9/23/24, 10:21 AM pandas - Jupyter Notebook

In [1]: import numpy as np

In [6]: arr=np.array([1,2,3,4])
arr

Out[6]: array([1, 2, 3, 4])

In [4]: arr1=arr.reshape(2,2)

In [7]: arr1
arr1.ndim

Out[7]: 2

In [8]: arr1.mean()

Out[8]: 2.5

In [20]: import pandas as pd

In [23]: df=pd.read_csv("D:\myFolder\SKCET\cricket.csv")

In [24]: df

Out[24]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NaN

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

6 Charles Coventry 194 NaN

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

9 Sanath Jayasuriya 189 NaN

10 Martin Guptill 189 NaN

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

15 Sourav Ganguly 183 NaN

16 MS Dhoni 183 india

localhost:8888/notebooks/pandas.ipynb# 1/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [38]: df=pd.read_csv("C://Users/naren/AppData/Local/Programs/Python/Python310/cri

In [35]: df

Out[35]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NaN

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

6 Charles Coventry 194 NaN

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

9 Sanath Jayasuriya 189 NaN

10 Martin Guptill 189 NaN

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

15 Sourav Ganguly 183 NaN

16 MS Dhoni 183 india

In [39]: df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 17 entries, 0 to 16
Data columns (total 3 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 player_name 17 non-null object
1 score 17 non-null int64
2 country 12 non-null object
dtypes: int64(1), object(2)
memory usage: 536.0+ bytes

In [40]: df.to_string()

Out[40]: ' player_name score country\n0 Rohit Sharma 264 indi

a\n1 Martin Guptill 237 NaN\n2 Virender Sehwag 219 in
dia\n3 Chris Gayle 215 wind\n4 Rohit Sharma 209
india\n5 Sachin Tendulkar 200 india\n6 Charles Coventry 194
NaN\n7 Saeed Anwar 194 pak\n8 Sir Viv Richards 189
wind\n9 Sanath Jayasuriya 189 NaN\n10 Martin Guptill 189
NaN\n11 Gary Kirsten 188 SA\n12 Sachin Tendulkar 186
india\n13 Shane Watson 185 Aus\n14 Virat Kohli 183
india\n15 Sourav Ganguly 183 NaN\n16 MS Dhoni 183
india'

localhost:8888/notebooks/pandas.ipynb# 2/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [41]: df.to_string

Out[41]: <bound method DataFrame.to_string of player_name score country

0 Rohit Sharma 264 india
1 Martin Guptill 237 NaN
2 Virender Sehwag 219 india
3 Chris Gayle 215 wind
4 Rohit Sharma 209 india
5 Sachin Tendulkar 200 india
6 Charles Coventry 194 NaN
7 Saeed Anwar 194 pak
8 Sir Viv Richards 189 wind
9 Sanath Jayasuriya 189 NaN
10 Martin Guptill 189 NaN
11 Gary Kirsten 188 SA
12 Sachin Tendulkar 186 india
13 Shane Watson 185 Aus
14 Virat Kohli 183 india
15 Sourav Ganguly 183 NaN
16 MS Dhoni 183 india>

In [42]: df.loc[0]

Out[42]: player_name Rohit Sharma

score 264
country india
Name: 0, dtype: object

In [43]: df.head()

Out[43]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NaN

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

In [44]: df.tail()

Out[44]: player_name score country

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

15 Sourav Ganguly 183 NaN

16 MS Dhoni 183 india

localhost:8888/notebooks/pandas.ipynb# 3/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [45]: df.mean()

C:\Users\naren\AppData\Local\Temp/ipykernel_18348/3698961737.py:1: FutureW
arning: Dropping of nuisance columns in DataFrame reductions (with 'numeri
c_only=None') is deprecated; in a future version this will raise TypeErro
r. Select only valid columns before calling the reduction.
df.mean()

Out[45]: score 200.411765

dtype: float64

In [46]: df['score'].mean()

Out[46]: 200.41176470588235

In [47]: df.dropna()

Out[47]: player_name score country

0 Rohit Sharma 264 india

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

16 MS Dhoni 183 india

In [48]: import pandas as pd

In [49]: data={"player_name":["sachin","dravid"], "score":[85,102]}

In [50]: data
​

Out[50]: {'player_name': ['sachin', 'dravid'], 'score': [85, 102]}

In [51]: df=pd.DataFrame(data)

localhost:8888/notebooks/pandas.ipynb# 4/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [52]: df

Out[52]: player_name score

0 sachin 85

1 dravid 102

In [55]: df=pd.read_csv("C://Users/naren/AppData/Local/Programs/Python/Python310/cri

In [56]: df

Out[56]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NaN

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

6 Charles Coventry 194 NaN

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

9 Sanath Jayasuriya 189 NaN

10 Martin Guptill 189 NaN

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

15 Sourav Ganguly 183 NaN

16 MS Dhoni 183 india

In [57]: df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 17 entries, 0 to 16
Data columns (total 3 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 player_name 17 non-null object
1 score 17 non-null int64
2 country 12 non-null object
dtypes: int64(1), object(2)
memory usage: 536.0+ bytes

localhost:8888/notebooks/pandas.ipynb# 5/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [58]: df.dropna()

