.Series([12,13,14,35,46,57,58,79,9])
x

11
[79]: 0 12
1 13
2 14
3 35
4 46
5 57
6 58
7 79
8 9
dtype: int64

[80]: x[0]

[80]: 12

[81]: x[-1]

---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
File c:\Program Files\Python312\Lib\site-packages\pandas\core\indexes\range.py:
↪413, in RangeIndex.get_loc(self, key)

412 try:
--> 413 return self._range.index(new_key)
414 except ValueError as err:

ValueError: -1 is not in range

The above exception was the direct cause of the following exception:

KeyError Traceback (most recent call last)

Cell In[81], line 1
----> 1 x[-1]

File c:\Program Files\Python312\Lib\site-packages\pandas\core\series.py:1111, in␣

↪Series.__getitem__(self, key)

1108 return self._values[key]

1110 elif key_is_scalar:
-> 1111 return self._get_value(key)
1113 # Convert generator to list before going through hashable part
1114 # (We will iterate through the generator there to check for slices)
1115 if is_iterator(key):

File c:\Program Files\Python312\Lib\site-packages\pandas\core\series.py:1227, in␣

↪Series._get_value(self, label, takeable)

1224 return self._values[label]

1226 # Similar to Index.get_value, but we do not fall back to positional
-> 1227 loc = self.index.get_loc(label)

12
 1229 if is_integer(loc):
1230 return self._values[loc]

File c:\Program Files\Python312\Lib\site-packages\pandas\core\indexes\range.py:

↪415, in RangeIndex.get_loc(self, key)

413 return self._range.index(new_key)

414 except ValueError as err:
--> 415 raise KeyError(key) from err
416 if isinstance(key, Hashable):
417 raise KeyError(key)

KeyError: -1

[ ]: movies

[ ]: movie
Uri: The Surgical Strike Vicky Kaushal
Battalion 609 Vicky Ahuja
The Accidental Prime Minister (film) Anupam Kher
Why Cheat India Emraan Hashmi
Evening Shadows Mona Ambegaonkar
…
Hum Tumhare Hain Sanam Shah Rukh Khan
Aankhen (2002 film) Amitabh Bachchan
Saathiya (film) Vivek Oberoi
Company (film) Ajay Devgn
Awara Paagal Deewana Akshay Kumar
Name: lead, Length: 1500, dtype: object

[ ]: movies.iloc[-1]

[ ]: 'Akshay Kumar'

[ ]: movies['Awara Paagal Deewana']

[ ]: 'Akshay Kumar'

0.7.1 Fancy Indexing

[ ]: vk[[1,3,4,5]] # Scores of 1st, 3rd, 4th and 5th matches

[ ]: match_no
1 1
3 13
4 12
5 1

13
 Name: runs, dtype: int32

0.8 Slicing
• negative indexing can be used for slicing
[ ]: vk[5:16]

[ ]: match_no
6 9
7 34
8 0
9 21
10 3
11 10
12 38
13 3
14 11
15 50
16 2
Name: runs, dtype: int32

[ ]: vk[-5:]

[ ]: match_no
211 0
212 20
213 73
214 25
215 7
Name: runs, dtype: int32

[ ]: movies[::2] # Alternet movies

[ ]: movie
Uri: The Surgical Strike Vicky Kaushal
The Accidental Prime Minister (film) Anupam Kher
Evening Shadows Mona Ambegaonkar
Fraud Saiyaan Arshad Warsi
Manikarnika: The Queen of Jhansi Kangana Ranaut
…
Raaz (2002 film) Dino Morea
Waisa Bhi Hota Hai Part II Arshad Warsi
Kaante Amitabh Bachchan
Aankhen (2002 film) Amitabh Bachchan
Company (film) Ajay Devgn
Name: lead, Length: 750, dtype: object

14
 0.9 Editing Series
[ ]: marks

[ ]: maths 84
english 57
science 89
hindi 97
Name: Dilkhush's Marks, dtype: int32

[ ]: marks.iloc[1] = 100

[ ]: marks

[ ]: maths 84
english 100
science 89
hindi 97
Name: Dilkhush's Marks, dtype: int32

[ ]: # What if an index does not exist

marks['sst'] = 87

[ ]: marks

[ ]: maths 84
english 100
science 89
hindi 97
sst 87
Name: Dilkhush's Marks, dtype: int32

[ ]: # Slicing
runs_ser

[ ]: 0 87
1 69
2 92
3 79
4 84
dtype: int64

[ ]: runs_ser[2:4] = 100

[ ]: runs_ser

15
[ ]: 0 87
1 69
2 100
3 100
4 84
dtype: int64

[ ]: # Fancy indexing
runs_ser[[0, 3, 4]] = 50
runs_ser

[ ]: 0 50
1 69
2 100
3 50
4 50
dtype: int64

[ ]: runs_ser[[0, 3, 4]] = [0, 25, 40]

runs_ser

[ ]: 0 0
1 69
2 100
3 25
4 40
dtype: int64

[ ]: # using index label

movies

[ ]: movie
Uri: The Surgical Strike Vicky Kaushal
Battalion 609 Vicky Ahuja
The Accidental Prime Minister (film) Anupam Kher
Why Cheat India Emraan Hashmi
Evening Shadows Mona Ambegaonkar
…
Hum Tumhare Hain Sanam Shah Rukh Khan
Aankhen (2002 film) Amitabh Bachchan
Saathiya (film) Vivek Oberoi
Company (film) Ajay Devgn
Awara Paagal Deewana Akshay Kumar
Name: lead, Length: 1500, dtype: object

[ ]: movies['2 States (2014 film)'] = 'Alia Bhatt'

movies

16
[ ]: movie
Uri: The Surgical Strike Vicky Kaushal
Battalion 609 Vicky Ahuja
The Accidental Prime Minister (film) Anupam Kher
Why Cheat India Emraan Hashmi
Evening Shadows Mona Ambegaonkar
…
Hum Tumhare Hain Sanam Shah Rukh Khan
Aankhen (2002 film) Amitabh Bachchan
Saathiya (film) Vivek Oberoi
Company (film) Ajay Devgn
Awara Paagal Deewana Akshay Kumar
Name: lead, Length: 1500, dtype: object

0.10 Python functionalities on Series objects

[ ]: # len/type/dir/sorted/max/min

len(subs)

[ ]: 365

[ ]: type(subs)

[ ]: pandas.core.series.Series

[ ]: dir(vk)

[ ]: ['T',
'_AXIS_LEN',
'_AXIS_ORDERS',
'_AXIS_TO_AXIS_NUMBER',
'_HANDLED_TYPES',
'__abs__',
'__add__',
'__and__',
'__annotations__',
'__array__',
'__array_priority__',
'__array_ufunc__',
'__bool__',
'__class__',
'__column_consortium_standard__',
'__contains__',
'__copy__',
'__deepcopy__',
'__delattr__',

17
'__delitem__',
'__dict__',
'__dir__',
'__divmod__',
'__doc__',
'__eq__',
'__finalize__',
'__float__',
'__floordiv__',
'__format__',
'__ge__',
'__getattr__',
'__getattribute__',
'__getitem__',
'__getstate__',
'__gt__',
'__hash__',
'__iadd__',
'__iand__',
'__ifloordiv__',
'__imod__',
'__imul__',
'__init__',
'__init_subclass__',
'__int__',
'__invert__',
'__ior__',
'__ipow__',
'__isub__',
'__iter__',
'__itruediv__',
'__ixor__',
'__le__',
'__len__',
'__lt__',
'__matmul__',
'__mod__',
'__module__',
'__mul__',
'__ne__',
'__neg__',
'__new__',
'__nonzero__',
'__or__',
'__pandas_priority__',
'__pos__',
'__pow__',

18
'__radd__',
'__rand__',
'__rdivmod__',
'__reduce__',
'__reduce_ex__',
'__repr__',
'__rfloordiv__',
'__rmatmul__',
'__rmod__',
'__rmul__',
'__ror__',
'__round__',
'__rpow__',
'__rsub__',
'__rtruediv__',
'__rxor__',
'__setattr__',
'__setitem__',
'__setstate__',
'__sizeof__',
'__str__',
'__sub__',
'__subclasshook__',
'__truediv__',
'__weakref__',
'__xor__',
'_accessors',
'_accum_func',
'_agg_examples_doc',
'_agg_see_also_doc',
'_align_for_op',
'_align_frame',
'_align_series',
'_append',
'_arith_method',
'_as_manager',
'_attrs',
'_binop',
'_cacher',
'_can_hold_na',
'_check_inplace_and_allows_duplicate_labels',
'_check_is_chained_assignment_possible',
'_check_label_or_level_ambiguity',
'_check_setitem_copy',
'_clear_item_cache',
'_clip_with_one_bound',
'_clip_with_scalar',

19
'_cmp_method',
'_consolidate',
'_consolidate_inplace',
'_construct_axes_dict',
'_construct_result',
'_constructor',
'_constructor_expanddim',
'_constructor_expanddim_from_mgr',
'_constructor_from_mgr',
'_data',
'_deprecate_downcast',
'_dir_additions',
'_dir_deletions',
'_drop_axis',
'_drop_labels_or_levels',
'_duplicated',
'_expanddim_from_mgr',
'_find_valid_index',
'_flags',
'_flex_method',
'_from_mgr',
'_get_axis',
'_get_axis_name',
'_get_axis_number',
'_get_axis_resolvers',
'_get_block_manager_axis',
'_get_bool_data',
'_get_cacher',
'_get_cleaned_column_resolvers',
'_get_index_resolvers',
'_get_label_or_level_values',
'_get_numeric_data',
'_get_rows_with_mask',
'_get_value',
'_get_values_tuple',
'_get_with',
'_getitem_slice',
'_gotitem',
'_hidden_attrs',
'_indexed_same',
'_info_axis',
'_info_axis_name',
'_info_axis_number',
'_init_dict',
'_init_mgr',
'_inplace_method',
'_internal_names',

20
'_internal_names_set',
'_is_cached',
'_is_copy',
'_is_label_or_level_reference',
'_is_label_reference',
'_is_level_reference',
'_is_mixed_type',
'_is_view',
'_is_view_after_cow_rules',
'_item_cache',
'_ixs',
'_logical_func',
'_logical_method',
'_map_values',
'_maybe_update_cacher',
'_memory_usage',
'_metadata',
'_mgr',
'_min_count_stat_function',
'_name',
'_needs_reindex_multi',
'_pad_or_backfill',
'_protect_consolidate',
'_reduce',
'_references',
'_reindex_axes',
'_reindex_indexer',
'_reindex_multi',
'_reindex_with_indexers',
'_rename',
'_replace_single',
'_repr_data_resource_',
'_repr_latex_',
'_reset_cache',
'_reset_cacher',
'_set_as_cached',
'_set_axis',
'_set_axis_name',
'_set_axis_nocheck',
'_set_is_copy',
'_set_labels',
'_set_name',
'_set_value',
'_set_values',
'_set_with',
'_set_with_engine',
'_shift_with_freq',

21
'_slice',
'_stat_function',
'_stat_function_ddof',
'_take_with_is_copy',
'_to_latex_via_styler',
'_typ',
'_update_inplace',
'_validate_dtype',
'_values',
'_where',
'abs',
'add',
'add_prefix',
'add_suffix',
'agg',
'aggregate',
'align',
'all',
'any',
'apply',
'argmax',
'argmin',
'argsort',
'array',
'asfreq',
'asof',
'astype',
'at',
'at_time',
'attrs',
'autocorr',
'axes',
'backfill',
'between',
'between_time',
'bfill',
'bool',
'case_when',
'clip',
'combine',
'combine_first',
'compare',
'convert_dtypes',
'copy',
'corr',
'count',
'cov',

22
'cummax',
'cummin',
'cumprod',
'cumsum',
'describe',
'diff',
'div',
'divide',
'divmod',
'dot',
'drop',
'drop_duplicates',
'droplevel',
'dropna',
'dtype',
'dtypes',
'duplicated',
'empty',
'eq',
'equals',
'ewm',
'expanding',
'explode',
'factorize',
'ffill',
'fillna',
'filter',
'first',
'first_valid_index',
'flags',
'floordiv',
'ge',
'get',
'groupby',
'gt',
'hasnans',
'head',
'hist',
'iat',
'idxmax',
'idxmin',
'iloc',
'index',
'infer_objects',
'info',
'interpolate',
'is_monotonic_decreasing',

23
'is_monotonic_increasing',
'is_unique',
'isin',
'isna',
'isnull',
'item',
'items',
'keys',
'kurt',
'kurtosis',
'last',
'last_valid_index',
'le',
'list',
'loc',
'lt',
'map',
'mask',
'max',
'mean',
'median',
'memory_usage',
'min',
'mod',
'mode',
'mul',
'multiply',
'name',
'nbytes',
'ndim',
'ne',
'nlargest',
'notna',
'notnull',
'nsmallest',
'nunique',
'pad',
'pct_change',
'pipe',
'plot',
'pop',
'pow',
'prod',
'product',
'quantile',
'radd',
'rank',

24
'ravel',
'rdiv',
'rdivmod',
'reindex',
'reindex_like',
'rename',
'rename_axis',
'reorder_levels',
'repeat',
'replace',
'resample',
'reset_index',
'rfloordiv',
'rmod',
'rmul',
'rolling',
'round',
'rpow',
'rsub',
'rtruediv',
'sample',
'searchsorted',
'sem',
'set_axis',
'set_flags',
'shape',
'shift',
'size',
'skew',
'sort_index',
'sort_values',
'squeeze',
'std',
'struct',
'sub',
'subtract',
'sum',
'swapaxes',
'swaplevel',
'tail',
'take',
'to_clipboard',
'to_csv',
'to_dict',
'to_excel',
'to_frame',
'to_hdf',

25
 'to_json',
'to_latex',
'to_list',
'to_markdown',
'to_numpy',
'to_period',
'to_pickle',
'to_sql',
'to_string',
'to_timestamp',
'to_xarray',
'transform',
'transpose',
'truediv',
'truncate',
'tz_convert',
'tz_localize',
'unique',
'unstack',
'update',
'value_counts',
'values',
'var',
'view',
'where',
'xs']

[ ]: sorted(subs)

[ ]: [33,
33,
35,
37,
39,
40,
40,
40,
40,
42,
42,
43,
44,
44,
44,
45,
46,
46,

26
48,
49,
49,
49,
49,
50,
50,
50,
51,
54,
56,
56,
56,
56,
57,
61,
62,
64,
65,
65,
66,
66,
66,
66,
67,
68,
70,
70,
70,
71,
71,
72,
72,
72,
72,
72,
73,
74,
74,
75,
76,
76,
76,
76,
77,
77,
78,

27
78,
78,
79,
79,
80,
80,
80,
81,
81,
82,
82,
83,
83,
83,
84,
84,
84,
85,
86,
86,
86,
87,
87,
87,
87,
88,
88,
88,
88,
88,
89,
89,
89,
90,
90,
90,
90,
91,
92,
92,
92,
93,
93,
93,
93,
95,
95,

28
96,
96,
96,
96,
97,
97,
98,
98,
99,
99,
100,
100,
100,
101,
101,
101,
102,
102,
103,
103,
104,
104,
104,
105,
105,
105,
105,
105,
105,
105,
105,
105,
108,
108,
108,
108,
108,
108,
109,
109,
110,
110,
110,
111,
111,
112,
113,

29
113,
113,
114,
114,
114,
114,
115,
115,
115,
115,
117,
117,
117,
118,
118,
119,
119,
119,
119,
120,
122,
123,
123,
123,
123,
123,
124,
125,
126,
127,
128,
128,
129,
130,
131,
131,
132,
132,
134,
134,
134,
135,
135,
136,
136,
136,
137,

30
138,
138,
138,
139,
140,
144,
145,
146,
146,
146,
146,
147,
149,
150,
150,
150,
150,
151,
152,
152,
152,
153,
153,
153,
154,
154,
154,
155,
155,
156,
156,
156,
156,
157,
157,
157,
157,
158,
158,
159,
159,
160,
160,
160,
160,
162,
164,

31
166,
167,
167,
168,
170,
170,
170,
170,
171,
172,
172,
173,
173,
173,
174,
174,
175,
175,
176,
176,
177,
178,
179,
179,
180,
180,
180,
182,
183,
183,
183,
184,
184,
184,
185,
185,
185,
185,
186,
186,
186,
188,
189,
190,
190,
192,
192,

32
192,
196,
196,
196,
197,
197,
202,
202,
202,
203,
204,
206,
207,
209,
210,
210,
211,
212,
213,
214,
216,
219,
220,
221,
221,
222,
222,
224,
225,
225,
226,
227,
228,
229,
230,
231,
233,
236,
236,
237,
241,
243,
244,
245,
247,
249,
254,

33
 254,
258,
259,
259,
261,
261,
265,
267,
268,
269,
276,
276,
290,
295,
301,
306,
312,
396]

[ ]: min(subs)

[ ]: 33

[ ]: max(subs)

[ ]: 396

[ ]: # type conversion
list(marks)

[ ]: [84, 100, 89, 97, 87]

[ ]: dict(marks)

[ ]: {'maths': 84, 'english': 100, 'science': 89, 'hindi': 97, 'sst': 87}

[ ]: # membership operator

'2 States (2014 film)' in movies # checks index values

[ ]: True

[ ]: 'Alia Bhatt' in movies.values

[ ]: True

34
[ ]: # Looping
for i in movies: # returns values
print(i)

Vicky Kaushal
Vicky Ahuja
Anupam Kher
Emraan Hashmi
Mona Ambegaonkar
Geetika Vidya Ohlyan
Arshad Warsi
Radhika Apte
Kangana Ranaut
Nawazuddin Siddiqui
Ali Asgar
Ranveer Singh
Prit Kamani
Ajay Devgn
Sushant Singh Rajput
Amitabh Bachchan
Abhimanyu Dasani
Talha Arshad Reshi
Nawazuddin Siddiqui
Garima Agarwal
Rasika Agashe
Barun Sobti
Akshay Kumar
Zaheer Iqbal
Vidyut Jammwal
Deepika Amin
Manav Kaul
Naseeruddin Shah
Varun Dhawan
Shreyas Talpade
Tiger Shroff
Boman Irani
Ajay Devgn
Arjun Kapoor
Gavie Chahal
Prabhu Deva
Shahid Kapoor
Ayushmann Khurrana
Anupam Kher
Karanvir Bohra
Hrithik Roshan
Jimmy Sheirgill
John Abraham

35
Rishi Kapoor
Kangana Ranaut
Natalia Janoszek
Diljit Dosanjh
Sidharth Malhotra
Rajeev Khandelwal
Zaira Wasim
Akshay Kumar
Jacqueline Fernandez
Ayushmann Khurrana
Akshaye Khanna
Sonam Kapoor
Karan Deol
Sanjay Dutt
Bhavesh Kumar
Sanaya Irani
Ayushmann Khurrana
Siddhanth Kapoor
Akshay Kumar
Taapsee Pannu
Rajkummar Rao
Sunny Singh Nijjar
Neil Nitin Mukesh
Suraj Pancholi
Boman Irani
Riteish Deshmukh
Nawazuddin Siddiqui
Shahbaaz Khan
Kriti Kharbanda
Naseeruddin Shah
Vardhan Puri
Sushant Singh Rajput
Kartik Aaryan
Vidyut Jammwal
Rani Mukerji
Salman Khan
Akshay Kumar
Saif Ali Khan
Kay Kay Menon
Nora Fatehi
Ashmit Patel
Viineet Kumar
Rahul Bhat
Vicky Kaushal
Sidharth Malhotra
Deepika Padukone
Geetanjali Thapa
Akshay Anand

36
Pulkit Samrat
Kartik Aaryan
Lee Byford
Taapsee Pannu
Aisha Ahmed
Ajay Devgn
Rani Mukerji
Manoj Bajpayee
Tiger Shroff
Varun Dhawan
Prabhu Deva
Ishaan Khattar
Abhay Deol
Yogesh Raj Mishra
Rajkummar Rao
Alia Bhatt
Naseeruddin Shah
Sumeet Vyas
Vinay Pathak
John Abraham
Danny Denzongpa
Harshvardhan Kapoor
Jimmy Sheirgill
Anil Kapoor
Ishaan Khattar
Ranbir Kapoor
Sanjay Dutt
Dharmesh Yelande
Taapsee Pannu
Arjun Mathur
Irrfan Khan
Akshay Kumar
John Abraham
Sonakshi Sinha
Utkarsh Sharma
Dharmendra
Rajkummar Rao
Jackie Shroff
Avinash Tiwary
Manoj Bajpayee
Paoli Dam
Sanya Malhotra
Shahid Kapoor
Abhishek Bharate
Nawazuddin Siddiqui
Manish Anand
Taapsee Pannu
Jackky Bhagnani

37
Anushka Sharma
Radhika Apte
Rhea Chakraborty
Govinda
Sohum Shah
Kajol
Arjun Kapoor
Ayushmann Khurrana
Ayushmann Khurrana
Nargis Fakhri
Aishwarya Devan
Neil Nitin Mukesh
Shakti Kapoor
Amit Sadh
Sunny Deol
Rahul Bagga
Sunny Deol
Amyra Dastur
Shah Rukh Khan
Ranveer Singh
Salman Khan
Ajay Devgn
Varun Dhawan
Shraddha Kapoor
Sunil Grover
Hrithik Roshan
Raj Arjun
Aamir Khan
Gurmeet Ram Rahim Singh
Arsh Bajwa
Rana Daggubati
Naseeruddin Shah
Kangana Ranaut
Nana Patekar
Arbaaz Khan
Varun Dhawan
Rajkummar Rao
Govinda
Rajat Kapoor
Anushka Sharma
Kiara Advani
Shaurya Singh
Pankaj Tripathi
Taapsee Pannu
Adil Hussain
Amitabh Bachchan
Sunny Leone
Hema Malini

38
Raveena Tandon
Amitabh Bachchan
Amardeep Insan
Shraddha Kapoor
Ayushmann Khurrana
Sachin Tendulkar
Irrfan Khan
Himansh Kohli
Adil Hussain
Jayesh Raj
Manisha Koirala
Deepika Padukone
Rajkummar Rao
Salman Khan
Riteish Deshmukh
Shiv Darshan
Ranbir Kapoor
Ashish Bisht
Aahana Kumra
Manoj Babani
Rajveer Ankur Singh
Kirti Kulhari
Shah Rukh Khan
Tiger Shroff
Akshay Kumar
Anil Kapoor
Kartik Aaryan
Ayushmann Khurrana
Nawazuddin Siddiqui
Prisha Aneja
Aadar Jain
Ayushmann Khurrana
Kunal Kapoor
Arjun Rampal
Kangana Ranaut
Farhan Akhtar
Sidharth Malhotra
Hugh Bonneville
Rishi Kapoor
Rajkummar Rao
Kunaal Roy Kapur
Sunny Leone
Shraddha Kapoor
Rina Charaniya
Nawazuddin Siddiqui
Sunny Deol
Sridevi
Saif Ali Khan

39
Soundarya Sharma
Sudha Chandran
Manoj Bajpayee
Zaira Wasim
Prakash Belawadi
Kalki Koechlin
Rajkummar Rao
Richa Chadha
Irrfan Khan
Zareen Khan
Nayna Bandhopadhyay
Vidya Balan
Nishikant Kamat
Sanjay Mishra
Kapil Sharma
Pulkit Samrat
Vijay Varma
Sushama Deshpande
Richa Chadha
Prince Shah
Tanima Bhattacharya
Akshay Kumar
Zeenat Aman
Madhavan
Tusshar Kapoor
Tusshar Kapoor
Himansh Kohli
Sadhana Singh
Sunny Deol
Aditya Roy Kapoor
Rishi Kapoor
Rajniesh Duggall
Krishna Chaturvedi
Girish Taurani
Sonam Kapoor
Sukhesh Arora
Raima Sen
Anuj Sachdeva
Parthaa Akerkar
Priyanka Chopra
Sidharth Malhotra
John Abraham
Patralekhaa Paul
Shah Rukh Khan
Swara Bhaskar
Randeep Hooda
Shraddha Kapoor
Pankaj Tripathi

40
Jimmy Sheirgill
Kartik Elangovan
Boman Irani
Manoj Bajpayee
Sharman Joshi
Emraan Hashmi
Aanchal Dwivedi
Sanjay Singh
Arvind Swamy
Radhika Apte
Randeep Hooda
Sachiin Joshi
Kajal Aggarwal
Amitabh Bachchan
Shahid Kapoor
Hazel Croney
V. Ravichandran
Vipin Sharma
Nawazuddin Siddiqui
Pulkit Samrat
Tannishtha Chatterjee
Krrish Chhabria
Avinash Dhyani
Zeenat Aman
Salman Khan
Shashank Arora
Urvashi Rautela
Naseeruddin Shah
Sara Loren
Tom Alter
Irrfan Khan
John Abraham
Rajeev Khandelwal
Ileana D'Cruz
Sahil Anand
Hrithik Roshan
Diana Penty
Niharica Raizada
Tiger Shroff
Sidharth Malhotra
Nawazuddin Siddiqui
Emraan Hashmi
Taapsee Pannu
Tannishtha Chatterjee
Riteish Deshmukh
Yash Soni
Shreyas Talpade
Vinay Pathak

41
Jimmy Sharma
Sushant Singh Rajput
Ashok Insan
RJ Balaji
Saurav Chakraborty
Shashank Udapurkar
Shubham
Manoj Bajpayee
Sunny Leone
Aashish Bhatt
Ajay Devgn
Ronit Roy
Ranbir Kapoor
Neha Sharma
Farhan Akhtar
John Abraham
Alia Bhatt
Vaani Kapoor
Neha Dhupia
Jimmy Sheirgill
Sonarika Bhadoria
Amitabh Bachchan
Sharman Joshi
Aamir Khan
Harshvardhan Kapoor
Salman Khan
Kangana Ranaut
Kangana Ranaut
Soha Ali Khan
Prabhu Deva
Shah Rukh Khan
Salman Khan
Ranveer Singh
Anil Kapoor
Akshay Kumar
Akshay Kumar
Akshay Kumar
Akshay Kumar
Shakti Kapoor
Bipasha Basu
Arjun Kapoor
Zayed Khan
Malaika Arora
Naman Jain
Gurmeet Choudhary
Kay Kay Menon
Rati Agnihotri
Amitabh Bachchan

42
Arjun Rampal
Varun Dhawan
Swanand Kirkire
Sulabha Arya
Irrfan Khan
Nana Patekar
Ayushmann Khurrana
Anupam Kher
Gurmeet Ram Rahim Singh
Sidhant Gupta
Arjun Mathur
Ganesh Acharya
Anushka Sharma
Gulshan Devaiah
Sushant Singh Rajput
Adhyayan Suman
Vira Sathidar
Kalki Koechlin
Sunny Leone
Sara Loren
Emraan Hashmi
Auroshika Dey
Ira Dubey
Naseeruddin Shah
Vinay Pathak
Ram Kapoor
Deepika Padukone
Ranbir Kapoor
Shakti Anand
Anil Kapoor
Arshad Warsi
Meenakshi Dixit
Yash Acharya
Rajkummar Rao
Rahul Bagga
Mohit Baghel
Rishi Verma
Mimoh Chakraborty
Swara Bhaskar
Richa Chadha
Arshad Warsi
Mugdha Godse
Yashpal Sharma
Dharmendra
Sunny Deol
Smitha Gondkar
Kunal Kapoor
Ajay Devgn

43
Jacqueline Fernandez
Rishi Kapoor
Akshay Kumar
Vinay Pathak
Nawazuddin Siddiqui
Bhavita Anand
Saif Ali Khan
Suraj Pancholi
Shamim Khan
Irrfan Khan
Suhaas Ahuja
Jaideep Ahlawat
Charanpreet Insan
Akanksha Puri
Kunal Khemu
Aishwarya Rai Bachchan
Seema Azmi
Parveen Kaur
Kapil Sharma
Kartik Aaryan
Diganth
Shahid Kapoor
Nawazuddin Siddiqui
Kunal Khemu
Mann Bagga
Manish Paul
Sanjeev Kumar
Madhuri Dixit
Shiv Darshan
Gopi Desai
Mohinder Gujral
Zeenat Aman
Ranveer Singh
Salman Khan
Sidharth Malhotra
Adhyayan Suman
Indrapal Ahuja
Jimmy Sheirgill
Abhay Deol
Sahil Anand
Alia Bhatt
Sampat Pal Devi
Farhan Akhtar
Madhuri Dixit
Kangana Ranaut
Ayushmann Khurrana
Ali Zafar
Mahek Chahal

44
Monali Thakur
Sunny Leone
Harman Baweja
Sanjay Mishra
Sharman Joshi
Sachin Khedekar
Leeza Mangaldas
Pulkit Samrat
Zara Sheikh
Alia Bhatt
Purab Kohli
Amitabh Bachchan
Varun Dhawan
Arvinder Bhatti
Kanika Batra
Jackky Bhagnani
Rajeev Khandelwal
Tanuj Virwani
Vijay Raaz
Kannan Arunachalam
Anjori Alagh
Satish Kaushik
Rahul Bagga
Himesh Reshammiya
Farooq Shaikh
Makrand Deshpande
Eesha Agarwal
Siddharth Gupta
Tiger Shroff
Rajkummar Rao
Sharib Hashmi
Kangana Ranaut
Kartik Aaryan
Swara Bhaskar
Simer Motiani
Anshuman Jha
Sidharth Malhotra
Vidya Balan
Saif Ali Khan
Varun Dhawan
Jay Bhanushali
Armaan Jain
Rajesh Khanna
Vir Das
Akshay Kumar
Jimmy Sheirgill
Reshmi Ghosh
Akshay Oberoi

45
Akshay Kumar
Anupam Kher
Rani Mukerji
Emraan Hashmi
Priyanka Chopra
Bipasha Basu
Deepika Padukone
Sonam Kapoor
Salil Acharya
Salman Khan
Saahil Prem
Alieesa P Badresia
Manoj Amarnani
Sasha Aagha
Tabu
Hrithik Roshan
Rati Agnihotri
Aditya Roy Kapoor
Asrani
Harshvardhan Deo
Nikhil Dwivedi
Karanvir Bohra
Puru Chibber
Soha Ali Khan
Rhea Chakraborty
Shah Rukh Khan
Rekha
Anupam Kher
Randeep Hooda
Akshay Kumar
Aadil Chahal
Shabana Azmi
Dimple Kapadia
Nishant Dahiya
Ranveer Singh
Emraan Hashmi
Saif Ali Khan
Vinod Acharya
Mannara Chopra
Prabhas
Mischa Barton
Shiv Panditt
Annu Kapoor
Barun Sobti
Rahul Bhat
Aamir Khan
Adhyayan Suman
Imran Khan

46
Naveen Kasturia
Arjun Rampal
Sarita Joshi
Kartik Aaryan
Juhi Chawla
Saif Ali Khan
Manisha Kelkar
Farooq Shaikh
Akshay Kumar
Randeep Hooda
Vivek Oberoi
Rajkummar Rao
Akash
Vishwa Mohan Badola
Neil Nitin Mukesh
Saqib Saleem
Arshad Warsi
Jimmy Sheirgill
Asha Bhosle
Kamal Haasan
Jackky Bhagnani
Aditya Roy Kapoor
Emraan Hashmi
Ajay Devgn
Ayushmann Khurrana
Vivek Oberoi
Vidyut Jammwal
Rani Mukerji
Saif Ali Khan
Riya Vij
Arjun Kapoor
Preity Zinta
Veena Malik
Ranbir Kapoor
Pulkit Samrat
Rupa Bhimani
Dhanush
Kay Kay Menon
Neil Nitin Mukesh
Vidya Balan
Anupam Kher
Sanjay Dutt
Farhan Akhtar
Wamiqa Gabbi
Shadab Kamal
Sunil Shetty
Prateik
Tusshar Kapoor

47
Tanuj Virwani
Poonam Pandey
Deepak Dobriyal
Hemant Gopal
Joy Mukherjee
Rishi Kapoor
Rajesh Tailang
Akshay Kumar
John Abraham
Amitabh Bachchan
Sushant Singh Rajput
Shruti Haasan
Deepika Padukone
Vivek Oberoi
Naseeruddin Shah
Karan Kundrra
Shahid Kapoor
Aida Elkashef
Irrfan Khan
Anisa Butt
Akshay Kumar
Rajkummar Rao
Manish Paul
Puneet Singh Ratn
Kangana Ranaut
Sumit Nijhawan
Tinnu Anand
Chandan Roy Sanyal
Elisha Kriis
Ashmit Patel
Imran Khan
Manu Rishi Chadha
Naseeruddin Shah
Paresh Rawal
Saif Ali Khan
Aamir Khan
Ali Zafar
Ranveer Singh
Sharman Joshi
Naseeruddin Shah
Shiney Ahuja
Karan Sharma
Sunny Deol
Ranveer Singh
Hrithik Roshan
Kareena Kapoor
Prateik
Kiran Bhatia

48
Bipasha Basu
Riteish Deshmukh
Jahangir Khan
Irrfan Khan
Vidya Balan
Mithun Chakraborty
Kareena Kapoor
Manish Chaudhary
Kavin Dave
Shikhi Gupta
Archana Joglekar
Tusshar Kapoor
Pulkit Samrat
Ayushmann Khurrana
Nikhil Dwivedi
Anil Kapoor
Karisma Kapoor
Arjun Kapoor
Sanjay Dutt
Gul Panag
Yudhveer Bakoliya
Kay Kay Menon
Emraan Hashmi
Sharman Joshi
Shahid Kapoor
Anupam Kher
Anya Anand
Julia Datt
Manoj Bajpayee
Manoj Bajpayee
Saif Ali Khan
Naresh Sharma
Riteish Deshmukh
Sonu Sood
Nassar Abdulla
Salman Khan
Vickrant Mahajan
Freny Bhagat
Akshay Kumar
Omkar Das Manikpuri
Sunil Shetty
Manoj Bajpayee
Bidita Bag
Harish Chabbra
Ranbir Kapoor
Kareena Kapoor
Sagar Bhangade
Vivek Oberoi

49
Ravi Kishan
Paresh Rawal
Rani Mukerji
Manoj Bajpayee
J.D. Chakravarthi
Cary Elwes
Arjun Rampal
Alia Bhatt
Jackky Bhagnani
Emraan Hashmi
Vicky Ahuja
Sunidhi Chauhan
Asrani
Shah Rukh Khan
Aamir Khan
Himanshu Bhatt
Ajay Devgn
Ashok Banthia
Salman Khan
Vinod Khanna
Akshay Kumar
Amitabh Bachchan
Sridevi
Vivek Sudershan
Nafisa Ali
Mohsin
Prateik
Gul Panag
Vatsal Sheth
Ajay Devgn
Russell Geoffrey Banks
Vinay Pathak
Rishi Kapoor
Priyanka Chopra
Madhavan
Arshad Warsi
Deepti Naval
Akshay Kumar
Sumit Arora
Anay
Om Puri
Abhishek Bachchan
Sendhil Ramamurthy
Darsheel Safary
Vinay Pathak
Ishaan Manhaas
Sanjay Mishra
Ashutosh Rana

50
Juhi Chawla
Govinda
Mimoh Chakraborty
Tusshar Kapoor
Kainaz Motivala
Partho A. Gupte
Nana Patekar
Sara Arjun
Kalki Koechlin
Kartik Aaryan
Vinay Pathak
Lillete Dubey
Sanjay Dutt
Amitabh Bachchan
Imran Khan
Emraan Hashmi
Aarav Khanna
Hrithik Roshan
Raghuvir Yadav
Gulshan Grover
Naushaad Abbas
Shefali Shah
Ajay Devgn
Rahul Jaiswal
Apoorva Arora
Isha Koppikar
Rajniesh Duggall
Amitabh Bachchan
Sanjay Dutt
Anupam Kher
Salman Khan
Deepshika Nagpal
Deepak Dobriyal
Tusshar Kapoor
Kiron Kher
Imran Khan
Shahid Kapoor
Mikaal
John Abraham
Jimmy Sheirgill
Vinay Pathak
Vinay Virmani
Dev Anand
Zayed Khan
Saqib Saleem
Sachiin Joshi
Shah Rukh Khan
Ranbir Kapoor

51
Chirag Paswan
Dharmendra
Himesh Reshammiya
Ranveer Singh
Akshay Kumar
Abhishek Bachchan
Rani Mukerji
Ajay Devgn
Vidya Balan
Priyanka Chopra
Shahid Kapoor
Prateik
Salman Khan
Siddharth
Amitabh Bachchan
Vidya Balan
Paresh Rawal
Sunny Gill
Shreyas Talpade
Tabu
Shah Rukh Khan
Amitabh Bachchan
Siddhartha Gupta
Shah Rukh Khan
Tanushree Dutta
Paul Sidhu
Sunny Deol
Gurdas Maan
Master Shams
Om Puri
Vikrum Kumar
Aditya Narayan
Arshad Warsi
Boman Irani
Nana Patekar
Priyanka Chopra
Arbaaz Khan
Rekha
Rahul Bose
Nana Patekar
Sudeep
Farooq Shaikh
Rohit Roy
Sachin Khedekar
Anuj Saxena
Akshay Kumar
Hazel Croney
Sanjeev Bhaskar

52
Vivek Oberoi
Abhishek Bachchan
Atul Kulkarni
Rajpal Yadav
Hrithik Roshan
Nushrat Bharucha
Kareena Kapoor
Bhushan Agarwal
Prashant Narayanan
Sanjay Dutt
Akshay Kumar
Ali Zafar
Rajat Barmecha
Ajay Devgn
Bobby Deol
Omkar Das Manikpuri
Neil Nitin Mukesh
Gul Panag
Raj Singh Chaudhary
John Abraham
Barkha Madan
Salman Khan
Supriya Pathak
Sunil Shetty
Rituparna Sengupta
Ranvir Shorey
Mallika Sherawat
Emraan Hashmi
Rishi Kapoor
Ajay Devgn
Manoj Bajpayee
Sanjay Dutt
John Abraham
Hrithik Roshan
Varun Bhagwat
Deepika Padukone
Sunny Deol
Rajat Kapoor
Akanksha
Jimmy Sheirgill
Sanjay Dutt
Ranveer Singh
Aditya Srivastava
Arunoday Singh
Akshay Kumar
Akshay Oberoi
Ajay Devgn
Neil Nitin Mukesh

53
Sahil Khan
Imran Khan
Sushmita Sen
Priyanka Chopra
Zeenat Aman
Bipasha Basu
Akshay Kumar
Aamir Khan
Farhan Akhtar
Saif Ali Khan
Salman Khan
Waheeda Rehman
Kangana Ranaut
Hrishitaa Bhatt
Ranbir Kapoor
Asrani
Irrfan Khan
Kay Kay Menon
Arshad Warsi
Paresh Rawal
Rati Agnihotri
Harman Baweja
Shahid Kapoor
Fardeen Khan
John Abraham
Kay Kay Menon
Aftab Shivdasani
Naseeruddin Shah
Inaamulhaq
Neil Nitin Mukesh
Kunal Khemu
Bobby Deol
Anita
Parzaan Dastur
Meghan Jadhav
Shreyas Talpade
John Abraham
Kay Kay Menon
Sanjay Dutt
Mithun Chakraborty
Govinda
Sunil Shetty
Jackie Shroff
Anupam Kher
Shreyas Talpade
Rishi Kapoor
Rajendra Prasad
Arjun Rampal

54
Mithun Chakraborty
Mithun Chakraborty
Bobby Deol
Shahid Kapoor
Harman Baweja
Fardeen Khan
Sanjay Dutt
Ranbir Kapoor
Salman Khan
Akshay Kumar
Atmaram Bhende
Amitabh Bachchan
Salman Khan
Manoj Bajpayee
Emraan Hashmi
Lewis Tan
Akshay Kumar
Amitabh Bachchan
Ranbir Kapoor
Aamir Bashir
Farooq Shaikh
Mithun Chakraborty
Abhishek Bachchan
Saif Ali Khan
Shah Rukh Khan
Aamir Khan
Akshay Kumar
Ajay Devgn
Hrithik Roshan
Ranbir Kapoor
Amitabh Bachchan
Amitabh Bachchan
Ajay Devgn
Omkar Bhatkar
Shreyas Talpade
Manisha Koirala
Ajay Devgn
Tusshar Kapoor
Juhi Chawla
Ajay Devgn
Kay Kay Menon
Akshay Kumar
Dino Morea
Mimoh Chakraborty
Emraan Hashmi
Mithun Chakraborty
Sikander Kher
Paresh Rawal

55
Ahraz Ahmed
Aftab Shivdasani
Amita Pathak
Saahil Chadha
Saif Ali Khan
Kay Kay Menon
Shahid Kapoor
Harman Baweja
Adhvik Mahajan
Vivek Oberoi
Govinda
Amitabh Bachchan
Paresh Rawal
Mallika Sherawat
Arjun Rampal
Tusshar Kapoor
Bobby Deol
Sammir Dattani
Victor Banerjee
Rajniesh Duggall
Amitabh Bachchan
Shreyas Talpade
Kiron Kher
Jackie Shroff
Jayshree Arora
Sharman Joshi
Himesh Reshammiya
Sohail Khan
Saif Ali Khan
Isha Koppikar
Kamal Rashid Khan
Priyanka Chopra
Vinay Pathak
Salman Khan
Abhay Deol
Vinay Pathak
Shabana Azmi
Manoj Bajpayee
Anupam Kher
Rajesh Khanna
Dino Morea
Irrfan Khan
Amitabh Bachchan
Himesh Reshammiya
Tusshar Kapoor
Nauheed Cyrusi
Madhuri Dixit
Dharmendra

56
Emraan Hashmi
Vinay Pathak
Akshay Kumar
Dino Morea
Sunny Deol
Mouli Ganguly
Krishna Abhishek
Irrfan Khan
Kay Kay Menon
Pankaj Kapur
Jazzy Doe
Mona Ambegaonkar
Ajay Devgn
Amitabh Bachchan
Jimmy Sheirgill
Fardeen Khan
Shah Rukh Khan
Sanjay Dutt
John Abraham
Pankaj Kapur
Sunil Pal
Muzamil Ibrahim
Imaaduddin Shah
Sharman Joshi
Abhay Deol
Arjun Rampal
Akshaye Khanna
Rishi Kapoor
Arbaaz Khan
Amitabh Bachchan
Gautam Gupta
Mohan Azaad
Juanna Sanghvi
Mithun Chakraborty
Ranvir Shorey
Govinda
Abhishek Bachchan
Shahid Kapoor
Tusshar Kapoor
Shahid Kapoor
Shiney Ahuja
Dharmendra
Fardeen Khan
Tusshar Kapoor
Rekha
Jimmy Sheirgill
Rani Mukerji
Dharmendra

