SAI SHREE INTERNATIONAL ACADEMY RATLAM
#6 Write a Pandas program to select the rows the percentage is between 70
and 90 (inclusive)
import pandas as pd
import numpy as np
exam_data = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
labels = ['A', 'B', 'C', 'B', 'E', 'F', 'G', 'H', 'I', 'J']
df = pd.DataFrame(exam_data , index=labels)
print("Number of student whoes percentage more than 70:")
print(df[df['perc'].between(70,90)])
# 7 Write a Pandas program to change the percentage in given row by user.
import pandas as pd
import numpy as np
exam_dic = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
labels = ['A', 'B', 'C', 'B', 'E', 'F', 'G', 'H', 'I', 'J']
df = pd.DataFrame(exam_dic , index=labels)
print("\nOriginal data frame:")
print(df)
ch = input("Enter the index of row : ")
per = float(input("Enter percentage to be changed: "))
print('\nChange the percentage in row '+ch+ ' to',per)
df.loc[ch, 'perc'] = per
print(df)
# 8 Write a Pandas program to select the rows where the percentage greater
than 70.
import pandas as pd
import numpy as np
exam_data = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
labels = ['A', 'B', 'C', 'B', 'E', 'F', 'G', 'H', 'I', 'J']
df = pd.DataFrame(exam_data , index=labels)
print("Number of student whoes percentage more than 70:")
print(df[df['perc'] > 70])
#9 Write a Pandas program to join the two given dataframes along rows and
assign all data.
import pandas as pd
import numpy as np
exam_dic1 = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
exam_data1 = pd.DataFrame(exam_dic1)
exam_dic2 = {'name': ['Parveen', 'Ahil', 'Ashaz', 'Shifin', 'Hanash'],
'perc': [89.5, 92, 90.5, 91.5, 90],
'qualify': ['yes', 'yes', 'yes', 'yes', 'yes']}
exam_data2 = pd.DataFrame(exam_dic2)
print("Original DataFrames:")
print(exam_data1)
print("-------------------------------------")
print(exam_data2)
print("\nJoin the said two dataframes along rows:")
result_data = pd.concat([exam_data1, exam_data2])
print(result_data)
#10 Write a Pandas program to append a list of dictioneries or series to a
existing DataFrame and display the combined data.
import pandas as pd
import numpy as np
exam_dic1 = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
exam_data1 = pd.DataFrame(exam_dic1)
s = pd.Series(['Sukhvir', 54,'yes'], index=['name', 'perc','qualify'])
dicts = [{'name': 'Krish', 'perc': 45,'qualify':'yes'},
{'name': 'Kumar', 'perc': 67,'qualify':'yes'}]
print("Original DataFrames:")
print(exam_data1)
print("\nDictionary:")
print(s)
# Add Series
combined_data = exam_data1.append(s, ignore_index=True, sort=False)
# Add Dictionary
combined_info = combined_data.append(dicts, ignore_index=True,
sort=False)
print("\nCombined Data:")
# Print Combined Data/info
print(combined_info)
#11 Program to select or filter rows from a DataFrame based on values in
columns in pandas?
# ( Use of Relational and Logical Operators)
import pandas as pd
import numpy as np
exam_dic1 = {'name': ['Aman', 'Kamal', 'Amjad', 'Rohan', 'Amit', 'Sumit',
'Matthew', 'Kartik', 'Kavita', 'Pooja'],
'perc': [79.5, 29, 90.5, np.nan, 32, 65, 56, np.nan, 29, 89],
'qualify': ['yes', 'no', 'yes', 'no', 'no', 'yes', 'yes', 'no', 'no', 'yes']}
exam_data1 = pd.DataFrame(exam_dic1)
print("Original DataFrames:")
print(exam_data1)
print("\nUse == operator\n")
print(exam_data1.loc[exam_data1['name'] == 'Rohan'])
print("\nUse < operator\n")
print(exam_data1.loc[exam_data1['perc'] < 40])
print("\n Use != operator\n")
print(exam_data1.loc[exam_data1['qualify'] != 'no'])
print("\n Multiple Conditions\n")
print(exam_data1.loc[(exam_data1['qualify'] != 'yes') & (exam_data1['perc']
<40)])
#12 Importing and exporting data between pandas and CSV file.