Out[58]: player_name score country

0 Rohit Sharma 264 india

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

16 MS Dhoni 183 india

In [59]: df.head()

Out[59]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NaN

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

In [61]: df['score'].median()

Out[61]: 189.0

localhost:8888/notebooks/pandas.ipynb# 6/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [63]: df.fillna("NK")

Out[63]: player_name score country

0 Rohit Sharma 264 india

1 Martin Guptill 237 NK

2 Virender Sehwag 219 india

3 Chris Gayle 215 wind

4 Rohit Sharma 209 india

5 Sachin Tendulkar 200 india

6 Charles Coventry 194 NK

7 Saeed Anwar 194 pak

8 Sir Viv Richards 189 wind

9 Sanath Jayasuriya 189 NK

10 Martin Guptill 189 NK

11 Gary Kirsten 188 SA

12 Sachin Tendulkar 186 india

13 Shane Watson 185 Aus

14 Virat Kohli 183 india

15 Sourav Ganguly 183 NK

16 MS Dhoni 183 india

In [1]: readDF=pd.read_csv("C:\Users\naren\AppData\Local\Programs\Python\Python311\

File "C:\Users\naren\AppData\Local\Temp/ipykernel_35668/930507820.py", l
ine 1
readDF=pd.read_csv("C:\Users\naren\AppData\Local\Programs\Python\Pytho
n311\Data.csv")

^
SyntaxError: (unicode error) 'unicodeescape' codec can't decode bytes in p
osition 2-3: truncated \UXXXXXXXX escape

In [4]: import pandas as pd

readDF=pd.read_csv("C://Users/naren/AppData/Local/Programs/Python/Python311

localhost:8888/notebooks/pandas.ipynb# 7/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [5]: readDF

Out[5]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 NaN Yes

5 France 35.0 58000.0 Yes

6 Spain NaN 52000.0 No

7 France 48.0 79000.0 NaN

8 Germany 50.0 83000.0 No

9 France 37.0 67000.0 Yes

10 France 35.0 58000.0 Yes

11 Spain NaN 52000.0 No

12 France 34.0 79000.0 Yes

In [8]: data

--------------------------------------------------------------------------
-
TypeError Traceback (most recent call las
t)
~\AppData\Local\Temp/ipykernel_35668/2092712167.py in <module>
----> 1 pd['Country']

TypeError: 'module' object is not subscriptable

In [9]: readDF.loc[0]

Out[9]: Country France

Age 44.0
Salary 72000.0
Purchased No
Name: 0, dtype: object

In [10]: readDF.loc[0:4]

Out[10]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 NaN Yes

localhost:8888/notebooks/pandas.ipynb# 8/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [11]: readDF.head(6)

Out[11]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 NaN Yes

5 France 35.0 58000.0 Yes

In [12]: readDF.head()

Out[12]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 NaN Yes

In [13]: readDF.tail(6)

Out[13]: Country Age Salary Purchased

7 France 48.0 79000.0 NaN

8 Germany 50.0 83000.0 No

9 France 37.0 67000.0 Yes

10 France 35.0 58000.0 Yes

11 Spain NaN 52000.0 No

12 France 34.0 79000.0 Yes

In [14]: readDF.tail()

Out[14]: Country Age Salary Purchased

8 Germany 50.0 83000.0 No

9 France 37.0 67000.0 Yes

10 France 35.0 58000.0 Yes

11 Spain NaN 52000.0 No

12 France 34.0 79000.0 Yes

localhost:8888/notebooks/pandas.ipynb# 9/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [15]: readDF.mean()

C:\Users\naren\AppData\Local\Temp/ipykernel_35668/1770479177.py:1: FutureW
arning: Dropping of nuisance columns in DataFrame reductions (with 'numeri
c_only=None') is deprecated; in a future version this will raise TypeErro
r. Select only valid columns before calling the reduction.
readDF.mean()

Out[15]: Age 38.000000

Salary 63583.333333
dtype: float64

In [16]: M=readDF['Age'].mean()

Out[16]: 38.0

In [18]: readDF.fillna(readDF['Age'].mean())

Out[18]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 38.0 Yes

5 France 35.0 58000.0 Yes

6 Spain 38.0 52000.0 No

7 France 48.0 79000.0 38.0

8 Germany 50.0 83000.0 No

9 France 37.0 67000.0 Yes

10 France 35.0 58000.0 Yes

11 Spain 38.0 52000.0 No

12 France 34.0 79000.0 Yes

localhost:8888/notebooks/pandas.ipynb# 10/11
9/23/24, 10:21 AM pandas - Jupyter Notebook

In [19]: readDF
​

Out[19]: Country Age Salary Purchased

0 France 44.0 72000.0 No

1 Spain 27.0 48000.0 Yes

2 Germany 30.0 54000.0 No

3 Spain 38.0 61000.0 No

4 Germany 40.0 NaN Yes

5 France 35.0 58000.0 Yes

6 Spain NaN 52000.0 No

7 France 48.0 79000.0 NaN

8 Germany 50.0 83000.0 No

9 France 37.0 67000.0 Yes

10 France 35.0 58000.0 Yes

11 Spain NaN 52000.0 No

12 France 34.0 79000.0 Yes

In [ ]: ​

localhost:8888/notebooks/pandas.ipynb# 11/11