57
Shabana Azmi
Abhay Deol
Salman Khan
Menekka Arora
Nana Patekar
Bobby Deol
Linda Arsenio
Kal Penn
Akshay Kumar
Jason Lewis
Sanjay Dutt
Amitabh Bachchan
John Abraham
Shah Rukh Khan
Salman Khan
Rahul Khanna
Dwij Yadav
Aftab Shivdasani
Vinod Khanna
Bobby Deol
Sherlyn Chopra
Salman Khan
Rani Mukerji
Mahima Chaudhry
Mandar Jadhav
Aftab Shivdasani
Amitabh Bachchan
Jimmy Sheirgill
Manoj Bajpayee
Darsheel Safary
Saif Ali Khan
Urmila Matondkar
Kunal Khemu
Emraan Hashmi
Tushar Jalota
Jaya Bachchan
Akshay Kumar
Akshaye Khanna
Jeetendra
Akshaye Khanna
Abhay Deol
Emraan Hashmi
Akshay Kapoor
Sanjay Dutt
Bobby Darling
Aftab Shivdasani
Rekha
Amitabh Bachchan

58
Rati Agnihotri
Rahul Dev
Naseeruddin Shah
Urmila Matondkar
Juhi Chawla
Akshay Kumar
Sushmita Sen
Jackie Shroff
Somesh Agarwal
Sohail Khan
Kareena Kapoor
Bipasha Basu
Amitabh Bachchan
Rajit Kapoor
Emraan Hashmi
Ishrat Ali
Raj Tara
Hrithik Roshan
Ayesha Takia
Shah Rukh Khan
Amitabh Bachchan
Aamir Khan
Kangana Ranaut
Ajay Devgn
Ram Kapoor
Sunil Shetty
Ajay Devgn
Akshay Kumar
Arjun Rampal
Arjun Rampal
Aftab Shivdasani
Salman Khan
Emraan Hashmi
Onjolee Nair
Amarjeet
Anupam Kher
Amitabh Bachchan
Rishi Kapoor
Sanjay Dutt
John Abraham
Nassar Abdulla
Rekha
Paresh Rawal
Ajay Devgn
Rahul Bose
Sunny Deol
Akshay Kumar
Fardeen Khan

59
Akshay Kumar
Jeetendra
Sarika
Aamir Khan
Salman Khan
Govinda
Akshaye Khanna
Salman Khan
Mohit Ahlawat
Mahima Chaudhry
Ajay Devgn
Mohammad Amir Naji
Sanjay Dutt
Irrfan Khan
Aishwarya Rai Bachchan
Nana Patekar
Sunny Deol
Shahid Kapoor
Priyanshu Chatterjee
Gurdas Maan
Kangana Ranaut
Paresh Rawal
Jimmy Sheirgill
Sushmita Sen
Rakesh Bedi
Emraan Hashmi
Manisha Koirala
Ajay Devgn
Rekha
Juhi Chawla
Bobby Deol
Anil Kapoor
Amitabh Bachchan
Sanjay Dutt
Abhishek Bachchan
Shawar Ali
Ali Asgar
Tabu
Ajay Devgn
Abhishek Bachchan
Aryan Vaid
Jatin Grewal
Samir Aftab
Anil Kapoor
Randeep Hooda
Akshay Kumar
Saayli Buva
Bipasha Basu

60
Amitabh Bachchan
Akshay Kumar
Mithun Chakraborty
Sanjay Dutt
Arjun Rampal
Shilpa Shetty Kundra
Amitabh Bachchan
Siddharth Koirala
Fardeen Khan
Ayesha Jhulka
Aseel Adel
Vivek Oberoi
Akshay Kumar
Shreyas Talpade
Chiranjeevi
Kay Kay Menon
Akshay Kumar
Sunny Deol
John Abraham
Ajay Devgn
Kunal Khemu
Lucky Ali
Mukesh Khanna
Mohit Ahlawat
Vivek Oberoi
Aftab Shivdasani
Shilpa Shetty Kundra
Kamal Adib
Arshad Warsi
Tusshar Kapoor
Salman Khan
Ajay Devgn
Salman Khan
Rajpal Yadav
Anupam Kher
Salman Khan
Aamir Khan
Dia Mirza
Dev Anand
Sanjay Suri
Anil Kapoor
Urmila Matondkar
Uday Chopra
Anil Kapoor
Sunil Shetty
Konkona Sen Sharma
Shabana Azmi
Saif Ali Khan

61
Vinod Khanna
Shah Rukh Khan
Irrfan Khan
Rishi Kapoor
Saif Ali Khan
Kashmira Shah
Amitabh Bachchan
Arshad Warsi
Sanjay Dutt
Ashutosh Rana
Neha Dhupia
Madhavan
Tabu
Abhay Deol
Zulfi Sayed
Ajay Devgn
Nassar Abdulla
Arjun Rampal
Shahid Kapoor
Aarti Chhabria
Fardeen Khan
Amitabh Bachchan
Amitabh Bachchan
Vikram Aditya
Arjun Rampal
Emraan Hashmi
Shah Rukh Khan
Shah Rukh Khan
Ajay Devgn
Salman Khan
Abhishek Bachchan
Amitabh Bachchan
Saif Ali Khan
Akshaye Khanna
Mallika Sherawat
Ajay Devgn
Akshay Kumar
Amitabh Bachchan
Amitabh Bachchan
Shatrughan Sinha
Bobby Deol
Kareena Kapoor
Jimmy Sheirgill
Arjun Rampal
Jimmy Sheirgill
Amitabh Bachchan
Amitabh Bachchan
Shahid Kapoor

62
Salman Khan
Jackie Shroff
Naveen Bawa
Vikaas Kalantari
Tusshar Kapoor
Kareena Kapoor
Salman Khan
Sunil Shetty
Saif Ali Khan
Isha Koppikar
Akshay Kumar
Aniket Vishwasrao
Shawar Ali
Tisca Chopra
Neha Dhupia
Raqesh Bapat
Manoj Bajpayee
Mallika Sherawat
Dino Morea
Sohail Khan
Kiron Kher
Bobby Deol
Sunny Deol
Sohail Khan
Amitabh Bachchan
Bipasha Basu
Hrithik Roshan
Dino Morea
Irrfan Khan
Aftab Shivdasani
Tabu
Anil Kapoor
Prithviraj Kapoor
Aftab Shivdasani
Akshay Kumar
Antara Mali
Vinay Anand
John Abraham
Salman Khan
Sanjay Dutt
Akshay Kumar
Manisha Koirala
Akshay Kapoor
Sanjay Dutt
Ajay Devgn
Sanjay Dutt
Sanjay Suri
Abhishek Bachchan

63
Sunny Deol
Aftab Shivdasani
Shah Rukh Khan
Vatsal Sheth
Madhavan
Tusshar Kapoor
Emraan Hashmi
Vicky Ahuja
Shah Rukh Khan
Tarun Arora
Diwakar Pathak
Arya Babbar
Rekha
Shah Rukh Khan
Anupam Kher
Shah Rukh Khan
Sunny Deol
Amitabh Bachchan
Hrithik Roshan
Sanjay Dutt
Sanjay Dutt
Sanjay Dutt
Ajay Devgn
Atul Kulkarni
Naseeruddin Shah
Arun Bakshi
Priyanshu Chatterjee
Ajay Devgn
Amitabh Bachchan
Sudesh Berry
Akshay Kumar
Akshay Kumar
Amitabh Bachchan
Ajay Devgn
Anil Kapoor
Jackie Shroff
Sadashiv Amrapurkar
Sooraj Balaji
Arjun Rampal
Sameera Reddy
Om Puri
Amar Upadhyaya
Zayed Khan
Nawazuddin Siddiqui
Vivek Oberoi
Kapil Jhaveri
Nandita Das
Aftab Shivdasani

64
Manisha Koirala
Rahul Bose
Ajay Devgn
Tabu
Jimmy Sheirgill
Sanjay Dutt
Akshaye Khanna
Vikram Dasu
Reef Karim
Jaz Pandher
Rushali Arora
Ashmit Patel
Sunny Deol
Shahid Kapoor
Babbu Mann
Javed Jaffrey
Bipasha Basu
Sanjay Suri
Om Puri
Juhi Babbar
Sunny Deol
Feroz Khan
Amit Hingorani
Fardeen Khan
Himanshu Malik
Tusshar Kapoor
Aishwarya Rai Bachchan
Antara Mali
Victor Banerjee
Manisha Koirala
Attin Bhalla
Riteish Deshmukh
Rahul Bose
Tulip Joshi
Ajay Devgn
Urmila Matondkar
Abhishek Bachchan
John Abraham
Sushmita Sen
Vikas Kalantri
Raveena Tandon
Tanishaa Mukerji
Raveena Tandon
Vijay Raaz
Raveena Tandon
Tanuja
Ankit
Sadashiv Amrapurkar

65
 Salman Khan
Riteish Deshmukh
Rakhee Gulzar
Shabana Azmi
Edwin Fernandes
Tusshar Kapoor
Sharman Joshi
Dino Morea
Ajay Devgn
Arshad Warsi
Shah Rukh Khan
Amitabh Bachchan
Shah Rukh Khan
Amitabh Bachchan
Vivek Oberoi
Ajay Devgn
Akshay Kumar

[ ]: for i in movies.index: # for accessing index we have to use movies.index

print(i)

Uri: The Surgical Strike

Battalion 609
The Accidental Prime Minister (film)
Why Cheat India
Evening Shadows
Soni (film)
Fraud Saiyaan
Bombairiya
Manikarnika: The Queen of Jhansi
Thackeray (film)
Amavas
Gully Boy
Hum Chaar
Total Dhamaal
Sonchiriya
Badla (2019 film)
Mard Ko Dard Nahi Hota
Hamid (film)
Photograph (film)
Risknamaa
Mere Pyare Prime Minister
22 Yards
Kesari (film)
Notebook (2019 film)
Junglee (2019 film)
Gone Kesh
Albert Pinto Ko Gussa Kyun Aata Hai?

66
The Tashkent Files
Kalank
Setters (film)
Student of the Year 2
PM Narendra Modi
De De Pyaar De
India's Most Wanted (film)
Yeh Hai India
Khamoshi (2019 film)
Kabir Singh
Article 15 (film)
One Day: Justice Delivered
Hume Tumse Pyaar Kitna
Super 30 (film)
Family of Thakurganj
Batla House
Jhootha Kahin Ka
Judgementall Hai Kya
Chicken Curry Law
Arjun Patiala
Jabariya Jodi
Pranaam
The Sky Is Pink
Mission Mangal
Saaho
Dream Girl (2019 film)
Section 375
The Zoya Factor (film)
Pal Pal Dil Ke Paas
Prassthanam
P Se Pyaar F Se Faraar
Ghost (2019 film)
Bala (2019 film)
Yaaram (2019 film)
Housefull 4
Saand Ki Aankh
Made in China (2019 film)
Ujda Chaman
Bypass Road (film)
Satellite Shankar
Jhalki
Marjaavaan
Motichoor Chaknachoor
Keep Safe Distance (film)
Pagalpanti (2019 film)
Ramprasad Ki Tehrvi
Yeh Saali Aashiqui
Dil Bechara

67
Pati Patni Aur Woh (2019 film)
Commando 3 (film)
Mardaani 2
Dabangg 3
Good Newwz
Kaalakaandi
Vodka Diaries
My Birthday Song
Nirdosh
Mukkabaaz
Union Leader (film)
Love per Square Foot
Aiyaary
Padmaavat
Kuchh Bheege Alfaaz
Jaane Kyun De Yaaron
Veerey Ki Wedding
Sonu Ke Titu Ki Sweety
Hate Story 4
Dil Juunglee
3 Storeys
Raid (2018 film)
Hichki
Missing (2018 film)
Baaghi 2
October (2018 film)
Mercury (film)
Beyond the Clouds (2017 film)
Nanu Ki Jaanu
Daas Dev
Omerta (film)
Raazi
Hope Aur Hum
High Jack (film)
Khajoor Pe Atke
Parmanu: The Story of Pokhran
Bioscopewala
Bhavesh Joshi Superhero
Phamous
Race 3
Dhadak
Sanju
Saheb Biwi Aur Gangster 3
Nawabzaade
Mulk (film)
Brij Mohan Amar Rahe
Karwaan
Gold (2018 film)

68
Satyameva Jayate (2018 film)
Happy Phirr Bhag Jayegi
Genius (2018 Hindi film)
Yamla Pagla Deewana: Phir Se
Stree (2018 film)
Paltan (film)
Laila Majnu (2018 film)
Gali Guleiyan
Halkaa
Pataakha
Batti Gul Meter Chalu
Love Sonia
Manto (2018 film)
Ishqeria
Manmarziyaan
Mitron
Sui Dhaaga
Baazaar
Jalebi (film)
FryDay
Tumbbad
Helicopter Eela
Namaste England
Andhadhun
Badhaai Ho
5 Weddings
Kaashi in Search of Ganga
Dassehra
The Journey of Karma
Jack and Dil
Mohalla Assi
Pihu
Bhaiaji Superhit
Rajma Chawal
Zero (2018 film)
Simmba
Tiger Zinda Hai
Golmaal Again
Judwaa 2
Ok Jaanu
Coffee with D
Kaabil
Raees (film)
Thugs of Hindostan
Hind Ka Napak Ko Jawab: MSG Lion Heart 2
Running Shaadi
The Ghazi Attack
Irada (2017 film)

69
Rangoon (2017 Hindi film)
Wedding Anniversary
Jeena Isi Ka Naam Hai (film)
Badrinath Ki Dulhania
Trapped (2016 Hindi film)
Aa Gaya Hero
Mantra (2016 film)
Phillauri (film)
Machine (2017 film)
Bhanwarey
Anaarkali of Aarah
Naam Shabana
Hotel Salvation
Begum Jaan
Noor (film)
Ek Thi Rani Aisi Bhi
Maatr
Sarkar 3
Jattu Engineer
Half Girlfriend (film)
Meri Pyaari Bindu
Sachin: A Billion Dreams
Hindi Medium
Sweetiee Weds NRI
Dobaara: See Your Evil
Flat 211
Dear Maya
Raabta (film)
Behen Hogi Teri
Tubelight (2017 Hindi film)
Bank Chor
Ek Haseena Thi Ek Deewana Tha
Jagga Jasoos
Shab (film)
Lipstick Under My Burkha
Bachche Kachche Sachche
G Kutta Se
Indu Sarkar
Jab Harry Met Sejal
Munna Michael
Toilet: Ek Prem Katha
Mubarakan
Guest iin London
Bareilly Ki Barfi
Babumoshai Bandookbaaz
Yadvi – The Dignified Princess
Qaidi Band
Shubh Mangal Saavdhan

70
Raag Desh (film)
Daddy (2017 film)
Simran (film)
Lucknow Central
A Gentleman
Viceroy's House (film)
Patel Ki Punjabi Shaadi
Newton (film)
The Final Exit
Bhoomi (film)
Haseena Parkar
JD (film)
Haraamkhor
Poster Boys
Mom (film)
Chef (2017 film)
Ranchi Diaries
Babuji Ek Ticket Bambai
Rukh (film)
Secret Superstar
Aval (2017 film)
Ribbon (film)
Shaadi Mein Zaroor Aana
Jia Aur Jia
Qarib Qarib Singlle
Aksar 2
Panchlait
Tumhari Sulu
Julie 2
Kadvi Hawa
Firangi
Fukrey Returns
Monsoon Shootout
Ajji
Chalk n Duster
Rebellious Flower
Saankal
Airlift (film)
Sallu Ki Shaadi
Irudhi Suttru
Kyaa Kool Hain Hum 3
Mastizaade
Dil Jo Na Keh Saka
Jugni (2016 film)
Ghayal: Once Again
Fitoor
Sanam Re
Direct Ishq

71
Ishq Forever
Loveshhuda
Neerja
Aligarh (film)
Bollywood Diaries
Love Shagun
Tere Bin Laden: Dead or Alive
Jai Gangaajal
Kapoor & Sons
Rocky Handsome
Love Games (film)
Fan (film)
Nil Battey Sannata
Laal Rang
Baaghi (2016 film)
Global Baba
Shortcut Safari
The Blueberry Hunt
Santa Banta Pvt Ltd
Traffic (2016 film)
1920: London
Azhar (film)
Buddha in a Traffic Jam
Murari the Mad Gentleman
Dear Dad (film)
Phobia (2016 film)
Sarbjit (film)
Veerappan (2016 film)
Do Lafzon Ki Kahani (film)
Te3n
Udta Punjab
Khel Toh Ab Shuru Hoga
Luv U Alia
7 Hours to Go
Raman Raghav 2.0
Junooniyat
Rough Book
Dhanak
Fredrick (film)
Dil Toh Deewana Hai
Sultan (2016 film)
Brahman Naman
Great Grand Masti
Waiting (2015 film)
Ishq Click
M Cream
Madaari
Dishoom

72
Fever (2016 film)
Rustom (film)
Hai Apna Dil Toh Awara
Mohenjo Daro (film)
Happy Bhag Jayegi
Waarrior Savitri
A Flying Jatt
Baar Baar Dekho
Freaky Ali
Raaz: Reboot
Pink (2016 film)
Parched
Banjo (2016 film)
Days of Tafree
Wah Taj
Island City (2015 film)
Ek Kahani Julie Ki
M.S. Dhoni: The Untold Story
MSG: The Warrior Lion Heart
Devi (2016 film)
Motu Patlu: King of Kings
Anna (2016 film)
Fuddu
Saat Uchakkey
Beiimaan Love
Umrika
Shivaay
Dongari Ka Raja
Ae Dil Hai Mushkil
Tum Bin II
Rock On 2
Force 2
Dear Zindagi
Befikre
Moh Maya Money
Shorgul
Saansein
Ki & Ka
Wajah Tum Ho
Dangal (film)
Mirzya (film)
Prem Ratan Dhan Payo
Tanu Weds Manu: Returns
Tanu Weds Manu: Returns
31st October (film)
ABCD 2
Dilwale (2015 film)
Bajrangi Bhaijaan

73
Bajirao Mastani
Welcome Back (film)
Baby (2015 Hindi film)
Singh Is Bliing
Gabbar Is Back
Gabbar Is Back
Mumbai Can Dance Saala
Alone (2015 Hindi film)
Tevar
Sharafat Gayi Tel Lene
Dolly Ki Doli
Hawaizaada
Khamoshiyan
Rahasya
Jai Jawaan Jai Kisaan (film)
Shamitabh
Roy (film)
Badlapur (film)
Crazy Cukkad Family
Take It Easy (2015 film)
Qissa (film)
Ab Tak Chhappan 2
Dum Laga Ke Haisha
Dirty Politics (film)
MSG: The Messenger
Badmashiyaan
Coffee Bloom
Hey Bro
NH10 (film)
Hunterrr
Detective Byomkesh Bakshy!
Luckhnowi Ishq
Court (film)
Margarita with a Straw
Ek Paheli Leela
Barkhaa
Mr. X (2015 film)
NH-8 Road to Nidhivan
Dilliwali Zaalim Girlfriend
Dharam Sankat Mein
Kaagaz Ke Fools
Kuch Kuch Locha Hai
Piku
Bombay Velvet
I Love Desi
Dil Dhadakne Do
Welcome 2 Karachi
P Se PM Tak

74
Mere Genie Uncle
Hamari Adhuri Kahani
Miss Tanakpur Haazir Ho
Uvaa
Ishq Ke Parindey
Ishqedarriyaan
Sabki Bajegi Band
Masaan
Guddu Rangeela
Bezubaan Ishq
Aisa Yeh Jahaan
Second Hand Husband
I Love NY (2015 film)
Main Hoon Part-Time Killer
Kaun Kitne Paani Mein
Drishyam (2015 film)
Bangistan
All Is Well (2015 film)
Brothers (2015 film)
Gour Hari Dastaan
Manjhi – The Mountain Man
Thoda Lutf Thoda Ishq
Phantom (2015 film)
Hero (2015 Hindi film)
Sorry Daddy
Talvar (film)
Katti Batti
Meeruthiya Gangsters
MSG-2 The Messenger
Calendar Girls (2015 film)
Bhaag Johnny
Jazbaa
Bumper Draw
Chinar Daastaan-E-Ishq
Kis Kisko Pyaar Karoon
Pyaar Ka Punchnama 2
Wedding Pullav
Shaandaar
Titli (2014 film)
Guddu Ki Gun
The Silent Heroes
Ranbanka
Sholay
Dedh Ishqiya
Karle Pyaar Karle
Om-Dar-B-Dar
Paranthe Wali Gali
Strings of Passion

75
Gunday
Jai Ho (film)
Hasee Toh Phasee
Heartless (2014 film)
Ya Rab
Darr @ the Mall
One by Two (2014 film)
Babloo Happy Hai
Highway (2014 Hindi film)
Gulabi Gang (film)
Shaadi Ke Side Effects
Gulaab Gang
Queen (2014 film)
Bewakoofiyaan
Total Siyapaa
Karar: The Deal
Lakshmi (2014 film)
Ragini MMS 2
Dishkiyaoon
Ankhon Dekhi
Gang of Ghosts
Anuradha (2014 film)
W (2014 film)
O Teri
Honour Killing (film)
2 States (2014 film)
Jal (film)
Bhoothnath Returns
Main Tera Hero
Lucky Kabootar
Station (2014 film)
Youngistaan
Samrat & Co.
Purani Jeans
Kya Dilli Kya Lahore
Koyelaanchal
Manjunath (film)
Dekh Tamasha Dekh
Mastram
The Xposé
Children of War (2014 film)
Hawaa Hawaai
Kahin Hai Mera Pyar
Kuku Mathur Ki Jhand Ho Gayi
Heropanti
CityLights (2014 film)
Filmistaan
Revolver Rani

76
Kaanchi: The Unbreakable
Machhli Jal Ki Rani Hai
Khwaabb
Yeh Hai Bakrapur
Ek Villain
Bobby Jasoos
Humshakals
Humpty Sharma Ki Dulhania
Hate Story 2
Lekar Hum Deewana Dil
Riyasat (film)
Amit Sahni Ki List
Holiday: A Soldier Is Never Off Duty
Fugly (film)
Bazaar E Husn
Pizza (2014 film)
Entertainment (2014 film)
Singham Returns
Mardaani
Raja Natwarlal
Mary Kom (film)
Creature 3D
Finding Fanny
Khoobsurat (2014 film)
3 A.M. (2014 film)
Kick (2014 film)
Mad About Dance
Mumbhai Connection
Life Is Beautiful (2014 film)
Desi Kattey
Haider (film)
Bang Bang!
Spark (2014 film)
Daawat-e-Ishq
Balwinder Singh Famous Ho Gaya
Jigariyaa
Tamanchey
Mumbai 125 KM
Meinu Ek Ladki Chaahiye
Chaarfutiya Chhokare
Sonali Cable
Happy New Year (2014 film)
Super Nani
Ekkees Toppon Ki Salaami
Rang Rasiya
The Shaukeens
Roar: Tigers of the Sundarbans
A Decent Arrangement

77
Gollu Aur Pappu
Titoo MBA
Kill Dil
Ungli
Happy Ending (film)
Zed Plus
Zid (2014 film)
Action Jackson (2014 film)
Bhopal: A Prayer for Rain
Mumbai Delhi Mumbai
Badlapur Boys
Main Aur Mr. Riight
Ugly (film)
PK (film)
Dehraadun Diary
Matru Ki Bijlee Ka Mandola
Sulemani Keeda
Inkaar (2013 film)
Gangoobai
Akaash Vani
Main Krishna Hoon
Race 2
Bandook
Listen… Amaya
Special 26
Murder 3
Zila Ghaziabad
Kai Po Che!
Bloody Isshq
Saare Jahaan Se Mehnga
3G (film)
Mere Dad Ki Maruti
Jolly LLB
Saheb Biwi Aur Gangster Returns
Mai (2013 film)
Vishwaroopam
Rangrezz
Aashiqui 2
Ek Thi Daayan
Himmatwala (2013 film)
Nautanki Saala!
Jayantabhai Ki Luv Story
Commando: A One Man Army
Bombay Talkies (film)
Go Goa Gone
Gippi
Aurangzeb (film)
Ishkq in Paris

78
Zindagi 50-50
Yeh Jawaani Hai Deewani
Fukrey
Chhota Bheem and the Throne of Bali
Raanjhanaa
Ankur Arora Murder Case
Shortcut Romeo
Ghanchakkar (film)
Hum Hai Raahi Car Ke
Policegiri
Bhaag Milkha Bhaag
Sixteen (2013 Indian film)
B.A. Pass
Enemmy
Issaq
Bajatey Raho
Luv U Soniyo
Nasha (film)
Chor Chor Super Chor
Calapor (film)
Love in Bombay
D-Day (2013 film)
Siddharth (2013 film)
Once Upon ay Time in Mumbai Dobaara!
Madras Cafe
Satyagraha (film)
Shuddh Desi Romance
Ramaiya Vastavaiya
Chennai Express
Grand Masti
John Day (film)
Horror Story (film)
Phata Poster Nikhla Hero
Ship of Theseus (film)
The Lunchbox
Baat Bann Gayi
Boss (2013 Hindi film)
Shahid (film)
Mickey Virus
Satya 2
Rajjo
Maazii
Sooper Se Ooper
Prague (2013 film)
Wake Up India
Super Model (film)
Gori Tere Pyaar Mein
What the Fish

79
Jackpot (2013 film)
Table No. 21
Bullett Raja
Dhoom 3
Chashme Baddoor (2013 film)
Lootera
War Chhod Na Yaar
Chaalis Chauraasi
Ghost (2012 film)
Sadda Adda
Singh Saab the Great
Goliyon Ki Raasleela Ram-Leela
Agneepath (2012 film)
Ek Main Aur Ekk Tu
Ekk Deewana Tha
?: A Question Mark
Jodi Breakers
Tere Naal Love Ho Gaya
Staying Alive (2012 film)
Paan Singh Tomar (film)
Kahaani
Zindagi Tere Naam
Agent Vinod (2012 film)
Blood Money (2012 film)
Bumboo
Valentine's Night
Married 2 America
Chaar Din Ki Chandni
Bittoo Boss
Vicky Donor
Hate Story
Tezz
Dangerous Ishhq
Ishaqzaade
Department (film)
Fatso!
Arjun: The Warrior Prince
Life Ki Toh Lag Gayi
Shanghai (2012 film)
Ferrari Ki Sawaari
Teri Meri Kahaani (film)
Mr. Bhatti on Chutti
Yeh Khula Aasmaan
Rakhtbeej
Gangs of Wasseypur
Gangs of Wasseypur – Part 2
Cocktail (2012 film)
Gattu

80
Kyaa Super Kool Hain Hum
Maximum (film)
Paanch Ghantey Mien Paanch Crore
Ek Tha Tiger
Challo Driver
Shirin Farhad Ki Toh Nikal Padi
Joker (2012 film)
Aalaap (film)
Mere Dost Picture Abhi Baki Hai
Krishna Aur Kans
From Sydney with Love
Jalpari: The Desert Mermaid
Barfi!
Heroine (2012 film)
Chal Pichchur Banate Hain
Kismat Love Paisa Dilli
Jeena Hai Toh Thok Daal
OMG – Oh My God!
Aiyyaa
Chittagong (film)
Bhoot Returns
Delhi Safari
Chakravyuh (2012 film)
Student of the Year
Ajab Gazabb Love
Rush (2012 film)
1920: The Evil Returns
Sons of Ram
Ata Pata Laapata
Jab Tak Hai Jaan
Talaash: The Answer Lies Within
Login (film)
Son of Sardaar
Cigarette Ki Tarah
Dabangg 2
Players (2012 film)
Housefull 2
Bol Bachchan
English Vinglish
Impatient Vivek
Yamla Pagla Deewana
Mumbai Mast Kallander
Dhobi Ghat (film)
Turning 30
Hostel (2011 film)
Dil Toh Baccha Hai Ji
United Six
Utt Pataang

81
Patiala House (film)
7 Khoon Maaf
Tanu Weds Manu
F.A.L.T.U
Memories in March
Thank You (2011 film)
Angel (2011 film)
Happy Husbands (2011 film)
Teen Thay Bhai
Dum Maaro Dum (film)
Shor in the City
Zokkomon
Chalo Dilli
Aashiqui.in
Satrangee Parachute
Monica (film)
I Am (2010 Indian film)
Naughty @ 40
Haunted – 3D
Love U…Mr. Kalakaar!
Ragini MMS
Stanley Ka Dabba
Shagird (2011 film)
404 (film)
Shaitan (film)
Pyaar Ka Punchnama
Bheja Fry 2
Always Kabhi Kabhi
Double Dhamaal
Bbuddah… Hoga Terra Baap
Delhi Belly (film)
Murder 2
Chillar Party
Zindagi Na Milegi Dobara
Dear Friend Hitler
I Am Kalam
Bin Bulaye Baraati
Kucch Luv Jaisaa
Singham
Khap (film)
Bubble Gum (film)
Shabri
Phhir
Aarakshan
Chatur Singh Two Star
Sahi Dhandhe Galat Bande
Bodyguard (2011 Hindi film)
Yeh Dooriyan

82
Not a Love Story (2011 film)
Hum Tum Shabana
Mummy Punjabi
Mere Brother Ki Dulhan
Mausam (2011 film)
U R My Jaan
Force (2011 film)
Saheb Biwi Aur Gangster
Tere Mere Phere
Breakaway (2011 film)
Chargesheet (film)
Love Breakups Zindagi
Mujhse Fraaandship Karoge
Aazaan
Ra.One
Rockstar (2011 film)
Miley Naa Miley Hum
Tell Me O Kkhuda
Damadamm!
Ladies vs Ricky Bahl
Desi Boyz
Game (2011 film)
No One Killed Jessica
Rascals (2011 film)
The Dirty Picture
Pyaar Impossible!
Chance Pe Dance
My Friend Pinto
Veer (2010 film)
Striker (2010 film)
Rann (film)
Ishqiya
Road to Sangam
Jo Hum Chahein
Click (2010 film)
Toh Baat Pakki!
My Name Is Khan
Teen Patti (film)
Karthik Calling Karthik
Don 2
Rokkk
Aakhari Decision
Right Yaaa Wrong
Sukhmani: Hope for Life
Thanks Maa
Na Ghar Ke Na Ghaat Ke
Trump Card (film)
Shaapit

83
Hum Tum Aur Ghost
Well Done Abba
Tum Milo Toh Sahi
Jaane Kahan Se Aayi Hai
Prem Kaa Game
Sadiyaan
The Japanese Wife
Paathshaala
Phoonk 2
Lahore (film)
Apartment (film)
City of Gold (2010 film)
Chase (2010 film)
Housefull (2010 film)
Mittal v/s Mittal
It's a Wonderful Afterlife
Prince (2010 film)
Raavan
Bumm Bumm Bole
Kushti (film)
Kites (film)
Love Sex Aur Dhokha
Milenge Milenge
Ek Second… Jo Zindagi Badal De?
Mr. Singh Mrs. Mehta
Lamhaa
Khatta Meetha (2010 film)
Tere Bin Laden
Udaan (2010 film)
Once Upon a Time in Mumbaai
Help (film)
Peepli Live
Lafangey Parindey
Hello Darling
Antardwand
Aashayein
Soch Lo
Dabangg
Khichdi: The Movie
Red Alert: The War Within
Life Express (2010 film)
The Film Emotional Atyachar
Hisss
Crook (film)
Do Dooni Chaar
Aakrosh (2010 film)
Ramayana: The Epic
Knock Out (2010 film)

84
Jhootha Hi Sahi
Guzaarish (film)
Allah Ke Banday
Break Ke Baad
Khuda Kasam
Phas Gaye Re Obama
Malik Ek
A Flat (film)
No Problem (2010 film)
Band Baaja Baaraat
Kaalo
Mirch
Tees Maar Khan (2010 film)
Isi Life Mein
Toonpur Ka Super Hero
Tera Kya Hoga Johnny
Ramaa: The Saviour
I Hate Luv Storys
Dulha Mil Gaya
Anjaana Anjaani
Dunno Y… Na Jaane Kyon
Pankh
Action Replayy
3 Idiots
Luck by Chance
Love Aaj Kal
Wanted (2009 film)
Delhi-6
Raaz: The Mystery Continues
Aasma: The Sky Is the Limit
Ajab Prem Ki Ghazab Kahani
Chal Chala Chal
Billu
The Stoneman Murders
Kisse Pyaar Karoon
Dhoondte Reh Jaaoge
Karma Aur Holi
Victory (2009 film)
Kaminey
Jai Veeru
Little Zizou
Gulaal (film)
Aloo Chaat (film)
Barah Aana
Firaaq
Aa Dekhen Zara
99 (2009 film)
Ek: The Power of One

85
Ek Se Bure Do
Sikandar (2009 film)
Zor Lagaa Ke…Haiya!
Paying Guests
New York (2009 film)
Sankat City
Shortkut
Luck (2009 film)
Life Partner
Daddy Cool (2009 Hindi film)
Kisaan
Yeh Mera India
Aagey Se Right
Chintu Ji
Quick Gun Murugun
Fox (film)
Baabarr
Phir Kabhi
Vaada Raha
Dil Bole Hadippa!
What's Your Raashee?
Acid Factory
All the Best: Fun Begins
Wake Up Sid
Main Aurr Mrs Khanna
Blue (2009 film)
Fruit and Nut (film)
Aladin (film)
London Dreams
Jail (2009 film)
Tum Mile
Kurbaan (2009 film)
De Dana Dan
Paa (film)
Rocket Singh: Salesman of the Year
Raat Gayi Baat Gayi?
Accident on Hill Road
Chandni Chowk to China
Dostana (2008 film)
Race (2008 film)
Rab Ne Bana Di Jodi
Ghajini (2008 film)
Singh Is Kinng
Golmaal Returns
Jodhaa Akbar
Bachna Ae Haseeno
Bhoothnath
Sarkar Raj

86
Halla Bol
Humne Jeena Seekh Liya
Bombay to Bangkok
Tulsi (film)
Sunday (2008 film)
One Two Three
Krazzy 4
U Me Aur Hum
Sirf (film)
Tashan (film)
Anamika (2008 film)
Jimmy (2008 film)
Jannat (film)
Don Muthu Swami
Woodstock Villa
Mere Baap Pehle Aap
Summer 2007
De Taali
Haal-e-Dil
Thodi Life Thoda Magic
Thoda Pyaar Thoda Magic
Via Darjeeling
Kismat Konnection
Love Story 2050
Contract (2008 film)
Mission Istaanbul
Money Hai Toh Honey Hai
God Tussi Great Ho
Mumbai Meri Jaan
Maan Gaye Mughal-e-Azam
Rock On!!
C Kkompany
Chamku
Mukhbiir
Tahaan
1920 (film)
The Last Lear
Welcome to Sajjanpur
Saas Bahu Aur Sensex
Hari Puttar: A Comedy of Terrors
Drona (2008 film)
Hello (2008 film)
Karzzzz
Heroes (2008 film)
Roadside Romeo
Ek Vivaah… Aisa Bhi
Deshdrohi
Fashion (2008 film)

87
Dasvidaniya
Yuvvraaj
Oye Lucky! Lucky Oye!
Oh My God (2008 film)
Sorry Bhai!
1971 (2007 film)
Meerabai Not Out
Wafa: A Deadly Love Story
Gumnaam – The Mystery
Dil Kabaddi
Aag (2007 film)
Aap Kaa Surroor
Aggar (film)
Anwar (2007 film)
Aaja Nachle
Apne
Awarapan
Bheja Fry (film)
Bhool Bhulaiyaa
Bhram
Big Brother (2007 film)
68 Pages
Aur Pappu Paas Ho Gaya
Apna Asmaan
Black Friday (2007 film)
The Blue Umbrella (2005 film)
Blood Brothers (2007 Indian film)
Buddha Mar Gaya
Cash (2007 film)
Cheeni Kum
Chhodon Naa Yaar
Darling (2007 Indian film)
Chak De! India
Dhamaal
Goal (2007 Hindi film)
Dharm (film)
Bombay to Goa (2007 film)
Dhokha
Dil Dosti Etc
Dhol (film)
Ek Chalis Ki Last Local
Familywala
Gandhi My Father
Don't Stop Dreaming
Dus Kahaniyaan
Eklavya: The Royal Guard
Go (2007 film)
Gauri: The Unborn

88
Heyy Babyy
Guru (2007 film)
Honeymoon Travels Pvt. Ltd.
Jahan Jaaeyega Hamen Paaeyega
Jhoom Barabar Jhoom
Jab We Met
Good Boy Bad Boy
Fool & Final
Khoya Khoya Chand
Johnny Gaddaar
Just Married (2007 film)
Kya Love Story Hai
Kudiyon Ka Hai Zamana
Hastey Hastey
Laaga Chunari Mein Daag
Life in a… Metro
Loins of Punjab Presents
Manorama Six Feet Under
Marigold (2007 film)
MP3: Mera Pehla Pehla Pyaar
Hattrick (film)
Naqaab
Mumbai Salsa
The Namesake (film)
Namastey London
My Bollywood Bride
Nehlle Pe Dehlla
Nishabd
No Smoking (2007 film)
Om Shanti Om
Partner (2007 film)
Raqeeb
Nanhe Jaisalmer
Life Mein Kabhie Kabhiee
Risk (2007 film)
Shakalaka Boom Boom
Red Swastik
Salaam-e-Ishq: A Tribute to Love
Saawariya
Sarhad Paar
Say Salaam India
Red: The Dark Side
Shootout at Lokhandwala
Strangers (2007 Hindi film)
Swami (2007 film)
Taare Zameen Par
Ta Ra Rum Pum
Speed (2007 film)

89
Traffic Signal (film)
The Train (2007 film)
Showbiz (film)
Sunglass (film)
Welcome (2007 film)
36 China Town
Zamaanat
Aap Ki Khatir (2006 film)
Ahista Ahista (2006 film)
Aksar
Alag
Anthony Kaun Hai?
Apna Sapna Money Money
Ankahee (2006 film)
Yatra (2007 film)
Baabul (2006 film)
Aisa Kyon Hota Hai?
Adharm (2006 film)
Being Cyrus
Banaras (2006 film)
Bas Ek Pal
Bhagam Bhag
Chingaari
Bhoot Unkle
Chand Ke Paar Chalo (film)
Aryan: Unbreakable
Chup Chup Ke
Corporate (2006 film)
Darna Zaroori Hai
Deadline: Sirf 24 Ghante
Dil Diya Hai
Darwaaza Bandh Rakho
Eight: The Power of Shani
Dhoom 2
Dor (film)
Don (2006 Hindi film)
Family (2006 film)
Fanaa (2006 film)
Gangster (2006 film)
Golmaal: Fun Unlimited
Devaki (2005 film)
Fight Club – Members Only
Dharti Kahe Pukar Ke (2006 film)
Humko Deewana Kar Gaye
Humko Tumse Pyaar Hai
I See You (2006 film)
Jaane Hoga Kya
Jaan-E-Mann

90
Jawani Diwani: A Youthful Joyride
Holiday (2006 film)
Iqraar by Chance
Khosla Ka Ghosla
Kabhi Alvida Naa Kehna
Love Ke Chakkar Mein
Lage Raho Munna Bhai
Kabul Express
Jigyaasa
Krrish
Malamaal Weekly
Omkara (2006 film)
Pyaar Ke Side Effects
Naksha
Phir Hera Pheri
Pyare Mohan
Mere Jeevan Saathi (2006 film)
Prateeksha
Sacred Evil – A True Story
Rang De Basanti
Shaadi Karke Phas Gaya Yaar
Sandwich (2006 film)
Shaadi Se Pehle
Saawan… The Love Season
Shiva (2006 film)
Souten: The Other Woman
Shikhar (film)
Children of Heaven
Tathastu
The Killer (2006 film)
Umrao Jaan (2006 film)
Taxi No. 9211
Teesri Aankh: The Hidden Camera
Vivah
Utthaan
Waris Shah: Ishq Daa Waaris
Woh Lamhe…
Yun Hota Toh Kya Hota
Umar (film)
Zindaggi Rocks
Tom Dick and Harry (2006 film)
Aashiq Banaya Aapne
Anjaane (2005 film)
Apaharan
Bachke Rehna Re Baba
7½ Phere
Barsaat (2005 film)
Bewafaa (2005 film)

91
Black (2005 film)
Zinda (film)
Bluffmaster!
99.9 FM (film)
Bhola in Bollywood
Bhagmati (2005 film)
Blackmail (2005 film)
Bunty Aur Babli
Chaahat – Ek Nasha
Chetna: The Excitement
Chand Sa Roshan Chehra
Chocolate (2005 film)
D (film)
Deewane Huye Paagal
Bullet: Ek Dhamaka
Chehraa
Dil Jo Bhi Kahey…
Dosti: Friends Forever
Classic – Dance of Love
Dus
Elaan (2005 film)
Fareb (2005 film)
Ek Ajnabee
Fun – Can Be Dangerous Sometimes
Ek Khiladi Ek Haseena (film)
Double Cross (2005 film)
Dreams (2006 film)
Home Delivery
Garam Masala (2005 film)
Iqbal (film)
Jai Chiranjeeva
Hazaaron Khwaishein Aisi
Insan
Jo Bole So Nihaal (film)
Karam (film)
Kaal (2005 film)
Kalyug (2005 film)
Kasak (2005 film)
Hanuman (2005 film)
James (2005 film)
Kisna: The Warrior Poet
Koi Aap Sa
Khamoshh… Khauff Ki Raat
Jurm (2005 film)
Kuchh Meetha Ho Jaye
Kyaa Kool Hai Hum
Lucky: No Time for Love
Main Aisa Hi Hoon

92
Kyon Ki
Main Meri Patni Aur Woh
Maine Gandhi Ko Nahin Mara
Maine Pyaar Kyun Kiya?
Mangal Pandey: The Rising
Koi Mere Dil Mein Hai
Mr Prime Minister
My Brother…Nikhil
My Wife's Murder
Naina (2005 film)
Neal 'n' Nikki
No Entry
Padmashree Laloo Prasad Yadav
Page 3 (film)
Morning Raga
Parineeta (2005 film)
Pehchaan: The Face of Truth
Paheli
Rog
Pyaar Mein Twist
Salaam Namaste
Revati (film)
Sarkar (2005 film)
Sehar
Shabd (film)
Shabnam Mausi
Sheesha (2005 film)
Ramji Londonwaley
Silsiilay
Socha Na Tha
Taj Mahal: An Eternal Love Story
Tango Charlie
The Film
Vaada (film)
Vaah! Life Ho Toh Aisi!
Ssukh
Shaadi No. 1
Viruddh… Family Comes First
Waqt: The Race Against Time
Vidyaarthi
Yakeen (2005 film)
Zeher
Veer-Zaara
Main Hoon Na
Zameer: The Fire Within
Mujhse Shaadi Karogi
Dhoom
Khakee