import pandas as pd
import csv
#Reading the Data
df = pd.read_csv("student_result.csv")
# Display Name of Columns
print(df.columns)
# Display no of rows and column
print(df.shape)
# Display Column Names and their types
print(df.info())
#13 Read the ‘Student_result.csv’ to create data frame
import pandas as pd
import csv
#To display Adm_No, Gender and Percentage from ‘student_result.csv’ file.
df = pd.read_csv("student_result.csv",usecols = ['ADM_NO','GENDER',
'PERCENTAGE'])
print("To display Adm_No, Gender and Percentage from ‘student_result.csv’
file.")
print(df)
#To display first 5 and last 5 records from ‘student_result.csv’ file.
df1 = pd.read_csv("student_result.csv")
print(df1.head())
print(df1.tail())
#14 Read the ‘Student_result.csv’ to create data frame and to display
Student_result and to modify the Percentage of student with NaN value in
dataframe.
import pandas as pd
import numpy as np
import csv
df = pd.read_csv("student_result.csv")
print(df)
#To display Student_result file with new column names.
df1 = pd.read_csv("student_result.csv",skiprows = 1,
names = ['Adno','Sex','Name','Eng','Hin',
'Maths','Sc.','SSt','San','IT','Perc'])
print("To display Student_result file with new column names")
print(df1)
# To modify the Percentage of student below 40 with NaN value.
df2 = pd.read_csv("student_result.csv")
print(df2)
print("To modify the Percentage of student below 40 with NaN value.")
df2.loc[(df2['PERCENTAGE'] <40, 'PERCENTAGE')] = np.nan
print(df2)
# Read the ‘Student_result.csv’ to create data frame and to create a duplicate
file for ‘student_result.csv’ containing Adm_No, Name and Percentage.
import pandas as pd
import numpy as np
import csv
#15 To create a duplicate file for ‘student_result.csv’ containing Adm_No,
Name and Percentage.
df = pd.read_csv("student_result.csv")
df.to_csv('copyStudent_result.csv',columns=['ADM_NO',"STUDENT'S_NAME"
,"PERCENTAGE"])
# Display Copied Dataframe
df2=pd.read_csv("copyStudent_result.csv")
print(df2)
# find the highest percentage and also print the student’s name and
percentage.
df1 = pd.read_csv("student_result.csv")
df1 = df1[["STUDENT'S_NAME",'PERCENTAGE']][
df1.PERCENTAGE== df1['PERCENTAGE'].max()]
print(df1)
#16 Given the school result data, analyses the performance of the students
on different parameters, e.g subject wise or class wise.
# x-axis is shows the subject and y -axis
# shows the markers in each subject
# import pandas and matplotlib
import pandas as pd
import matplotlib.pyplot as plt
# Simple Line Chart with setting of Label of X and Y axis,
# title for chart line and color of line
subject = ['Physic','Chemistry','Mathematics', 'Biology','Computer']
marks =[80,75,70,78,60]
plt.plot(subject,marks,'green',marker ='*') # To draw line in red colour
plt.title('Marks Scored') # To Write Title of the Line Chart
plt.xlabel('SUBJECT') # To Put Label At Y Axis
plt.ylabel('MARKS') # To Put Label At X Axis
plt.show()
#17Write a program to plot a bar chart in python to display
#the result of a school for five consecutive years.
import matplotlib.pyplot as pl
year=['2015','2016','2017','2018','2019'] # list of years
p=[98.50,70.25,55.20,90.5,61.50] #list of pass percentage
j=['b','g','r','m','c'] # color code of bar charts
pl.bar(year, p, width=0.2, color=j) # bar( ) function to create the bar chart
pl.xlabel("year") # label for x-axis
pl.ylabel("Pass%") # label for y-axis
pl.show( ) # function to display bar chart
**************