93
Hum Tum
Hulchul (2004 film)
Murder (2004 film)
Yuva
Aitraaz
Aetbaar
Ab Tumhare Hawale Watan Saathiyo
Aan: Men at Work
Bardaasht
Chameli (film)
Agnipankh
Asambhav
Charas (2004 film)
Deewaar (2004 film)
Dev (2004 film)
Dil Maange More
Dil Ne Jise Apna Kahaa
Dobara
Aabra Ka Daabra
Dil Bechara Pyaar Ka Maara
Gayab
Fida
Garv: Pride & Honour
Ek Se Badhkar Ek (2004 film)
Ek Hasina Thi (film)
Girlfriend (2004 film)
Hatya (2004 film)
Hava Aney Dey
Hawas (2004 film)
Hyderabad Blues 2
Julie (2004 film)
Kaun Hai Jo Sapno Mein Aaya
Inteqam: The Perfect Game
Kis Kis Ki Kismat
Insaaf: The Justice
I Proud to Be an Indian
Khamosh Pani
Kismat (2004 film)
Lakeer – Forbidden Lines
Krishna Cottage
Kyun! Ho Gaya Na…
Madhoshi
Lakshya (film)
Ishq Hai Tumse
Maqbool
Masti (2004 film)
Meenaxi: A Tale of Three Cities
Musafir (2004 film)

94
Mughal-e-Azam
Muskaan
Meri Biwi Ka Jawaab Nahin
Naach (2004 film)
Netaji Subhas Chandra Bose: The Forgotten Hero
Paap
Phir Milenge
Plan (film)
Police Force: An Inside Story
Paisa Vasool
Popcorn Khao! Mast Ho Jao
Rakht
Raincoat (film)
Rudraksh (film)
Shaadi Ka Laddoo
Run (2004 film)
Rok Sako To Rok Lo
Suno Sasurjee
Swades
Taarzan: The Wonder Car
Nothing but Life
Shart: The Challenge
Tumsa Nahin Dekha: A Love Story
Vaastu Shastra (film)
Yeh Lamhe Judaai Ke
Sheen (film)
Dude Where's the Party?
Thoda Tum Badlo Thoda Hum
Koi… Mil Gaya
Kal Ho Naa Ho
Shukriya: Till Death Do Us Apart
Chalte Chalte (2003 film)
The Hero: Love Story of a Spy
Baghban (2003 film)
Main Prem Ki Diwani Hoon
LOC Kargil
Border (1997 film)
Munna Bhai M.B.B.S.
Qayamat: City Under Threat
88 Antop Hill
3 Deewarein
Aanch
Aapko Pehle Bhi Kahin Dekha Hai
Bhoot (film)
Boom (film)
Aaj Ka Andha Kanoon
Andaaz
Andaaz

95
Armaan (2003 film)
Chori Chori (2003 film)
Calcutta Mail
Baaz: A Bird in Danger
Basti (film)
Magic Magic 3D
Dil Ka Rishta
Darna Mana Hai
Dhoop
Dhund (2003 film)
Chura Liyaa Hai Tumne
The Bypass
Dum (2003 Hindi film)
Dil Pardesi Ho Gayaa
Ek Alag Mausam
Footpath (2003 film)
Escape from Taliban
Ek Din 24 Ghante
Gangaajal
Hawa (film)
Haasil
Ek Aur Ek Gyarah
Hungama (2003 film)
Green Card Fever
Flavors (film)
Indian Babu
Fun2shh… Dudes in the 10th Century
Inteha (2003 film)
Jaal: The Trap
Ishq Vishk
Hawayein
Jajantaram Mamantaram
Jism (2003 film)
Jhankaar Beats
Kagaar: Life on the Edge
Kash Aap Hamare Hote
Khel – No Ordinary Game
Janasheen
Kaise Kahoon Ke… Pyaar Hai
Khushi (2003 Hindi film)
Khwahish
Kucch To Hai
Kuch Naa Kaho
Main Madhuri Dixit Banna Chahti Hoon
Joggers' Park (film)
Market (2003 film)
Om (2003 film)
Out of Control (2003 film)

96
 Mumbai Matinee
Matrubhoomi
Parwana (2003 film)
Pinjar (film)
Mumbai Se Aaya Mera Dost
Saaya (2003 film)
Samay: When Time Strikes
Nayee Padosan
Satta (film)
Sssshhh…
Praan Jaye Par Shaan Na Jaye
Raghu Romeo
Stumped (film)
Rules: Pyaar Ka Superhit Formula
Right Here Right Now (film)
Raja Bhaiya (film)
Tere Naam
Tujhe Meri Kasam
Talaash: The Hunt Begins…
Tehzeeb (2003 film)
The Pink Mirror
Yeh Dil
Xcuse Me
Raaz (2002 film)
Zameen (2003 film)
Waisa Bhi Hota Hai Part II
Devdas (2002 Hindi film)
Kaante
Hum Tumhare Hain Sanam
Aankhen (2002 film)
Saathiya (film)
Company (film)
Awara Paagal Deewana

[ ]: # Arithmetic Operators

100 - marks

[ ]: maths 16
english 0
science 11
hindi 3
sst 13
Name: Dilkhush's Marks, dtype: int32

[ ]: # Relational Operators

97
 vk[vk>50]

[ ]: match_no
34 58
41 71
44 56
45 67
52 70
57 57
68 73
71 51
73 58
74 65
80 57
81 93
82 99
85 56
97 67
99 73
103 51
104 62
110 82
116 75
117 79
119 80
120 100
122 52
123 108
126 109
127 75
128 113
129 54
131 54
132 62
134 64
137 55
141 58
144 57
145 92
148 68
152 70
160 84
162 67
164 100
175 72
178 90
188 72

98
 197 51
198 53
209 58
213 73
Name: runs, dtype: int32

0.11 Boolean Indexing on Series

[ ]: # Find 50's and 100's scored by kohli

vk[(vk==50) | (vk==100)]

[ ]: match_no
15 50
120 100
164 100
182 50
Name: runs, dtype: int32

[ ]: # find number of ducks

vk[vk==0].size

[ ]: 9

[ ]: # count no of days when subscriber gain is more than 200

subs[subs>200].size

[ ]: 59

[ ]: # find actors who have done more than 20 movies

num_movies = movies.value_counts()
num_movies[num_movies>20]

[ ]: lead
Akshay Kumar 48
Amitabh Bachchan 45
Ajay Devgn 38
Salman Khan 31
Sanjay Dutt 26
Shah Rukh Khan 22
Emraan Hashmi 21
Name: count, dtype: int64

99
 0.12 Plotting Graphs on Series
[ ]: subs.plot()

[ ]: <Axes: >

[ ]: movies.value_counts().head(20).plot(kind='bar')

[ ]: <Axes: xlabel='lead'>

100
[ ]: movies.value_counts().head(20).plot(kind='pie')

[ ]: <Axes: ylabel='count'>

101
 0.13 Important series methods
0.13.1 ser.astype(‘new_datatype’)
• Change the datatype of series.
• no permanent changes.
[ ]: import sys
sys.getsizeof(vk)

[ ]: 8000

[ ]: sys.getsizeof(vk.astype('int16'))

[ ]: 7570

0.13.2 ser.between(start, end)

• returns boolean series including start and end.
[ ]: vk[vk.between(51, 99)]

[ ]: match_no
34 58

102
41 71
44 56
45 67
52 70
57 57
68 73
71 51
73 58
74 65
80 57
81 93
82 99
85 56
97 67
99 73
103 51
104 62
110 82
116 75
117 79
119 80
122 52
127 75
129 54
131 54
132 62
134 64
137 55
141 58
144 57
145 92
148 68
152 70
160 84
162 67
175 72
178 90
188 72
197 51
198 53
209 58
213 73
Name: runs, dtype: int32

0.13.3 ser.clip
• returns a series in which all the values are clipped in the given range.

103
 • no change in original series
[ ]: subs.clip(100, 200)

[ ]: 0 100
1 100
2 100
3 100
4 100
…
360 200
361 200
362 155
363 144
364 172
Name: Subscribers gained, Length: 365, dtype: int64

0.13.4 series.drop_duplicates(keep=‘first’)
• return a series in which duplicated values are dropped.
• keep parameter decides which occurence to be included into series.
• by default it keeps first occurence.
[ ]: temp = pd.Series([1,1,2,2,3,3,4,4])
temp

[ ]: 0 1
1 1
2 2
3 2
4 3
5 3
6 4
7 4
dtype: int64

[ ]: temp.drop_duplicates()

[ ]: 0 1
2 2
4 3
6 4
dtype: int64

[ ]: temp.drop_duplicates(keep='last')

[ ]: 1 1
3 2

104
 5 3
7 4
dtype: int64

0.13.5 ser.duplicated()
• returns a boolean series, if values is duplicated it is true.
[ ]: temp.duplicated()

[ ]: 0 False
1 True
2 False
3 True
4 False
5 True
6 False
7 True
dtype: bool

[ ]: temp.duplicated().sum()

[ ]: 4

0.13.6 ser.size
• returns total values in the series

0.13.7 ser.count()
• returns total not-NaN values
[ ]: temp = pd.Series([1,2,3,np.nan,5,6,np.nan,8,np.nan,10])
temp

[ ]: 0 1.0
1 2.0
2 3.0
3 NaN
4 5.0
5 6.0
6 NaN
7 8.0
8 NaN
9 10.0
dtype: float64

[ ]: temp.size

105
[ ]: 10

[ ]: temp.count()

[ ]: 7

0.13.8 ser.isnull()
• returns a boolean series in which every element is checked whether is it null or not
[ ]: temp.isnull().sum()

[ ]: 3

0.13.9 ser.dropna()
• returns a series after dropping all the Nan values.
[ ]: temp.dropna()

[ ]: 0 1.0
1 2.0
2 3.0
4 5.0
5 6.0
7 8.0
9 10.0
dtype: float64

0.13.10 ser.fillna()
• returns a series in which NaN values are filled using some conditions
[ ]: temp.fillna(0)

[ ]: 0 1.0
1 2.0
2 3.0
3 0.0
4 5.0
5 6.0
6 0.0
7 8.0
8 0.0
9 10.0
dtype: float64

[ ]: temp.fillna(temp.mean())

106
[ ]: 0 1.0
1 2.0
2 3.0
3 5.0
4 5.0
5 6.0
6 5.0
7 8.0
8 5.0
9 10.0
dtype: float64

0.13.11 ser.isin(list_of_items)
• returns a boolean series which checks the elements of provided list are in the series or not
[ ]: vk[vk.isin([49, 99])]

[ ]: match_no
82 99
86 49
Name: runs, dtype: int32

0.13.12 ser.apply(func)
• returns series after applying the given function on all the values.
[ ]: movies.apply(lambda x: x.split()[0].upper())

[ ]: movie
Uri: The Surgical Strike VICKY
Battalion 609 VICKY
The Accidental Prime Minister (film) ANUPAM
Why Cheat India EMRAAN
Evening Shadows MONA
…
Hum Tumhare Hain Sanam SHAH
Aankhen (2002 film) AMITABH
Saathiya (film) VIVEK
Company (film) AJAY
Awara Paagal Deewana AKSHAY
Name: lead, Length: 1500, dtype: object

[ ]: subs.apply(lambda x:'good day' if x>subs.mean() else 'bad day')

[ ]: 0 bad day
1 bad day
2 bad day

107
 3 bad day
4 bad day
…
360 good day
361 good day
362 good day
363 good day
364 good day
Name: Subscribers gained, Length: 365, dtype: object

0.13.13 ser.copy()
• copy the series
[ ]: vk

[ ]: match_no
1 1
2 23
3 13
4 12
5 1
..
211 0
212 20
213 73
214 25
215 7
Name: runs, Length: 215, dtype: int32

[ ]: new = vk.head()
new

[ ]: match_no
1 1
2 23
3 13
4 12
5 1
Name: runs, dtype: int32

[ ]: new[1] = 100
new

[ ]: match_no
1 100
2 23

108
 3 13
4 12
5 1
Name: runs, dtype: int32

[ ]: vk

[ ]: match_no
1 100
2 23
3 13
4 12
5 1
…
211 0
212 20
213 73
214 25
215 7
Name: runs, Length: 215, dtype: int32

[ ]: new = vk.head().copy()
new

[ ]: match_no
1 100
2 23
3 13
4 12
5 1
Name: runs, dtype: int32

[ ]: new[1] = 1
new

[ ]: match_no
1 1
2 23
3 13
4 12
5 1
Name: runs, dtype: int32

[ ]: vk

[ ]: match_no
1 100

109
 2 23
3 13
4 12
5 1
…
211 0
212 20
213 73
214 25
215 7
Name: runs, Length: 215, dtype: int32

[5]: import numpy as np

import pandas as pd

1 DataFrame
A DataFrame represents a rectangular table of data and contains an ordered, named collection
of columns, each of which can be a different value type (numeric, string, Boolean, etc.). The
DataFrame has both a row and column index; it can be thought of as a dictionary of Series all
sharing the same index.

1.1 Creating DataFrame

Type Notes
2D ndarray A matrix of data, passing optional row and column labels
Dictionary of arrays, Each sequence becomes a column in the DataFrame; all sequences must
lists, or tuples be the same length
NumPy Treated as the “dictionary of arrays” case
structured/record
array
Dictionary of Series Each value becomes a column; indexes from each Series are unioned
together to form the result’s row index if no explicit index is passed
Dictionary of Each inner dictionary becomes a column; keys are unioned to form the
dictionaries row index as in the “dictionary of Series” case
List of dictionaries Each item becomes a row in the DataFrame; unions of dictionary keys
or Series or Series indexes become the DataFrame’s column labels
List of lists or tuples Treated as the “2D ndarray” case
Another DataFrame The DataFrame’s indexes are used unless different ones are passed
NumPy Like the “2D ndarray” case except masked values are missing in the
MaskedArray DataFrame result

110
 1.1.1 From Lists
[6]: student_data = [
[100, 80, 10],
[90, 70, 7],
[120, 100, 14],
[80, 50, 2]
]

pd.DataFrame(student_data, columns=['iq', 'marks', 'package'])

[6]: iq marks package

0 100 80 10
1 90 70 7
2 120 100 14
3 80 50 2

1.1.2 From Dictionary

[7]: student_dict = {
'name':['dilkush', 'ankit', 'neeraj', 'ritu', 'pankaj', 'pankaj'],
'iq':[100, 90, 120, 80, 0, 0],
'marks':[80, 70, 100, 50, 0, 0],
'package':[10, 7, 14, 2, 0, 0]
}

students = pd.DataFrame(student_dict)
students

[7]: name iq marks package

0 dilkush 100 80 10
1 ankit 90 70 7
2 neeraj 120 100 14
3 ritu 80 50 2
4 pankaj 0 0 0
5 pankaj 0 0 0

Assigning names of index and columns

[8]: students.index.name = 'ser no.'
students.columns.name = 'details'

[9]: students

[9]: details name iq marks package

ser no.
0 dilkush 100 80 10
1 ankit 90 70 7

111
 2 neeraj 120 100 14
3 ritu 80 50 2
4 pankaj 0 0 0
5 pankaj 0 0 0

Adding another column

[10]: students['age'] = np.nan

[11]: students

[11]: details name iq marks package age

ser no.
0 dilkush 100 80 10 NaN
1 ankit 90 70 7 NaN
2 neeraj 120 100 14 NaN
3 ritu 80 50 2 NaN
4 pankaj 0 0 0 NaN
5 pankaj 0 0 0 NaN

[12]: students['age'] = 20

[13]: students

[13]: details name iq marks package age

ser no.
0 dilkush 100 80 10 20
1 ankit 90 70 7 20
2 neeraj 120 100 14 20
3 ritu 80 50 2 20
4 pankaj 0 0 0 20
5 pankaj 0 0 0 20

[14]: del students['age']

[15]: students

[15]: details name iq marks package

ser no.
0 dilkush 100 80 10
1 ankit 90 70 7
2 neeraj 120 100 14
3 ritu 80 50 2
4 pankaj 0 0 0
5 pankaj 0 0 0

112
 1.1.3 From csv files
[16]: movies = pd.read_csv('movies.csv')
movies

[16]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208
2 The Accidental Prime Minister (film) tt6986710
3 Why Cheat India tt8108208
4 Evening Shadows tt6028796
… … …
1624 Tera Mera Saath Rahen tt0301250
1625 Yeh Zindagi Ka Safar tt0298607
1626 Sabse Bada Sukh tt0069204
1627 Daaka tt10833860
1628 Humsafar tt2403201

poster_path \
0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN
2 https://upload.wikimedia.org/wikipedia/en/thum…
3 https://upload.wikimedia.org/wikipedia/en/thum…
4 NaN
… …
1624 https://upload.wikimedia.org/wikipedia/en/2/2b…
1625 https://upload.wikimedia.org/wikipedia/en/thum…
1626 NaN
1627 https://upload.wikimedia.org/wikipedia/en/thum…
1628 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
1 https://en.wikipedia.org/wiki/Battalion_609
2 https://en.wikipedia.org/wiki/The_Accidental_P…
3 https://en.wikipedia.org/wiki/Why_Cheat_India
4 https://en.wikipedia.org/wiki/Evening_Shadows
… …
1624 https://en.wikipedia.org/wiki/Tera_Mera_Saath_…
1625 https://en.wikipedia.org/wiki/Yeh_Zindagi_Ka_S…
1626 https://en.wikipedia.org/wiki/Sabse_Bada_Sukh
1627 https://en.wikipedia.org/wiki/Daaka
1628 https://en.wikipedia.org/wiki/Humsafar

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
1 Battalion 609 Battalion 609 0

113
2 The Accidental Prime Minister The Accidental Prime Minister 0
3 Why Cheat India Why Cheat India 0
4 Evening Shadows Evening Shadows 0
… … … …
1624 Tera Mera Saath Rahen Tera Mera Saath Rahen 0
1625 Yeh Zindagi Ka Safar Yeh Zindagi Ka Safar 0
1626 Sabse Bada Sukh Sabse Bada Sukh 0
1627 Daaka Daaka 0
1628 Humsafar Humsafar 0

year_of_release runtime genres imdb_rating imdb_votes \

0 2019 138 Action|Drama|War 8.4 35112
1 2019 131 War 4.1 73
2 2019 112 Biography|Drama 6.1 5549
3 2019 121 Crime|Drama 6.0 1891
4 2018 102 Drama 7.3 280
… … … … … …
1624 2001 148 Drama 4.9 278
1625 2001 146 Drama 3.0 133
1626 2018 \N Comedy|Drama 6.1 13
1627 2019 136 Action 7.4 38
1628 2011 35 Drama|Romance 9.0 2968

story \
0 Divided over five chapters the film chronicle…
1 The story revolves around a cricket match betw…
2 Based on the memoir by Indian policy analyst S…
3 The movie focuses on existing malpractices in …
4 While gay rights and marriage equality has bee…
… …
1624 Raj Dixit lives with his younger brother Rahu…
1625 Hindi pop-star Sarina Devan lives a wealthy …
1626 Village born Lalloo re-locates to Bombay and …
1627 Shinda tries robbing a bank so he can be wealt…
1628 Sara and Ashar are childhood friends who share…

summary tagline \
0 Indian army special forces execute a covert op… NaN
1 The story of Battalion 609 revolves around a c… NaN
2 Explores Manmohan Singh's tenure as the Prime … NaN
3 The movie focuses on existing malpractices in … NaN
4 Under the 'Evening Shadows' truth often plays… NaN
… … …
1624 A man is torn between his handicapped brother … NaN
1625 A singer finds out she was adopted when the ed… NaN
1626 Village born Lalloo re-locates to Bombay and … NaN
1627 Shinda tries robbing a bank so he can be wealt… NaN

114
 1628 Ashar and Khirad are forced to get married due… NaN

actors \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga…
1 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen…
2 Anupam Kher|Akshaye Khanna|Aahana Kumra|Atul S…
3 Emraan Hashmi|Shreya Dhanwanthary|Snighdadeep …
4 Mona Ambegaonkar|Ananth Narayan Mahadevan|Deva…
… …
1624 Ajay Devgn|Sonali Bendre|Namrata Shirodkar|Pre…
1625 Ameesha Patel|Jimmy Sheirgill|Nafisa Ali|Gulsh…
1626 Vijay Arora|Asrani|Rajni Bala|Kumud Damle|Utpa…
1627 Gippy Grewal|Zareen Khan|
1628 Fawad Khan|

wins_nominations release_date
0 4 wins 11 January 2019 (USA)
1 NaN 11 January 2019 (India)
2 NaN 11 January 2019 (USA)
3 NaN 18 January 2019 (USA)
4 17 wins & 1 nomination 11 January 2019 (India)
… … …
1624 NaN 7 November 2001 (India)
1625 NaN 16 November 2001 (India)
1626 NaN NaN
1627 NaN 1 November 2019 (USA)
1628 NaN TV Series (2011–2012)

[1629 rows x 18 columns]

[17]: ipl = pd.read_csv('ipl-matches.csv')

ipl

[17]: ID City Date Season MatchNumber \

0 1312200 Ahmedabad 2022-05-29 2022 Final
1 1312199 Ahmedabad 2022-05-27 2022 Qualifier 2
2 1312198 Kolkata 2022-05-25 2022 Eliminator
3 1312197 Kolkata 2022-05-24 2022 Qualifier 1
4 1304116 Mumbai 2022-05-22 2022 70
.. … … … … …
945 335986 Kolkata 2008-04-20 2007/08 4
946 335985 Mumbai 2008-04-20 2007/08 5
947 335984 Delhi 2008-04-19 2007/08 3
948 335983 Chandigarh 2008-04-19 2007/08 2
949 335982 Bangalore 2008-04-18 2007/08 1

Team1 Team2 \

115
0 Rajasthan Royals Gujarat Titans
1 Royal Challengers Bangalore Rajasthan Royals
2 Royal Challengers Bangalore Lucknow Super Giants
3 Rajasthan Royals Gujarat Titans
4 Sunrisers Hyderabad Punjab Kings
.. … …
945 Kolkata Knight Riders Deccan Chargers
946 Mumbai Indians Royal Challengers Bangalore
947 Delhi Daredevils Rajasthan Royals
948 Kings XI Punjab Chennai Super Kings
949 Royal Challengers Bangalore Kolkata Knight Riders

Venue TossWinner \
0 Narendra Modi Stadium, Ahmedabad Rajasthan Royals
1 Narendra Modi Stadium, Ahmedabad Rajasthan Royals
2 Eden Gardens, Kolkata Lucknow Super Giants
3 Eden Gardens, Kolkata Gujarat Titans
4 Wankhede Stadium, Mumbai Sunrisers Hyderabad
.. … …
945 Eden Gardens Deccan Chargers
946 Wankhede Stadium Mumbai Indians
947 Feroz Shah Kotla Rajasthan Royals
948 Punjab Cricket Association Stadium, Mohali Chennai Super Kings
949 M Chinnaswamy Stadium Royal Challengers Bangalore

TossDecision SuperOver WinningTeam WonBy Margin \

0 bat N Gujarat Titans Wickets 7.0
1 field N Rajasthan Royals Wickets 7.0
2 field N Royal Challengers Bangalore Runs 14.0
3 field N Gujarat Titans Wickets 7.0
4 bat N Punjab Kings Wickets 5.0
.. … … … … …
945 bat N Kolkata Knight Riders Wickets 5.0
946 bat N Royal Challengers Bangalore Wickets 5.0
947 bat N Delhi Daredevils Wickets 9.0
948 bat N Chennai Super Kings Runs 33.0
949 field N Kolkata Knight Riders Runs 140.0

method Player_of_Match Team1Players \

0 NaN HH Pandya ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
1 NaN JC Buttler ['V Kohli', 'F du Plessis', 'RM Patidar', 'GJ …
2 NaN RM Patidar ['V Kohli', 'F du Plessis', 'RM Patidar', 'GJ …
3 NaN DA Miller ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
4 NaN Harpreet Brar ['PK Garg', 'Abhishek Sharma', 'RA Tripathi', …
.. … … …
945 NaN DJ Hussey ['WP Saha', 'BB McCullum', 'RT Ponting', 'SC G…
946 NaN MV Boucher ['L Ronchi', 'ST Jayasuriya', 'DJ Thornely', '…

116
 947 NaN MF Maharoof ['G Gambhir', 'V Sehwag', 'S Dhawan', 'MK Tiwa…
948 NaN MEK Hussey ['K Goel', 'JR Hopes', 'KC Sangakkara', 'Yuvra…
949 NaN BB McCullum ['R Dravid', 'W Jaffer', 'V Kohli', 'JH Kallis…

Team2Players Umpire1 \
0 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… CB Gaffaney
1 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D … CB Gaffaney
2 ['Q de Kock', 'KL Rahul', 'M Vohra', 'DJ Hooda… J Madanagopal
3 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… BNJ Oxenford
4 ['JM Bairstow', 'S Dhawan', 'M Shahrukh Khan',… AK Chaudhary
.. … …
945 ['AC Gilchrist', 'Y Venugopal Rao', 'VVS Laxma… BF Bowden
946 ['S Chanderpaul', 'R Dravid', 'LRPL Taylor', '… SJ Davis
947 ['T Kohli', 'YK Pathan', 'SR Watson', 'M Kaif'… Aleem Dar
948 ['PA Patel', 'ML Hayden', 'MEK Hussey', 'MS Dh… MR Benson
949 ['SC Ganguly', 'BB McCullum', 'RT Ponting', 'D… Asad Rauf

Umpire2
0 Nitin Menon
1 Nitin Menon
2 MA Gough
3 VK Sharma
4 NA Patwardhan
.. …
945 K Hariharan
946 DJ Harper
947 GA Pratapkumar
948 SL Shastri
949 RE Koertzen

[950 rows x 20 columns]

1.2 DataFrame Attributes and Methods

1.2.1 DF.head(n=5)
• returns DF containing first n rows.
• if no n specified then by default n is 5
[18]: movies.head(2)

[18]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208

poster_path \
0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN

117
 wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
1 https://en.wikipedia.org/wiki/Battalion_609

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
1 Battalion 609 Battalion 609 0

year_of_release runtime genres imdb_rating imdb_votes \

0 2019 138 Action|Drama|War 8.4 35112
1 2019 131 War 4.1 73

story \
0 Divided over five chapters the film chronicle…
1 The story revolves around a cricket match betw…

summary tagline \
0 Indian army special forces execute a covert op… NaN
1 The story of Battalion 609 revolves around a c… NaN

actors wins_nominations \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga… 4 wins
1 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen… NaN

release_date
0 11 January 2019 (USA)
1 11 January 2019 (India)

1.2.2 DF.tail(n=5)
• same as DF.head(n), just returns last rows

[19]: ipl.tail()

[19]: ID City Date Season MatchNumber \

945 335986 Kolkata 2008-04-20 2007/08 4
946 335985 Mumbai 2008-04-20 2007/08 5
947 335984 Delhi 2008-04-19 2007/08 3
948 335983 Chandigarh 2008-04-19 2007/08 2
949 335982 Bangalore 2008-04-18 2007/08 1

Team1 Team2 \
945 Kolkata Knight Riders Deccan Chargers
946 Mumbai Indians Royal Challengers Bangalore
947 Delhi Daredevils Rajasthan Royals
948 Kings XI Punjab Chennai Super Kings

118
 949 Royal Challengers Bangalore Kolkata Knight Riders

Venue TossWinner \
945 Eden Gardens Deccan Chargers
946 Wankhede Stadium Mumbai Indians
947 Feroz Shah Kotla Rajasthan Royals
948 Punjab Cricket Association Stadium, Mohali Chennai Super Kings
949 M Chinnaswamy Stadium Royal Challengers Bangalore

TossDecision SuperOver WinningTeam WonBy Margin \

945 bat N Kolkata Knight Riders Wickets 5.0
946 bat N Royal Challengers Bangalore Wickets 5.0
947 bat N Delhi Daredevils Wickets 9.0
948 bat N Chennai Super Kings Runs 33.0
949 field N Kolkata Knight Riders Runs 140.0

method Player_of_Match Team1Players \

945 NaN DJ Hussey ['WP Saha', 'BB McCullum', 'RT Ponting', 'SC G…
946 NaN MV Boucher ['L Ronchi', 'ST Jayasuriya', 'DJ Thornely', '…
947 NaN MF Maharoof ['G Gambhir', 'V Sehwag', 'S Dhawan', 'MK Tiwa…
948 NaN MEK Hussey ['K Goel', 'JR Hopes', 'KC Sangakkara', 'Yuvra…
949 NaN BB McCullum ['R Dravid', 'W Jaffer', 'V Kohli', 'JH Kallis…

Team2Players Umpire1 \
945 ['AC Gilchrist', 'Y Venugopal Rao', 'VVS Laxma… BF Bowden
946 ['S Chanderpaul', 'R Dravid', 'LRPL Taylor', '… SJ Davis
947 ['T Kohli', 'YK Pathan', 'SR Watson', 'M Kaif'… Aleem Dar
948 ['PA Patel', 'ML Hayden', 'MEK Hussey', 'MS Dh… MR Benson
949 ['SC Ganguly', 'BB McCullum', 'RT Ponting', 'D… Asad Rauf

Umpire2
945 K Hariharan
946 DJ Harper
947 GA Pratapkumar
948 SL Shastri
949 RE Koertzen

[20]: data = {"state": ["Ohio", "Ohio", "Ohio", "Nevada", "Nevada", "Nevada"],

"year": [2000, 2001, 2002, 2001, 2002, 2003],
"pop": [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}

frame = pd.DataFrame(data)
frame

[20]: state year pop

0 Ohio 2000 1.5
1 Ohio 2001 1.7

119
 2 Ohio 2002 3.6
3 Nevada 2001 2.4
4 Nevada 2002 2.9
5 Nevada 2003 3.2

Note - If you specify a sequence of columns, the DataFrame’s columns will be arranged in that
order:
[21]: pd.DataFrame(data, columns=['year', 'pop', 'state'])

[21]: year pop state

0 2000 1.5 Ohio
1 2001 1.7 Ohio
2 2002 3.6 Ohio
3 2001 2.4 Nevada
4 2002 2.9 Nevada
5 2003 3.2 Nevada

1.2.3 DF.shape
• returns tuple containing shape of DataFrame
[22]: movies.shape

[22]: (1629, 18)

[23]: ipl.shape

[23]: (950, 20)

1.2.4 DF.dtypes
• returns series containing datatype of each column
[24]: movies.dtypes

[24]: title_x object

imdb_id object
poster_path object
wiki_link object
title_y object
original_title object
is_adult int64
year_of_release int64
runtime object
genres object
imdb_rating float64
imdb_votes int64

120
 story object
summary object
tagline object
actors object
wins_nominations object
release_date object
dtype: object

[25]: ipl.dtypes

[25]: ID int64
City object
Date object
Season object
MatchNumber object
Team1 object
Team2 object
Venue object
TossWinner object
TossDecision object
SuperOver object
WinningTeam object
WonBy object
Margin float64
method object
Player_of_Match object
Team1Players object
Team2Players object
Umpire1 object
Umpire2 object
dtype: object

1.2.5 DF.index
• returns RangeIndex object if index is not explicitely decided
[26]: movies.index

[26]: RangeIndex(start=0, stop=1629, step=1)

[27]: ipl.index

[27]: RangeIndex(start=0, stop=950, step=1)

1.2.6 DF.columns
• returns Index object containing all column names

121
[28]: movies.columns

[28]: Index(['title_x', 'imdb_id', 'poster_path', 'wiki_link', 'title_y',

'original_title', 'is_adult', 'year_of_release', 'runtime', 'genres',
'imdb_rating', 'imdb_votes', 'story', 'summary', 'tagline', 'actors',
'wins_nominations', 'release_date'],
dtype='object')

[29]: ipl.columns

[29]: Index(['ID', 'City', 'Date', 'Season', 'MatchNumber', 'Team1', 'Team2',

'Venue', 'TossWinner', 'TossDecision', 'SuperOver', 'WinningTeam',
'WonBy', 'Margin', 'method', 'Player_of_Match', 'Team1Players',
'Team2Players', 'Umpire1', 'Umpire2'],
dtype='object')

1.2.7 DF.values
• returns numpy ndarray containig all the values
[30]: students.values

[30]: array([['dilkush', 100, 80, 10],

['ankit', 90, 70, 7],
['neeraj', 120, 100, 14],
['ritu', 80, 50, 2],
['pankaj', 0, 0, 0],
['pankaj', 0, 0, 0]], dtype=object)

[31]: ipl.values

[31]: array([[1312200, 'Ahmedabad', '2022-05-29', …,

"['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pandya', 'DA Miller', 'R
Tewatia', 'Rashid Khan', 'R Sai Kishore', 'LH Ferguson', 'Yash Dayal', 'Mohammed
Shami']",
'CB Gaffaney', 'Nitin Menon'],
[1312199, 'Ahmedabad', '2022-05-27', …,
"['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D Padikkal', 'SO Hetmyer',
'R Parag', 'R Ashwin', 'TA Boult', 'YS Chahal', 'M Prasidh Krishna', 'OC
McCoy']",
'CB Gaffaney', 'Nitin Menon'],
[1312198, 'Kolkata', '2022-05-25', …,
"['Q de Kock', 'KL Rahul', 'M Vohra', 'DJ Hooda', 'MP Stoinis', 'E
Lewis', 'KH Pandya', 'PVD Chameera', 'Mohsin Khan', 'Avesh Khan', 'Ravi
Bishnoi']",
'J Madanagopal', 'MA Gough'],
…,

122
 [335984, 'Delhi', '2008-04-19', …,
"['T Kohli', 'YK Pathan', 'SR Watson', 'M Kaif', 'DS Lehmann', 'RA
Jadeja', 'M Rawat', 'D Salunkhe', 'SK Warne', 'SK Trivedi', 'MM Patel']",
'Aleem Dar', 'GA Pratapkumar'],
[335983, 'Chandigarh', '2008-04-19', …,
"['PA Patel', 'ML Hayden', 'MEK Hussey', 'MS Dhoni', 'SK Raina', 'JDP
Oram', 'S Badrinath', 'Joginder Sharma', 'P Amarnath', 'MS Gony', 'M
Muralitharan']",
'MR Benson', 'SL Shastri'],
[335982, 'Bangalore', '2008-04-18', …,
"['SC Ganguly', 'BB McCullum', 'RT Ponting', 'DJ Hussey', 'Mohammad
Hafeez', 'LR Shukla', 'WP Saha', 'AB Agarkar', 'AB Dinda', 'M Kartik', 'I
Sharma']",
'Asad Rauf', 'RE Koertzen']], dtype=object)

1.2.8 DF.sample(n=1)
• returns randomly selected n rows from the DF
[32]: ipl.sample(2)

[32]: ID City Date Season MatchNumber \

660 548350 Bangalore 2012-05-02 2012 44
338 1082626 Chandigarh 2017-04-30 2017 36

Team1 Team2 \
660 Royal Challengers Bangalore Kings XI Punjab
338 Kings XI Punjab Delhi Daredevils

Venue TossWinner \
660 M Chinnaswamy Stadium Kings XI Punjab
338 Punjab Cricket Association IS Bindra Stadium, … Kings XI Punjab

TossDecision SuperOver WinningTeam WonBy Margin method \

660 field N Kings XI Punjab Wickets 4.0 NaN
338 field N Kings XI Punjab Wickets 10.0 NaN

Player_of_Match Team1Players \
660 Azhar Mahmood ['MA Agarwal', 'CH Gayle', 'V Kohli', 'AB de V…
338 Sandeep Sharma ['MJ Guptill', 'HM Amla', 'M Vohra', 'SE Marsh…

Team2Players Umpire1 \
660 ['Mandeep Singh', 'SE Marsh', 'N Saini', 'DJ H… BF Bowden
338 ['SV Samson', 'SW Billings', 'KK Nair', 'SS Iy… YC Barde

Umpire2
660 C Shamshuddin

123
 338 CK Nandan

1.2.9 DF.info()
• returns DF containing various informations
[33]: movies.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1629 entries, 0 to 1628
Data columns (total 18 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 title_x 1629 non-null object
1 imdb_id 1629 non-null object
2 poster_path 1526 non-null object
3 wiki_link 1629 non-null object
4 title_y 1629 non-null object
5 original_title 1629 non-null object
6 is_adult 1629 non-null int64
7 year_of_release 1629 non-null int64
8 runtime 1629 non-null object
9 genres 1629 non-null object
10 imdb_rating 1629 non-null float64
11 imdb_votes 1629 non-null int64
12 story 1609 non-null object
13 summary 1629 non-null object
14 tagline 557 non-null object
15 actors 1624 non-null object
16 wins_nominations 707 non-null object
17 release_date 1522 non-null object
dtypes: float64(1), int64(3), object(14)
memory usage: 229.2+ KB

[34]: ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null int64
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null object
4 MatchNumber 950 non-null object
5 Team1 950 non-null object
6 Team2 950 non-null object

124
 7 Venue 950 non-null object
8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null object
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
dtypes: float64(1), int64(1), object(18)
memory usage: 148.6+ KB

1.2.10 DF.describe()
• only applies to numerical columns,
• returns DF containing various statistical info
[35]: movies.describe()

[35]: is_adult year_of_release imdb_rating imdb_votes

count 1629.0 1629.000000 1629.000000 1629.000000
mean 0.0 2010.263966 5.557459 5384.263352
std 0.0 5.381542 1.567609 14552.103231
min 0.0 2001.000000 0.000000 0.000000
25% 0.0 2005.000000 4.400000 233.000000
50% 0.0 2011.000000 5.600000 1000.000000
75% 0.0 2015.000000 6.800000 4287.000000
max 0.0 2019.000000 9.400000 310481.000000

1.2.11 DF.isnull()
• returns boolean DF, used with sum() to count total null values in each column of DF

[36]: movies.isnull().sum()

[36]: title_x 0
imdb_id 0
poster_path 103
wiki_link 0
title_y 0
original_title 0
is_adult 0
year_of_release 0
runtime 0

125
 genres 0
imdb_rating 0
imdb_votes 0
story 20
summary 0
tagline 1072
actors 5
wins_nominations 922
release_date 107
dtype: int64

1.2.12 DF.duplicated()
• return boolean DF
[37]: students.duplicated()

[37]: ser no.

0 False
1 False
2 False
3 False
4 False
5 True
dtype: bool

[38]: students.duplicated().sum()

[38]: 1

1.2.13 DF.rename(columns={‘existing_col_name’:‘new_col_name’}, in-

place=False)
• used to rename the columns.
• inplace parameter used to make permanent changes into DF
[39]: students.rename(columns={'marks':'percent', 'package':'lpa'}, inplace=True)

[40]: students

[40]: details name iq percent lpa

ser no.
0 dilkush 100 80 10
1 ankit 90 70 7
2 neeraj 120 100 14
3 ritu 80 50 2
4 pankaj 0 0 0
5 pankaj 0 0 0

126
 1.3 Mathematical Operations on DF
Descriptive and summary statistics | Method | Description | |—————|——————————
——————————————————————————-| | count | Number of non-NA values |
| describe | Compute set of summary statistics | | min, max | Compute minimum and maximum
values | | argmin, argmax | Compute index locations (integers) at which minimum or maximum
value is obtained, respectively; not available on DataFrame objects | | idxmin, idxmax | Compute
index labels at which minimum or maximum value is obtained, respectively | | quantile | Compute
sample quantile ranging from 0 to 1 (default: 0.5) | | sum | Sum of values | | mean | Mean of
values | | median | Arithmetic median (50% quantile) of values | | mad | Mean absolute deviation
from mean value | | prod | Product of all values | | var | Sample variance of values | | std | Sample
standard deviation of values | | skew | Sample skewness (third moment) of values | | kurt | Sample
kurtosis (fourth moment) of values | | cumsum | Cumulative sum of values | | cummin, cummax
| Cumulative minimum or maximum of values, respectively | | cumprod | Cumulative product of
values | | diff | Compute first arithmetic difference (useful for time series) | | pct_change | Compute
percent changes |

[41]: students = pd.DataFrame([

[100, 80, 10],
[90, 70, 7],
[120, 100, 14],
[80, 50, 2],
[0, 0, 0],
[0, 0, 0]
], columns=['iq', 'percent', 'lpa'])

students

[41]: iq percent lpa

0 100 80 10
1 90 70 7
2 120 100 14
3 80 50 2
4 0 0 0
5 0 0 0

1.3.1 DF.reindex([‘indexvalue1’, ’indexvalue2])

• used to change the order of indexes,
[42]: students.reindex([1,2,5,4,0,3])

[42]: iq percent lpa

1 90 70 7
2 120 100 14
5 0 0 0
4 0 0 0
0 100 80 10

127
 3 80 50 2

1.3.2 DF.sum(axis=0) / DF.max(axis) / DF.min(axis) / DF.mean(axis) /

DF.median(axis) / DF.var(axis) / DF.std(axis)
• various operations on values along specified axis.
• by default axis is 0
• axis = 1 -> row-wise
[43]: students.sum(axis=1)

[43]: 0 190
1 167
2 234
3 132
4 0
5 0
dtype: int64

[44]: students.max(axis=1)

[44]: 0 100
1 90
2 120
3 80
4 0
5 0
dtype: int64

[45]: students.min()

[45]: iq 0
percent 0
lpa 0
dtype: int64

[46]: students.mean(axis=1)

[46]: 0 63.333333
1 55.666667
2 78.000000
3 44.000000
4 0.000000
5 0.000000
dtype: float64

[47]: students.var()

128
[47]: iq 2710.0
percent 1760.0
lpa 33.5
dtype: float64

[48]: students.std()

[48]: iq 52.057660
percent 41.952354
lpa 5.787918
dtype: float64

1.4 Selecting

Type Notes
df[column] Select single column or sequence of columns from
the DataFrame
df.loc[rows] Select single row or subset of rows from the
DataFrame by label
df.loc[:, cols] Select single column or subset of columns by label
df.loc[rows, cols] Select both row(s) and column(s) by label
df.iloc[rows] Select single row or subset of rows from the
DataFrame by integer position
df.iloc[:, cols] Select single column or subset of columns by
integer position
df.iloc[rows, cols] Select both row(s) and column(s) by integer
position
df.at[row, col] Select a single scalar value by row and column
label
df.iat[row, col] Select a single scalar value by row and column
position (integers)
reindex method Select either rows or columns by labels

1.5 Selecting Columns

1.5.1 Selecting single column from DF

[49]: movies['title_x']

[49]: 0 Uri: The Surgical Strike

1 Battalion 609
2 The Accidental Prime Minister (film)
3 Why Cheat India
4 Evening Shadows
…
1624 Tera Mera Saath Rahen

129
 1625 Yeh Zindagi Ka Safar
1626 Sabse Bada Sukh
1627 Daaka
1628 Humsafar
Name: title_x, Length: 1629, dtype: object

[50]: ipl['Venue']

[50]: 0 Narendra Modi Stadium, Ahmedabad

1 Narendra Modi Stadium, Ahmedabad
2 Eden Gardens, Kolkata
3 Eden Gardens, Kolkata
4 Wankhede Stadium, Mumbai
…
945 Eden Gardens
946 Wankhede Stadium
947 Feroz Shah Kotla
948 Punjab Cricket Association Stadium, Mohali
949 M Chinnaswamy Stadium
Name: Venue, Length: 950, dtype: object

1.5.2 Selecting Multiple Columns from DF

[51]: movies[['year_of_release', 'actors', 'title_x']]

[51]: year_of_release actors \

0 2019 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga…
1 2019 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen…
2 2019 Anupam Kher|Akshaye Khanna|Aahana Kumra|Atul S…
3 2019 Emraan Hashmi|Shreya Dhanwanthary|Snighdadeep …
4 2018 Mona Ambegaonkar|Ananth Narayan Mahadevan|Deva…
… … …
1624 2001 Ajay Devgn|Sonali Bendre|Namrata Shirodkar|Pre…
1625 2001 Ameesha Patel|Jimmy Sheirgill|Nafisa Ali|Gulsh…
1626 2018 Vijay Arora|Asrani|Rajni Bala|Kumud Damle|Utpa…
1627 2019 Gippy Grewal|Zareen Khan|
1628 2011 Fawad Khan|

title_x
0 Uri: The Surgical Strike
1 Battalion 609
2 The Accidental Prime Minister (film)
3 Why Cheat India
4 Evening Shadows
… …
1624 Tera Mera Saath Rahen
1625 Yeh Zindagi Ka Safar

130
 1626 Sabse Bada Sukh
1627 Daaka
1628 Humsafar

[1629 rows x 3 columns]

[52]: ipl[['Team1', 'Team2', 'WinningTeam']]

[52]: Team1 Team2 \

0 Rajasthan Royals Gujarat Titans
1 Royal Challengers Bangalore Rajasthan Royals
2 Royal Challengers Bangalore Lucknow Super Giants
3 Rajasthan Royals Gujarat Titans
4 Sunrisers Hyderabad Punjab Kings
.. … …
945 Kolkata Knight Riders Deccan Chargers
946 Mumbai Indians Royal Challengers Bangalore
947 Delhi Daredevils Rajasthan Royals
948 Kings XI Punjab Chennai Super Kings
949 Royal Challengers Bangalore Kolkata Knight Riders

WinningTeam
0 Gujarat Titans
1 Rajasthan Royals
2 Royal Challengers Bangalore
3 Gujarat Titans
4 Punjab Kings
.. …
945 Kolkata Knight Riders
946 Royal Challengers Bangalore
947 Delhi Daredevils
948 Chennai Super Kings
949 Kolkata Knight Riders

[950 rows x 3 columns]

1.6 Selecting Rows

• iloc - searches using index positions
• loc - searches using index labels
Note - iloc doesn’t include last index while loc includes
[53]: student_dict = {
'name':['dilkush', 'ankit', 'neeraj', 'ritu', 'pankaj', 'pankaj'],
'iq':[100, 90, 120, 80, 0, 0],
'marks':[80, 70, 100, 50, 0, 0],
'package':[10, 7, 14, 2, 0, 0]

131
 }

students = pd.DataFrame(student_dict)
students

[53]: name iq marks package

0 dilkush 100 80 10
1 ankit 90 70 7
2 neeraj 120 100 14
3 ritu 80 50 2
4 pankaj 0 0 0
5 pankaj 0 0 0

[54]: students.set_index('name', inplace=True)

students

[54]: iq marks package

name
dilkush 100 80 10
ankit 90 70 7
neeraj 120 100 14
ritu 80 50 2
pankaj 0 0 0
pankaj 0 0 0

1.6.1 Single Row using iloc

[55]: movies.iloc[0]

[55]: title_x Uri: The Surgical Strike

imdb_id tt8291224
poster_path https://upload.wikimedia.org/wikipedia/en/thum…
wiki_link https://en.wikipedia.org/wiki/Uri:_The_Surgica…
title_y Uri: The Surgical Strike
original_title Uri: The Surgical Strike
is_adult 0
year_of_release 2019
runtime 138
genres Action|Drama|War
imdb_rating 8.4
imdb_votes 35112
story Divided over five chapters the film chronicle…
summary Indian army special forces execute a covert op…
tagline NaN
actors Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga…
wins_nominations 4 wins
release_date 11 January 2019 (USA)

132
 Name: 0, dtype: object

1.6.2 Multiple Rows using iloc

[56]: movies.iloc[5:16:2]

[56]: title_x imdb_id \

5 Soni (film) tt6078866
7 Bombairiya tt4971258
9 Thackeray (film) tt7777196
11 Gully Boy tt2395469
13 Total Dhamaal tt7639372
15 Badla (2019 film) tt8130968

poster_path \
5 https://upload.wikimedia.org/wikipedia/en/thum…
7 https://upload.wikimedia.org/wikipedia/en/thum…
9 https://upload.wikimedia.org/wikipedia/en/thum…
11 https://upload.wikimedia.org/wikipedia/en/thum…
13 https://upload.wikimedia.org/wikipedia/en/thum…
15 https://upload.wikimedia.org/wikipedia/en/0/0c…

wiki_link title_y \
5 https://en.wikipedia.org/wiki/Soni_(film) Soni
7 https://en.wikipedia.org/wiki/Bombairiya Bombairiya
9 https://en.wikipedia.org/wiki/Thackeray_(film) Thackeray
11 https://en.wikipedia.org/wiki/Gully_Boy Gully Boy
13 https://en.wikipedia.org/wiki/Total_Dhamaal Total Dhamaal
15 https://en.wikipedia.org/wiki/Badla_(2019_film) Badla

original_title is_adult year_of_release runtime genres \

5 Soni 0 2018 97 Drama
7 Bombairiya 0 2019 104 Comedy|Crime|Drama
9 Thackeray 0 2019 120 Biography|Drama
11 Gully Boy 0 2019 153 Drama|Music
13 Total Dhamaal 0 2019 130 Action|Adventure|Comedy
15 Badla 0 2019 118 Crime|Drama|Mystery

imdb_rating imdb_votes \
5 7.2 1595
7 4.3 295
9 5.1 2301
11 8.2 22440
13 4.3 4817
15 7.9 15499

story \

133
 5 Soni a young policewoman in Delhi and her su…
7 It follows the story of Meghna who gets embro…
9 Balasaheb Thackrey works as a cartoonist for a…
11 Gully Boy is a film about a 22-year-old boy "M…
13 Total Dhamaal is the third instalment in the D…
15 Naina Sethi a successful entrepreneur finds he…

summary \
5 While fighting crimes against women in Delhi …
7 It follows the story of Meghna who gets embro…
9 Biographical account of Shiv Sena Supremo Bal…
11 A coming-of-age story based on the lives of st…
13 A group of people learn about a hidden treasur…
15 A dynamic young entrepreneur finds herself loc…

tagline \
5 NaN
7 They didn't mean to change the world.
9 NaN
11 Apna Time Aayega!
13 The Wildest Adventure Ever
15 NaN

actors wins_nominations \
5 Geetika Vidya Ohlyan|Saloni Batra|Vikas Shukla… 3 wins & 5 nominations
7 Radhika Apte|Akshay Oberoi|Siddhanth Kapoor|Ra… NaN
9 Nawazuddin Siddiqui|Amrita Rao|Abdul Quadir Am… NaN
11 Ranveer Singh|Alia Bhatt|Siddhant Chaturvedi|V… 6 wins & 3 nominations
13 Ajay Devgn|Madhuri Dixit|Anil Kapoor|Riteish D… NaN
15 Amitabh Bachchan|Taapsee Pannu|Amrita Singh|An… 1 win

release_date
5 18 January 2019 (USA)
7 18 January 2019 (India)
9 25 January 2019 (India)
11 14 February 2019 (USA)
13 22 February 2019 (India)
15 8 March 2019 (India)

1.6.3 Fancy Indexing using iloc

[57]: movies.iloc[[0, 4, 5]]

[57]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
4 Evening Shadows tt6028796
5 Soni (film) tt6078866

134
 poster_path \
0 https://upload.wikimedia.org/wikipedia/en/thum…
4 NaN
5 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
4 https://en.wikipedia.org/wiki/Evening_Shadows
5 https://en.wikipedia.org/wiki/Soni_(film)

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
4 Evening Shadows Evening Shadows 0
5 Soni Soni 0

year_of_release runtime genres imdb_rating imdb_votes \

0 2019 138 Action|Drama|War 8.4 35112
4 2018 102 Drama 7.3 280
5 2018 97 Drama 7.2 1595

story \
0 Divided over five chapters the film chronicle…
4 While gay rights and marriage equality has bee…
5 Soni a young policewoman in Delhi and her su…

summary tagline \
0 Indian army special forces execute a covert op… NaN
4 Under the 'Evening Shadows' truth often plays… NaN
5 While fighting crimes against women in Delhi … NaN

actors wins_nominations \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga… 4 wins
4 Mona Ambegaonkar|Ananth Narayan Mahadevan|Deva… 17 wins & 1 nomination
5 Geetika Vidya Ohlyan|Saloni Batra|Vikas Shukla… 3 wins & 5 nominations

release_date
0 11 January 2019 (USA)
4 11 January 2019 (India)
5 18 January 2019 (USA)

1.6.4 Single Row using loc

[58]: students.loc['ritu']

135
[58]: iq 80
marks 50
package 2
Name: ritu, dtype: int64

1.6.5 Multiple Rows using loc

[59]: students

[59]: iq marks package

name
dilkush 100 80 10
ankit 90 70 7
neeraj 120 100 14
ritu 80 50 2
pankaj 0 0 0
pankaj 0 0 0

[60]: students.loc['dilkush':'pankaj']

[60]: iq marks package

name
dilkush 100 80 10
ankit 90 70 7
neeraj 120 100 14
ritu 80 50 2
pankaj 0 0 0
pankaj 0 0 0

1.6.6 Fancy Indexing using loc

[61]: students.loc[['dilkush', 'neeraj', 'ritu']]

[61]: iq marks package

name
dilkush 100 80 10
neeraj 120 100 14
ritu 80 50 2

1.7 Selecting both Rows and Columns

[62]: movies.iloc[:3, :3]

[62]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208

136
 2 The Accidental Prime Minister (film) tt6986710

poster_path
0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN
2 https://upload.wikimedia.org/wikipedia/en/thum…

[63]: movies.loc[:3, 'title_x':'poster_path']

[63]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208
2 The Accidental Prime Minister (film) tt6986710
3 Why Cheat India tt8108208

poster_path
0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN
2 https://upload.wikimedia.org/wikipedia/en/thum…
3 https://upload.wikimedia.org/wikipedia/en/thum…

1.8 Filtering a DF
[64]: ipl.head(2)

[64]: ID City Date Season MatchNumber \

0 1312200 Ahmedabad 2022-05-29 2022 Final
1 1312199 Ahmedabad 2022-05-27 2022 Qualifier 2

Team1 Team2 \
0 Rajasthan Royals Gujarat Titans
1 Royal Challengers Bangalore Rajasthan Royals

Venue TossWinner TossDecision SuperOver \

0 Narendra Modi Stadium, Ahmedabad Rajasthan Royals bat N
1 Narendra Modi Stadium, Ahmedabad Rajasthan Royals field N

WinningTeam WonBy Margin method Player_of_Match \

0 Gujarat Titans Wickets 7.0 NaN HH Pandya
1 Rajasthan Royals Wickets 7.0 NaN JC Buttler

Team1Players \
0 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
1 ['V Kohli', 'F du Plessis', 'RM Patidar', 'GJ …

Team2Players Umpire1 Umpire2

0 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… CB Gaffaney Nitin Menon

137
 1 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D … CB Gaffaney Nitin Menon

1. Find all the final winners in ipl

[65]: ipl[ipl['MatchNumber']=='Final'][['Season', 'WinningTeam']]

[65]: Season WinningTeam

0 2022 Gujarat Titans
74 2021 Chennai Super Kings
134 2020/21 Mumbai Indians
194 2019 Mumbai Indians
254 2018 Chennai Super Kings
314 2017 Mumbai Indians
373 2016 Sunrisers Hyderabad
433 2015 Mumbai Indians
492 2014 Kolkata Knight Riders
552 2013 Mumbai Indians
628 2012 Kolkata Knight Riders
702 2011 Chennai Super Kings
775 2009/10 Chennai Super Kings
835 2009 Deccan Chargers
892 2007/08 Rajasthan Royals

2. How many super over finishes have occured.

[66]: ipl[ipl['SuperOver']=='Y'].shape[0]

[66]: 14

3. How many matches has csk won in kolkata

[67]: ipl[(ipl['City']=='Kolkata') & (ipl['WinningTeam'] == 'Chennai Super Kings')].
↪shape[0]

[67]: 5

4. Toss winner is match winner in percentage

[68]: (ipl[ipl['TossWinner'] == ipl['WinningTeam']]).shape[0]/ ipl.shape[0] * 100

[68]: 51.473684210526315

5. Movies with rating higher than 8 and votes>10000

[69]: ipl[(movies['imdb_rating']>8) & (movies['imdb_votes']>10000)]

C:\Users\DILKHUSH\AppData\Local\Temp\ipykernel_15532\891066147.py:1:
UserWarning: Boolean Series key will be reindexed to match DataFrame index.
ipl[(movies['imdb_rating']>8) & (movies['imdb_votes']>10000)]

138
[69]: ID City Date Season MatchNumber \
0 1312200 Ahmedabad 2022-05-29 2022 Final
11 1304109 Mumbai 2022-05-15 2022 63
37 1304083 Mumbai 2022-04-24 2022 37
40 1304080 Mumbai 2022-04-22 2022 34
143 1216502 NaN 2020-10-31 2020/21 52
146 1216499 Abu Dhabi 2020-10-28 2020/21 48
325 1082639 Chandigarh 2017-05-09 2017 49
354 1082608 Delhi 2017-04-17 2017 18
418 980929 Rajkot 2016-04-21 2016 15
426 980913 Delhi 2016-04-15 2016 7
436 829817 Mumbai 2015-05-19 2015 Qualifier 1
469 829751 Mumbai 2015-04-25 2015 23
536 729309 NaN 2014-04-27 2014 16
566 598060 Mumbai 2013-05-13 2013 62
567 598058 Jaipur 2013-05-12 2013 61
589 598034 Chennai 2013-04-28 2013 38
612 598012 Chennai 2013-04-13 2013 16
638 548372 Delhi 2012-05-17 2012 67
668 548342 Delhi 2012-04-27 2012 36
669 548341 Pune 2012-04-26 2012 35
693 548314 Visakhapatnam 2012-04-09 2012 9
694 548313 Pune 2012-04-08 2012 8
709 501264 Dharamsala 2011-05-21 2011 67
714 501259 Mumbai 2011-05-16 2011 62
778 419162 Mumbai 2010-04-21 2009/10 Semi Final
869 392206 Johannesburg 2009-05-02 2009 26
912 336021 Mumbai 2008-05-16 2007/08 38
930 336001 Chennai 2008-05-02 2007/08 20

Team1 Team2 \
0 Rajasthan Royals Gujarat Titans
11 Rajasthan Royals Lucknow Super Giants
37 Lucknow Super Giants Mumbai Indians
40 Rajasthan Royals Delhi Capitals
143 Royal Challengers Bangalore Sunrisers Hyderabad
146 Royal Challengers Bangalore Mumbai Indians
325 Kings XI Punjab Kolkata Knight Riders
354 Delhi Daredevils Kolkata Knight Riders
418 Gujarat Lions Sunrisers Hyderabad
426 Delhi Daredevils Kings XI Punjab
436 Chennai Super Kings Mumbai Indians
469 Mumbai Indians Sunrisers Hyderabad
536 Delhi Daredevils Mumbai Indians
566 Mumbai Indians Sunrisers Hyderabad
567 Rajasthan Royals Chennai Super Kings
589 Chennai Super Kings Kolkata Knight Riders

139
612 Chennai Super Kings Royal Challengers Bangalore
638 Delhi Daredevils Royal Challengers Bangalore
668 Delhi Daredevils Mumbai Indians
669 Pune Warriors Deccan Chargers
693 Deccan Chargers Mumbai Indians
694 Pune Warriors Kings XI Punjab
709 Kings XI Punjab Deccan Chargers
714 Pune Warriors Deccan Chargers
778 Royal Challengers Bangalore Mumbai Indians
869 Chennai Super Kings Delhi Daredevils
912 Mumbai Indians Kolkata Knight Riders
930 Chennai Super Kings Delhi Daredevils

Venue TossWinner \
0 Narendra Modi Stadium, Ahmedabad Rajasthan Royals
11 Brabourne Stadium, Mumbai Rajasthan Royals
37 Wankhede Stadium, Mumbai Mumbai Indians
40 Wankhede Stadium, Mumbai Delhi Capitals
143 Sharjah Cricket Stadium Sunrisers Hyderabad
146 Sheikh Zayed Stadium Mumbai Indians
325 Punjab Cricket Association IS Bindra Stadium, … Kolkata Knight Riders
354 Feroz Shah Kotla Delhi Daredevils
418 Saurashtra Cricket Association Stadium Sunrisers Hyderabad
426 Feroz Shah Kotla Delhi Daredevils
436 Wankhede Stadium Mumbai Indians
469 Wankhede Stadium Mumbai Indians
536 Sharjah Cricket Stadium Mumbai Indians
566 Wankhede Stadium Sunrisers Hyderabad
567 Sawai Mansingh Stadium Rajasthan Royals
589 MA Chidambaram Stadium, Chepauk Kolkata Knight Riders
612 MA Chidambaram Stadium, Chepauk Chennai Super Kings
638 Feroz Shah Kotla Delhi Daredevils
668 Feroz Shah Kotla Mumbai Indians
669 Subrata Roy Sahara Stadium Deccan Chargers
693 Dr. Y.S. Rajasekhara Reddy ACA-VDCA Cricket St… Deccan Chargers
694 Subrata Roy Sahara Stadium Pune Warriors
709 Himachal Pradesh Cricket Association Stadium Kings XI Punjab
714 Dr DY Patil Sports Academy Deccan Chargers
778 Dr DY Patil Sports Academy Mumbai Indians
869 New Wanderers Stadium Delhi Daredevils
912 Wankhede Stadium Mumbai Indians
930 MA Chidambaram Stadium, Chepauk Chennai Super Kings

TossDecision SuperOver WinningTeam WonBy Margin \

0 bat N Gujarat Titans Wickets 7.0
11 bat N Rajasthan Royals Runs 24.0
37 field N Lucknow Super Giants Runs 36.0

140
40 field N Rajasthan Royals Runs 15.0
143 field N Sunrisers Hyderabad Wickets 5.0
146 field N Mumbai Indians Wickets 5.0
325 field N Kings XI Punjab Runs 14.0
354 bat N Kolkata Knight Riders Wickets 4.0
418 field N Sunrisers Hyderabad Wickets 10.0
426 field N Delhi Daredevils Wickets 8.0
436 bat N Mumbai Indians Runs 25.0
469 bat N Mumbai Indians Runs 20.0
536 bat N Delhi Daredevils Wickets 6.0
566 bat N Mumbai Indians Wickets 7.0
567 field N Rajasthan Royals Wickets 5.0
589 field N Chennai Super Kings Runs 14.0
612 field N Chennai Super Kings Wickets 4.0
638 field N Royal Challengers Bangalore Runs 21.0
668 field N Delhi Daredevils Runs 37.0
669 bat N Deccan Chargers Runs 18.0
693 bat N Mumbai Indians Wickets 5.0
694 bat N Pune Warriors Runs 22.0
709 field N Deccan Chargers Runs 82.0
714 field N Deccan Chargers Wickets 6.0
778 bat N Mumbai Indians Runs 35.0
869 field N Chennai Super Kings Runs 18.0
912 field N Mumbai Indians Wickets 8.0
930 bat N Delhi Daredevils Wickets 8.0

method Player_of_Match \
0 NaN HH Pandya
11 NaN TA Boult
37 NaN KL Rahul
40 NaN JC Buttler
143 NaN Sandeep Sharma
146 NaN SA Yadav
325 NaN MM Sharma
354 NaN NM Coulter-Nile
418 NaN B Kumar
426 NaN A Mishra
436 NaN KA Pollard
469 NaN SL Malinga
536 NaN M Vijay
566 NaN KA Pollard
567 NaN SR Watson
589 NaN MEK Hussey
612 NaN RA Jadeja
638 NaN CH Gayle
668 NaN V Sehwag
669 NaN CL White

141
693 NaN RG Sharma
694 NaN MN Samuels
709 NaN S Dhawan
714 NaN A Mishra
778 NaN KA Pollard
869 NaN SB Jakati
912 NaN SM Pollock
930 NaN V Sehwag

Team1Players \
0 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
11 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
37 ['Q de Kock', 'KL Rahul', 'MK Pandey', 'MP Sto…
40 ['JC Buttler', 'D Padikkal', 'SV Samson', 'SO …
143 ['JR Philippe', 'D Padikkal', 'V Kohli', 'AB d…
146 ['JR Philippe', 'D Padikkal', 'V Kohli', 'AB d…
325 ['MJ Guptill', 'M Vohra', 'SE Marsh', 'WP Saha…
354 ['SV Samson', 'SW Billings', 'KK Nair', 'SS Iy…
418 ['AJ Finch', 'BB McCullum', 'SK Raina', 'KD Ka…
426 ['Q de Kock', 'SS Iyer', 'SV Samson', 'P Negi'…
436 ['DR Smith', 'MEK Hussey', 'F du Plessis', 'SK…
469 ['LMP Simmons', 'PA Patel', 'UBT Chand', 'RG S…
536 ['Q de Kock', 'M Vijay', 'JP Duminy', 'KP Piet…
566 ['DR Smith', 'SR Tendulkar', 'KD Karthik', 'RG…
567 ['R Dravid', 'AM Rahane', 'JP Faulkner', 'SV S…
589 ['WP Saha', 'MEK Hussey', 'SK Raina', 'MS Dhon…
612 ['MEK Hussey', 'M Vijay', 'SK Raina', 'S Badri…
638 ['UBT Chand', 'DA Warner', 'Y Venugopal Rao', …
668 ['DPMD Jayawardene', 'V Sehwag', 'KP Pietersen…
669 ['MK Pandey', 'JD Ryder', 'SC Ganguly', 'RV Ut…
693 ['PA Patel', 'S Dhawan', 'B Chipli', 'DT Chris…
694 ['JD Ryder', 'SC Ganguly', 'MN Samuels', 'RV U…
709 ['PC Valthaty', 'AC Gilchrist', 'SE Marsh', 'K…
714 ['JD Ryder', 'MK Pandey', 'SC Ganguly', 'RV Ut…
778 ['JH Kallis', 'R Dravid', 'KP Pietersen', 'RV …
869 ['M Vijay', 'ML Hayden', 'SK Raina', 'S Badrin…
912 ['ST Jayasuriya', 'SR Tendulkar', 'RV Uthappa'…
930 ['PA Patel', 'SP Fleming', 'S Vidyut', 'MS Dho…

Team2Players Umpire1 \
0 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… CB Gaffaney
11 ['Q de Kock', 'KL Rahul', 'A Badoni', 'DJ Hood… PG Pathak
37 ['Ishan Kishan', 'RG Sharma', 'D Brevis', 'SA … M Erasmus
40 ['PP Shaw', 'DA Warner', 'SN Khan', 'RR Pant',… NA Patwardhan
143 ['DA Warner', 'WP Saha', 'MK Pandey', 'KS Will… KN Ananthapadmanabhan
146 ['Q de Kock', 'Ishan Kishan', 'SA Yadav', 'SS … UV Gandhe
325 ['SP Narine', 'CA Lynn', 'G Gambhir', 'RV Utha… A Nand Kishore

142
354 ['G Gambhir', 'C de Grandhomme', 'RV Uthappa',… Nitin Menon
418 ['DA Warner', 'S Dhawan', 'MC Henriques', 'EJG… K Bharatan
426 ['M Vijay', 'M Vohra', 'SE Marsh', 'DA Miller'… S Ravi
436 ['LMP Simmons', 'PA Patel', 'RG Sharma', 'KA P… HDPK Dharmasena
469 ['S Dhawan', 'DA Warner', 'KL Rahul', 'NV Ojha… HDPK Dharmasena
536 ['RG Sharma', 'AP Tare', 'CJ Anderson', 'AT Ra… Aleem Dar
566 ['PA Patel', 'S Dhawan', 'GH Vihari', 'CL Whit… AK Chaudhary
567 ['MEK Hussey', 'M Vijay', 'SK Raina', 'MS Dhon… HDPK Dharmasena
589 ['MS Bisla', 'G Gambhir', 'BB McCullum', 'JH K… Aleem Dar
612 ['CH Gayle', 'MA Agarwal', 'V Kohli', 'AB de V… Asad Rauf
638 ['CH Gayle', 'TM Dilshan', 'V Kohli', 'AB de V… HDPK Dharmasena
668 ['AC Blizzard', 'SR Tendulkar', 'RG Sharma', '… Aleem Dar
669 ['PA Patel', 'S Dhawan', 'CL White', 'KC Sanga… S Ravi
693 ['TL Suman', 'RE Levi', 'RG Sharma', 'AT Rayud… AK Chaudhary
694 ['AC Gilchrist', 'PC Valthaty', 'Mandeep Singh… S Das
709 ['S Dhawan', 'DB Ravi Teja', 'JP Duminy', 'CL … Asad Rauf
714 ['S Sohal', 'S Dhawan', 'KC Sangakkara', 'JP D… S Ravi
778 ['S Dhawan', 'SR Tendulkar', 'AM Nayar', 'AT R… BR Doctrove
869 ['G Gambhir', 'DA Warner', 'AB de Villiers', '… DJ Harper
912 ['Salman Butt', 'A Chopra', 'SC Ganguly', 'DJ … BR Doctrove
930 ['G Gambhir', 'V Sehwag', 'AB de Villiers', 'S… BF Bowden

Umpire2
0 Nitin Menon
11 Tapan Sharma
37 HAS Khalid
40 Nitin Menon
143 K Srinivasan
146 CB Gaffaney
325 S Ravi
354 CK Nandan
418 HDPK Dharmasena
426 C Shamshuddin
436 RK Illingworth
469 CB Gaffaney
536 VA Kulkarni
566 SJA Taufel
567 CK Nandan
589 SJA Taufel
612 AK Chaudhary
638 C Shamshuddin
668 BNJ Oxenford
669 RJ Tucker
693 JD Cloete
694 SJA Taufel
709 AM Saheba
714 SK Tarapore

143
 778 RB Tiffin
869 RE Koertzen
912 DJ Harper
930 K Hariharan

6. Action movies with rating higher than 7.5

[70]: movies[(movies['genres'].str.contains('Action')) & (movies['imdb_rating']>7.5)]

[70]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
41 Family of Thakurganj tt8897986
84 Mukkabaaz tt7180544
106 Raazi tt7098658
110 Parmanu: The Story of Pokhran tt6826438
112 Bhavesh Joshi Superhero tt6129302
169 The Ghazi Attack tt6299040
219 Raag Desh (film) tt6080746
258 Irudhi Suttru tt5310090
280 Laal Rang tt5600714
297 Udta Punjab tt4434004
354 Dangal (film) tt5074352
362 Bajrangi Bhaijaan tt3863552
365 Baby (2015 Hindi film) tt3848892
393 Detective Byomkesh Bakshy! tt3447364
449 Titli (2014 film) tt3019620
536 Haider (film) tt3390572
589 Vishwaroopam tt2199711
625 Madras Cafe tt2855648
668 Paan Singh Tomar (film) tt1620933
693 Gangs of Wasseypur tt1954470
694 Gangs of Wasseypur – Part 2 tt1954470
982 Jodhaa Akbar tt0449994
1039 1971 (2007 film) tt0983990
1058 Black Friday (2007 film) tt0400234
1188 Omkara (2006 film) tt0488414
1293 Sarkar (2005 film) tt0432047
1294 Sehar tt0477857
1361 Lakshya (film) tt0323013
1432 Gangaajal tt0373856
1495 Company (film) tt0296574
1554 The Legend of Bhagat Singh tt0319736
1607 Nayak (2001 Hindi film) tt0291376

poster_path \
0 https://upload.wikimedia.org/wikipedia/en/thum…
41 https://upload.wikimedia.org/wikipedia/en/9/99…

144
84 https://upload.wikimedia.org/wikipedia/en/thum…
106 https://upload.wikimedia.org/wikipedia/en/thum…
110 https://upload.wikimedia.org/wikipedia/en/thum…
112 https://upload.wikimedia.org/wikipedia/en/thum…
169 https://upload.wikimedia.org/wikipedia/en/thum…
219 https://upload.wikimedia.org/wikipedia/en/thum…
258 https://upload.wikimedia.org/wikipedia/en/f/fe…
280 NaN
297 https://upload.wikimedia.org/wikipedia/en/thum…
354 https://upload.wikimedia.org/wikipedia/en/thum…
362 https://upload.wikimedia.org/wikipedia/en/thum…
365 https://upload.wikimedia.org/wikipedia/en/thum…
393 https://upload.wikimedia.org/wikipedia/en/thum…
449 https://upload.wikimedia.org/wikipedia/en/thum…
536 https://upload.wikimedia.org/wikipedia/en/thum…
589 https://upload.wikimedia.org/wikipedia/en/thum…
625 https://upload.wikimedia.org/wikipedia/en/thum…
668 https://upload.wikimedia.org/wikipedia/en/thum…
693 https://upload.wikimedia.org/wikipedia/en/thum…
694 https://upload.wikimedia.org/wikipedia/en/thum…
982 https://upload.wikimedia.org/wikipedia/en/thum…
1039 https://upload.wikimedia.org/wikipedia/en/thum…
1058 https://upload.wikimedia.org/wikipedia/en/5/58…
1188 https://upload.wikimedia.org/wikipedia/en/thum…
1293 https://upload.wikimedia.org/wikipedia/en/thum…
1294 https://upload.wikimedia.org/wikipedia/en/thum…
1361 https://upload.wikimedia.org/wikipedia/en/thum…
1432 https://upload.wikimedia.org/wikipedia/en/thum…
1495 https://upload.wikimedia.org/wikipedia/en/thum…
1554 https://upload.wikimedia.org/wikipedia/en/thum…
1607 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
41 https://en.wikipedia.org/wiki/Family_of_Thakur…
84 https://en.wikipedia.org/wiki/Mukkabaaz
106 https://en.wikipedia.org/wiki/Raazi
110 https://en.wikipedia.org/wiki/Parmanu:_The_Sto…
112 https://en.wikipedia.org/wiki/Bhavesh_Joshi_Su…
169 https://en.wikipedia.org/wiki/The_Ghazi_Attack…
219 https://en.wikipedia.org/wiki/Raagdesh
258 https://en.wikipedia.org/wiki/Saala_Khadoos
280 https://en.wikipedia.org/wiki/Laal_Rang
297 https://en.wikipedia.org/wiki/Udta_Punjab
354 https://en.wikipedia.org/wiki/Dangal_(film)
362 https://en.wikipedia.org/wiki/Bajrangi_Bhaijaan
365 https://en.wikipedia.org/wiki/Baby_(2015_Hindi…

145
393 https://en.wikipedia.org/wiki/Detective_Byomke…
449 https://en.wikipedia.org/wiki/Titli_(2014_film)
536 https://en.wikipedia.org/wiki/Haider_(film)
589 https://en.wikipedia.org/wiki/Vishwaroop_(Hind…
625 https://en.wikipedia.org/wiki/Madras_Cafe
668 https://en.wikipedia.org/wiki/Paan_Singh_Tomar…
693 https://en.wikipedia.org/wiki/Gangs_of_Wasseypur
694 https://en.wikipedia.org/wiki/Gangs_of_Wasseyp…
982 https://en.wikipedia.org/wiki/Jodhaa_Akbar
1039 https://en.wikipedia.org/wiki/1971_(2007_film)
1058 https://en.wikipedia.org/wiki/Black_Friday_(20…
1188 https://en.wikipedia.org/wiki/Omkara_(2006_film)
1293 https://en.wikipedia.org/wiki/Sarkar_(2005_film)
1294 https://en.wikipedia.org/wiki/Sehar
1361 https://en.wikipedia.org/wiki/Lakshya_(film)
1432 https://en.wikipedia.org/wiki/Gangaajal
1495 https://en.wikipedia.org/wiki/Company_(film)
1554 https://en.wikipedia.org/wiki/The_Legend_of_Bh…
1607 https://en.wikipedia.org/wiki/Nayak_(2001_Hind…

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
41 Family of Thakurganj Family of Thakurganj 0
84 The Brawler Mukkabaaz 0
106 Raazi Raazi 0
110 Parmanu: The Story of Pokhran Parmanu: The Story of Pokhran 0
112 Bhavesh Joshi Superhero Bhavesh Joshi Superhero 0
169 The Ghazi Attack The Ghazi Attack 0
219 Raag Desh Raag Desh 0
258 Saala Khadoos Saala Khadoos 0
280 Laal Rang Laal Rang 0
297 Udta Punjab Udta Punjab 0
354 Dangal Dangal 0
362 Bajrangi Bhaijaan Bajrangi Bhaijaan 0
365 Baby Baby 0
393 Detective Byomkesh Bakshy! Detective Byomkesh Bakshy! 0
449 Titli Titli 0
536 Haider Haider 0
589 Vishwaroopam Vishwaroopam 0
625 Madras Cafe Madras Cafe 0
668 Paan Singh Tomar Paan Singh Tomar 0
693 Gangs of Wasseypur Gangs of Wasseypur 0
694 Gangs of Wasseypur Gangs of Wasseypur 0
982 Jodhaa Akbar Jodhaa Akbar 0
1039 1971 1971 0
1058 Black Friday Black Friday 0
1188 Omkara Omkara 0

146
1293 Sarkar Sarkar 0
1294 Sehar Sehar 0
1361 Lakshya Lakshya 0
1432 Gangaajal Gangaajal 0
1495 Company Company 0
1554 The Legend of Bhagat Singh The Legend of Bhagat Singh 0
1607 Nayak: The Real Hero Nayak: The Real Hero 0

year_of_release runtime genres imdb_rating \

0 2019 138 Action|Drama|War 8.4
41 2019 127 Action|Drama 9.4
84 2017 154 Action|Drama|Sport 8.1
106 2018 138 Action|Drama|Thriller 7.8
110 2018 129 Action|Drama|History 7.7
112 2018 154 Action|Drama 7.6
169 2017 116 Action|Thriller|War 7.6
219 2017 135 Action|Drama|History 8.3
258 2016 109 Action|Drama|Sport 7.6
280 2016 147 Action|Crime|Drama 8.0
297 2016 148 Action|Crime|Drama 7.8
354 2016 161 Action|Biography|Drama 8.4
362 2015 163 Action|Comedy|Drama 8.0
365 2015 159 Action|Thriller 8.0
393 2015 139 Action|Mystery|Thriller 7.6
449 2014 116 Action|Drama|Thriller 7.6
536 2014 160 Action|Crime|Drama 8.1
589 2013 148 Action|Thriller 8.2
625 2013 130 Action|Drama|Thriller 7.7
668 2012 135 Action|Biography|Crime 8.2
693 2012 321 Action|Comedy|Crime 8.2
694 2012 321 Action|Comedy|Crime 8.2
982 2008 213 Action|Drama|History 7.6
1039 2007 160 Action|Drama|War 7.9
1058 2004 143 Action|Crime|Drama 8.5
1188 2006 155 Action|Crime|Drama 8.1
1293 2005 124 Action|Crime|Drama 7.6
1294 2005 125 Action|Crime|Drama 7.8
1361 2004 186 Action|Drama|Romance 7.9
1432 2003 157 Action|Crime|Drama 7.8
1495 2002 155 Action|Crime|Drama 8.0
1554 2002 155 Action|Biography|Drama 8.1
1607 2001 187 Action|Drama|Thriller 7.8

imdb_votes story \
0 35112 Divided over five chapters the film chronicle…
41 895 The film is based on small town of North India…
84 5434 A boxer (Shravan) belonging to upper cast tra…

147
106 20289 Hidayat Khan is the son of an Indian freedom f…
110 18292 Captain Ashwat Raina's efforts to turn India i…
112 4928 Bhavesh Joshi Superhero is an action film abou…
169 10332 In 1971 amid rising tensions between India an…
219 341 A period film based on the historic 1945 India…
258 10507 An under-fire boxing coach Prabhu is transfer…
280 3741 The friendship of two men is tested when thing…
297 23995 What on earth can a rock star a migrant labor…
354 131338 Biopic of Mahavir Singh Phogat who taught wre…
362 65877 A little mute girl from a Pakistani village ge…
365 49426 The country is perpetually under threat from t…
393 14674 CALCUTTA 1943 A WAR - A MYSTERY - and A DETECT…
449 3677 In the badlands of Delhi's dystopic underbelly…
536 46912 Vishal Bhardwaj's adaptation of William Shakes…
589 38016 Vishwanathan a Kathak dance teacher in New Yo…
625 21393 An Indian Intelligence agent (portrayed by Joh…
668 29994 Paan Singh Tomar is a Hindi-language film bas…
693 71636 Shahid Khan is exiled after impersonating the …
694 71636 Shahid Khan is exiled after impersonating the …
982 27541 Jodhaa Akbar is a sixteenth century love story…
1039 1121 Based on true facts the film revolves around …
1058 16761 A dramatic presentation of the bomb blasts tha…
1188 17594 Advocate Raghunath Mishra has arranged the mar…
1293 14694 Meet Subhash Nagre - a wealthy and influential…
1294 1861 At the tender age of 8 Ajay Kumar is traumatiz…
1361 18777 Karan is a lazy good-for-nothing who lives on …
1432 14295 An SP Amit Kumar who is given charge of Tezpur…
1495 13474 Mallik is a henchman of Aslam Bhai a Mumbai u…
1554 13455 Bhagat was born in British India during the ye…
1607 12522 Employed as a camera-man at a popular televisi…

summary \
0 Indian army special forces execute a covert op…
41 The film is based on small town of North India…
84 A boxer struggles to make his mark in the boxi…
106 A Kashmiri woman agrees to marry a Pakistani a…
110 Ashwat Raina and his teammates arrive in Pokhr…
112 The origin story of Bhavesh Joshi an Indian s…
169 A Pakistani submarine Ghazi plans to secretly…
219 A period film based on the historic 1945 India…
258 The story of a former boxer who quits boxing f…
280 The friendship of two men is tested when thing…
297 A story that revolves around drug abuse in the…
354 Former wrestler Mahavir Singh Phogat and his t…
362 An Indian man with a magnanimous heart takes a…
365 An elite counter-intelligence unit learns of a…
393 While investigating the disappearance of a che…

148
449 A Hindi feature film set in the lower depths o…
536 A young man returns to Kashmir after his fathe…
589 When a classical dancer's suspecting wife sets…
625 An Indian intelligence agent journeys to a war…
668 The story of Paan Singh Tomar an Indian athle…
693 A clash between Sultan and Shahid Khan leads t…
694 A clash between Sultan and Shahid Khan leads t…
982 A sixteenth century love story about a marriag…
1039 Based on true facts the film revolves around …
1058 Black Friday is a film about the investigation…
1188 A politically-minded enforcer's misguided trus…
1293 The authority of a man who runs a parallel go…
1294 Ajay Kumar the newly appointed honest SSP of …
1361 An aimless jobless irresponsible grown man j…
1432 An IPS officer motivates and leads a dysfuncti…
1495 A small-time gangster named Chandu teams up wi…
1554 The story of a young revolutionary who raised …
1607 A man accepts a challenge by the chief ministe…

tagline \
0 NaN
41 NaN
84 NaN
106 An incredible true story
110 1998| India: one secret operation| six Indians…
112 This year| justice will have a new name.
169 The war you did not know about
219 NaN
258 NaN
280 Every job good or bad| must be done with honesty.
297 NaN
354 You think our girls are any lesser than boys?
362 NaN
365 History Is Made By Those Who Give A Damn!
393 Expect The Unexpected
449 Daring| Desireable| Dangerous
536 NaN
589 NaN
625 NaN
668 NaN
693 NaN
694 NaN
982 NaN
1039 Honor the heroes…
1058 The story of the Bombay bomb blasts
1188 NaN
1293 'There are no Rights and Wrongs. Only Power' -…

149
1294 NaN
1361 It took him 24 years and 18000 feet to find hi…
1432 NaN
1495 A law & order enterprise
1554 NaN
1607 Fight the power

actors \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga…
41 Jimmy Sheirgill|Mahie Gill|Nandish Singh|Prana…
84 Viineet Kumar|Jimmy Sheirgill|Zoya Hussain|Rav…
106 Alia Bhatt|Vicky Kaushal|Rajit Kapoor|Shishir …
110 John Abraham|Boman Irani|Diana Penty|Anuja Sat…
112 Harshvardhan Kapoor|Priyanshu Painyuli|Ashish …
169 Rana Daggubati|Kay Kay Menon|Atul Kulkarni|Om …
219 Kunal Kapoor|Amit Sadh|Mohit Marwah|Kenneth De…
258 Madhavan|Ritika Singh|Mumtaz Sorcar|Nassar|Rad…
280 Randeep Hooda|Akshay Oberoi|Rajniesh Duggall|P…
297 Shahid Kapoor|Alia Bhatt|Kareena Kapoor|Diljit…
354 Aamir Khan|Fatima Sana Shaikh|Sanya Malhotra|S…
362 Salman Khan|Harshaali Malhotra|Nawazuddin Sidd…
365 Akshay Kumar|Danny Denzongpa|Rana Daggubati|Ta…
393 Sushant Singh Rajput|Anand Tiwari|Neeraj Kabi|…
449 Nawazuddin Siddiqui|Niharika Singh|Anil George…
536 Tabu|Shahid Kapoor|Shraddha Kapoor|Kay Kay Men…
589 Kamal Haasan|Rahul Bose|Shekhar Kapur|Pooja Ku…
625 John Abraham|Nargis Fakhri|Raashi Khanna|Praka…
668 Irrfan Khan|
693 Manoj Bajpayee|Richa Chadha|Nawazuddin Siddiqu…
694 Manoj Bajpayee|Richa Chadha|Nawazuddin Siddiqu…
982 Hrithik Roshan|Aishwarya Rai Bachchan|Sonu Soo…
1039 Manoj Bajpayee|Ravi Kishan|Deepak Dobriyal|
1058 Kay Kay Menon|Pavan Malhotra|Aditya Srivastava…
1188 Ajay Devgn|Saif Ali Khan|Vivek Oberoi|Kareena …
1293 Amitabh Bachchan|Abhishek Bachchan|Kay Kay Men…
1294 Arshad Warsi|Pankaj Kapur|Mahima Chaudhry|Sush…
1361 Hrithik Roshan|Preity Zinta|Amitabh Bachchan|O…
1432 Ajay Devgn|Gracy Singh|Mohan Joshi|Yashpal Sha…
1495 Ajay Devgn|Mohanlal|Manisha Koirala|Seema Bisw…
1554 Ajay Devgn|Sushant Singh|D. Santosh|Akhilendra…
1607 Anil Kapoor|Rani Mukerji|Amrish Puri|Johnny Le…

wins_nominations release_date
0 4 wins 11 January 2019 (USA)
41 NaN 19 July 2019 (India)
84 3 wins & 6 nominations 12 January 2018 (USA)
106 21 wins & 26 nominations 11 May 2018 (USA)

150
 110 NaN 25 May 2018 (USA)
112 2 nominations 1 June 2018 (USA)
169 1 win & 7 nominations 17 February 2017 (USA)
219 NaN 28 July 2017 (India)
258 9 wins & 2 nominations 29 January 2016 (USA)
280 NaN 22 April 2016 (India)
297 11 wins & 19 nominations 17 June 2016 (USA)
354 23 wins & 4 nominations 21 December 2016 (USA)
362 25 wins & 13 nominations 17 July 2015 (USA)
365 1 win 23 January 2015 (India)
393 NaN 3 April 2015 (USA)
449 4 wins & 5 nominations 20 June 2014 (USA)
536 28 wins & 24 nominations 2 October 2014 (USA)
589 5 wins & 11 nominations 25 January 2013 (India)
625 10 wins & 10 nominations 23 August 2013 (India)
668 10 wins & 11 nominations 2 March 2012 (USA)
693 12 wins & 43 nominations 2 August 2012 (Singapore)
694 12 wins & 43 nominations 2 August 2012 (Singapore)
982 32 wins & 21 nominations 15 February 2008 (USA)
1039 1 win 9 March 2007 (India)
1058 3 nominations 9 February 2007 (India)
1188 19 wins & 20 nominations 28 July 2006 (USA)
1293 2 wins & 10 nominations 1 July 2005 (India)
1294 NaN 29 July 2005 (India)
1361 4 wins & 10 nominations 18 June 2004 (USA)
1432 4 wins & 29 nominations 29 August 2003 (India)
1495 16 wins & 9 nominations 15 April 2002 (India)
1554 11 wins & 5 nominations 7 June 2002 (India)
1607 2 nominations 7 September 2001 (India)

7. write a function that can return the track record of 2 teams against each other.
[ ]:

1.9 Adding new columns

1.9.1 Adding completely new column

[71]: movies['country'] = 'India'

[72]: movies.head(2)

[72]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208

poster_path \

151
 0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN

wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
1 https://en.wikipedia.org/wiki/Battalion_609

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
1 Battalion 609 Battalion 609 0

year_of_release runtime genres imdb_rating imdb_votes \

0 2019 138 Action|Drama|War 8.4 35112
1 2019 131 War 4.1 73

story \
0 Divided over five chapters the film chronicle…
1 The story revolves around a cricket match betw…

summary tagline \
0 Indian army special forces execute a covert op… NaN
1 The story of Battalion 609 revolves around a c… NaN

actors wins_nominations \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga… 4 wins
1 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen… NaN

release_date country
0 11 January 2019 (USA) India
1 11 January 2019 (India) India

1.9.2 Adding columns from existing

[73]: movies.dropna(inplace=True)

[74]: movies['lead actor'] = movies['actors'].str.split('|').apply(lambda x:x[0])

[75]: movies.head(2)

[75]: title_x imdb_id \

11 Gully Boy tt2395469
34 Yeh Hai India tt5525846

poster_path \
11 https://upload.wikimedia.org/wikipedia/en/thum…
34 https://upload.wikimedia.org/wikipedia/en/thum…

152
 wiki_link title_y original_title \
11 https://en.wikipedia.org/wiki/Gully_Boy Gully Boy Gully Boy
34 https://en.wikipedia.org/wiki/Yeh_Hai_India Yeh Hai India Yeh Hai India

is_adult year_of_release runtime genres imdb_rating \

11 0 2019 153 Drama|Music 8.2
34 0 2017 128 Action|Adventure|Drama 5.7

imdb_votes story \
11 22440 Gully Boy is a film about a 22-year-old boy "M…
34 169 Yeh Hai India follows the story of a 25 years…

summary \
11 A coming-of-age story based on the lives of st…
34 Yeh Hai India follows the story of a 25 years…

tagline \
11 Apna Time Aayega!
34 A Film for Every Indian

actors wins_nominations \
11 Ranveer Singh|Alia Bhatt|Siddhant Chaturvedi|V… 6 wins & 3 nominations
34 Gavie Chahal|Mohan Agashe|Mohan Joshi|Lom Harsh| 2 wins & 1 nomination

release_date country lead actor

11 14 February 2019 (USA) India Ranveer Singh
34 24 May 2019 (India) India Gavie Chahal

1.10 Important DataFrame Functions

1.10.1 DF[‘col’].astype(‘new_datatype’)

[76]: ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null int64
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null object
4 MatchNumber 950 non-null object
5 Team1 950 non-null object
6 Team2 950 non-null object
7 Venue 950 non-null object

153
 8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null object
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
dtypes: float64(1), int64(1), object(18)
memory usage: 148.6+ KB

[77]: ipl['ID'] = ipl['ID'].astype('int32')

[78]: ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null int32
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null object
4 MatchNumber 950 non-null object
5 Team1 950 non-null object
6 Team2 950 non-null object
7 Venue 950 non-null object
8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null object
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
dtypes: float64(1), int32(1), object(18)
memory usage: 144.9+ KB

154
[79]: ipl['Season'] = ipl['Season'].astype('category')

[80]: ipl['Team1'] = ipl['Team1'].astype('category')

ipl['Team2'] = ipl['Team2'].astype('category')
ipl['WinningTeam'] = ipl['WinningTeam'].astype('category')

[81]: ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null int32
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null category
4 MatchNumber 950 non-null object
5 Team1 950 non-null category
6 Team2 950 non-null category
7 Venue 950 non-null object
8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null category
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
dtypes: category(4), float64(1), int32(1), object(14)
memory usage: 121.6+ KB

1.10.2 DF.value_counts
• Counts the frequency of values in the DF.
• Mostly used in Series rather than DF
[82]: a = pd.Series([1,1,1,2,2,3])
a.value_counts()

[82]: 1 3
2 2
3 1
Name: count, dtype: int64

155
[83]: marks = pd.DataFrame([
[100, 80, 10],
[90, 70, 7],
[120, 100, 14],
[80, 70, 14],
[80, 70, 14]
], columns=['iq', 'marks', 'package'])

marks

[83]: iq marks package

0 100 80 10
1 90 70 7
2 120 100 14
3 80 70 14
4 80 70 14

[84]: marks.value_counts()

[84]: iq marks package

80 70 14 2
90 70 7 1
100 80 10 1
120 100 14 1
Name: count, dtype: int64

[85]: ipl = pd.read_csv('ipl-matches.csv')

ipl.head(2)

[85]: ID City Date Season MatchNumber \

0 1312200 Ahmedabad 2022-05-29 2022 Final
1 1312199 Ahmedabad 2022-05-27 2022 Qualifier 2

Team1 Team2 \
0 Rajasthan Royals Gujarat Titans
1 Royal Challengers Bangalore Rajasthan Royals

Venue TossWinner TossDecision SuperOver \

0 Narendra Modi Stadium, Ahmedabad Rajasthan Royals bat N
1 Narendra Modi Stadium, Ahmedabad Rajasthan Royals field N

WinningTeam WonBy Margin method Player_of_Match \

0 Gujarat Titans Wickets 7.0 NaN HH Pandya
1 Rajasthan Royals Wickets 7.0 NaN JC Buttler

Team1Players \
0 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …

156
 1 ['V Kohli', 'F du Plessis', 'RM Patidar', 'GJ …

Team2Players Umpire1 Umpire2

0 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… CB Gaffaney Nitin Menon
1 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D … CB Gaffaney Nitin Menon

1. Find which player has won most POTM in finals and qualifiers.
[86]: ipl[~ipl['MatchNumber'].str.isdigit()]['Player_of_Match'].value_counts()

[86]: Player_of_Match
KA Pollard 3
F du Plessis 3
SK Raina 3
A Kumble 2
MK Pandey 2
YK Pathan 2
M Vijay 2
JJ Bumrah 2
AB de Villiers 2
SR Watson 2
HH Pandya 1
Harbhajan Singh 1
A Nehra 1
V Sehwag 1
UT Yadav 1
MS Bisla 1
BJ Hodge 1
MEK Hussey 1
MS Dhoni 1
CH Gayle 1
MM Patel 1
DE Bollinger 1
AC Gilchrist 1
RG Sharma 1
DA Warner 1
MC Henriques 1
JC Buttler 1
RM Patidar 1
DA Miller 1
VR Iyer 1
SP Narine 1
RD Gaikwad 1
TA Boult 1
MP Stoinis 1
KS Williamson 1
RR Pant 1

157
 SA Yadav 1
Rashid Khan 1
AD Russell 1
KH Pandya 1
KV Sharma 1
NM Coulter-Nile 1
Washington Sundar 1
BCJ Cutting 1
M Ntini 1
Name: count, dtype: int64

2. Toss decision plot

[87]: ipl['TossDecision'].value_counts().plot(kind='pie')

[87]: <Axes: ylabel='count'>

3. How many matches each team has played

[88]: ipl['Team1'].value_counts() + ipl['Team2'].value_counts()

[88]: Chennai Super Kings 208

Deccan Chargers 75
Delhi Capitals 63

158
 Delhi Daredevils 161
Gujarat Lions 30
Gujarat Titans 16
Kings XI Punjab 190
Kochi Tuskers Kerala 14
Kolkata Knight Riders 223
Lucknow Super Giants 15
Mumbai Indians 231
Pune Warriors 46
Punjab Kings 28
Rajasthan Royals 192
Rising Pune Supergiant 16
Rising Pune Supergiants 14
Royal Challengers Bangalore 226
Sunrisers Hyderabad 152
Name: count, dtype: int64

1.10.3 DF.sort_values(‘col’, ascending=True, na_position=‘last’, inplace=False)

• Sorts the Series or DataFrame based on values
[89]: x = pd.Series([12, 14, 1, 56, 89])
x

[89]: 0 12
1 14
2 1
3 56
4 89
dtype: int64

[90]: x.sort_values()

[90]: 2 1
0 12
1 14
3 56
4 89
dtype: int64

[91]: movies = pd.read_csv('movies.csv')

movies.head(2)

[91]: title_x imdb_id \

0 Uri: The Surgical Strike tt8291224
1 Battalion 609 tt9472208

159
 poster_path \
0 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN

wiki_link \
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…
1 https://en.wikipedia.org/wiki/Battalion_609

title_y original_title is_adult \

0 Uri: The Surgical Strike Uri: The Surgical Strike 0
1 Battalion 609 Battalion 609 0

year_of_release runtime genres imdb_rating imdb_votes \

0 2019 138 Action|Drama|War 8.4 35112
1 2019 131 War 4.1 73

story \
0 Divided over five chapters the film chronicle…
1 The story revolves around a cricket match betw…

summary tagline \
0 Indian army special forces execute a covert op… NaN
1 The story of Battalion 609 revolves around a c… NaN

actors wins_nominations \
0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga… 4 wins
1 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen… NaN

release_date
0 11 January 2019 (USA)
1 11 January 2019 (India)

[92]: movies.sort_values('title_x')

[92]: title_x imdb_id \

1498 16 December (film) tt0313844
1021 1920 (film) tt1301698
287 1920: London tt5638500
723 1920: The Evil Returns tt2222550
1039 1971 (2007 film) tt0983990
… … …
778 Zindagi Na Milegi Dobara tt1562872
670 Zindagi Tere Naam tt2164702
756 Zokkomon tt1605790
939 Zor Lagaa Ke…Haiya! tt1479857
1623 Zubeidaa tt0255713

160
 poster_path \
1498 https://upload.wikimedia.org/wikipedia/en/thum…
1021 https://upload.wikimedia.org/wikipedia/en/thum…
287 https://upload.wikimedia.org/wikipedia/en/thum…
723 https://upload.wikimedia.org/wikipedia/en/e/e7…
1039 https://upload.wikimedia.org/wikipedia/en/thum…
… …
778 https://upload.wikimedia.org/wikipedia/en/thum…
670 https://upload.wikimedia.org/wikipedia/en/thum…
756 https://upload.wikimedia.org/wikipedia/en/thum…
939 https://upload.wikimedia.org/wikipedia/en/thum…
1623 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
1498 https://en.wikipedia.org/wiki/16_December_(film)
1021 https://en.wikipedia.org/wiki/1920_(film)
287 https://en.wikipedia.org/wiki/1920_London
723 https://en.wikipedia.org/wiki/1920:_The_Evil_R…
1039 https://en.wikipedia.org/wiki/1971_(2007_film)
… …
778 https://en.wikipedia.org/wiki/Zindagi_Na_Mileg…
670 https://en.wikipedia.org/wiki/Zindagi_Tere_Naam
756 https://en.wikipedia.org/wiki/Zokkomon
939 https://en.wikipedia.org/wiki/Zor_Lagaa_Ke…H…
1623 https://en.wikipedia.org/wiki/Zubeidaa

title_y original_title is_adult \

1498 16-Dec 16-Dec 0
1021 1920 1920 0
287 1920 London 1920 London 0
723 1920: Evil Returns 1920: Evil Returns 0
1039 1971 1971 0
… … … …
778 Zindagi Na Milegi Dobara Zindagi Na Milegi Dobara 0
670 Zindagi Tere Naam Zindagi Tere Naam 0
756 Zokkomon Zokkomon 0
939 Zor Lagaa Ke… Haiya! Zor Lagaa Ke… Haiya! 0
1623 Zubeidaa Zubeidaa 0

year_of_release runtime genres imdb_rating \

1498 2002 158 Action|Thriller 6.9
1021 2008 138 Horror|Mystery|Romance 6.4
287 2016 120 Horror|Mystery 4.1
723 2012 124 Drama|Horror|Romance 4.8
1039 2007 160 Action|Drama|War 7.9
… … … … …
778 2011 155 Comedy|Drama 8.1

161
670 2012 120 Romance 4.7
756 2011 109 Action|Adventure 4.0
939 2009 \N Comedy|Drama|Family 6.4
1623 2001 153 Biography|Drama|History 6.2

imdb_votes story \
1498 1091 16 December 1971 was the day when India won t…
1021 2588 A devotee of Bhagwan Shri Hanuman Arjun Singh…
287 1373 Shivangi (Meera Chopra) lives in London with h…
723 1587 This story revolves around a famous poet who m…
1039 1121 Based on true facts the film revolves around …
… … …
778 60826 Three friends decide to turn their fantasy vac…
670 27 Mr. Singh an elderly gentleman relates to hi…
756 274 After the passing of his parents in an acciden…
939 46 A tree narrates the story of four Mumbai-based…
1623 1384 The film begins with Riyaz (Rajat Kapoor) Zub…

summary \
1498 Indian intelligence agents race against time t…
1021 After forsaking his family and religion a hus…
287 After her husband is possessed by an evil spir…
723 This story revolves around a famous poet who m…
1039 Based on true facts the film revolves around …
… …
778 Three friends decide to turn their fantasy vac…
670 Mr. Singh an elderly gentleman relates to hi…
756 An orphan is abused and abandoned believed to…
939 Children build a tree-house to spy on a beggar…
1623 Zubeidaa an aspiring Muslim actress marries …

tagline \
1498 NaN
1021 A Love Made in Heaven…A Revenge Born in Hell…
287 Fear strikes again
723 Possession is back
1039 Honor the heroes…
… …
778 NaN
670 NaN
756 Betrayal. Friendship. Bravery.
939 NaN
1623 The Story of a Princess

actors \
1498 Danny Denzongpa|Gulshan Grover|Milind Soman|Di…
1021 Rajniesh Duggall|Adah Sharma|Anjori Alagh|Raj …

162
 287 Sharman Joshi|Meera Chopra|Vishal Karwal|Suren…
723 Vicky Ahuja|Tia Bajpai|Irma Jämhammar|Sharad K…
1039 Manoj Bajpayee|Ravi Kishan|Deepak Dobriyal|
… …
778 Hrithik Roshan|Farhan Akhtar|Abhay Deol|Katrin…
670 Mithun Chakraborty|Ranjeeta Kaur|Priyanka Meht…
756 Darsheel Safary|Anupam Kher|Manjari Fadnnis|Ti…
939 Meghan Jadhav|Mithun Chakraborty|Riya Sen|Seem…
1623 Karisma Kapoor|Rekha|Manoj Bajpayee|Rajit Kapo…

wins_nominations release_date
1498 2 nominations 22 March 2002 (India)
1021 NaN 12 September 2008 (India)
287 NaN 6 May 2016 (USA)
723 NaN 2 November 2012 (India)
1039 1 win 9 March 2007 (India)
… … …
778 30 wins & 22 nominations 15 July 2011 (India)
670 1 win 16 March 2012 (India)
756 NaN 22 April 2011 (India)
939 NaN NaN
1623 3 wins & 13 nominations 19 January 2001 (India)

[1629 rows x 18 columns]

[93]: students = pd.DataFrame(

{
'name':['nitish','ankit','rupesh',np.nan,'mrityunjay',np.
↪nan,'rishabh',np.nan,'aditya',np.nan],

'college':['bit','iit','vit',np.nan,np.nan,'vlsi','ssit',np.nan,np.
↪nan,'git'],

'branch':['eee','it','cse',np.nan,'me','ce','civ','cse','bio',np.nan],
'cgpa':[6.66,8.25,6.41,np.nan,5.6,9.0,7.4,10,7.4,np.nan],
'package':[4,5,6,np.nan,6,7,8,9,np.nan,np.nan]

}
)

students

[93]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0
3 NaN NaN NaN NaN NaN
4 mrityunjay NaN me 5.60 6.0
5 NaN vlsi ce 9.00 7.0

163
 6 rishabh ssit civ 7.40 8.0
7 NaN NaN cse 10.00 9.0
8 aditya NaN bio 7.40 NaN
9 NaN git NaN NaN NaN

[94]: students.sort_values('name', na_position='first', inplace=False)

[94]: name college branch cgpa package

3 NaN NaN NaN NaN NaN
5 NaN vlsi ce 9.00 7.0
7 NaN NaN cse 10.00 9.0
9 NaN git NaN NaN NaN
8 aditya NaN bio 7.40 NaN
1 ankit iit it 8.25 5.0
4 mrityunjay NaN me 5.60 6.0
0 nitish bit eee 6.66 4.0
6 rishabh ssit civ 7.40 8.0
2 rupesh vit cse 6.41 6.0

1.10.4 DF.sort_values(list_of_columns, ascending=list)

[95]: movies.sort_values(['year_of_release', 'title_x'], ascending=[True, False])

[95]: title_x imdb_id \

1623 Zubeidaa tt0255713
1625 Yeh Zindagi Ka Safar tt0298607
1622 Yeh Teraa Ghar Yeh Meraa Ghar tt0298606
1620 Yeh Raaste Hain Pyaar Ke tt0292740
1573 Yaadein (2001 film) tt0248617
… … …
37 Article 15 (film) tt10324144
46 Arjun Patiala tt7881524
10 Amavas tt8396186
26 Albert Pinto Ko Gussa Kyun Aata Hai? tt4355838
21 22 Yards tt9496212

poster_path \
1623 https://upload.wikimedia.org/wikipedia/en/thum…
1625 https://upload.wikimedia.org/wikipedia/en/thum…
1622 https://upload.wikimedia.org/wikipedia/en/thum…
1620 https://upload.wikimedia.org/wikipedia/en/thum…
1573 https://upload.wikimedia.org/wikipedia/en/thum…
… …
37 https://upload.wikimedia.org/wikipedia/en/thum…
46 https://upload.wikimedia.org/wikipedia/en/thum…
10 https://upload.wikimedia.org/wikipedia/en/thum…
26 https://upload.wikimedia.org/wikipedia/en/thum…

164
21 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
1623 https://en.wikipedia.org/wiki/Zubeidaa
1625 https://en.wikipedia.org/wiki/Yeh_Zindagi_Ka_S…
1622 https://en.wikipedia.org/wiki/Yeh_Teraa_Ghar_Y…
1620 https://en.wikipedia.org/wiki/Yeh_Raaste_Hain_…
1573 https://en.wikipedia.org/wiki/Yaadein_(2001_film)
… …
37 https://en.wikipedia.org/wiki/Article_15_(film)
46 https://en.wikipedia.org/wiki/Arjun_Patiala
10 https://en.wikipedia.org/wiki/Amavas
26 https://en.wikipedia.org/wiki/Albert_Pinto_Ko_…
21 https://en.wikipedia.org/wiki/22_Yards

title_y \
1623 Zubeidaa
1625 Yeh Zindagi Ka Safar
1622 Yeh Teraa Ghar Yeh Meraa Ghar
1620 Yeh Raaste Hain Pyaar Ke
1573 Yaadein…
… …
37 Article 15
46 Arjun Patiala
10 Amavas
26 Albert Pinto Ko Gussa Kyun Aata Hai?
21 22 Yards

original_title is_adult year_of_release runtime \

1623 Zubeidaa 0 2001 153
1625 Yeh Zindagi Ka Safar 0 2001 146
1622 Yeh Teraa Ghar Yeh Meraa Ghar 0 2001 175
1620 Yeh Raaste Hain Pyaar Ke 0 2001 149
1573 Yaadein… 0 2001 171
… … … … …
37 Article 15 0 2019 130
46 Arjun Patiala 0 2019 107
10 Amavas 0 2019 134
26 Albert Pinto Ko Gussa Kyun Aata Hai? 0 2019 100
21 22 Yards 0 2019 126

genres imdb_rating imdb_votes \

1623 Biography|Drama|History 6.2 1384
1625 Drama 3.0 133
1622 Comedy|Drama 5.7 704
1620 Drama|Romance 4.0 607
1573 Drama|Musical|Romance 4.4 3034

165
… … … …
37 Crime|Drama 8.3 13417
46 Action|Comedy 4.1 676
10 Horror|Thriller 2.8 235
26 Drama 4.8 56
21 Sport 5.3 124

story \
1623 The film begins with Riyaz (Rajat Kapoor) Zub…
1625 Hindi pop-star Sarina Devan lives a wealthy …
1622 In debt; Dayashankar Pandey is forced to go to…
1620 Two con artistes and car thieves Vicky (Ajay …
1573 Raj Singh Puri is best friends with L.K. Malho…
… …
37 In the rural heartlands of India an upright p…
46 Arjun Patiala(Diljit Dosanjh)has recently been…
10 Far away from the bustle of the city a young …
26 Albert leaves his house one morning without te…
21 A dramatic portrayal of a victorious tale of a…

summary \
1623 Zubeidaa an aspiring Muslim actress marries …
1625 A singer finds out she was adopted when the ed…
1622 In debt; Dayashankar Pandey is forced to go to…
1620 Two con artistes and car thieves Vicky (Ajay …
1573 Raj Singh Puri is best friends with L.K. Malho…
… …
37 In the rural heartlands of India an upright p…
46 This spoof comedy narrates the story of a cop …
10 The lives of a couple turn into a nightmare a…
26 Albert Pinto goes missing one day and his girl…
21 A dramatic portrayal of a victorious tale of a…

tagline \
1623 The Story of a Princess
1625 NaN
1622 NaN
1620 Love is a journey… not a destination
1573 memories to cherish…
… …
37 Farq Bahut Kar Liya| Ab Farq Laayenge.
46 NaN
10 NaN
26 NaN
21 NaN

actors \

166
 1623 Karisma Kapoor|Rekha|Manoj Bajpayee|Rajit Kapo…
1625 Ameesha Patel|Jimmy Sheirgill|Nafisa Ali|Gulsh…
1622 Sunil Shetty|Mahima Chaudhry|Paresh Rawal|Saur…
1620 Ajay Devgn|Madhuri Dixit|Preity Zinta|Vikram G…
1573 Jackie Shroff|Hrithik Roshan|Kareena Kapoor|Am…
… …
37 Ayushmann Khurrana|Nassar|Manoj Pahwa|Kumud Mi…
46 Diljit Dosanjh|Kriti Sanon|Varun Sharma|Ronit …
10 Ali Asgar|Vivan Bhatena|Nargis Fakhri|Sachiin …
26 Manav Kaul|Nandita Das|
21 Barun Sobti|Rajit Kapur|Panchhi Bora|Kartikey …

wins_nominations release_date
1623 3 wins & 13 nominations 19 January 2001 (India)
1625 NaN 16 November 2001 (India)
1622 1 nomination 12 October 2001 (India)
1620 NaN 10 August 2001 (India)
1573 1 nomination 27 June 2001 (India)
… … …
37 1 win 28 June 2019 (USA)
46 NaN 26 July 2019 (USA)
10 NaN 8 February 2019 (India)
26 NaN 12 April 2019 (India)
21 NaN 15 March 2019 (India)

[1629 rows x 18 columns]

1.10.5 Ser[‘col’].rank(ascending = False)

[96]: batsman = pd.read_csv('batsman_runs_ipl.csv')

batsman.head()

[96]: batter batsman_run

0 A Ashish Reddy 280
1 A Badoni 161
2 A Chandila 4
3 A Chopra 53
4 A Choudhary 25

[97]: batsman['batsman_rank'] = batsman['batsman_run'].rank(ascending=False)

[98]: batsman.sort_values('batsman_rank')

[98]: batter batsman_run batsman_rank

569 V Kohli 6634 1.0
462 S Dhawan 6244 2.0
130 DA Warner 5883 3.0

167
 430 RG Sharma 5881 4.0
493 SK Raina 5536 5.0
.. … … …
512 SS Cottrell 0 594.0
466 S Kaushik 0 594.0
203 IC Pandey 0 594.0
467 S Ladda 0 594.0
468 S Lamichhane 0 594.0

[605 rows x 3 columns]

1.10.6 DF.sort_index(ascending=True)

[99]: marks = {
'maths':67,
'english':57,
'science':89,
'hindi':100
}

marks_series = pd.Series(marks)
marks_series

[99]: maths 67
english 57
science 89
hindi 100
dtype: int64

[100]: marks_series.sort_index(ascending=False)

[100]: science 89
maths 67
hindi 100
english 57
dtype: int64

[101]: movies.sort_index(ascending=False)

[101]: title_x imdb_id \

1628 Humsafar tt2403201
1627 Daaka tt10833860
1626 Sabse Bada Sukh tt0069204
1625 Yeh Zindagi Ka Safar tt0298607
1624 Tera Mera Saath Rahen tt0301250
… … …
4 Evening Shadows tt6028796

168
3 Why Cheat India tt8108208
2 The Accidental Prime Minister (film) tt6986710
1 Battalion 609 tt9472208
0 Uri: The Surgical Strike tt8291224

poster_path \
1628 https://upload.wikimedia.org/wikipedia/en/thum…
1627 https://upload.wikimedia.org/wikipedia/en/thum…
1626 NaN
1625 https://upload.wikimedia.org/wikipedia/en/thum…
1624 https://upload.wikimedia.org/wikipedia/en/2/2b…
… …
4 NaN
3 https://upload.wikimedia.org/wikipedia/en/thum…
2 https://upload.wikimedia.org/wikipedia/en/thum…
1 NaN
0 https://upload.wikimedia.org/wikipedia/en/thum…

wiki_link \
1628 https://en.wikipedia.org/wiki/Humsafar
1627 https://en.wikipedia.org/wiki/Daaka
1626 https://en.wikipedia.org/wiki/Sabse_Bada_Sukh
1625 https://en.wikipedia.org/wiki/Yeh_Zindagi_Ka_S…
1624 https://en.wikipedia.org/wiki/Tera_Mera_Saath_…
… …
4 https://en.wikipedia.org/wiki/Evening_Shadows
3 https://en.wikipedia.org/wiki/Why_Cheat_India
2 https://en.wikipedia.org/wiki/The_Accidental_P…
1 https://en.wikipedia.org/wiki/Battalion_609
0 https://en.wikipedia.org/wiki/Uri:_The_Surgica…

title_y original_title is_adult \

1628 Humsafar Humsafar 0
1627 Daaka Daaka 0
1626 Sabse Bada Sukh Sabse Bada Sukh 0
1625 Yeh Zindagi Ka Safar Yeh Zindagi Ka Safar 0
1624 Tera Mera Saath Rahen Tera Mera Saath Rahen 0
… … … …
4 Evening Shadows Evening Shadows 0
3 Why Cheat India Why Cheat India 0
2 The Accidental Prime Minister The Accidental Prime Minister 0
1 Battalion 609 Battalion 609 0
0 Uri: The Surgical Strike Uri: The Surgical Strike 0

year_of_release runtime genres imdb_rating imdb_votes \

1628 2011 35 Drama|Romance 9.0 2968
1627 2019 136 Action 7.4 38

169
1626 2018 \N Comedy|Drama 6.1 13
1625 2001 146 Drama 3.0 133
1624 2001 148 Drama 4.9 278
… … … … … …
4 2018 102 Drama 7.3 280
3 2019 121 Crime|Drama 6.0 1891
2 2019 112 Biography|Drama 6.1 5549
1 2019 131 War 4.1 73
0 2019 138 Action|Drama|War 8.4 35112

story \
1628 Sara and Ashar are childhood friends who share…
1627 Shinda tries robbing a bank so he can be wealt…
1626 Village born Lalloo re-locates to Bombay and …
1625 Hindi pop-star Sarina Devan lives a wealthy …
1624 Raj Dixit lives with his younger brother Rahu…
… …
4 While gay rights and marriage equality has bee…
3 The movie focuses on existing malpractices in …
2 Based on the memoir by Indian policy analyst S…
1 The story revolves around a cricket match betw…
0 Divided over five chapters the film chronicle…

summary tagline \
1628 Ashar and Khirad are forced to get married due… NaN
1627 Shinda tries robbing a bank so he can be wealt… NaN
1626 Village born Lalloo re-locates to Bombay and … NaN
1625 A singer finds out she was adopted when the ed… NaN
1624 A man is torn between his handicapped brother … NaN
… … …
4 Under the 'Evening Shadows' truth often plays… NaN
3 The movie focuses on existing malpractices in … NaN
2 Explores Manmohan Singh's tenure as the Prime … NaN
1 The story of Battalion 609 revolves around a c… NaN
0 Indian army special forces execute a covert op… NaN

actors \
1628 Fawad Khan|
1627 Gippy Grewal|Zareen Khan|
1626 Vijay Arora|Asrani|Rajni Bala|Kumud Damle|Utpa…
1625 Ameesha Patel|Jimmy Sheirgill|Nafisa Ali|Gulsh…
1624 Ajay Devgn|Sonali Bendre|Namrata Shirodkar|Pre…
… …
4 Mona Ambegaonkar|Ananth Narayan Mahadevan|Deva…
3 Emraan Hashmi|Shreya Dhanwanthary|Snighdadeep …
2 Anupam Kher|Akshaye Khanna|Aahana Kumra|Atul S…
1 Vicky Ahuja|Shoaib Ibrahim|Shrikant Kamat|Elen…

170
 0 Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga…

wins_nominations release_date
1628 NaN TV Series (2011–2012)
1627 NaN 1 November 2019 (USA)
1626 NaN NaN
1625 NaN 16 November 2001 (India)
1624 NaN 7 November 2001 (India)
… … …
4 17 wins & 1 nomination 11 January 2019 (India)
3 NaN 18 January 2019 (USA)
2 NaN 11 January 2019 (USA)
1 NaN 11 January 2019 (India)
0 4 wins 11 January 2019 (USA)

[1629 rows x 18 columns]

1.10.7 DF.set_index(‘col’, inplace=False)

• Sets given column as index
[102]: batsman.set_index('batter', inplace=True)
batsman

[102]: batsman_run batsman_rank

batter
A Ashish Reddy 280 166.5
A Badoni 161 226.0
A Chandila 4 535.0
A Chopra 53 329.0
A Choudhary 25 402.5
… … …
Yash Dayal 0 594.0
Yashpal Singh 47 343.0
Younis Khan 3 547.5
Yuvraj Singh 2754 27.0
Z Khan 117 256.0

[605 rows x 2 columns]

1.10.8 DF.reset_index(inplace=False)
• resets the index.
• mostly used for transforming series into dataframe
[103]: batsman.reset_index(inplace=True)

171
[104]: batsman

[104]: batter batsman_run batsman_rank

0 A Ashish Reddy 280 166.5
1 A Badoni 161 226.0
2 A Chandila 4 535.0
3 A Chopra 53 329.0
4 A Choudhary 25 402.5
.. … … …
600 Yash Dayal 0 594.0
601 Yashpal Singh 47 343.0
602 Younis Khan 3 547.5
603 Yuvraj Singh 2754 27.0
604 Z Khan 117 256.0

[605 rows x 3 columns]

Note- How to replace existing index without loosing?

[105]: batsman.reset_index().set_index('batsman_rank')

[105]: index batter batsman_run

batsman_rank
166.5 0 A Ashish Reddy 280
226.0 1 A Badoni 161
535.0 2 A Chandila 4
329.0 3 A Chopra 53
402.5 4 A Choudhary 25
… … … …
594.0 600 Yash Dayal 0
343.0 601 Yashpal Singh 47
547.5 602 Younis Khan 3
27.0 603 Yuvraj Singh 2754
256.0 604 Z Khan 117

[605 rows x 3 columns]

[106]: marks_series.reset_index()

[106]: index 0
0 maths 67
1 english 57
2 science 89
3 hindi 100

172
 1.10.9 DF.rename(columns={‘existing_name’:‘new_name’}, inplace=True)

[107]: movies.set_index('title_x', inplace=True)

[108]: movies.rename(columns={'imdb_id':'imdb', 'poster_path':'link'}, inplace=True)

[109]: movies

[109]: imdb \
title_x
Uri: The Surgical Strike tt8291224
Battalion 609 tt9472208
The Accidental Prime Minister (film) tt6986710
Why Cheat India tt8108208
Evening Shadows tt6028796
… …
Tera Mera Saath Rahen tt0301250
Yeh Zindagi Ka Safar tt0298607
Sabse Bada Sukh tt0069204
Daaka tt10833860
Humsafar tt2403201

link \
title_x
Uri: The Surgical Strike
https://upload.wikimedia.org/wikipedia/en/thum…
Battalion 609
NaN
The Accidental Prime Minister (film)
https://upload.wikimedia.org/wikipedia/en/thum…
Why Cheat India
https://upload.wikimedia.org/wikipedia/en/thum…
Evening Shadows
NaN
…
…
Tera Mera Saath Rahen
https://upload.wikimedia.org/wikipedia/en/2/2b…
Yeh Zindagi Ka Safar
https://upload.wikimedia.org/wikipedia/en/thum…
Sabse Bada Sukh
NaN
Daaka
https://upload.wikimedia.org/wikipedia/en/thum…
Humsafar
https://upload.wikimedia.org/wikipedia/en/thum…

173
wiki_link \
title_x
Uri: The Surgical Strike
https://en.wikipedia.org/wiki/Uri:_The_Surgica…
Battalion 609
https://en.wikipedia.org/wiki/Battalion_609
The Accidental Prime Minister (film)
https://en.wikipedia.org/wiki/The_Accidental_P…
Why Cheat India
https://en.wikipedia.org/wiki/Why_Cheat_India
Evening Shadows
https://en.wikipedia.org/wiki/Evening_Shadows
…
…
Tera Mera Saath Rahen
https://en.wikipedia.org/wiki/Tera_Mera_Saath_…
Yeh Zindagi Ka Safar
https://en.wikipedia.org/wiki/Yeh_Zindagi_Ka_S…
Sabse Bada Sukh
https://en.wikipedia.org/wiki/Sabse_Bada_Sukh
Daaka
https://en.wikipedia.org/wiki/Daaka
Humsafar
https://en.wikipedia.org/wiki/Humsafar

title_y \
title_x
Uri: The Surgical Strike Uri: The Surgical Strike
Battalion 609 Battalion 609
The Accidental Prime Minister (film) The Accidental Prime Minister
Why Cheat India Why Cheat India
Evening Shadows Evening Shadows
… …
Tera Mera Saath Rahen Tera Mera Saath Rahen
Yeh Zindagi Ka Safar Yeh Zindagi Ka Safar
Sabse Bada Sukh Sabse Bada Sukh
Daaka Daaka
Humsafar Humsafar

original_title is_adult \
title_x
Uri: The Surgical Strike Uri: The Surgical Strike 0
Battalion 609 Battalion 609 0
The Accidental Prime Minister (film) The Accidental Prime Minister 0
Why Cheat India Why Cheat India 0
Evening Shadows Evening Shadows 0
… … …

174
Tera Mera Saath Rahen Tera Mera Saath Rahen 0
Yeh Zindagi Ka Safar Yeh Zindagi Ka Safar 0
Sabse Bada Sukh Sabse Bada Sukh 0
Daaka Daaka 0
Humsafar Humsafar 0

year_of_release runtime \
title_x
Uri: The Surgical Strike 2019 138
Battalion 609 2019 131
The Accidental Prime Minister (film) 2019 112
Why Cheat India 2019 121
Evening Shadows 2018 102
… … …
Tera Mera Saath Rahen 2001 148
Yeh Zindagi Ka Safar 2001 146
Sabse Bada Sukh 2018 \N
Daaka 2019 136
Humsafar 2011 35

genres imdb_rating \
title_x
Uri: The Surgical Strike Action|Drama|War 8.4
Battalion 609 War 4.1
The Accidental Prime Minister (film) Biography|Drama 6.1
Why Cheat India Crime|Drama 6.0
Evening Shadows Drama 7.3
… … …
Tera Mera Saath Rahen Drama 4.9
Yeh Zindagi Ka Safar Drama 3.0
Sabse Bada Sukh Comedy|Drama 6.1
Daaka Action 7.4
Humsafar Drama|Romance 9.0

imdb_votes \
title_x
Uri: The Surgical Strike 35112
Battalion 609 73
The Accidental Prime Minister (film) 5549
Why Cheat India 1891
Evening Shadows 280
… …
Tera Mera Saath Rahen 278
Yeh Zindagi Ka Safar 133
Sabse Bada Sukh 13
Daaka 38
Humsafar 2968

175
 story \
title_x
Uri: The Surgical Strike Divided over five chapters the film
chronicle…
Battalion 609 The story revolves around a cricket match
betw…
The Accidental Prime Minister (film) Based on the memoir by Indian policy
analyst S…
Why Cheat India The movie focuses on existing malpractices
in …
Evening Shadows While gay rights and marriage equality has
bee…
…
…
Tera Mera Saath Rahen Raj Dixit lives with his younger brother
Rahu…
Yeh Zindagi Ka Safar Hindi pop-star Sarina Devan lives a
wealthy …
Sabse Bada Sukh Village born Lalloo re-locates to Bombay
and …
Daaka Shinda tries robbing a bank so he can be
wealt…
Humsafar Sara and Ashar are childhood friends who
share…

summary \
title_x
Uri: The Surgical Strike Indian army special forces execute a
covert op…
Battalion 609 The story of Battalion 609 revolves around
a c…
The Accidental Prime Minister (film) Explores Manmohan Singh's tenure as the
Prime …
Why Cheat India The movie focuses on existing malpractices
in …
Evening Shadows Under the 'Evening Shadows' truth often
plays…
…
…
Tera Mera Saath Rahen A man is torn between his handicapped
brother …
Yeh Zindagi Ka Safar A singer finds out she was adopted when
the ed…
Sabse Bada Sukh Village born Lalloo re-locates to Bombay
and …
Daaka Shinda tries robbing a bank so he can be

176
wealt…
Humsafar Ashar and Khirad are forced to get married
due…

tagline \
title_x
Uri: The Surgical Strike NaN
Battalion 609 NaN
The Accidental Prime Minister (film) NaN
Why Cheat India NaN
Evening Shadows NaN
… …
Tera Mera Saath Rahen NaN
Yeh Zindagi Ka Safar NaN
Sabse Bada Sukh NaN
Daaka NaN
Humsafar NaN

actors \
title_x
Uri: The Surgical Strike Vicky Kaushal|Paresh Rawal|Mohit
Raina|Yami Ga…
Battalion 609 Vicky Ahuja|Shoaib Ibrahim|Shrikant
Kamat|Elen…
The Accidental Prime Minister (film) Anupam Kher|Akshaye Khanna|Aahana
Kumra|Atul S…
Why Cheat India Emraan Hashmi|Shreya
Dhanwanthary|Snighdadeep …
Evening Shadows Mona Ambegaonkar|Ananth Narayan
Mahadevan|Deva…
…
…
Tera Mera Saath Rahen Ajay Devgn|Sonali Bendre|Namrata
Shirodkar|Pre…
Yeh Zindagi Ka Safar Ameesha Patel|Jimmy Sheirgill|Nafisa
Ali|Gulsh…
Sabse Bada Sukh Vijay Arora|Asrani|Rajni Bala|Kumud
Damle|Utpa…
Daaka Gippy
Grewal|Zareen Khan|
Humsafar
Fawad Khan|

wins_nominations \
title_x
Uri: The Surgical Strike 4 wins
Battalion 609 NaN

177
 The Accidental Prime Minister (film) NaN
Why Cheat India NaN
Evening Shadows 17 wins & 1 nomination
… …
Tera Mera Saath Rahen NaN
Yeh Zindagi Ka Safar NaN
Sabse Bada Sukh NaN
Daaka NaN
Humsafar NaN

release_date
title_x
Uri: The Surgical Strike 11 January 2019 (USA)
Battalion 609 11 January 2019 (India)
The Accidental Prime Minister (film) 11 January 2019 (USA)
Why Cheat India 18 January 2019 (USA)
Evening Shadows 11 January 2019 (India)
… …
Tera Mera Saath Rahen 7 November 2001 (India)
Yeh Zindagi Ka Safar 16 November 2001 (India)
Sabse Bada Sukh NaN
Daaka 1 November 2019 (USA)
Humsafar TV Series (2011–2012)

[1629 rows x 17 columns]

1.10.10 Ser.unique()
• Returns ndarray array containing unique values
[110]: temp = pd.Series([1,1,2,2,3,3,4,4,5,5, np.nan,np.nan])
temp

[110]: 0 1.0
1 1.0
2 2.0
3 2.0
4 3.0
5 3.0
6 4.0
7 4.0
8 5.0
9 5.0
10 NaN
11 NaN
dtype: float64

178
[111]: temp.unique()

[111]: array([ 1., 2., 3., 4., 5., nan])

1.10.11 DF.unique()
• returns the total number of values excluding nan values
• Note - uniques includes nan values while nunique don’t count them.
[112]: temp.nunique()

[112]: 5

1.10.12 DF[‘col’].isnull()
• checks every value of Series or DF whether it is null or not
[113]: students[students['name'].isnull()]

[113]: name college branch cgpa package

3 NaN NaN NaN NaN NaN
5 NaN vlsi ce 9.0 7.0
7 NaN NaN cse 10.0 9.0
9 NaN git NaN NaN NaN

1.10.13 DF[‘col’].notnull()
• works same as isnull()
• only difference is that it returns True if values is not null otherwise False
[114]: students[students['name'].notnull()]

[114]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0
4 mrityunjay NaN me 5.60 6.0
6 rishabh ssit civ 7.40 8.0
8 aditya NaN bio 7.40 NaN

1.10.14 DF[‘col’].hasnans
• used for checking the Nan in whole DF or series
[115]: students['name'].hasnans

[115]: True

179
 1.10.15 DF[‘col’].dropna(how=‘any’, inplace=False)
• Drops the whole rows in which Nan is present.
• How parameter defines which row should be dropped.
1. if how is any it means if any of the values is nan then drop whole row
2. if how is all than row will be dropped if all values are nan
[116]: students

[116]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0
3 NaN NaN NaN NaN NaN
4 mrityunjay NaN me 5.60 6.0
5 NaN vlsi ce 9.00 7.0
6 rishabh ssit civ 7.40 8.0
7 NaN NaN cse 10.00 9.0
8 aditya NaN bio 7.40 NaN
9 NaN git NaN NaN NaN

[117]: students.dropna()

[117]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0
6 rishabh ssit civ 7.40 8.0

[118]: students.dropna(how='all')

[118]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0
4 mrityunjay NaN me 5.60 6.0
5 NaN vlsi ce 9.00 7.0
6 rishabh ssit civ 7.40 8.0
7 NaN NaN cse 10.00 9.0
8 aditya NaN bio 7.40 NaN
9 NaN git NaN NaN NaN

[119]: students.dropna(subset=['name', 'college'])

[119]: name college branch cgpa package

0 nitish bit eee 6.66 4.0
1 ankit iit it 8.25 5.0
2 rupesh vit cse 6.41 6.0

180
 6 rishabh ssit civ 7.40 8.0

1.10.16 DF[‘col’].fillna()
• Handling missing values
[120]: students['name'].fillna('unknown')

[120]: 0 nitish
1 ankit
2 rupesh
3 unknown
4 mrityunjay
5 unknown
6 rishabh
7 unknown
8 aditya
9 unknown
Name: name, dtype: object

[121]: students['package'].fillna(students['package'].mean())

[121]: 0 4.000000
1 5.000000
2 6.000000
3 6.428571
4 6.000000
5 7.000000
6 8.000000
7 9.000000
8 6.428571
9 6.428571
Name: package, dtype: float64

Note- There is another way to handle filling missing values, we can fill by previous value or
upcoming value
[122]: students['name'].bfill()

[122]: 0 nitish
1 ankit
2 rupesh
3 mrityunjay
4 mrityunjay
5 rishabh
6 rishabh
7 aditya
8 aditya

181
 9 NaN
Name: name, dtype: object

[123]: students['name'].ffill()

[123]: 0 nitish
1 ankit
2 rupesh
3 rupesh
4 mrityunjay
5 mrityunjay
6 rishabh
7 rishabh
8 aditya
9 aditya
Name: name, dtype: object

1.10.17 DF.drop_duplicates(keep=‘first’)
• droppes duplicated rows
• keep parameter tells which occurrence should be included.
[124]: temp = pd.Series([1,1,1,2,3,3,4,4])
temp.drop_duplicates()

[124]: 0 1
3 2
4 3
6 4
dtype: int64

[125]: marks = pd.DataFrame([

[100,80,10],
[90,70,7],
[120,100,14],
[80,70,14],
[80,70,14]
], columns=['iq', 'marks', 'package'])
marks

[125]: iq marks package

0 100 80 10
1 90 70 7
2 120 100 14
3 80 70 14
4 80 70 14

182
[126]: marks.duplicated().sum()

[126]: 1

[127]: marks.drop_duplicates(keep='last')

[127]: iq marks package

0 100 80 10
1 90 70 7
2 120 100 14
4 80 70 14

Find the last match played by virat kohli in Delhi

[128]: ipl.head(2)

[128]: ID City Date Season MatchNumber \

0 1312200 Ahmedabad 2022-05-29 2022 Final
1 1312199 Ahmedabad 2022-05-27 2022 Qualifier 2

Team1 Team2 \
0 Rajasthan Royals Gujarat Titans
1 Royal Challengers Bangalore Rajasthan Royals

Venue TossWinner TossDecision SuperOver \

0 Narendra Modi Stadium, Ahmedabad Rajasthan Royals bat N
1 Narendra Modi Stadium, Ahmedabad Rajasthan Royals field N

WinningTeam WonBy Margin method Player_of_Match \

0 Gujarat Titans Wickets 7.0 NaN HH Pandya
1 Rajasthan Royals Wickets 7.0 NaN JC Buttler

Team1Players \
0 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D …
1 ['V Kohli', 'F du Plessis', 'RM Patidar', 'GJ …

Team2Players Umpire1 Umpire2

0 ['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pan… CB Gaffaney Nitin Menon
1 ['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D … CB Gaffaney Nitin Menon

[129]: ipl['all_players'] = ipl['Team1Players'] + ipl['Team2Players']

[130]: def did_kohli_play(players_list):

return 'V Kohli' in players_list

ipl['did_kohli_played'] = ipl['all_players'].apply(did_kohli_play)

183
[131]: ipl[(ipl['City'] == 'Delhi') & (ipl['did_kohli_played'])].
↪drop_duplicates(subset=['City', 'did_kohli_played'], keep='first')

[131]: ID City Date Season MatchNumber Team1 \

208 1178421 Delhi 2019-04-28 2019 46 Delhi Capitals

Team2 Venue TossWinner \

208 Royal Challengers Bangalore Arun Jaitley Stadium Delhi Capitals

TossDecision … WonBy Margin method Player_of_Match \

208 bat … Runs 16.0 NaN S Dhawan

Team1Players \
208 ['PP Shaw', 'S Dhawan', 'SS Iyer', 'RR Pant', …

Team2Players Umpire1 \
208 ['PA Patel', 'V Kohli', 'AB de Villiers', 'S D… BNJ Oxenford

Umpire2 all_players \
208 KN Ananthapadmanabhan ['PP Shaw', 'S Dhawan', 'SS Iyer', 'RR Pant', …

did_kohli_played
208 True

[1 rows x 22 columns]

1.10.18 DF.drop(index=[], columns=[])

• dropping specific rows
[132]: temp = pd.Series([10,2,3,16,45,78,10])
temp

[132]: 0 10
1 2
2 3
3 16
4 45
5 78
6 10
dtype: int64

[133]: temp.drop(index=[0,6])

[133]: 1 2
2 3
3 16

184
 4 45
5 78
dtype: int64

[134]: students.drop(columns=['branch', 'cgpa'])

[134]: name college package

0 nitish bit 4.0
1 ankit iit 5.0
2 rupesh vit 6.0
3 NaN NaN NaN
4 mrityunjay NaN 6.0
5 NaN vlsi 7.0
6 rishabh ssit 8.0
7 NaN NaN 9.0
8 aditya NaN NaN
9 NaN git NaN

1.10.19 DF.apply(func)
• apply function on every value of the series or DF
[135]: temp = pd.Series([10, 20, 30, 40, 50])
temp

[135]: 0 10
1 20
2 30
3 40
4 50
dtype: int64

[136]: def sigmoid(val):

return 1/1+np.exp(-val)

temp.apply(sigmoid)

[136]: 0 1.000045
1 1.000000
2 1.000000
3 1.000000
4 1.000000
dtype: float64

[2]: import numpy as np

import pandas as pd

185
[3]: movies = pd.read_csv('imdb-top-1000.csv')
movies.head(1)

[3]: Series_Title Released_Year Runtime Genre IMDB_Rating \

0 The Shawshank Redemption 1994 142 Drama 9.3

Director Star1 No_of_Votes Gross Metascore

0 Frank Darabont Tim Robbins 2343110 28341469.0 80.0

[4]: genres = movies.groupby('Genre')

[5]: genres

[5]: <pandas.core.groupby.generic.DataFrameGroupBy object at 0x000001CB1B0423F0>

1.10.20 Applying builtin aggregation functions on groupby objects

[6]: genres.min()

[6]: Series_Title Released_Year Runtime \

Genre
Action 300 1924 45
Adventure 2001: A Space Odyssey 1925 88
Animation Akira 1940 71
Biography 12 Years a Slave 1928 93
Comedy (500) Days of Summer 1921 68
Crime 12 Angry Men 1931 80
Drama 1917 1925 64
Family E.T. the Extra-Terrestrial 1971 100
Fantasy Das Cabinet des Dr. Caligari 1920 76
Film-Noir Shadow of a Doubt 1941 100
Horror Alien 1933 71
Mystery Dark City 1938 96
Thriller Wait Until Dark 1967 108
Western Il buono, il brutto, il cattivo 1965 132

IMDB_Rating Director Star1 \

Genre
Action 7.6 Abhishek Chaubey Aamir Khan
Adventure 7.6 Akira Kurosawa Aamir Khan
Animation 7.6 Adam Elliot Adrian Molina
Biography 7.6 Adam McKay Adrien Brody
Comedy 7.6 Alejandro G. Iñárritu Aamir Khan
Crime 7.6 Akira Kurosawa Ajay Devgn
Drama 7.6 Aamir Khan Abhay Deol
Family 7.8 Mel Stuart Gene Wilder
Fantasy 7.9 F.W. Murnau Max Schreck

186
 Film-Noir 7.8 Alfred Hitchcock Humphrey Bogart
Horror 7.6 Alejandro Amenábar Anthony Perkins
Mystery 7.6 Alex Proyas Bernard-Pierre Donnadieu
Thriller 7.8 Terence Young Audrey Hepburn
Western 7.8 Clint Eastwood Clint Eastwood

No_of_Votes Gross Metascore

Genre
Action 25312 3296.0 33.0
Adventure 29999 61001.0 41.0
Animation 25229 128985.0 61.0
Biography 27254 21877.0 48.0
Comedy 26337 1305.0 45.0
Crime 27712 6013.0 47.0
Drama 25088 3600.0 28.0
Family 178731 4000000.0 67.0
Fantasy 57428 337574718.0 NaN
Film-Noir 59556 449191.0 94.0
Horror 27007 89029.0 46.0
Mystery 33982 1035953.0 52.0
Thriller 27733 17550741.0 81.0
Western 65659 5321508.0 69.0

1. find the top 3 genres by total earning

[10]: movies.groupby('Genre').sum()['Gross'].sort_values(ascending=False).head(3)

[10]: Genre
Drama 3.540997e+10
Action 3.263226e+10
Comedy 1.566387e+10
Name: Gross, dtype: float64

[11]: # Another way for same

movies.groupby('Genre')['Gross'].sum().sort_values(ascending=False).head(3)

[11]: Genre
Drama 3.540997e+10
Action 3.263226e+10
Comedy 1.566387e+10
Name: Gross, dtype: float64

2. Find the genre with highest avg IMDB rating

[12]: movies.groupby('Genre')['IMDB_Rating'].mean().sort_values(ascending=False).
↪head(1)

187
[12]: Genre
Western 8.35
Name: IMDB_Rating, dtype: float64

3. Find director with most popularity

[17]: movies.groupby('Director')['No_of_Votes'].sum().sort_values(ascending=False).
↪head(1)

[17]: Director
Christopher Nolan 11578345
Name: No_of_Votes, dtype: int64

4. Find the highest rating of movies in each genre.

[18]: movies.groupby('Genre')['IMDB_Rating'].max()

[18]: Genre
Action 9.0
Adventure 8.6
Animation 8.6
Biography 8.9
Comedy 8.6
Crime 9.2
Drama 9.3
Family 7.8
Fantasy 8.1
Film-Noir 8.1
Horror 8.5
Mystery 8.4
Thriller 7.8
Western 8.8
Name: IMDB_Rating, dtype: float64

5. Find the number of movies done by each actor

[19]: # Using groupby()
movies.groupby('Star1')['Series_Title'].count().sort_values(ascending=False)

[19]: Star1
Tom Hanks 12
Robert De Niro 11
Clint Eastwood 10
Al Pacino 10
Leonardo DiCaprio 9
..
Glen Hansard 1
Giuseppe Battiston 1

188
 Giulietta Masina 1
Gerardo Taracena 1
Ömer Faruk Sorak 1
Name: Series_Title, Length: 660, dtype: int64

[20]: # Using value_counts()

movies['Star1'].value_counts()

[20]: Star1
Tom Hanks 12
Robert De Niro 11
Al Pacino 10
Clint Eastwood 10
Humphrey Bogart 9
..
Preity Zinta 1
Javier Bardem 1
Ki-duk Kim 1
Vladimir Garin 1
Robert Donat 1
Name: count, Length: 660, dtype: int64

1.11 Attributes and Methods

1.11.1 len(DF.groupy(‘col’))
• Returns total number of groups.
[21]: len(movies.groupby('Genre'))

[21]: 14

[23]: movies['Genre'].nunique()

[23]: 14

1.11.2 DF.groupby(‘col’).size()
• Returns series where index is group name and value is the values belongs to that group.
• output is same as DF[‘col’].value_counts()

[24]: movies.groupby('Genre').size()

[24]: Genre
Action 172
Adventure 72
Animation 82
Biography 88

189
 Comedy 155
Crime 107
Drama 289
Family 2
Fantasy 2
Film-Noir 3
Horror 11
Mystery 12
Thriller 1
Western 4
dtype: int64

[25]: movies.groupby('Released_Year').size()

[25]: Released_Year
1920 1
1921 1
1922 1
1924 1
1925 2
..
2017 22
2018 19
2019 23
2020 6
PG 1
Length: 100, dtype: int64

1.11.3 DF.groupby(‘Col’).first()/last()/nth(n)
• returns DF containing first or last or nth indexed values from each group.
• If any group has less values than n index than it ignores that group
[26]: genres = movies.groupby('Genre')
genres.first()

[26]: Series_Title Released_Year Runtime \

Genre
Action The Dark Knight 2008 152
Adventure Interstellar 2014 169
Animation Sen to Chihiro no kamikakushi 2001 125
Biography Schindler's List 1993 195
Comedy Gisaengchung 2019 132
Crime The Godfather 1972 175
Drama The Shawshank Redemption 1994 142
Family E.T. the Extra-Terrestrial 1982 115
Fantasy Das Cabinet des Dr. Caligari 1920 76

190
 Film-Noir The Third Man 1949 104
Horror Psycho 1960 109
Mystery Memento 2000 113
Thriller Wait Until Dark 1967 108
Western Il buono, il brutto, il cattivo 1966 161

IMDB_Rating Director Star1 \

Genre
Action 9.0 Christopher Nolan Christian Bale
Adventure 8.6 Christopher Nolan Matthew McConaughey
Animation 8.6 Hayao Miyazaki Daveigh Chase
Biography 8.9 Steven Spielberg Liam Neeson
Comedy 8.6 Bong Joon Ho Kang-ho Song
Crime 9.2 Francis Ford Coppola Marlon Brando
Drama 9.3 Frank Darabont Tim Robbins
Family 7.8 Steven Spielberg Henry Thomas
Fantasy 8.1 Robert Wiene Werner Krauss
Film-Noir 8.1 Carol Reed Orson Welles
Horror 8.5 Alfred Hitchcock Anthony Perkins
Mystery 8.4 Christopher Nolan Guy Pearce
Thriller 7.8 Terence Young Audrey Hepburn
Western 8.8 Sergio Leone Clint Eastwood

No_of_Votes Gross Metascore

Genre
Action 2303232 534858444.0 84.0
Adventure 1512360 188020017.0 74.0
Animation 651376 10055859.0 96.0
Biography 1213505 96898818.0 94.0
Comedy 552778 53367844.0 96.0
Crime 1620367 134966411.0 100.0
Drama 2343110 28341469.0 80.0
Family 372490 435110554.0 91.0
Fantasy 57428 337574718.0 NaN
Film-Noir 158731 449191.0 97.0
Horror 604211 32000000.0 97.0
Mystery 1125712 25544867.0 80.0
Thriller 27733 17550741.0 81.0
Western 688390 6100000.0 90.0

[27]: genres.last()

[27]: Series_Title Released_Year Runtime \

Genre
Action Escape from Alcatraz 1979 112
Adventure Kelly's Heroes 1970 144
Animation The Jungle Book 1967 78

191
 Biography Midnight Express 1978 121
Comedy Breakfast at Tiffany's 1961 115
Crime The 39 Steps 1935 86
Drama Lifeboat 1944 97
Family Willy Wonka & the Chocolate Factory 1971 100
Fantasy Nosferatu 1922 94
Film-Noir Shadow of a Doubt 1943 108
Horror The Others 2001 101
Mystery Lost Highway 1997 134
Thriller Wait Until Dark 1967 108
Western The Outlaw Josey Wales 1976 135

IMDB_Rating Director Star1 No_of_Votes \

Genre
Action 7.6 Don Siegel Clint Eastwood 121731
Adventure 7.6 Brian G. Hutton Clint Eastwood 45338
Animation 7.6 Wolfgang Reitherman Phil Harris 166409
Biography 7.6 Alan Parker Brad Davis 73662
Comedy 7.6 Blake Edwards Audrey Hepburn 166544
Crime 7.6 Alfred Hitchcock Robert Donat 51853
Drama 7.6 Alfred Hitchcock Tallulah Bankhead 26471
Family 7.8 Mel Stuart Gene Wilder 178731
Fantasy 7.9 F.W. Murnau Max Schreck 88794
Film-Noir 7.8 Alfred Hitchcock Teresa Wright 59556
Horror 7.6 Alejandro Amenábar Nicole Kidman 337651
Mystery 7.6 David Lynch Bill Pullman 131101
Thriller 7.8 Terence Young Audrey Hepburn 27733
Western 7.8 Clint Eastwood Clint Eastwood 65659

Gross Metascore
Genre
Action 43000000.0 76.0
Adventure 1378435.0 50.0
Animation 141843612.0 65.0
Biography 35000000.0 59.0
Comedy 679874270.0 76.0
Crime 302787539.0 93.0
Drama 852142728.0 78.0
Family 4000000.0 67.0
Fantasy 445151978.0 NaN
Film-Noir 123353292.0 94.0
Horror 96522687.0 74.0
Mystery 3796699.0 52.0
Thriller 17550741.0 81.0
Western 31800000.0 69.0

[28]: genres.nth(6) # 7th values is at 6th index

192
[28]: Series_Title Released_Year Runtime \
16 Star Wars: Episode V - The Empire Strikes Back 1980 124
27 Se7en 1995 127
32 It's a Wonderful Life 1946 130
66 WALL·E 2008 98
83 The Great Dictator 1940 125
102 Braveheart 1995 178
118 North by Northwest 1959 136
420 Sleuth 1972 138
724 Get Out 2017 104

Genre IMDB_Rating Director Star1 \

16 Action 8.7 Irvin Kershner Mark Hamill
27 Crime 8.6 David Fincher Morgan Freeman
32 Drama 8.6 Frank Capra James Stewart
66 Animation 8.4 Andrew Stanton Ben Burtt
83 Comedy 8.4 Charles Chaplin Charles Chaplin
102 Biography 8.3 Mel Gibson Mel Gibson
118 Adventure 8.3 Alfred Hitchcock Cary Grant
420 Mystery 8.0 Joseph L. Mankiewicz Laurence Olivier
724 Horror 7.7 Jordan Peele Daniel Kaluuya

No_of_Votes Gross Metascore

16 1159315 290475067.0 82.0
27 1445096 100125643.0 65.0
32 405801 82385199.0 89.0
66 999790 223808164.0 95.0
83 203150 288475.0 NaN
102 959181 75600000.0 68.0
118 299198 13275000.0 98.0
420 44748 4081254.0 NaN
724 492851 176040665.0 85.0

1.11.4 DF.groupby(‘col’).get_group(‘group’)
• returns DF containing specific values belonging to that column
• same output by column specific filtering
[29]: genres.get_group('Horror')

[29]: Series_Title Released_Year Runtime Genre IMDB_Rating \

49 Psycho 1960 109 Horror 8.5
75 Alien 1979 117 Horror 8.4
271 The Thing 1982 109 Horror 8.1
419 The Exorcist 1973 122 Horror 8.0
544 Night of the Living Dead 1968 96 Horror 7.9
707 The Innocents 1961 100 Horror 7.8

193
 724 Get Out 2017 104 Horror 7.7
844 Halloween 1978 91 Horror 7.7
876 The Invisible Man 1933 71 Horror 7.7
932 Saw 2004 103 Horror 7.6
948 The Others 2001 101 Horror 7.6

Director Star1 No_of_Votes Gross Metascore

49 Alfred Hitchcock Anthony Perkins 604211 32000000.0 97.0
75 Ridley Scott Sigourney Weaver 787806 78900000.0 89.0
271 John Carpenter Kurt Russell 371271 13782838.0 57.0
419 William Friedkin Ellen Burstyn 362393 232906145.0 81.0
544 George A. Romero Duane Jones 116557 89029.0 89.0
707 Jack Clayton Deborah Kerr 27007 2616000.0 88.0
724 Jordan Peele Daniel Kaluuya 492851 176040665.0 85.0
844 John Carpenter Donald Pleasence 233106 47000000.0 87.0
876 James Whale Claude Rains 30683 298791505.0 87.0
932 James Wan Cary Elwes 379020 56000369.0 46.0
948 Alejandro Amenábar Nicole Kidman 337651 96522687.0 74.0

1.11.5 DF.groupby(‘col’).groups
• Returns dictionary having group names as keys and index values belonging to that group as
values in dictionary
[31]: genres.groups

[31]: {'Action': [2, 5, 8, 10, 13, 14, 16, 29, 30, 31, 39, 42, 44, 55, 57, 59, 60, 63,
68, 72, 106, 109, 129, 130, 134, 140, 142, 144, 152, 155, 160, 161, 166, 168,
171, 172, 177, 181, 194, 201, 202, 216, 217, 223, 224, 236, 241, 262, 275, 294,
308, 320, 325, 326, 331, 337, 339, 340, 343, 345, 348, 351, 353, 356, 357, 362,
368, 369, 375, 376, 390, 410, 431, 436, 473, 477, 479, 482, 488, 493, 496, 502,
507, 511, 532, 535, 540, 543, 564, 569, 570, 573, 577, 582, 583, 602, 605, 608,
615, 623, …], 'Adventure': [21, 47, 93, 110, 114, 116, 118, 137, 178, 179,
191, 193, 209, 226, 231, 247, 267, 273, 281, 300, 301, 304, 306, 323, 329, 361,
366, 377, 402, 406, 415, 426, 458, 470, 497, 498, 506, 513, 514, 537, 549, 552,
553, 566, 576, 604, 609, 618, 638, 647, 675, 681, 686, 692, 711, 713, 739, 755,
781, 797, 798, 851, 873, 884, 912, 919, 947, 957, 964, 966, 984, 991],
'Animation': [23, 43, 46, 56, 58, 61, 66, 70, 101, 135, 146, 151, 158, 170, 197,
205, 211, 213, 219, 229, 230, 242, 245, 246, 270, 330, 332, 358, 367, 378, 386,
389, 394, 395, 399, 401, 405, 409, 469, 499, 510, 516, 518, 522, 578, 586, 592,
595, 596, 599, 633, 640, 643, 651, 665, 672, 694, 728, 740, 741, 744, 756, 758,
761, 771, 783, 796, 799, 822, 828, 843, 875, 891, 892, 902, 906, 920, 956, 971,
976, 986, 992], 'Biography': [7, 15, 18, 35, 38, 54, 102, 107, 131, 139, 147,
157, 159, 173, 176, 212, 215, 218, 228, 235, 243, 263, 276, 282, 290, 298, 317,
328, 338, 342, 346, 359, 360, 365, 372, 373, 385, 411, 416, 418, 424, 429, 484,
525, 536, 542, 545, 575, 579, 587, 600, 606, 614, 622, 632, 635, 644, 649, 650,
657, 671, 673, 684, 729, 748, 753, 757, 759, 766, 770, 779, 809, 810, 815, 820,

194
 831, 849, 858, 877, 882, 897, 910, 915, 923, 940, 949, 952, 987], 'Comedy': [19,
26, 51, 52, 64, 78, 83, 95, 96, 112, 117, 120, 127, 128, 132, 153, 169, 183,
192, 204, 207, 208, 214, 221, 233, 238, 240, 250, 251, 252, 256, 261, 266, 277,
284, 311, 313, 316, 318, 322, 327, 374, 379, 381, 392, 396, 403, 413, 414, 417,
427, 435, 445, 446, 449, 455, 459, 460, 463, 464, 466, 471, 472, 475, 481, 490,
494, 500, 503, 509, 526, 528, 530, 531, 533, 538, 539, 541, 547, 557, 558, 562,
563, 565, 574, 591, 593, 594, 598, 613, 626, 630, 660, 662, 667, 679, 680, 683,
687, 701, …], 'Crime': [1, 3, 4, 6, 22, 25, 27, 28, 33, 37, 41, 71, 77, 79,
86, 87, 103, 108, 111, 113, 123, 125, 133, 136, 162, 163, 164, 165, 180, 186,
187, 189, 198, 222, 232, 239, 255, 257, 287, 288, 299, 305, 335, 363, 364, 380,
384, 397, 437, 438, 441, 442, 444, 450, 451, 465, 474, 480, 485, 487, 505, 512,
519, 520, 523, 527, 546, 556, 560, 584, 597, 603, 607, 611, 621, 639, 653, 664,
669, 676, 695, 708, 723, 762, 763, 767, 775, 791, 795, 802, 811, 823, 827, 833,
885, 895, 921, 922, 926, 938, …], 'Drama': [0, 9, 11, 17, 20, 24, 32, 34, 36,
40, 45, 50, 53, 62, 65, 67, 73, 74, 76, 80, 82, 84, 85, 88, 89, 90, 91, 92, 94,
97, 98, 99, 100, 104, 105, 121, 122, 124, 126, 138, 141, 143, 148, 149, 150,
154, 156, 167, 174, 175, 182, 184, 185, 188, 190, 195, 196, 199, 200, 203, 206,
210, 225, 227, 234, 237, 244, 248, 249, 253, 254, 258, 259, 260, 264, 265, 268,
269, 272, 274, 278, 279, 280, 283, 285, 286, 289, 291, 292, 293, 295, 296, 297,
302, 303, 307, 310, 312, 314, 315, …], 'Family': [688, 698], 'Fantasy': [321,
568], 'Film-Noir': [309, 456, 712], 'Horror': [49, 75, 271, 419, 544, 707, 724,
844, 876, 932, 948], 'Mystery': [69, 81, 119, 145, 220, 393, 420, 714, 829, 899,
959, 961], 'Thriller': [700], 'Western': [12, 48, 115, 691]}

1.11.6 DF.groupby(‘col’).describe()
• applies specific statistical functions to numeric columns of each group
[32]: genres.describe()

[32]: Runtime \
count mean std min 25% 50% 75% max
Genre
Action 172.0 129.046512 28.500706 45.0 110.75 127.5 143.25 321.0
Adventure 72.0 134.111111 33.317320 88.0 109.00 127.0 149.00 228.0
Animation 82.0 99.585366 14.530471 71.0 90.00 99.5 106.75 137.0
Biography 88.0 136.022727 25.514466 93.0 120.00 129.0 146.25 209.0
Comedy 155.0 112.129032 22.946213 68.0 96.00 106.0 124.50 188.0
Crime 107.0 126.392523 27.689231 80.0 106.50 122.0 141.50 229.0
Drama 289.0 124.737024 27.740490 64.0 105.00 121.0 137.00 242.0
Family 2.0 107.500000 10.606602 100.0 103.75 107.5 111.25 115.0
Fantasy 2.0 85.000000 12.727922 76.0 80.50 85.0 89.50 94.0
Film-Noir 3.0 104.000000 4.000000 100.0 102.00 104.0 106.00 108.0
Horror 11.0 102.090909 13.604812 71.0 98.00 103.0 109.00 122.0
Mystery 12.0 119.083333 14.475423 96.0 110.75 117.5 130.25 138.0
Thriller 1.0 108.000000 NaN 108.0 108.00 108.0 108.00 108.0
Western 4.0 148.250000 17.153717 132.0 134.25 148.0 162.00 165.0

195
 IMDB_Rating … Gross Metascore \
count mean … 75% max count
Genre …
Action 172.0 7.949419 … 2.674437e+08 936662225.0 143.0
Adventure 72.0 7.937500 … 1.998070e+08 874211619.0 64.0
Animation 82.0 7.930488 … 2.520612e+08 873839108.0 75.0
Biography 88.0 7.938636 … 9.829924e+07 753585104.0 79.0
Comedy 155.0 7.901290 … 8.107809e+07 886752933.0 125.0
Crime 107.0 8.016822 … 7.102163e+07 790482117.0 87.0
Drama 289.0 7.957439 … 1.164461e+08 924558264.0 241.0
Family 2.0 7.800000 … 3.273329e+08 435110554.0 2.0
Fantasy 2.0 8.000000 … 4.182577e+08 445151978.0 0.0
Film-Noir 3.0 7.966667 … 6.273068e+07 123353292.0 3.0
Horror 11.0 7.909091 … 1.362817e+08 298791505.0 11.0
Mystery 12.0 7.975000 … 1.310949e+08 474203697.0 8.0
Thriller 1.0 7.800000 … 1.755074e+07 17550741.0 1.0
Western 4.0 8.350000 … 1.920000e+07 31800000.0 4.0

mean std min 25% 50% 75% max

Genre
Action 73.419580 12.421252 33.0 65.00 74.0 82.00 98.0
Adventure 78.437500 12.345393 41.0 69.75 80.5 87.25 100.0
Animation 81.093333 8.813646 61.0 75.00 82.0 87.50 96.0
Biography 76.240506 11.028187 48.0 70.50 76.0 84.50 97.0
Comedy 78.720000 11.829160 45.0 72.00 79.0 88.00 99.0
Crime 77.080460 13.099102 47.0 69.50 77.0 87.00 100.0
Drama 79.701245 12.744687 28.0 72.00 82.0 89.00 100.0
Family 79.000000 16.970563 67.0 73.00 79.0 85.00 91.0
Fantasy NaN NaN NaN NaN NaN NaN NaN
Film-Noir 95.666667 1.527525 94.0 95.00 96.0 96.50 97.0
Horror 80.000000 15.362291 46.0 77.50 87.0 88.50 97.0
Mystery 79.125000 18.604435 52.0 65.25 77.0 98.50 100.0
Thriller 81.000000 NaN 81.0 81.00 81.0 81.00 81.0
Western 78.250000 9.032349 69.0 72.75 77.0 82.50 90.0

[14 rows x 40 columns]

1.11.7
1.11.8 DF.groupby(‘col’).sample(n, replace=False)
• Returns n random samples from each group
• if the total values in a group is less than n then replace should be true because if samples is
less than n then there will be error
• by default n is 1

196
[33]: genres.sample(2, replace=True)

[33]: Series_Title Released_Year Runtime Genre \

59 Avengers: Endgame 2019 181 Action
106 Aliens 1986 137 Action
798 Interstate 60: Episodes of the Road 2002 116 Adventure
470 Hunt for the Wilderpeople 2016 101 Adventure
330 Zootopia 2016 108 Animation
43 The Lion King 1994 88 Animation
18 Hamilton 2020 160 Biography
940 Finding Neverland 2004 106 Biography
687 The King of Comedy 1982 109 Comedy
379 Yeopgijeogin geunyeo 2001 137 Comedy
6 Pulp Fiction 1994 154 Crime
288 Cool Hand Luke 1967 127 Crime
32 It's a Wonderful Life 1946 130 Drama
825 Fried Green Tomatoes 1991 130 Drama
698 Willy Wonka & the Chocolate Factory 1971 100 Family
688 E.T. the Extra-Terrestrial 1982 115 Family
321 Das Cabinet des Dr. Caligari 1920 76 Fantasy
568 Nosferatu 1922 94 Fantasy
309 The Third Man 1949 104 Film-Noir
456 The Maltese Falcon 1941 100 Film-Noir
844 Halloween 1978 91 Horror
707 The Innocents 1961 100 Horror
829 Spoorloos 1988 107 Mystery
829 Spoorloos 1988 107 Mystery
700 Wait Until Dark 1967 108 Thriller
700 Wait Until Dark 1967 108 Thriller
691 The Outlaw Josey Wales 1976 135 Western
691 The Outlaw Josey Wales 1976 135 Western

IMDB_Rating Director Star1 No_of_Votes \

59 8.4 Anthony Russo Joe Russo 809955
106 8.3 James Cameron Sigourney Weaver 652719
798 7.7 Bob Gale James Marsden 29999
470 7.9 Taika Waititi Sam Neill 111483
330 8.0 Byron Howard Rich Moore 434143
43 8.5 Roger Allers Rob Minkoff 942045
18 8.6 Thomas Kail Lin-Manuel Miranda 55291
940 7.6 Marc Forster Johnny Depp 198677
687 7.8 Martin Scorsese Robert De Niro 88511
379 8.0 Jae-young Kwak Tae-Hyun Cha 45403
6 8.9 Quentin Tarantino John Travolta 1826188
288 8.1 Stuart Rosenberg Paul Newman 161984
32 8.6 Frank Capra James Stewart 405801
825 7.7 Jon Avnet Kathy Bates 66941

197
698 7.8 Mel Stuart Gene Wilder 178731
688 7.8 Steven Spielberg Henry Thomas 372490
321 8.1 Robert Wiene Werner Krauss 57428
568 7.9 F.W. Murnau Max Schreck 88794
309 8.1 Carol Reed Orson Welles 158731
456 8.0 John Huston Humphrey Bogart 148928
844 7.7 John Carpenter Donald Pleasence 233106
707 7.8 Jack Clayton Deborah Kerr 27007
829 7.7 George Sluizer Bernard-Pierre Donnadieu 33982
829 7.7 George Sluizer Bernard-Pierre Donnadieu 33982
700 7.8 Terence Young Audrey Hepburn 27733
700 7.8 Terence Young Audrey Hepburn 27733
691 7.8 Clint Eastwood Clint Eastwood 65659
691 7.8 Clint Eastwood Clint Eastwood 65659

Gross Metascore
59 858373000.0 78.0
106 85160248.0 84.0
798 174381905.0 NaN
470 5202582.0 81.0
330 341268248.0 78.0
43 422783777.0 88.0
18 440984783.0 90.0
940 51680613.0 67.0
687 2500000.0 73.0
379 772721890.0 NaN
6 107928762.0 94.0
288 16217773.0 92.0
32 82385199.0 89.0
825 82418501.0 64.0
698 4000000.0 67.0
688 435110554.0 91.0
321 337574718.0 NaN
568 445151978.0 NaN
309 449191.0 97.0
456 2108060.0 96.0
844 47000000.0 87.0
707 2616000.0 88.0
829 367916835.0 NaN
829 367916835.0 NaN
700 17550741.0 81.0
700 17550741.0 81.0
691 31800000.0 69.0
691 31800000.0 69.0

198
 1.11.9 DF.groupby(‘col’).nunique()
• unique values in each column of each group in form of DF
[35]: genres.nunique()

[35]: Series_Title Released_Year Runtime IMDB_Rating Director Star1 \

Genre
Action 172 61 78 15 123 121
Adventure 72 49 58 10 59 59
Animation 82 35 41 11 51 77
Biography 88 44 56 13 76 72
Comedy 155 72 70 11 113 133
Crime 106 56 65 14 86 85
Drama 289 83 95 14 211 250
Family 2 2 2 1 2 2
Fantasy 2 2 2 2 2 2
Film-Noir 3 3 3 3 3 3
Horror 11 11 10 8 10 11
Mystery 12 11 10 8 10 11
Thriller 1 1 1 1 1 1
Western 4 4 4 4 2 2

No_of_Votes Gross Metascore

Genre
Action 172 172 50
Adventure 72 72 33
Animation 82 82 29
Biography 88 88 40
Comedy 155 155 44
Crime 107 107 39
Drama 288 287 52
Family 2 2 2
Fantasy 2 2 0
Film-Noir 3 3 3
Horror 11 11 9
Mystery 12 12 7
Thriller 1 1 1
Western 4 4 4

1.12 passing aggregation methods as dict

1.12.1 DF.goupby(‘col’).agg({‘col’:‘agg_func’})
• Apply specific aggregation functions of specific columns of each group
• We can apply more than one agg func on one column.

199
[36]: genres.agg({
'Runtime':'mean',
'IMDB_Rating':'mean',
'No_of_Votes':'sum',
'Gross':'sum',
'Metascore':'max'
})

[36]: Runtime IMDB_Rating No_of_Votes Gross Metascore

Genre
Action 129.046512 7.949419 72282412 3.263226e+10 98.0
Adventure 134.111111 7.937500 22576163 9.496922e+09 100.0
Animation 99.585366 7.930488 21978630 1.463147e+10 96.0
Biography 136.022727 7.938636 24006844 8.276358e+09 97.0
Comedy 112.129032 7.901290 27620327 1.566387e+10 99.0
Crime 126.392523 8.016822 33533615 8.452632e+09 100.0
Drama 124.737024 7.957439 61367304 3.540997e+10 100.0
Family 107.500000 7.800000 551221 4.391106e+08 91.0
Fantasy 85.000000 8.000000 146222 7.827267e+08 NaN
Film-Noir 104.000000 7.966667 367215 1.259105e+08 97.0
Horror 102.090909 7.909091 3742556 1.034649e+09 97.0
Mystery 119.083333 7.975000 4203004 1.256417e+09 100.0
Thriller 108.000000 7.800000 27733 1.755074e+07 81.0
Western 148.250000 8.350000 1289665 5.822151e+07 90.0

[38]: genres.agg({
'Runtime':['min', 'mean'],
'IMDB_Rating':'mean',
'No_of_Votes':['sum', 'max'],
'Gross':'sum',
'Metascore':'max'
})

[38]: Runtime IMDB_Rating No_of_Votes Gross \

min mean mean sum max sum
Genre
Action 45 129.046512 7.949419 72282412 2303232 3.263226e+10
Adventure 88 134.111111 7.937500 22576163 1512360 9.496922e+09
Animation 71 99.585366 7.930488 21978630 999790 1.463147e+10
Biography 93 136.022727 7.938636 24006844 1213505 8.276358e+09
Comedy 68 112.129032 7.901290 27620327 939631 1.566387e+10
Crime 80 126.392523 8.016822 33533615 1826188 8.452632e+09
Drama 64 124.737024 7.957439 61367304 2343110 3.540997e+10
Family 100 107.500000 7.800000 551221 372490 4.391106e+08
Fantasy 76 85.000000 8.000000 146222 88794 7.827267e+08
Film-Noir 100 104.000000 7.966667 367215 158731 1.259105e+08
Horror 71 102.090909 7.909091 3742556 787806 1.034649e+09

200
 Mystery 96 119.083333 7.975000 4203004 1129894 1.256417e+09
Thriller 108 108.000000 7.800000 27733 27733 1.755074e+07
Western 132 148.250000 8.350000 1289665 688390 5.822151e+07

Metascore
max
Genre
Action 98.0
Adventure 100.0
Animation 96.0
Biography 97.0
Comedy 99.0
Crime 100.0
Drama 100.0
Family 91.0
Fantasy NaN
Film-Noir 97.0
Horror 97.0
Mystery 100.0
Thriller 81.0
Western 90.0

Highest rated movie from each group

[41]: temp = pd.DataFrame(columns=movies.columns)
for group, data in genres:
temp = temp.append(data[data['IMDB_Rating'] == data['IMDB_Rating'].max()])
temp

---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_20716\2112507160.py in ?()
1 temp = pd.DataFrame(columns=movies.columns)
2 for group, data in genres:
----> 3 temp = temp.append(data[data['IMDB_Rating'] == data['IMDB_Rating'].
↪max()])

4 temp

c:\Program Files\Python312\Lib\site-packages\pandas\core\generic.py in ?(self,␣

↪name)

6289 and name not in self._accessors

6290 and self._info_axis.
↪_can_hold_identifiers_and_holds_name(name)

6291 ):
6292 return self[name]
-> 6293 return object.__getattribute__(self, name)

201
 AttributeError: 'DataFrame' object has no attribute 'append'

1.13 Split Apply Combine

1.13.1 DF.groupby(‘col’).apply(func, include_groups=False)

[45]: genres.apply(np.minimum.reduce, include_groups=False)

[45]: Series_Title Released_Year Runtime \

Genre
Action 300 1924 45
Adventure 2001: A Space Odyssey 1925 88
Animation Akira 1940 71
Biography 12 Years a Slave 1928 93
Comedy (500) Days of Summer 1921 68
Crime 12 Angry Men 1931 80
Drama 1917 1925 64
Family E.T. the Extra-Terrestrial 1971 100
Fantasy Das Cabinet des Dr. Caligari 1920 76
Film-Noir Shadow of a Doubt 1941 100
Horror Alien 1933 71
Mystery Dark City 1938 96
Thriller Wait Until Dark 1967 108
Western Il buono, il brutto, il cattivo 1965 132

IMDB_Rating Director Star1 \

Genre
Action 7.6 Abhishek Chaubey Aamir Khan
Adventure 7.6 Akira Kurosawa Aamir Khan
Animation 7.6 Adam Elliot Adrian Molina
Biography 7.6 Adam McKay Adrien Brody
Comedy 7.6 Alejandro G. Iñárritu Aamir Khan
Crime 7.6 Akira Kurosawa Ajay Devgn
Drama 7.6 Aamir Khan Abhay Deol
Family 7.8 Mel Stuart Gene Wilder
Fantasy 7.9 F.W. Murnau Max Schreck
Film-Noir 7.8 Alfred Hitchcock Humphrey Bogart
Horror 7.6 Alejandro Amenábar Anthony Perkins
Mystery 7.6 Alex Proyas Bernard-Pierre Donnadieu
Thriller 7.8 Terence Young Audrey Hepburn
Western 7.8 Clint Eastwood Clint Eastwood

No_of_Votes Gross Metascore

Genre
Action 25312 3296.0 NaN
Adventure 29999 61001.0 NaN
Animation 25229 128985.0 NaN

202
 Biography 27254 21877.0 NaN
Comedy 26337 1305.0 NaN
Crime 27712 6013.0 NaN
Drama 25088 3600.0 NaN
Family 178731 4000000.0 67.0
Fantasy 57428 337574718.0 NaN
Film-Noir 59556 449191.0 94.0
Horror 27007 89029.0 46.0
Mystery 33982 1035953.0 NaN
Thriller 27733 17550741.0 81.0
Western 65659 5321508.0 69.0

[46]: def foo(group):

return group['Series_Title'].str.startswith('A').sum()

[48]: genres.apply(foo, include_groups=False)

[48]: Genre
Action 10
Adventure 2
Animation 2
Biography 9
Comedy 14
Crime 4
Drama 21
Family 0
Fantasy 0
Film-Noir 0
Horror 1
Mystery 0
Thriller 0
Western 0
dtype: int64

Find ranking of each movie in the group according to IMDB rating

[50]: def rank_movie(group):
group['genre_rank'] = group['IMDB_Rating'].rank(ascending=False)
return group

[51]: genres.apply(rank_movie, include_groups=False)

[51]: Series_Title Released_Year \

Genre
Action 2 The Dark Knight 2008
5 The Lord of the Rings: The Return of the King 2003
8 Inception 2010

203
 10 The Lord of the Rings: The Fellowship of the Ring 2001
13 The Lord of the Rings: The Two Towers 2002
… … …
Thriller 700 Wait Until Dark 1967
Western 12 Il buono, il brutto, il cattivo 1966
48 Once Upon a Time in the West 1968
115 Per qualche dollaro in più 1965
691 The Outlaw Josey Wales 1976

Runtime IMDB_Rating Director Star1 \

Genre
Action 2 152 9.0 Christopher Nolan Christian Bale
5 201 8.9 Peter Jackson Elijah Wood
8 148 8.8 Christopher Nolan Leonardo DiCaprio
10 178 8.8 Peter Jackson Elijah Wood
13 179 8.7 Peter Jackson Elijah Wood
… … … … …
Thriller 700 108 7.8 Terence Young Audrey Hepburn
Western 12 161 8.8 Sergio Leone Clint Eastwood
48 165 8.5 Sergio Leone Henry Fonda
115 132 8.3 Sergio Leone Clint Eastwood
691 135 7.8 Clint Eastwood Clint Eastwood

No_of_Votes Gross Metascore genre_rank

Genre
Action 2 2303232 534858444.0 84.0 1.0
5 1642758 377845905.0 94.0 2.0
8 2067042 292576195.0 74.0 3.5
10 1661481 315544750.0 92.0 3.5
13 1485555 342551365.0 87.0 6.0
… … … … …
Thriller 700 27733 17550741.0 81.0 1.0
Western 12 688390 6100000.0 90.0 1.0
48 302844 5321508.0 80.0 2.0
115 232772 15000000.0 74.0 3.0
691 65659 31800000.0 69.0 4.0

[1000 rows x 10 columns]

Find normalized IMDB rating group wise

[52]: def normalizer(group):
group['norm_rating'] = (group['IMDB_Rating'] - group['IMDB_Rating'].min())/
↪(group['IMDB_Rating'].max() - group['IMDB_Rating'].min())

return group

204
 1.14 Groupby on multiple columns
[55]: duo = movies.groupby(['Director', 'Star1'])
duo

[55]: <pandas.core.groupby.generic.DataFrameGroupBy object at 0x000001CB1EA0D0D0>

[57]: duo.size()

[57]: Director Star1

Aamir Khan Amole Gupte 1
Aaron Sorkin Eddie Redmayne 1
Abdellatif Kechiche Léa Seydoux 1
Abhishek Chaubey Shahid Kapoor 1
Abhishek Kapoor Amit Sadh 1
..
Zaza Urushadze Lembit Ulfsak 1
Zoya Akhtar Hrithik Roshan 1
Vijay Varma 1
Çagan Irmak Çetin Tekindor 1
Ömer Faruk Sorak Cem Yilmaz 1
Length: 898, dtype: int64

[58]: duo.get_group(('Aaron Sorkin', 'Eddie Redmayne'))

[58]: Series_Title Released_Year Runtime Genre IMDB_Rating \

612 The Trial of the Chicago 7 2020 129 Drama 7.8

Director Star1 No_of_Votes Gross Metascore

612 Aaron Sorkin Eddie Redmayne 89896 853090410.0 77.0

Find most earning actor - director combo

[59]: duo['Gross'].sum().sort_values(ascending=False).head(1)

[59]: Director Star1

Akira Kurosawa Toshirô Mifune 2.999877e+09
Name: Gross, dtype: float64

Find the bes actor-genre combo based on metascore

[62]: movies.groupby(['Star1', 'Genre'])['Metascore'].mean().reset_index().
↪sort_values('Metascore',ascending=False).head(1)

[62]: Star1 Genre Metascore

230 Ellar Coltrane Drama 100.0

205
 1.15 Exercises
[63]: ipl = pd.read_csv('deliveries1.csv')
ipl.head(2)

[63]: match_id inning batting_team bowling_team over \

0 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1
1 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1

ball batsman non_striker bowler is_super_over … bye_runs \

0 1 DA Warner S Dhawan TS Mills 0 … 0
1 2 DA Warner S Dhawan TS Mills 0 … 0

legbye_runs noball_runs penalty_runs batsman_runs extra_runs \

0 0 0 0 0 0
1 0 0 0 0 0

total_runs player_dismissed dismissal_kind fielder

0 0 NaN NaN NaN
1 0 NaN NaN NaN

[2 rows x 21 columns]

[64]: ipl.shape

[64]: (179078, 21)

1. Find the top 10 batsman in terms of runs

[65]: ipl.groupby('batsman')['batsman_runs'].sum().sort_values(ascending=False).
↪head(10)

[65]: batsman
V Kohli 5434
SK Raina 5415
RG Sharma 4914
DA Warner 4741
S Dhawan 4632
CH Gayle 4560
MS Dhoni 4477
RV Uthappa 4446
AB de Villiers 4428
G Gambhir 4223
Name: batsman_runs, dtype: int64

2. Find the batsman with max no of sixes

206
[71]: six = ipl[ipl['batsman_runs'] == 6]
six.groupby('batsman')['batsman_runs'].sum().sort_values(ascending=False).
↪head(1)

[71]: batsman
CH Gayle 1962
Name: batsman_runs, dtype: int64

3. Find batsman with most number of 4s and 6s in last 5 overs

[77]: last_overs = ipl[ipl['over'] > 15]
last_overs[(last_overs['batsman_runs'] == 4) | (last_overs['batsman_runs']==6)].
↪groupby('batsman')['batsman'].count().sort_values(ascending=False).head(1)

[77]: batsman
MS Dhoni 340
Name: batsman, dtype: int64

4. Virat Kohli’s runs against all the teams

[79]: temp_df = ipl[ipl['batsman'] == 'V Kohli']
temp_df.groupby('bowling_team')['batsman_runs'].sum().reset_index()

[79]: bowling_team batsman_runs

0 Chennai Super Kings 749
1 Deccan Chargers 306
2 Delhi Capitals 66
3 Delhi Daredevils 763
4 Gujarat Lions 283
5 Kings XI Punjab 636
6 Kochi Tuskers Kerala 50
7 Kolkata Knight Riders 675
8 Mumbai Indians 628
9 Pune Warriors 128
10 Rajasthan Royals 370
11 Rising Pune Supergiant 83
12 Rising Pune Supergiants 188
13 Sunrisers Hyderabad 509

5. Highest score of any batsman

[80]: def highest(batsman):
temp_df = ipl[ipl['batsman'] == batsman]
return temp_df.groupby('match_id')['batsman_runs'].sum().
↪sort_values(ascending=False).head(1).values[0]

[81]: highest('V Kohli')

207
[81]: 113

[1]: import numpy as np

import pandas as pd

[69]: courses = pd.read_csv('courses.csv')

students = pd.read_csv('students.csv')
nov = pd.read_csv('reg-month1.csv')
dec = pd.read_csv('reg-month2.csv')

[5]: nov

[5]: student_id course_id

0 23 1
1 15 5
2 18 6
3 23 4
4 16 9
5 18 1
6 1 1
7 7 8
8 22 3
9 15 1
10 19 4
11 1 6
12 7 10
13 11 7
14 13 3
15 24 4
16 21 1
17 16 5
18 23 3
19 17 7
20 23 6
21 25 1
22 19 2
23 25 10
24 3 3

[6]: dec

[6]: student_id course_id

0 3 5
1 16 7
2 12 10
3 12 1
4 14 9

208
 5 7 7
6 7 2
7 16 3
8 17 10
9 11 8
10 14 6
11 12 5
12 12 7
13 18 8
14 1 10
15 1 9
16 2 5
17 7 6
18 22 5
19 22 6
20 23 9
21 23 5
22 14 4
23 14 1
24 11 10
25 42 9
26 50 8
27 38 1

1.16 Concating DataFrames

[9]: regs = pd.concat([nov, dec], ignore_index=True)
regs

[9]: student_id course_id

0 23 1
1 15 5
2 18 6
3 23 4
4 16 9
5 18 1
6 1 1
7 7 8
8 22 3
9 15 1
10 19 4
11 1 6
12 7 10
13 11 7
14 13 3
15 24 4
16 21 1

209
 17 16 5
18 23 3
19 17 7
20 23 6
21 25 1
22 19 2
23 25 10
24 3 3
25 3 5
26 16 7
27 12 10
28 12 1
29 14 9
30 7 7
31 7 2
32 16 3
33 17 10
34 11 8
35 14 6
36 12 5
37 12 7
38 18 8
39 1 10
40 1 9
41 2 5
42 7 6
43 22 5
44 22 6
45 23 9
46 23 5
47 14 4
48 14 1
49 11 10
50 42 9
51 50 8
52 38 1

1.16.1 Multiindex DataFrame

[10]: pd.concat([nov, dec], keys=['Nov', 'Dec'])

[10]: student_id course_id

Nov 0 23 1
1 15 5
2 18 6
3 23 4
4 16 9

210
 5 18 1
6 1 1
7 7 8
8 22 3
9 15 1
10 19 4
11 1 6
12 7 10
13 11 7
14 13 3
15 24 4
16 21 1
17 16 5
18 23 3
19 17 7
20 23 6
21 25 1
22 19 2
23 25 10
24 3 3
Dec 0 3 5
1 16 7
2 12 10
3 12 1
4 14 9
5 7 7
6 7 2
7 16 3
8 17 10
9 11 8
10 14 6
11 12 5
12 12 7
13 18 8
14 1 10
15 1 9
16 2 5
17 7 6
18 22 5
19 22 6
20 23 9
21 23 5
22 14 4
23 14 1
24 11 10
25 42 9
26 50 8

211
 27 38 1

[11]: pd.concat([nov, dec], axis=1)

[11]: student_id course_id student_id course_id

0 23.0 1.0 3 5
1 15.0 5.0 16 7
2 18.0 6.0 12 10
3 23.0 4.0 12 1
4 16.0 9.0 14 9
5 18.0 1.0 7 7
6 1.0 1.0 7 2
7 7.0 8.0 16 3
8 22.0 3.0 17 10
9 15.0 1.0 11 8
10 19.0 4.0 14 6
11 1.0 6.0 12 5
12 7.0 10.0 12 7
13 11.0 7.0 18 8
14 13.0 3.0 1 10
15 24.0 4.0 1 9
16 21.0 1.0 2 5
17 16.0 5.0 7 6
18 23.0 3.0 22 5
19 17.0 7.0 22 6
20 23.0 6.0 23 9
21 25.0 1.0 23 5
22 19.0 2.0 14 4
23 25.0 10.0 14 1
24 3.0 3.0 11 10
25 NaN NaN 42 9
26 NaN NaN 50 8
27 NaN NaN 38 1

1.17 Join
1.17.1 Inner Join
[12]: students.merge(regs, how='inner', on='student_id')

[12]: student_id name partner course_id

0 1 Kailash Harjo 23 1
1 1 Kailash Harjo 23 6
2 1 Kailash Harjo 23 10
3 1 Kailash Harjo 23 9
4 2 Esha Butala 1 5
5 3 Parveen Bhalla 3 3

212
6 3 Parveen Bhalla 3 5
7 7 Tarun Thaker 9 8
8 7 Tarun Thaker 9 10
9 7 Tarun Thaker 9 7
10 7 Tarun Thaker 9 2
11 7 Tarun Thaker 9 6
12 11 David Mukhopadhyay 20 7
13 11 David Mukhopadhyay 20 8
14 11 David Mukhopadhyay 20 10
15 12 Radha Dutt 19 10
16 12 Radha Dutt 19 1
17 12 Radha Dutt 19 5
18 12 Radha Dutt 19 7
19 13 Munni Varghese 24 3
20 14 Pranab Natarajan 22 9
21 14 Pranab Natarajan 22 6
22 14 Pranab Natarajan 22 4
23 14 Pranab Natarajan 22 1
24 15 Preet Sha 16 5
25 15 Preet Sha 16 1
26 16 Elias Dodiya 25 9
27 16 Elias Dodiya 25 5
28 16 Elias Dodiya 25 7
29 16 Elias Dodiya 25 3
30 17 Yasmin Palan 7 7
31 17 Yasmin Palan 7 10
32 18 Fardeen Mahabir 13 6
33 18 Fardeen Mahabir 13 1
34 18 Fardeen Mahabir 13 8
35 19 Qabeel Raman 12 4
36 19 Qabeel Raman 12 2
37 21 Seema Kota 15 1
38 22 Yash Sethi 21 3
39 22 Yash Sethi 21 5
40 22 Yash Sethi 21 6
41 23 Chhavi Lachman 18 1
42 23 Chhavi Lachman 18 4
43 23 Chhavi Lachman 18 3
44 23 Chhavi Lachman 18 6
45 23 Chhavi Lachman 18 9
46 23 Chhavi Lachman 18 5
47 24 Radhika Suri 17 4
48 25 Shashank D’Alia 2 1
49 25 Shashank D’Alia 2 10

213
 1.17.2 Left Join
[13]: courses.merge(regs, how='left', on='course_id')

[13]: course_id course_name price student_id

0 1 python 2499 23.0
1 1 python 2499 18.0
2 1 python 2499 1.0
3 1 python 2499 15.0
4 1 python 2499 21.0
5 1 python 2499 25.0
6 1 python 2499 12.0
7 1 python 2499 14.0
8 1 python 2499 38.0
9 2 sql 3499 19.0
10 2 sql 3499 7.0
11 3 data analysis 4999 22.0
12 3 data analysis 4999 13.0
13 3 data analysis 4999 23.0
14 3 data analysis 4999 3.0
15 3 data analysis 4999 16.0
16 4 machine learning 9999 23.0
17 4 machine learning 9999 19.0
18 4 machine learning 9999 24.0
19 4 machine learning 9999 14.0
20 5 tableau 2499 15.0
21 5 tableau 2499 16.0
22 5 tableau 2499 3.0
23 5 tableau 2499 12.0
24 5 tableau 2499 2.0
25 5 tableau 2499 22.0
26 5 tableau 2499 23.0
27 6 power bi 1899 18.0
28 6 power bi 1899 1.0
29 6 power bi 1899 23.0
30 6 power bi 1899 14.0
31 6 power bi 1899 7.0
32 6 power bi 1899 22.0
33 7 ms sxcel 1599 11.0
34 7 ms sxcel 1599 17.0
35 7 ms sxcel 1599 16.0
36 7 ms sxcel 1599 7.0
37 7 ms sxcel 1599 12.0
38 8 pandas 1099 7.0
39 8 pandas 1099 11.0
40 8 pandas 1099 18.0
41 8 pandas 1099 50.0

214
 42 9 plotly 699 16.0
43 9 plotly 699 14.0
44 9 plotly 699 1.0
45 9 plotly 699 23.0
46 9 plotly 699 42.0
47 10 pyspark 2499 7.0
48 10 pyspark 2499 25.0
49 10 pyspark 2499 12.0
50 10 pyspark 2499 17.0
51 10 pyspark 2499 1.0
52 10 pyspark 2499 11.0
53 11 Numpy 699 NaN
54 12 C++ 1299 NaN

1.17.3 Right Join

[15]: temp = pd.DataFrame({

'student_id':[26, 27, 28],
'name':['Nitish', 'Ankit', 'Rahul'],
'partner':[28, 26, 27]
})

students = pd.concat([students, temp], ignore_index=True)

[18]: students.merge(regs, how='right', on='student_id')

[18]: student_id name partner course_id

0 23 Chhavi Lachman 18.0 1
1 15 Preet Sha 16.0 5
2 18 Fardeen Mahabir 13.0 6
3 23 Chhavi Lachman 18.0 4
4 16 Elias Dodiya 25.0 9
5 18 Fardeen Mahabir 13.0 1
6 1 Kailash Harjo 23.0 1
7 7 Tarun Thaker 9.0 8
8 22 Yash Sethi 21.0 3
9 15 Preet Sha 16.0 1
10 19 Qabeel Raman 12.0 4
11 1 Kailash Harjo 23.0 6
12 7 Tarun Thaker 9.0 10
13 11 David Mukhopadhyay 20.0 7
14 13 Munni Varghese 24.0 3
15 24 Radhika Suri 17.0 4
16 21 Seema Kota 15.0 1
17 16 Elias Dodiya 25.0 5
18 23 Chhavi Lachman 18.0 3
19 17 Yasmin Palan 7.0 7

215
 20 23 Chhavi Lachman 18.0 6
21 25 Shashank D’Alia 2.0 1
22 19 Qabeel Raman 12.0 2
23 25 Shashank D’Alia 2.0 10
24 3 Parveen Bhalla 3.0 3
25 3 Parveen Bhalla 3.0 5
26 16 Elias Dodiya 25.0 7
27 12 Radha Dutt 19.0 10
28 12 Radha Dutt 19.0 1
29 14 Pranab Natarajan 22.0 9
30 7 Tarun Thaker 9.0 7
31 7 Tarun Thaker 9.0 2
32 16 Elias Dodiya 25.0 3
33 17 Yasmin Palan 7.0 10
34 11 David Mukhopadhyay 20.0 8
35 14 Pranab Natarajan 22.0 6
36 12 Radha Dutt 19.0 5
37 12 Radha Dutt 19.0 7
38 18 Fardeen Mahabir 13.0 8
39 1 Kailash Harjo 23.0 10
40 1 Kailash Harjo 23.0 9
41 2 Esha Butala 1.0 5
42 7 Tarun Thaker 9.0 6
43 22 Yash Sethi 21.0 5
44 22 Yash Sethi 21.0 6
45 23 Chhavi Lachman 18.0 9
46 23 Chhavi Lachman 18.0 5
47 14 Pranab Natarajan 22.0 4
48 14 Pranab Natarajan 22.0 1
49 11 David Mukhopadhyay 20.0 10
50 42 NaN NaN 9
51 50 NaN NaN 8
52 38 NaN NaN 1

1.17.4 Outer Join

[20]: students.merge(regs, how='outer', on='student_id').tail(10)

[20]: student_id name partner course_id

53 23 Chhavi Lachman 18.0 5.0
54 24 Radhika Suri 17.0 4.0
55 25 Shashank D’Alia 2.0 1.0
56 25 Shashank D’Alia 2.0 10.0
57 26 Nitish 28.0 NaN
58 27 Ankit 26.0 NaN
59 28 Rahul 27.0 NaN
60 38 NaN NaN 1.0

216
 61 42 NaN NaN 9.0
62 50 NaN NaN 8.0

1. Find total revenue generated

[22]: regs.merge(courses, how='inner', on='course_id')['price'].sum()

[22]: 154247

2. Find month by month revenue

[30]: temp = pd.concat([nov, dec], keys=['Nov', 'Dec']).reset_index()
temp.merge(courses, how='inner', on='course_id').groupby('level_0')['price'].
↪sum()

[30]: level_0
Dec 65072
Nov 89175
Name: price, dtype: int64

3. Print the registration table with cols name, course, price

[32]: students.merge(regs, on='student_id').merge(courses, on='course_id')[['name',␣
↪'course_name', 'price']]

[32]: name course_name price

0 Kailash Harjo python 2499
1 Kailash Harjo power bi 1899
2 Kailash Harjo pyspark 2499
3 Kailash Harjo plotly 699
4 Esha Butala tableau 2499
5 Parveen Bhalla data analysis 4999
6 Parveen Bhalla tableau 2499
7 Tarun Thaker pandas 1099
8 Tarun Thaker pyspark 2499
9 Tarun Thaker ms sxcel 1599
10 Tarun Thaker sql 3499
11 Tarun Thaker power bi 1899
12 David Mukhopadhyay ms sxcel 1599
13 David Mukhopadhyay pandas 1099
14 David Mukhopadhyay pyspark 2499
15 Radha Dutt pyspark 2499
16 Radha Dutt python 2499
17 Radha Dutt tableau 2499
18 Radha Dutt ms sxcel 1599
19 Munni Varghese data analysis 4999
20 Pranab Natarajan plotly 699
21 Pranab Natarajan power bi 1899

217
 22 Pranab Natarajan machine learning 9999
23 Pranab Natarajan python 2499
24 Preet Sha tableau 2499
25 Preet Sha python 2499
26 Elias Dodiya plotly 699
27 Elias Dodiya tableau 2499
28 Elias Dodiya ms sxcel 1599
29 Elias Dodiya data analysis 4999
30 Yasmin Palan ms sxcel 1599
31 Yasmin Palan pyspark 2499
32 Fardeen Mahabir power bi 1899
33 Fardeen Mahabir python 2499
34 Fardeen Mahabir pandas 1099
35 Qabeel Raman machine learning 9999
36 Qabeel Raman sql 3499
37 Seema Kota python 2499
38 Yash Sethi data analysis 4999
39 Yash Sethi tableau 2499
40 Yash Sethi power bi 1899
41 Chhavi Lachman python 2499
42 Chhavi Lachman machine learning 9999
43 Chhavi Lachman data analysis 4999
44 Chhavi Lachman power bi 1899
45 Chhavi Lachman plotly 699
46 Chhavi Lachman tableau 2499
47 Radhika Suri machine learning 9999
48 Shashank D’Alia python 2499
49 Shashank D’Alia pyspark 2499

4. Plot bar chart for revenue/courses

[40]: regs.merge(courses, on='course_id').groupby('course_name')['price'].sum().

↪plot(kind='bar')

[40]: <Axes: xlabel='course_name'>

218
 5. Find students who enrolled in both the months
[43]: common_students = np.intersect1d(nov['student_id'], dec['student_id'])
students[students['student_id'].isin(common_students)]

[43]: student_id name partner

0 1 Kailash Harjo 23
2 3 Parveen Bhalla 3
6 7 Tarun Thaker 9
10 11 David Mukhopadhyay 20
15 16 Elias Dodiya 25
16 17 Yasmin Palan 7
17 18 Fardeen Mahabir 13
21 22 Yash Sethi 21
22 23 Chhavi Lachman 18

219
 6. Find course that got no enrollment
[46]: course_id = np.setdiff1d(courses['course_id'], regs['course_id'])
courses[courses['course_id'].isin(course_id)]

[46]: course_id course_name price

10 11 Numpy 699
11 12 C++ 1299

7. Find students who did not enrolled into any of the courses
[48]: student_id = np.setdiff1d(students['student_id'], regs['student_id'])
students[students['student_id'].isin(student_id)]

[48]: student_id name partner

3 4 Marlo Dugal 14
4 5 Kusum Bahri 6
5 6 Lakshmi Contractor 10
7 8 Radheshyam Dey 5
8 9 Nitika Chatterjee 4
9 10 Aayushman Sant 8
19 20 Hanuman Hegde 11
25 26 Nitish 28
26 27 Ankit 26
27 28 Rahul 27

8. Print student name and partner name for all enrolled students
[52]: students.merge(students, left_on='student_id', right_on='partner')[['name_x',␣
↪'name_y']]

[52]: name_x name_y

0 Kailash Harjo Esha Butala
1 Esha Butala Shashank D’Alia
2 Parveen Bhalla Parveen Bhalla
3 Marlo Dugal Nitika Chatterjee
4 Kusum Bahri Radheshyam Dey
5 Lakshmi Contractor Kusum Bahri
6 Tarun Thaker Yasmin Palan
7 Radheshyam Dey Aayushman Sant
8 Nitika Chatterjee Tarun Thaker
9 Aayushman Sant Lakshmi Contractor
10 David Mukhopadhyay Hanuman Hegde
11 Radha Dutt Qabeel Raman
12 Munni Varghese Fardeen Mahabir
13 Pranab Natarajan Marlo Dugal
14 Preet Sha Seema Kota
15 Elias Dodiya Preet Sha

220
 16 Yasmin Palan Radhika Suri
17 Fardeen Mahabir Chhavi Lachman
18 Qabeel Raman Radha Dutt
19 Hanuman Hegde David Mukhopadhyay
20 Seema Kota Yash Sethi
21 Yash Sethi Pranab Natarajan
22 Chhavi Lachman Kailash Harjo
23 Radhika Suri Munni Varghese
24 Shashank D’Alia Elias Dodiya
25 Nitish Ankit
26 Ankit Rahul
27 Rahul Nitish

9. Find top 3 students who did most number enrollments

[56]: top3students= regs.value_counts('student_id').head(3).reset_index()
top3students.merge(students, on='student_id')

[56]: student_id count name partner

0 23 6 Chhavi Lachman 18
1 7 5 Tarun Thaker 9
2 1 4 Kailash Harjo 23

[63]: regs.merge(students, on='student_id').groupby(['student_id', 'name'])['name'].

↪count().sort_values(ascending=False).head(3)

[63]: student_id name

23 Chhavi Lachman 6
7 Tarun Thaker 5
1 Kailash Harjo 4
Name: name, dtype: int64

10. Find top 3 students who spent most amount of money on courses
[68]: regs.merge(students, on='student_id').merge(courses, on='course_id').
↪groupby(['student_id', 'name'])['price'].sum().sort_values(ascending=False).

↪head(3)

[68]: student_id name

23 Chhavi Lachman 22594
14 Pranab Natarajan 15096
19 Qabeel Raman 13498
Name: price, dtype: int64

1.18 Practise
1. Find top 3 stadiums with highest sixes/match ratio

221
[71]: matches = pd.read_csv('matches.csv')
delivery = pd.read_csv('deliveries.csv')

[74]: matches.head(2)

[74]: id season city date team1 \

0 1 2017 Hyderabad 2017-04-05 Sunrisers Hyderabad
1 2 2017 Pune 2017-04-06 Mumbai Indians

team2 toss_winner toss_decision \

0 Royal Challengers Bangalore Royal Challengers Bangalore field
1 Rising Pune Supergiant Rising Pune Supergiant field

result dl_applied winner win_by_runs win_by_wickets \

0 normal 0 Sunrisers Hyderabad 35 0
1 normal 0 Rising Pune Supergiant 0 7

player_of_match venue umpire1 \

0 Yuvraj Singh Rajiv Gandhi International Stadium, Uppal AY Dandekar
1 SPD Smith Maharashtra Cricket Association Stadium A Nand Kishore

umpire2 umpire3
0 NJ Llong NaN
1 S Ravi NaN

[75]: delivery.head(2)

[75]: match_id inning batting_team bowling_team over \

0 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1
1 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1

ball batsman non_striker bowler is_super_over … bye_runs \

0 1 DA Warner S Dhawan TS Mills 0 … 0
1 2 DA Warner S Dhawan TS Mills 0 … 0

legbye_runs noball_runs penalty_runs batsman_runs extra_runs \

0 0 0 0 0 0
1 0 0 0 0 0

total_runs player_dismissed dismissal_kind fielder

0 0 NaN NaN NaN
1 0 NaN NaN NaN

[2 rows x 21 columns]

[81]: temp = delivery.merge(matches, left_on='match_id', right_on='id')

temp.head(2)

222
[81]: match_id inning batting_team bowling_team over \
0 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1
1 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 1

ball batsman non_striker bowler is_super_over … result \

0 1 DA Warner S Dhawan TS Mills 0 … normal
1 2 DA Warner S Dhawan TS Mills 0 … normal

dl_applied winner win_by_runs win_by_wickets \

0 0 Sunrisers Hyderabad 35 0
1 0 Sunrisers Hyderabad 35 0

player_of_match venue umpire1 \

0 Yuvraj Singh Rajiv Gandhi International Stadium, Uppal AY Dandekar
1 Yuvraj Singh Rajiv Gandhi International Stadium, Uppal AY Dandekar

umpire2 umpire3
0 NJ Llong NaN
1 NJ Llong NaN

[2 rows x 39 columns]

[84]: six = temp[temp['batsman_runs'] == 6]

six.head(2)

[84]: match_id inning batting_team bowling_team over \

10 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 2
47 1 1 Sunrisers Hyderabad Royal Challengers Bangalore 8

ball batsman non_striker bowler is_super_over … result \

10 4 DA Warner S Dhawan A Choudhary 0 … normal
47 4 MC Henriques S Dhawan TM Head 0 … normal

dl_applied winner win_by_runs win_by_wickets \

10 0 Sunrisers Hyderabad 35 0
47 0 Sunrisers Hyderabad 35 0

player_of_match venue umpire1 \

10 Yuvraj Singh Rajiv Gandhi International Stadium, Uppal AY Dandekar
47 Yuvraj Singh Rajiv Gandhi International Stadium, Uppal AY Dandekar

umpire2 umpire3
10 NJ Llong NaN
47 NJ Llong NaN

[2 rows x 39 columns]

223
[88]: num_sixes = six.groupby('venue')['venue'].count()

[89]: num_matches = matches['venue'].value_counts()

[90]: (num_sixes/num_matches).sort_values(ascending=False).head(3)

[90]: venue
Holkar Cricket Stadium 17.600000
M Chinnaswamy Stadium 13.227273
Sharjah Cricket Stadium 12.666667
dtype: float64

2. Find orange cap holder of all the seasons

[95]: temp.groupby(['season', 'batsman'])['batsman_runs'].sum().reset_index().
↪sort_values('batsman_runs', ascending=False).

↪drop_duplicates(subset=['season']).sort_values('season

␣
↪ ␣
↪ ')

[95]: season batsman batsman_runs

1383 2016 V Kohli 973
910 2013 MEK Hussey 733
684 2012 CH Gayle 733
1088 2014 RV Uthappa 660
1422 2017 DA Warner 641
446 2010 SR Tendulkar 618
115 2008 SE Marsh 616
502 2011 CH Gayle 608
229 2009 ML Hayden 572
1148 2015 DA Warner 562

2 Multiindex
[1]: import numpy as np
import pandas as pd

2.0.1 Series -> 1D DataFrame -> 2D

[3]: index_val = [('cse',2019), ('cse',2020), ('cse',2021), ('cse',2022),␣
↪('ece',2019), ('ece',2020), ('ece',2021), ('ece',2022)]

a = pd.Series([1,2,3,4,5,6,7,8], index=index_val)
a

224
[3]: (cse, 2019) 1
(cse, 2020) 2
(cse, 2021) 3
(cse, 2022) 4
(ece, 2019) 5
(ece, 2020) 6
(ece, 2021) 7
(ece, 2022) 8
dtype: int64

2.0.2 The Problem

[5]: a['cse']

---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
File c:\Program Files\Python312\Lib\site-packages\pandas\core\indexes\base.py:
↪3802, in Index.get_loc(self, key)

3801 try:
-> 3802 return self._engine.get_loc(casted_key)
3803 except KeyError as err:

File index.pyx:153, in pandas._libs.index.IndexEngine.get_loc()

File index.pyx:182, in pandas._libs.index.IndexEngine.get_loc()

File pandas\\_libs\\hashtable_class_helper.pxi:7081, in pandas._libs.hashtable.

↪PyObjectHashTable.get_item()

File pandas\\_libs\\hashtable_class_helper.pxi:7089, in pandas._libs.hashtable.

↪PyObjectHashTable.get_item()

KeyError: 'cse'

The above exception was the direct cause of the following exception:

KeyError Traceback (most recent call last)

Cell In[5], line 1
----> 1 a['cse']

File c:\Program Files\Python312\Lib\site-packages\pandas\core\series.py:1111, in␣

↪Series.__getitem__(self, key)

1108 return self._values[key]

1110 elif key_is_scalar:
-> 1111 return self._get_value(key)
1113 # Convert generator to list before going through hashable part
1114 # (We will iterate through the generator there to check for slices)

225
 1115 if is_iterator(key):

File c:\Program Files\Python312\Lib\site-packages\pandas\core\series.py:1227, in␣

↪Series._get_value(self, label, takeable)

1224 return self._values[label]

1226 # Similar to Index.get_value, but we do not fall back to positional
-> 1227 loc = self.index.get_loc(label)
1229 if is_integer(loc):
1230 return self._values[loc]

File c:\Program Files\Python312\Lib\site-packages\pandas\core\indexes\base.py:

↪3809, in Index.get_loc(self, key)

3804 if isinstance(casted_key, slice) or (

3805 isinstance(casted_key, abc.Iterable)
3806 and any(isinstance(x, slice) for x in casted_key)
3807 ):
3808 raise InvalidIndexError(key)
-> 3809 raise KeyError(key) from err
3810 except TypeError:
3811 # If we have a listlike key, _check_indexing_error will raise
3812 # InvalidIndexError. Otherwise we fall through and re-raise
3813 # the TypeError.
3814 self._check_indexing_error(key)

KeyError: 'cse'

2.0.3 The Solution - Multiindex

2.1 Creating Multiindex Series
1. pd.MultiIndex.from_tuples()
[6]: index_val = [('cse',2019), ('cse',2020), ('cse',2021), ('cse',2022),␣
↪('ece',2019), ('ece',2020), ('ece',2021), ('ece',2022)]

multiindex = pd.MultiIndex.from_tuples(index_val)
multiindex

[6]: MultiIndex([('cse', 2019),

('cse', 2020),
('cse', 2021),
('cse', 2022),
('ece', 2019),
('ece', 2020),
('ece', 2021),
('ece', 2022)],
)

2. pd.MultiIndex.from_product()

226
[7]: pd.MultiIndex.from_product([['cse', 'ece'], [2019, 2020, 2021, 2022]])

[7]: MultiIndex([('cse', 2019),

('cse', 2020),
('cse', 2021),
('cse', 2022),
('ece', 2019),
('ece', 2020),
('ece', 2021),
('ece', 2022)],
)

level inside MultiIndex object

[8]: multiindex.levels

[8]: FrozenList([['cse', 'ece'], [2019, 2020, 2021, 2022]])

[9]: multiindex.levels[0]

[9]: Index(['cse', 'ece'], dtype='object')

[10]: multiindex.levels[1]

[10]: Index([2019, 2020, 2021, 2022], dtype='int64')

2.1.1 Creating Series with MultiIndex object

[13]: s = pd.Series([1,2,3,4,5,6,7,8], index=multiindex)

s

[13]: cse 2019 1

2020 2
2021 3
2022 4
ece 2019 5
2020 6
2021 7
2022 8
dtype: int64

[14]: # Fetching items

s['cse']

[14]: 2019 1
2020 2
2021 3

227
 2022 4
dtype: int64

[15]: s['cse',2020]

[15]: 2

2.2 MultiIndex DataFrame

[16]: branch_df = pd.DataFrame(
[
[1,2],
[3,4],
[5,6],
[7,8],
[9,10],
[11,12],
[13,14],
[15,16]
],
index=multiindex,
columns=['avg_pkg', 'students']
)

branch_df

[16]: avg_pkg students

cse 2019 1 2
2020 3 4
2021 5 6
2022 7 8
ece 2019 9 10
2020 11 12
2021 13 14
2022 15 16

[17]: branch_df.loc['cse']

[17]: avg_pkg students

2019 1 2
2020 3 4
2021 5 6
2022 7 8

[23]: branch_df.loc['cse', 2019]

228
[23]: avg_pkg 1
students 2
Name: (cse, 2019), dtype: int64

[24]: branch_df['avg_pkg']

[24]: cse 2019 1

2020 3
2021 5
2022 7
ece 2019 9
2020 11
2021 13
2022 15
Name: avg_pkg, dtype: int64

Another perspective
[25]: branch_df2 = pd.DataFrame(
[
[1,2,0,0],
[3,4,0,0],
[5,6,0,0],
[7,8,0,0]
],
index= [2019, 2020, 2021, 2022],
columns= pd.MultiIndex.from_product([['delhi', 'mumbai'], ['avg_pkg',␣
↪'students']])

branch_df2

[25]: delhi mumbai

avg_pkg students avg_pkg students
2019 1 2 0 0
2020 3 4 0 0
2021 5 6 0 0
2022 7 8 0 0

[26]: branch_df2['delhi']['avg_pkg']

[26]: 2019 1
2020 3
2021 5
2022 7
Name: avg_pkg, dtype: int64

229
[29]: branch_df2.loc[2022]

[29]: delhi avg_pkg 7

students 8
mumbai avg_pkg 0
students 0
Name: 2022, dtype: int64

MultiIndex DF in terms of both cols and index

[30]: branch_df3 = pd.DataFrame(
[
[1,2,0,0],
[3,4,0,0],
[5,6,0,0],
[7,8,0,0],
[9,10,0,0],
[11,12,0,0],
[13,14,0,0],
[15,16,0,0]
],
index=multiindex,
columns= pd.MultiIndex.from_product([['delhi', 'mumbai'], ['avg_pkg',␣
↪'students']])

branch_df3

[30]: delhi mumbai

avg_pkg students avg_pkg students
cse 2019 1 2 0 0
2020 3 4 0 0
2021 5 6 0 0
2022 7 8 0 0
ece 2019 9 10 0 0
2020 11 12 0 0
2021 13 14 0 0
2022 15 16 0 0

2.3 Stacking and Unstacking

• Stacking - last level of col transform into last level of index.
• Unstacking - last level of index transform into last level of col.
[34]: branch_df3.stack(future_stack=True)

230
[34]: delhi mumbai
cse 2019 avg_pkg 1 0
students 2 0
2020 avg_pkg 3 0
students 4 0
2021 avg_pkg 5 0
students 6 0
2022 avg_pkg 7 0
students 8 0
ece 2019 avg_pkg 9 0
students 10 0
2020 avg_pkg 11 0
students 12 0
2021 avg_pkg 13 0
students 14 0
2022 avg_pkg 15 0
students 16 0

[35]: branch_df3.unstack()

[35]: delhi mumbai \

avg_pkg students avg_pkg
2019 2020 2021 2022 2019 2020 2021 2022 2019 2020 2021 2022
cse 1 3 5 7 2 4 6 8 0 0 0 0
ece 9 11 13 15 10 12 14 16 0 0 0 0

students
2019 2020 2021 2022
cse 0 0 0 0
ece 0 0 0 0

Note - MultiIndex DataFrame is also DataFrame so all the operations which can be performed on
Normal DataFrame can also be performed on the MultiIndex DataFrame

2.3.1 Extracting Single Row

[39]: branch_df3

[39]: delhi mumbai

avg_pkg students avg_pkg students
cse 2019 1 2 0 0
2020 3 4 0 0
2021 5 6 0 0
2022 7 8 0 0
ece 2019 9 10 0 0
2020 11 12 0 0

231
 2021 13 14 0 0
2022 15 16 0 0

[38]: branch_df3.loc[('cse',2020)]

[38]: delhi avg_pkg 3

students 4
mumbai avg_pkg 0
students 0
Name: (cse, 2020), dtype: int64

[51]: branch_df3.iloc[1]

[51]: delhi avg_pkg 3

students 4
mumbai avg_pkg 0
students 0
Name: (cse, 2020), dtype: int64

2.3.2 Extracting Multiple Rows

[43]: branch_df3.loc[('cse',2019):('ece',2020):2]

[43]: delhi mumbai

avg_pkg students avg_pkg students
cse 2019 1 2 0 0
2021 5 6 0 0
ece 2019 9 10 0 0

[52]: branch_df3.iloc[0:5:2]

[52]: delhi mumbai

avg_pkg students avg_pkg students
cse 2019 1 2 0 0
2021 5 6 0 0
ece 2019 9 10 0 0

2.3.3 Extracting Columns

[56]: branch_df3['delhi']['avg_pkg']

[56]: cse 2019 1

2020 3
2021 5
2022 7
ece 2019 9

232
 2020 11
2021 13
2022 15
Name: avg_pkg, dtype: int64

[57]: branch_df3.iloc[:, 0]

[57]: cse 2019 1

2020 3
2021 5
2022 7
ece 2019 9
2020 11
2021 13
2022 15
Name: (delhi, avg_pkg), dtype: int64

2.3.4 Extracting Rows and Cols

[58]: branch_df3.iloc[[0,4], [1,2]]

[58]: delhi mumbai

students avg_pkg
cse 2019 2 0
ece 2019 10 0

[59]: branch_df3.iloc[[2,6], [0,2]]

[59]: delhi mumbai

avg_pkg avg_pkg
cse 2021 5 0
ece 2021 13 0

2.3.5 Sort_index(ascending=True)

[60]: branch_df3.sort_index(ascending=False)

[60]: delhi mumbai

avg_pkg students avg_pkg students
ece 2022 15 16 0 0
2021 13 14 0 0
2020 11 12 0 0
2019 9 10 0 0
cse 2022 7 8 0 0
2021 5 6 0 0
2020 3 4 0 0

233
 2019 1 2 0 0

[61]: branch_df3.sort_index(ascending=[True, False])

[61]: delhi mumbai

avg_pkg students avg_pkg students
cse 2022 7 8 0 0
2021 5 6 0 0
2020 3 4 0 0
2019 1 2 0 0
ece 2022 15 16 0 0
2021 13 14 0 0
2020 11 12 0 0
2019 9 10 0 0

[62]: branch_df3.sort_index(level=0, ascending=False)

[62]: delhi mumbai

avg_pkg students avg_pkg students
ece 2022 15 16 0 0
2021 13 14 0 0
2020 11 12 0 0
2019 9 10 0 0
cse 2022 7 8 0 0
2021 5 6 0 0
2020 3 4 0 0
2019 1 2 0 0

DF.transpose()
[63]: branch_df3.transpose()

[63]: cse ece

2019 2020 2021 2022 2019 2020 2021 2022
delhi avg_pkg 1 3 5 7 9 11 13 15
students 2 4 6 8 10 12 14 16
mumbai avg_pkg 0 0 0 0 0 0 0 0
students 0 0 0 0 0 0 0 0

DF.swaplevel(axis=0)
[70]: branch_df3.swaplevel(axis=1)

[70]: avg_pkg students avg_pkg students

delhi delhi mumbai mumbai
cse 2019 1 2 0 0
2020 3 4 0 0
2021 5 6 0 0

234
 2022 7 8 0 0
ece 2019 9 10 0 0
2020 11 12 0 0
2021 13 14 0 0
2022 15 16 0 0

2.3.6 Long Vs Wide Data

Wide format is where we have a single row for every data point with multiple columns to hold
the values of various attributes.
Long format is where, for each data point we have as many rows as the number of attributes and
each row contains the value of a particular attribute for a given data point.

2.4 DF.melt()
DF.melt(id_vars=‘cols_to_keep_as_it_is’, var_name=‘name’,
value_name=‘name’)
• Wide to Long
[72]: pd.DataFrame({'cse':[120]}).melt()

[72]: variable value

0 cse 120

[75]: temp = pd.DataFrame({'cse':[120], 'ece':[100], 'mech':[50]})

temp

[75]: cse ece mech

0 120 100 50

[76]: temp.melt()

[76]: variable value

0 cse 120
1 ece 100
2 mech 50

[77]: temp.melt(var_name='branch', value_name='num_students')

[77]: branch num_students

0 cse 120
1 ece 100
2 mech 50

235
[80]: temp = pd.DataFrame(
{
'branch':['cse','ece','mech'],
'2020':[100,150,60],
'2021':[120,130,80],
'2022':[150,140,70]
}
)

temp

[80]: branch 2020 2021 2022

0 cse 100 120 150
1 ece 150 130 140
2 mech 60 80 70

[81]: temp.melt(id_vars=['branch'],var_name='year',value_name='students')

[81]: branch year students

0 cse 2020 100
1 ece 2020 150
2 mech 2020 60
3 cse 2021 120
4 ece 2021 130
5 mech 2021 80
6 cse 2022 150
7 ece 2022 140
8 mech 2022 70

[96]: death = pd.read_csv('time_series_covid19_deaths_global.csv')

confirm = pd.read_csv('time_series_covid19_confirmed_global.csv')

death.head(2)

[96]: Province/State Country/Region Lat Long 1/22/20 1/23/20 \

0 NaN Afghanistan 33.93911 67.709953 0 0
1 NaN Albania 41.15330 20.168300 0 0

1/24/20 1/25/20 1/26/20 1/27/20 … 12/24/22 12/25/22 12/26/22 \

0 0 0 0 0 … 7845 7846 7846
1 0 0 0 0 … 3595 3595 3595

12/27/22 12/28/22 12/29/22 12/30/22 12/31/22 1/1/23 1/2/23

0 7846 7846 7847 7847 7849 7849 7849
1 3595 3595 3595 3595 3595 3595 3595

[2 rows x 1081 columns]

236
[97]: death = death.melt(id_vars=['Province/State','Country/Region', 'Lat', 'Long'],␣
↪var_name='date', value_name='num_deaths')

print(death.shape)
death.head(2)

(311253, 6)

[97]: Province/State Country/Region Lat Long date num_deaths

0 NaN Afghanistan 33.93911 67.709953 1/22/20 0
1 NaN Albania 41.15330 20.168300 1/22/20 0

[98]: confirm = confirm.melt(id_vars=['Province/State','Country/Region', 'Lat',␣

↪'Long'], var_name='date', value_name='num_confirmed')

print(confirm.shape)
confirm.head(2)

(311253, 6)

[98]: Province/State Country/Region Lat Long date num_confirmed

0 NaN Afghanistan 33.93911 67.709953 1/22/20 0
1 NaN Albania 41.15330 20.168300 1/22/20 0

[100]: confirm.merge(death, on=['Province/State','Country/Region', 'Lat', 'Long',␣

↪'date'])[['Country/Region', 'date', 'num_confirmed', 'num_deaths']]

[100]: Country/Region date num_confirmed num_deaths

0 Afghanistan 1/22/20 0 0
1 Albania 1/22/20 0 0
2 Algeria 1/22/20 0 0
3 Andorra 1/22/20 0 0
4 Angola 1/22/20 0 0
… … … … …
311248 West Bank and Gaza 1/2/23 703228 5708
311249 Winter Olympics 2022 1/2/23 535 0
311250 Yemen 1/2/23 11945 2159
311251 Zambia 1/2/23 334661 4024
311252 Zimbabwe 1/2/23 259981 5637

[311253 rows x 4 columns]

2.5 Pivot Table

The pivot table takes simple column-wise data as input, and groups the entries into a two-
dimensional table that provides a multidimensional summarization of the data.
[2]: import numpy as np
import pandas as pd
import seaborn as sns

237
[3]: df = sns.load_dataset('tips')
df

[3]: total_bill tip sex smoker day time size

0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
4 24.59 3.61 Female No Sun Dinner 4
.. … … … … … … …
239 29.03 5.92 Male No Sat Dinner 3
240 27.18 2.00 Female Yes Sat Dinner 2
241 22.67 2.00 Male Yes Sat Dinner 2
242 17.82 1.75 Male No Sat Dinner 2
243 18.78 3.00 Female No Thur Dinner 2

[244 rows x 7 columns]

[4]: df.groupby(['sex', 'smoker'], observed=False)[['total_bill']].mean().unstack()

[4]: total_bill
smoker Yes No
sex
Male 22.284500 19.791237
Female 17.977879 18.105185

[5]: df.pivot_table(index='sex', columns='smoker', values='total_bill',␣

↪observed=False)

[5]: smoker Yes No

sex
Male 22.284500 19.791237
Female 17.977879 18.105185

Multidimensional Pivot Tables

[8]: df.pivot_table(index=['sex', 'smoker'], columns=['day', 'time'],␣
↪aggfunc={'size':'mean', 'tip':'max', 'total_bill':'sum'}, observed=False)

[8]: size tip \

day Thur Fri Sat Sun Thur
time Lunch Dinner Lunch Dinner Dinner Dinner Lunch
sex smoker
Male Yes 2.300000 NaN 1.666667 2.4 2.629630 2.600000 5.00
No 2.500000 NaN NaN 2.0 2.656250 2.883721 6.70
Female Yes 2.428571 NaN 2.000000 2.0 2.200000 2.500000 5.00
No 2.500000 2.0 3.000000 2.0 2.307692 3.071429 5.17

238
 total_bill \
day Fri Sat Sun Thur Fri
time Dinner Lunch Dinner Dinner Dinner Lunch Dinner Lunch
sex smoker
Male Yes NaN 2.20 4.73 10.00 6.5 191.71 0.00 34.16
No NaN NaN 3.50 9.00 6.0 369.73 0.00 0.00
Female Yes NaN 3.48 4.30 6.50 4.0 134.53 0.00 39.78
No 3.0 3.00 3.25 4.67 5.2 381.58 18.78 15.98

day Sat Sun

time Dinner Lunch Dinner Lunch Dinner
sex smoker
Male Yes 129.46 0.0 589.62 0.0 392.12
No 34.95 0.0 637.73 0.0 877.34
Female Yes 48.80 0.0 304.00 0.0 66.16
No 22.75 0.0 247.05 0.0 291.54

Margins
• Additional Rows and Cols containing sum of rows and cols
[10]: df.pivot_table(index='sex', columns='smoker', values='total_bill',␣
↪aggfunc='sum', observed=False, margins=True)

[10]: smoker Yes No All

sex
Male 1337.07 1919.75 3256.82
Female 593.27 977.68 1570.95
All 1930.34 2897.43 4827.77

Plotting Graphs
[23]: df = pd.read_csv('expense_data.csv')
df

[23]: Date Account Category Subcategory \

0 3/2/2022 10:11 CUB - online payment Food NaN
1 3/2/2022 10:11 CUB - online payment Other NaN
2 3/1/2022 19:50 CUB - online payment Food NaN
3 3/1/2022 18:56 CUB - online payment Transportation NaN
4 3/1/2022 18:22 CUB - online payment Food NaN
.. … … … …
272 11/22/2021 14:16 CUB - online payment Food NaN
273 11/22/2021 14:16 CUB - online payment Food NaN
274 11/21/2021 17:07 CUB - online payment Transportation NaN
275 11/21/2021 15:50 CUB - online payment Food NaN
276 11/21/2021 13:30 CUB - online payment Other NaN

239
 Note INR Income/Expense Note.1 Amount Currency \
0 Brownie 50.0 Expense NaN 50.0 INR
1 To lended people 300.0 Expense NaN 300.0 INR
2 Dinner 78.0 Expense NaN 78.0 INR
3 Metro 30.0 Expense NaN 30.0 INR
4 Snacks 67.0 Expense NaN 67.0 INR
.. … … … … … …
272 Dinner 90.0 Expense NaN 90.0 INR
273 Lunch with company 97.0 Expense NaN 97.0 INR
274 Rapido 130.0 Expense NaN 130.0 INR
275 Lunch 875.0 Expense NaN 875.0 INR
276 Got from gobi 2000.0 Income NaN 2000.0 INR

Account.1
0 50.0
1 300.0
2 78.0
3 30.0
4 67.0
.. …
272 90.0
273 97.0
274 130.0
275 875.0
276 2000.0

[277 rows x 11 columns]

[24]: df['Category'].value_counts()

[24]: Category
Food 156
Other 60
Transportation 31
Apparel 7
Household 6
Allowance 6
Social Life 5
Education 1
Salary 1
Self-development 1
Beauty 1
Gift 1
Petty cash 1
Name: count, dtype: int64

240
[25]: df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 277 entries, 0 to 276
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Date 277 non-null object
1 Account 277 non-null object
2 Category 277 non-null object
3 Subcategory 0 non-null float64
4 Note 273 non-null object
5 INR 277 non-null float64
6 Income/Expense 277 non-null object
7 Note.1 0 non-null float64
8 Amount 277 non-null float64
9 Currency 277 non-null object
10 Account.1 277 non-null float64
dtypes: float64(5), object(6)
memory usage: 23.9+ KB

[26]: df['Date'] = pd.to_datetime(df['Date'])

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 277 entries, 0 to 276
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Date 277 non-null datetime64[ns]
1 Account 277 non-null object
2 Category 277 non-null object
3 Subcategory 0 non-null float64
4 Note 273 non-null object
5 INR 277 non-null float64
6 Income/Expense 277 non-null object
7 Note.1 0 non-null float64
8 Amount 277 non-null float64
9 Currency 277 non-null object
10 Account.1 277 non-null float64
dtypes: datetime64[ns](1), float64(5), object(5)
memory usage: 23.9+ KB

[27]: df['month'] = df['Date'].dt.month_name()

[28]: df.head(2)

241
[28]: Date Account Category Subcategory \
0 2022-03-02 10:11:00 CUB - online payment Food NaN
1 2022-03-02 10:11:00 CUB - online payment Other NaN

Note INR Income/Expense Note.1 Amount Currency Account.1 \

0 Brownie 50.0 Expense NaN 50.0 INR 50.0
1 To lended people 300.0 Expense NaN 300.0 INR 300.0

month
0 March
1 March

[29]: df.pivot_table(index='month', columns='Category', values='INR', aggfunc='sum',␣

↪fill_value=0).plot()

[29]: <Axes: xlabel='month'>

[30]: df.pivot_table(index='month', columns='Income/Expense', values='INR',␣

↪aggfunc='sum', fill_value=0).plot()

[30]: <Axes: xlabel='month'>

242
[32]: df.pivot_table(index='month', columns='Account', values='INR', aggfunc='sum',␣
↪fill_value=0).plot()

[32]: <Axes: xlabel='month'>

243
[1]: import numpy as np
import pandas as pd

2.5.1 Vectorized Operations

[3]: a = np.array([1,2,3,4])
a * 4

[3]: array([ 4, 8, 12, 16])

The problem with vectorized operations.

[4]: s = ['cat', 'mat', None, 'rat']
[i.startswith('c') for i in s]

---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[4], line 2
1 s = ['cat', 'mat', None, 'rat']
----> 2 [i.startswith('c') for i in s]

244
 AttributeError: 'NoneType' object has no attribute 'startswith'

How Pandas solves this issue?

• .str is string accessor.
• it is fast and optimized in compare to traditional python code
[5]: s = pd.Series(['cat', 'mat', None, 'rat'])

s.str.startswith('c')

[5]: 0 True
1 False
2 None
3 False
dtype: object

[6]: df = pd.read_csv('titanic.csv')
df.head(2)

[6]: PassengerId Survived Pclass \

0 1 0 3
1 2 1 1

Name Sex Age SibSp \

0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th… female 38.0 1

Parch Ticket Fare Cabin Embarked

0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C

[7]: df['Name']

[7]: 0 Braund, Mr. Owen Harris

1 Cumings, Mrs. John Bradley (Florence Briggs Th…
2 Heikkinen, Miss. Laina
3 Futrelle, Mrs. Jacques Heath (Lily May Peel)
4 Allen, Mr. William Henry
…
886 Montvila, Rev. Juozas
887 Graham, Miss. Margaret Edith
888 Johnston, Miss. Catherine Helen "Carrie"
889 Behr, Mr. Karl Howell
890 Dooley, Mr. Patrick
Name: Name, Length: 891, dtype: object

245
 2.6 Common Functions
2.6.1 DF[‘col’].str.upper()
• Change to uppercase
[8]: df['Name'].str.upper()

[8]: 0 BRAUND, MR. OWEN HARRIS

1 CUMINGS, MRS. JOHN BRADLEY (FLORENCE BRIGGS TH…
2 HEIKKINEN, MISS. LAINA
3 FUTRELLE, MRS. JACQUES HEATH (LILY MAY PEEL)
4 ALLEN, MR. WILLIAM HENRY
…
886 MONTVILA, REV. JUOZAS
887 GRAHAM, MISS. MARGARET EDITH
888 JOHNSTON, MISS. CATHERINE HELEN "CARRIE"
889 BEHR, MR. KARL HOWELL
890 DOOLEY, MR. PATRICK
Name: Name, Length: 891, dtype: object

2.6.2 DF[‘col’].str.lower()
• change to lowercase
[9]: df['Name'].str.lower()

[9]: 0 braund, mr. owen harris

1 cumings, mrs. john bradley (florence briggs th…
2 heikkinen, miss. laina
3 futrelle, mrs. jacques heath (lily may peel)
4 allen, mr. william henry
…
886 montvila, rev. juozas
887 graham, miss. margaret edith
888 johnston, miss. catherine helen "carrie"
889 behr, mr. karl howell
890 dooley, mr. patrick
Name: Name, Length: 891, dtype: object

2.6.3 DF[‘col’].str.capitalize()
• change first letter of the first word into uppercase
[10]: df['Name'].str.capitalize()

[10]: 0 Braund, mr. owen harris

1 Cumings, mrs. john bradley (florence briggs th…
2 Heikkinen, miss. laina

246
 3 Futrelle, mrs. jacques heath (lily may peel)
4 Allen, mr. william henry
…
886 Montvila, rev. juozas
887 Graham, miss. margaret edith
888 Johnston, miss. catherine helen "carrie"
889 Behr, mr. karl howell
890 Dooley, mr. patrick
Name: Name, Length: 891, dtype: object

2.6.4 DF[‘col’].str.title()
• Change first letter of every word into uppercase
[11]: df['Name'].str.title()

[11]: 0 Braund, Mr. Owen Harris

1 Cumings, Mrs. John Bradley (Florence Briggs Th…
2 Heikkinen, Miss. Laina
3 Futrelle, Mrs. Jacques Heath (Lily May Peel)
4 Allen, Mr. William Henry
…
886 Montvila, Rev. Juozas
887 Graham, Miss. Margaret Edith
888 Johnston, Miss. Catherine Helen "Carrie"
889 Behr, Mr. Karl Howell
890 Dooley, Mr. Patrick
Name: Name, Length: 891, dtype: object

2.6.5 DF[‘col’].str.len()
• Returns length of the string
[12]: df['Name'].str.len()

[12]: 0 23
1 51
2 22
3 44
4 24
..
886 21
887 28
888 40
889 21
890 19
Name: Name, Length: 891, dtype: int64

247
 2.6.6 str.strip(‘char’)
• Remove unwanted trailing characters
[20]: "---,,--,-Khush- ---,,,--".strip('-, ')

[20]: 'Khush'

[21]: df['Name'].str.strip()

[21]: 0 Braund, Mr. Owen Harris

1 Cumings, Mrs. John Bradley (Florence Briggs Th…
2 Heikkinen, Miss. Laina
3 Futrelle, Mrs. Jacques Heath (Lily May Peel)
4 Allen, Mr. William Henry
…
886 Montvila, Rev. Juozas
887 Graham, Miss. Margaret Edith
888 Johnston, Miss. Catherine Helen "Carrie"
889 Behr, Mr. Karl Howell
890 Dooley, Mr. Patrick
Name: Name, Length: 891, dtype: object

2.6.7 DF[‘col’].str.split(‘char’)
• Splits the string based on the char
[27]: df['lastname'] = df['Name'].str.split(',').str.get(0)
df.head()

[27]: PassengerId Survived Pclass \

0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3

Name Sex Age SibSp \

0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th… female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0

Parch Ticket Fare Cabin Embarked lastname

0 0 A/5 21171 7.2500 NaN S Braund
1 0 PC 17599 71.2833 C85 C Cumings
2 0 STON/O2. 3101282 7.9250 NaN S Heikkinen

248
 3 0 113803 53.1000 C123 S Futrelle
4 0 373450 8.0500 NaN S Allen

[34]: df[['title', 'firstname']] = df['Name'].str.split(',').str.get(1).str.strip().

↪str.split(' ', n=1, expand=True)

df['title'].value_counts()

[34]: title
Mr. 517
Miss. 182
Mrs. 125
Master. 40
Dr. 7
Rev. 6
Mlle. 2
Major. 2
Col. 2
the 1
Capt. 1
Ms. 1
Sir. 1
Lady. 1
Mme. 1
Don. 1
Jonkheer. 1
Name: count, dtype: int64

2.6.8 DF[‘col’].str.replace(‘existing_str’, ‘new_str’)

• Replace the string
[36]: df['title'] = df['title'].str.replace('Ms.', 'Miss.')
df['title'] = df['title'].str.replace('Mlle.', 'Miss.')

[37]: df['title'].value_counts()

[37]: title
Mr. 517
Miss. 185
Mrs. 125
Master. 40
Dr. 7
Rev. 6
Major. 2
Col. 2
Don. 1
Mme. 1

249
 Lady. 1
Sir. 1
Capt. 1
the 1
Jonkheer. 1
Name: count, dtype: int64

2.7 Filtering
2.7.1 DF[‘col’].str.startswith(‘char’)
• Check each string whether it starts with specific char or not
[39]: df[df['firstname'].str.startswith('A')]

[39]: PassengerId Survived Pclass Name \

13 14 0 3 Andersson, Mr. Anders Johan
22 23 1 3 McGowan, Miss. Anna "Annie"
35 36 0 1 Holverson, Mr. Alexander Oskar
38 39 0 3 Vander Planke, Miss. Augusta Maria
61 62 1 1 Icard, Miss. Amelie
.. … … … …
842 843 1 1 Serepeca, Miss. Augusta
845 846 0 3 Abbing, Mr. Anthony
866 867 1 2 Duran y More, Miss. Asuncion
875 876 1 3 Najib, Miss. Adele Kiamie "Jane"
876 877 0 3 Gustafsson, Mr. Alfred Ossian

Sex Age SibSp Parch Ticket Fare Cabin Embarked \

13 male 39.0 1 5 347082 31.2750 NaN S
22 female 15.0 0 0 330923 8.0292 NaN Q
35 male 42.0 1 0 113789 52.0000 NaN S
38 female 18.0 2 0 345764 18.0000 NaN S
61 female 38.0 0 0 113572 80.0000 B28 NaN
.. … … … … … … … …
842 female 30.0 0 0 113798 31.0000 NaN C
845 male 42.0 0 0 C.A. 5547 7.5500 NaN S
866 female 27.0 1 0 SC/PARIS 2149 13.8583 NaN C
875 female 15.0 0 0 2667 7.2250 NaN C
876 male 20.0 0 0 7534 9.8458 NaN S

lastname title firstname

13 Andersson Mr. Anders Johan
22 McGowan Miss. Anna "Annie"
35 Holverson Mr. Alexander Oskar
38 Vander Planke Miss. Augusta Maria
61 Icard Miss. Amelie
.. … … …

250
 842 Serepeca Miss. Augusta
845 Abbing Mr. Anthony
866 Duran y More Miss. Asuncion
875 Najib Miss. Adele Kiamie "Jane"
876 Gustafsson Mr. Alfred Ossian

[95 rows x 15 columns]

2.7.2 DF[‘col’].str.endswith(‘char’)

[41]: df[df['firstname'].str.endswith('D')]

[41]: PassengerId Survived Pclass Name Sex Age \

168 169 0 1 Baumann, Mr. John D male NaN
629 630 0 3 O'Connell, Mr. Patrick D male NaN

SibSp Parch Ticket Fare Cabin Embarked lastname title \

168 0 0 PC 17318 25.9250 NaN S Baumann Mr.
629 0 0 334912 7.7333 NaN Q O'Connell Mr.

firstname
168 John D
629 Patrick D

2.7.3 DF[‘col’].str.isdigit()
• True if str is consisting of only digits
[43]: df[df['firstname'].str.isdigit()]

[43]: Empty DataFrame

Columns: [PassengerId, Survived, Pclass, Name, Sex, Age, SibSp, Parch, Ticket,
Fare, Cabin, Embarked, lastname, title, firstname]
Index: []

2.7.4 Slicing

[51]: df['Name'].str[::-1]

[51]: 0 sirraH newO .rM ,dnuarB

1 )reyahT sggirB ecnerolF( yeldarB nhoJ .srM ,sg…
2 aniaL .ssiM ,nenikkieH
3 )leeP yaM yliL( htaeH seuqcaJ .srM ,ellertuF
4 yrneH mailliW .rM ,nellA
…
886 sazouJ .veR ,alivtnoM
887 htidE teragraM .ssiM ,maharG

251
 888 "eirraC" neleH enirehtaC .ssiM ,notsnhoJ
889 llewoH lraK .rM ,rheB
890 kcirtaP .rM ,yelooD
Name: Name, Length: 891, dtype: object

2.8 Applying Regular Expressions

Any firstname contains John in both cases
[47]: df[df['firstname'].str.contains('john', case=False)]

[47]: PassengerId Survived Pclass \

1 2 1 1
41 42 0 2
45 46 0 3
98 99 1 2
112 113 0 3
117 118 0 2
160 161 0 3
162 163 0 3
165 166 1 3
168 169 0 1
188 189 0 3
212 213 0 3
226 227 1 2
227 228 0 3
324 325 0 3
328 329 1 3
401 402 0 3
418 419 0 2
467 468 0 1
527 528 0 1
548 549 0 3
549 550 1 2
550 551 1 1
563 564 0 3
572 573 1 1
574 575 0 3
581 582 1 1
583 584 0 1
586 587 0 2
594 595 0 2
613 614 0 3
624 625 0 3
657 658 0 3
694 695 0 1
698 699 0 1

252
700 701 1 1
733 734 0 2
760 761 0 3
765 766 1 1
818 819 0 3
822 823 0 1
825 826 0 3
848 849 0 2
864 865 0 2

Name Sex Age SibSp \

1 Cumings, Mrs. John Bradley (Florence Briggs Th… female 38.0 1
41 Turpin, Mrs. William John Robert (Dorothy Ann … female 27.0 1
45 Rogers, Mr. William John male NaN 0
98 Doling, Mrs. John T (Ada Julia Bone) female 34.0 0
112 Barton, Mr. David John male 22.0 0
117 Turpin, Mr. William John Robert male 29.0 1
160 Cribb, Mr. John Hatfield male 44.0 0
162 Bengtsson, Mr. John Viktor male 26.0 0
165 Goldsmith, Master. Frank John William "Frankie" male 9.0 0
168 Baumann, Mr. John D male NaN 0
188 Bourke, Mr. John male 40.0 1
212 Perkin, Mr. John Henry male 22.0 0
226 Mellors, Mr. William John male 19.0 0
227 Lovell, Mr. John Hall ("Henry") male 20.5 0
324 Sage, Mr. George John Jr male NaN 8
328 Goldsmith, Mrs. Frank John (Emily Alice Brown) female 31.0 1
401 Adams, Mr. John male 26.0 0
418 Matthews, Mr. William John male 30.0 0
467 Smart, Mr. John Montgomery male 56.0 0
527 Farthing, Mr. John male NaN 0
548 Goldsmith, Mr. Frank John male 33.0 1
549 Davies, Master. John Morgan Jr male 8.0 1
550 Thayer, Mr. John Borland Jr male 17.0 0
563 Simmons, Mr. John male NaN 0
572 Flynn, Mr. John Irwin ("Irving") male 36.0 0
574 Rush, Mr. Alfred George John male 16.0 0
581 Thayer, Mrs. John Borland (Marian Longstreth M… female 39.0 1
583 Ross, Mr. John Hugo male 36.0 0
586 Jarvis, Mr. John Denzil male 47.0 0
594 Chapman, Mr. John Henry male 37.0 1
613 Horgan, Mr. John male NaN 0
624 Bowen, Mr. David John "Dai" male 21.0 0
657 Bourke, Mrs. John (Catherine) female 32.0 1
694 Weir, Col. John male 60.0 0
698 Thayer, Mr. John Borland male 49.0 1
700 Astor, Mrs. John Jacob (Madeleine Talmadge Force) female 18.0 1

253
733 Berriman, Mr. William John male 23.0 0
760 Garfirth, Mr. John male NaN 0
765 Hogeboom, Mrs. John C (Anna Andrews) female 51.0 1
818 Holm, Mr. John Fredrik Alexander male 43.0 0
822 Reuchlin, Jonkheer. John George male 38.0 0
825 Flynn, Mr. John male NaN 0
848 Harper, Rev. John male 28.0 0
864 Gill, Mr. John William male 24.0 0

Parch Ticket Fare Cabin Embarked lastname title \

1 0 PC 17599 71.2833 C85 C Cumings Mrs.
41 0 11668 21.0000 NaN S Turpin Mrs.
45 0 S.C./A.4. 23567 8.0500 NaN S Rogers Mr.
98 1 231919 23.0000 NaN S Doling Mrs.
112 0 324669 8.0500 NaN S Barton Mr.
117 0 11668 21.0000 NaN S Turpin Mr.
160 1 371362 16.1000 NaN S Cribb Mr.
162 0 347068 7.7750 NaN S Bengtsson Mr.
165 2 363291 20.5250 NaN S Goldsmith Master.
168 0 PC 17318 25.9250 NaN S Baumann Mr.
188 1 364849 15.5000 NaN Q Bourke Mr.
212 0 A/5 21174 7.2500 NaN S Perkin Mr.
226 0 SW/PP 751 10.5000 NaN S Mellors Mr.
227 0 A/5 21173 7.2500 NaN S Lovell Mr.
324 2 CA. 2343 69.5500 NaN S Sage Mr.
328 1 363291 20.5250 NaN S Goldsmith Mrs.
401 0 341826 8.0500 NaN S Adams Mr.
418 0 28228 13.0000 NaN S Matthews Mr.
467 0 113792 26.5500 NaN S Smart Mr.
527 0 PC 17483 221.7792 C95 S Farthing Mr.
548 1 363291 20.5250 NaN S Goldsmith Mr.
549 1 C.A. 33112 36.7500 NaN S Davies Master.
550 2 17421 110.8833 C70 C Thayer Mr.
563 0 SOTON/OQ 392082 8.0500 NaN S Simmons Mr.
572 0 PC 17474 26.3875 E25 S Flynn Mr.
574 0 A/4. 20589 8.0500 NaN S Rush Mr.
581 1 17421 110.8833 C68 C Thayer Mrs.
583 0 13049 40.1250 A10 C Ross Mr.
586 0 237565 15.0000 NaN S Jarvis Mr.
594 0 SC/AH 29037 26.0000 NaN S Chapman Mr.
613 0 370377 7.7500 NaN Q Horgan Mr.
624 0 54636 16.1000 NaN S Bowen Mr.
657 1 364849 15.5000 NaN Q Bourke Mrs.
694 0 113800 26.5500 NaN S Weir Col.
698 1 17421 110.8833 C68 C Thayer Mr.
700 0 PC 17757 227.5250 C62 C64 C Astor Mrs.
733 0 28425 13.0000 NaN S Berriman Mr.

254
760 0 358585 14.5000 NaN S Garfirth Mr.
765 0 13502 77.9583 D11 S Hogeboom Mrs.
818 0 C 7075 6.4500 NaN S Holm Mr.
822 0 19972 0.0000 NaN S Reuchlin Jonkheer.
825 0 368323 6.9500 NaN Q Flynn Mr.
848 1 248727 33.0000 NaN S Harper Rev.
864 0 233866 13.0000 NaN S Gill Mr.

firstname
1 John Bradley (Florence Briggs Thayer)
41 William John Robert (Dorothy Ann Wonnacott)
45 William John
98 John T (Ada Julia Bone)
112 David John
117 William John Robert
160 John Hatfield
162 John Viktor
165 Frank John William "Frankie"
168 John D
188 John
212 John Henry
226 William John
227 John Hall ("Henry")
324 George John Jr
328 Frank John (Emily Alice Brown)
401 John
418 William John
467 John Montgomery
527 John
548 Frank John
549 John Morgan Jr
550 John Borland Jr
563 John
572 John Irwin ("Irving")
574 Alfred George John
581 John Borland (Marian Longstreth Morris)
583 John Hugo
586 John Denzil
594 John Henry
613 John
624 David John "Dai"
657 John (Catherine)
694 John
698 John Borland
700 John Jacob (Madeleine Talmadge Force)
733 William John
760 John

255
 765 John C (Anna Andrews)
818 John Fredrik Alexander
822 John George
825 John
848 John
864 John William

Find lastnames with start and end char is vowel

[50]: df[df['lastname'].str.contains('^[aeiouAEIOU].+[aeiouAEIOU]$')]

[50]: PassengerId Survived Pclass \

30 31 0 1
49 50 0 3
207 208 1 3
210 211 0 3
353 354 0 3
493 494 0 1
518 519 1 2
784 785 0 3
840 841 0 3

Name Sex Age SibSp \

30 Uruchurtu, Don. Manuel E male 40.0 0
49 Arnold-Franchi, Mrs. Josef (Josefine Franchi) female 18.0 1
207 Albimona, Mr. Nassef Cassem male 26.0 0
210 Ali, Mr. Ahmed male 24.0 0
353 Arnold-Franchi, Mr. Josef male 25.0 1
493 Artagaveytia, Mr. Ramon male 71.0 0
518 Angle, Mrs. William A (Florence "Mary" Agnes H… female 36.0 1
784 Ali, Mr. William male 25.0 0
840 Alhomaki, Mr. Ilmari Rudolf male 20.0 0

Parch Ticket Fare Cabin Embarked lastname title \

30 0 PC 17601 27.7208 NaN C Uruchurtu Don.
49 0 349237 17.8000 NaN S Arnold-Franchi Mrs.
207 0 2699 18.7875 NaN C Albimona Mr.
210 0 SOTON/O.Q. 3101311 7.0500 NaN S Ali Mr.
353 0 349237 17.8000 NaN S Arnold-Franchi Mr.
493 0 PC 17609 49.5042 NaN C Artagaveytia Mr.
518 0 226875 26.0000 NaN S Angle Mrs.
784 0 SOTON/O.Q. 3101312 7.0500 NaN S Ali Mr.
840 0 SOTON/O2 3101287 7.9250 NaN S Alhomaki Mr.

firstname
30 Manuel E
49 Josef (Josefine Franchi)

256
 207 Nassef Cassem
210 Ahmed
353 Josef
493 Ramon
518 William A (Florence "Mary" Agnes Hughes)
784 William
840 Ilmari Rudolf

3 Date and Time in Pandas

Note why separate objects to handle data and time when python already has datetime
functionality?
• syntax wise datetime is very convenient
• But the performance takes a hit while working with huge data. List vs Numpy Array
• The weaknesses of Python’s datetime format inspired the NumPy team to add a set of native
time series data type to NumPy.
• The datetime64 dtype encodes dates as 64-bit integers, and thus allows arrays of dates to be
represented very compactly.
[86]: date = np.array('2024-07-05', dtype=np.datetime64)
date

[86]: array('2024-07-05', dtype='datetime64[D]')

[87]: date + np.arange(12)

[87]: array(['2024-07-05', '2024-07-06', '2024-07-07', '2024-07-08',

'2024-07-09', '2024-07-10', '2024-07-11', '2024-07-12',
'2024-07-13', '2024-07-14', '2024-07-15', '2024-07-16'],
dtype='datetime64[D]')

• Because of the uniform type in NumPy datetime64 arrays, this type of operation can be
accomplished much more quickly than if we were working directly with Python’s datetime
objects, especially as arrays get large
• Pandas Timestamp object combines the ease-of-use of python datetime with the efficient
storage and vectorized interface of numpy.datetime64
• From a group of these Timestamp objects, Pandas can construct a DatetimeIndex that can
be used to index data in a Series or DataFrame

3.1 Timestamp Object

Time stamps reference particular moments in time (e.g. Oct 16th, 2003 at 02:00am)

257
 3.1.1 Creating Timestamp objects

[52]: pd.Timestamp('2024/07/05')

[52]: Timestamp('2024-07-05 00:00:00')

[57]: # Variations

pd.Timestamp('2024, 07, 05')

pd.Timestamp('2024-07-05')
pd.Timestamp('2024, 07, 05')
pd.Timestamp('2024-07-05')

[57]: Timestamp('2024-07-05 00:00:00')

[69]: pd.Timestamp('5th July 2024')

[69]: Timestamp('2024-07-05 00:00:00')

[68]: pd.Timestamp('2024')

[68]: Timestamp('2024-01-01 00:00:00')

[73]: pd.Timestamp('5th July 2024 1:7pm')

[73]: Timestamp('2024-07-05 13:07:00')

using Python’s datetime module

[76]: import datetime as dt

x = pd.Timestamp(dt.datetime(2024, 7, 5, 13, 10))

x

[76]: Timestamp('2024-07-05 13:10:00')

3.1.2 Attributes of Timestamp

[77]: x.year

[77]: 2024

[78]: x.month

[78]: 7

[80]: x.day

258
[80]: 5

[81]: x.hour

[81]: 13

[82]: x.minute

[82]: 10

[83]: x.second

[83]: 0

3.2 DatetimeIndex Object

A collection of pandas Timestamps

3.2.1 Creating DatetimeIndex Object

3.2.2 From strings

[90]: pd.DatetimeIndex(['2024/1/1', '2023/1/1', '2022/1/1', '2021/1/1'])

[90]: DatetimeIndex(['2024-01-01', '2023-01-01', '2022-01-01', '2021-01-01'],

dtype='datetime64[ns]', freq=None)

3.2.3 Using Python datetime object

[92]: pd.DatetimeIndex([dt.datetime(2024,1,1), dt.datetime(2023,1,1), dt.

↪datetime(2023,1,1)])

[92]: DatetimeIndex(['2024-01-01', '2023-01-01', '2023-01-01'],

dtype='datetime64[ns]', freq=None)

3.2.4 Using pd.timestamps

[95]: dt_index = pd.DatetimeIndex([pd.Timestamp(2024,1,1), pd.Timestamp(2023,1,1), pd.

↪Timestamp(2022,1,1) ])

3.2.5 Creating Series from DatetimeIndex as index

[96]: pd.Series([1,2,3], index=dt_index)

[96]: 2024-01-01 1
2023-01-01 2
2022-01-01 3

259
 dtype: int64

3.3 date_range function

3.3.1 pd.date_range(start=‘start/date’, end=‘end/date’, freq=‘D’)
• Genrate DatetimeIndex from start date to end date based on frequency
• freq

val description
‘h’ Every hour
‘nh’ Every n hour
‘D’ Daily date
‘2D’ Alternate days
‘nD’ days with n gap
‘W’ week days
‘W-MON’ every Mon
‘B’ Business days
‘MS’ Month start
‘ME’ Month end
‘AS’ Year start
‘YE’ Year end
‘YE-DEC’ Every Dec

periods parameter
• four among start, end, freq and periods, three are compulsory
• if end is not specified we can decide num of results by periods
• if freq is not specified it divides the range among n periods.
• all four will throw error
[102]: pd.date_range(start='2024/1/1', end='2025/1/1', freq='D')

[102]: DatetimeIndex(['2024-01-01', '2024-01-02', '2024-01-03', '2024-01-04',

'2024-01-05', '2024-01-06', '2024-01-07', '2024-01-08',
'2024-01-09', '2024-01-10',
…
'2024-12-23', '2024-12-24', '2024-12-25', '2024-12-26',
'2024-12-27', '2024-12-28', '2024-12-29', '2024-12-30',
'2024-12-31', '2025-01-01'],
dtype='datetime64[ns]', length=367, freq='D')

[103]: pd.date_range(start='2024/07/05', end='2024/08/05', freq='2D')

[103]: DatetimeIndex(['2024-07-05', '2024-07-07', '2024-07-09', '2024-07-11',

'2024-07-13', '2024-07-15', '2024-07-17', '2024-07-19',
'2024-07-21', '2024-07-23', '2024-07-25', '2024-07-27',

260
 '2024-07-29', '2024-07-31', '2024-08-02', '2024-08-04'],
dtype='datetime64[ns]', freq='2D')

[104]: pd.date_range(start='2024/07/05', end='2024/08/05', freq='3D')

[104]: DatetimeIndex(['2024-07-05', '2024-07-08', '2024-07-11', '2024-07-14',

'2024-07-17', '2024-07-20', '2024-07-23', '2024-07-26',
'2024-07-29', '2024-08-01', '2024-08-04'],
dtype='datetime64[ns]', freq='3D')

[105]: pd.date_range(start='2024/07/05', end='2024/08/05', freq='W')

[105]: DatetimeIndex(['2024-07-07', '2024-07-14', '2024-07-21', '2024-07-28',

'2024-08-04'],
dtype='datetime64[ns]', freq='W-SUN')

[106]: pd.date_range(start='2024/07/05', end='2024/08/05', freq='W-MON')

[106]: DatetimeIndex(['2024-07-08', '2024-07-15', '2024-07-22', '2024-07-29',

'2024-08-05'],
dtype='datetime64[ns]', freq='W-MON')

[112]: pd.date_range(start='2024/07/05', end='2024/07/15', freq='100h')

[112]: DatetimeIndex(['2024-07-05 00:00:00', '2024-07-09 04:00:00',

'2024-07-13 08:00:00'],
dtype='datetime64[ns]', freq='100h')

[116]: pd.date_range(start='2024/07/05', end='2030/08/05', freq='YE')

[116]: DatetimeIndex(['2024-12-31', '2025-12-31', '2026-12-31', '2027-12-31',

'2028-12-31', '2029-12-31'],
dtype='datetime64[ns]', freq='YE-DEC')

[119]: # Equidistant dates between range

pd.date_range(start='2024/07/05', end='2030/08/05', periods=10)

[119]: DatetimeIndex(['2024-07-05 00:00:00', '2025-03-08 21:20:00',

'2025-11-10 18:40:00', '2026-07-15 16:00:00',
'2027-03-19 13:20:00', '2027-11-21 10:40:00',
'2028-07-25 08:00:00', '2029-03-29 05:20:00',
'2029-12-01 02:40:00', '2030-08-05 00:00:00'],
dtype='datetime64[ns]', freq=None)

3.4 to_datetime function

Converts an existing objects to pandas timestamp/datetimeindex object

261
[122]: date_series = pd.Series(['2024/1/1', '2023/1/1', '2022/1/1'])
s = pd.to_datetime(date_series)
s

[122]: 0 2024-01-01
1 2023-01-01
2 2022-01-01
dtype: datetime64[ns]

[123]: s.dt.day_name()

[123]: 0 Monday
1 Sunday
2 Saturday
dtype: object

dt accessor Accessor object for datetimelike properties of the Series values

[127]: s = pd.Series(['2024/1/1', '2023/1/1', '2022/120/1'])
pd.to_datetime(s, errors='coerce').dt.month_name()

[127]: 0 January
1 January
2 NaN
dtype: object

[128]: df = pd.read_csv('expense_data.csv')
df.shape

[128]: (277, 11)

[131]: df.head()

[131]: Date Account Category Subcategory \

0 3/2/2022 10:11 CUB - online payment Food NaN
1 3/2/2022 10:11 CUB - online payment Other NaN
2 3/1/2022 19:50 CUB - online payment Food NaN
3 3/1/2022 18:56 CUB - online payment Transportation NaN
4 3/1/2022 18:22 CUB - online payment Food NaN

Note INR Income/Expense Note.1 Amount Currency Account.1

0 Brownie 50.0 Expense NaN 50.0 INR 50.0
1 To lended people 300.0 Expense NaN 300.0 INR 300.0
2 Dinner 78.0 Expense NaN 78.0 INR 78.0
3 Metro 30.0 Expense NaN 30.0 INR 30.0
4 Snacks 67.0 Expense NaN 67.0 INR 67.0

262
[137]: df['Date'] = pd.to_datetime(df['Date'])
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 277 entries, 0 to 276
Data columns (total 11 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Date 277 non-null datetime64[ns]
1 Account 277 non-null object
2 Category 277 non-null object
3 Subcategory 0 non-null float64
4 Note 273 non-null object
5 INR 277 non-null float64
6 Income/Expense 277 non-null object
7 Note.1 0 non-null float64
8 Amount 277 non-null float64
9 Currency 277 non-null object
10 Account.1 277 non-null float64
dtypes: datetime64[ns](1), float64(5), object(5)
memory usage: 23.9+ KB

[138]: df['Date'].dt.month_name()

[138]: 0 March
1 March
2 March
3 March
4 March
…
272 November
273 November
274 November
275 November
276 November
Name: Date, Length: 277, dtype: object

3.4.1 Plotting Graphs

[139]: import matplotlib.pyplot as plt

plt.plot(df['Date'], df['INR'])

[139]: [<matplotlib.lines.Line2D at 0x1cfcc57fb30>]

263
[141]: df['day_name'] = df['Date'].dt.day_name()

[142]: df.head()

[142]: Date Account Category Subcategory \

0 2022-03-02 10:11:00 CUB - online payment Food NaN
1 2022-03-02 10:11:00 CUB - online payment Other NaN
2 2022-03-01 19:50:00 CUB - online payment Food NaN
3 2022-03-01 18:56:00 CUB - online payment Transportation NaN
4 2022-03-01 18:22:00 CUB - online payment Food NaN

Note INR Income/Expense Note.1 Amount Currency Account.1 \

0 Brownie 50.0 Expense NaN 50.0 INR 50.0
1 To lended people 300.0 Expense NaN 300.0 INR 300.0
2 Dinner 78.0 Expense NaN 78.0 INR 78.0
3 Metro 30.0 Expense NaN 30.0 INR 30.0
4 Snacks 67.0 Expense NaN 67.0 INR 67.0

day_name
0 Wednesday
1 Wednesday
2 Tuesday

264
 3 Tuesday
4 Tuesday

[143]: df.groupby('day_name')['INR'].mean().plot(kind='bar')

[143]: <Axes: xlabel='day_name'>

[145]: df['month_name'] = df['Date'].dt.month_name()

df.head()

[145]: Date Account Category Subcategory \

0 2022-03-02 10:11:00 CUB - online payment Food NaN
1 2022-03-02 10:11:00 CUB - online payment Other NaN
2 2022-03-01 19:50:00 CUB - online payment Food NaN
3 2022-03-01 18:56:00 CUB - online payment Transportation NaN
4 2022-03-01 18:22:00 CUB - online payment Food NaN

265
 Note INR Income/Expense Note.1 Amount Currency Account.1 \
0 Brownie 50.0 Expense NaN 50.0 INR 50.0
1 To lended people 300.0 Expense NaN 300.0 INR 300.0
2 Dinner 78.0 Expense NaN 78.0 INR 78.0
3 Metro 30.0 Expense NaN 30.0 INR 30.0
4 Snacks 67.0 Expense NaN 67.0 INR 67.0

day_name month_name
0 Wednesday March
1 Wednesday March
2 Tuesday March
3 Tuesday March
4 Tuesday March

[146]: df.groupby('month_name')['INR'].sum().plot(kind='bar')

[146]: <Axes: xlabel='month_name'>

266
[149]: # Expense on month ends

df[df['Date'].dt.is_month_end]

[149]: Date Account Category Subcategory \

7 2022-02-28 11:56:00 CUB - online payment Food NaN
8 2022-02-28 11:45:00 CUB - online payment Other NaN
61 2022-01-31 08:44:00 CUB - online payment Transportation NaN
62 2022-01-31 08:27:00 CUB - online payment Other NaN
63 2022-01-31 08:26:00 CUB - online payment Transportation NaN
242 2021-11-30 14:24:00 CUB - online payment Gift NaN
243 2021-11-30 14:17:00 CUB - online payment Food NaN
244 2021-11-30 10:11:00 CUB - online payment Food NaN

Note INR Income/Expense Note.1 Amount Currency \

7 Pizza 339.15 Expense NaN 339.15 INR
8 From kumara 200.00 Income NaN 200.00 INR
61 Vnr to apk 50.00 Expense NaN 50.00 INR
62 To vicky 200.00 Expense NaN 200.00 INR
63 To ksr station 153.00 Expense NaN 153.00 INR
242 Bharath birthday 115.00 Expense NaN 115.00 INR
243 Lunch with company 128.00 Expense NaN 128.00 INR
244 Breakfast 70.00 Expense NaN 70.00 INR

Account.1 day_name month_name

7 339.15 Monday February
8 200.00 Monday February
61 50.00 Monday January
62 200.00 Monday January
63 153.00 Monday January
242 115.00 Tuesday November
243 128.00 Tuesday November
244 70.00 Tuesday November

267