PYTHON DATA SCIENCE

May 27, 2021

1 Hello Students I Abhishek Dixit Welcomes You

2 To Learn Python Data Science Tutorials

Name,Email,Phone Number,Address
Bob Smith,[email protected],123-456-7890,123 Fake Street
Mike Jones,[email protected],098-765-4321,321 Fake venue
[ ]: import csv

[ ]: with open('/content/MODIFIED MID SEMESTER EXAMINATION MARKS.csv', 'r') as data:

reader = csv.reader(data)
for data in reader:
print(data)

[ ]: import json

[ ]: with open('/content/sample_data/anscombe.json') as data:

reader = json.load(data)
for data in reader:
print(data)

[ ]: from google.colab import files

uploaded = files.upload()

[ ]: with open('/content/MODIFIED MID SEMESTER EXAMINATION MARKS.csv','w') as file:

writer = csv.writer(file)
writer.writerow(['NAME', 'ROLL NO.', 'MARKS'])
writer.writerow(['Abhishek', '0901FT201001.', 15])
writer.writerow(['Pawan', '0901FT201112.', 17])

[ ]: with open('/content/MODIFIED MID SEMESTER EXAMINATION MARKS.csv', 'r') as file:

reader = csv.DictReader(file)
for row in reader:

1
 print(row)

OrderedDict([('NAME', 'Abhishek'), ('ROLL NO.', '0901FT201001.'), ('MARKS',

'15')])
OrderedDict([('NAME', 'Pawan'), ('ROLL NO.', '0901FT201112.'), ('MARKS', '17')])

[ ]: import os

[ ]: os.remove('/content/MODIFIED MID SEMESTER EXAMINATION MARKS.csv')

[ ]: os.makedirs('Test.csv')

[ ]: os.rmdir('/content/Test.csv')

3 PANDAS
[ ]: import pandas
print('Now Pandas is imprted and ready to use')

Now Pandas is imprted and ready to use

[ ]: import pandas as pd

[ ]: print(pd.__version__)

1.1.5
Series
DataFrame
[ ]: ms=pd.Series(data, index)

[ ]: v=[11, 17, 22]

data=pd.Series(v)
print(data)

0 11
1 17
2 22
dtype: int64

[ ]: v=[11, 17, 22]

data=pd.Series(v, index = [1, 2, 3])
print(data)

1 11
2 17

2
 3 22
dtype: int64

[ ]: v=[11, 17, 22]

data=pd.Series(v, index = ['a', 'b', 'c'])
print(data)

[ ]: print(data['a'])

11

[ ]: calories = {"Day1": 420, "Day2": 320, "day3": 356}

pd.Series(calories, index= ["Day1", 2, 3])

[ ]: series1 = pd.Series([1, 2, 3 ,4], index =['a', 'b','c','d'])

series2 = pd.Series([1, 3, 6 ,4], index =['a', 'e','c','f'])

[ ]: series1+series2

[ ]: series1-series2

[ ]: series1*series2

[ ]: series1/series2

DATAFRAME
pd.DataFrame(data,index)

[ ]: data = {"Name": ['Abhishek', 'Ram', 'Kartik'],

"Age":[30, 28, 3]}
v= pd.DataFrame(data)
print(v)

Name Age
0 Abhishek 30
1 Ram 28
2 Kartik 3

[ ]: v.loc[0]

[ ]: Name Abhishek
Age 30
Name: 0, dtype: object

[ ]: v.iloc[0]

3
[ ]: Name Abhishek
Age 30
Name: 0, dtype: object

[ ]: data = {"Name": ['Abhishek', 'Suman', 'Kartik'],

"Age":[30, 28, 3],
"Gender":['M','F','M']}
v= pd.DataFrame(data, index= [3, 4, 5])
print(v)

Name Age Gender

3 Abhishek 30 M
4 Suman 28 F
5 Kartik 3 M

[ ]: print(v.loc[3])

Name Abhishek
Age 30
Name: 3, dtype: object

[ ]: v.iloc[3]

[ ]: v.loc[(v.Age>=10) & (v.Gender =='M')]

[ ]: Name Age Gender

3 Abhishek 30 M

[ ]: data = {"Name": ['Abhishek', 'Ram', 'Kartik'],

"Age":[30, 28, 3]}
v= pd.DataFrame(data)
print(v)

Name Age
0 Abhishek 30
1 Ram 28
2 Kartik 3

[ ]: v.iloc[[0,1]]

[ ]: Name Age
0 Abhishek 30
1 Ram 28

[ ]: v.iloc[[0,2]]

4
[ ]: Name Age
0 Abhishek 30
2 Kartik 3

[ ]: v.iloc[0:3]

[ ]: Name Age
0 Abhishek 30
1 Ram 28
2 Kartik 3

[ ]: data = {"Name": ['Abhishek', 'Ram', 'Kartik'],

"Age":[30, 28, 3],
"Gender":['M','F','M']}
v= pd.DataFrame(data, index = ['a','b','c'])
print(v)

Name Age Gender

a Abhishek 30 M
b Ram 28 F
c Kartik 3 M

[ ]: v.loc[['a','b'],['Name', 'Age']]

[ ]: Name Age
a Abhishek 30
b Ram 28

[ ]: v.shape

[ ]: (3, 3)

[ ]: df1=pd.DataFrame({'A': ['A0','A1', 'A2', 'A3'],

'B': ['B0','B1', 'B2', 'B3'],
'C': ['C0','C1', 'C2', 'C3'],
'D': ['D0','D1', 'D2', 'D3']}, index = [0, 1, 2 ,3])
df2=pd.DataFrame({'A': ['A4','A5', 'A6', 'A7'],
'B': ['B4','B5', 'B6', 'B7'],
'C': ['C4','C5', 'C6', 'C7'],
'D': ['D4','D5', 'D6', 'D7']}, index = [4, 5, 6 ,7])

[ ]: pd.concat([df1,df2], axis=0)

[ ]: pd.concat([df1,df2], axis=1)

pd.merge(left, right, how = ‘inner/outer’, on = ‘key’)

5
[ ]: left =pd.DataFrame({'KEY': ['A0','A1', 'A2', 'A3'],
'B': ['B0','B1', 'B2', 'B3'],
'C': ['C0','C1', 'C2', 'C3']})
right =pd.DataFrame({'KEY': ['A0','A1', 'A2', 'A4'],
'D': ['B0','B1', 'B6', 'B3'],
'E': ['C0','C5', 'C2', 'C3']})

[ ]: pd.merge(left, right, how='inner', on='KEY')

[ ]: KEY B C D E
0 A0 B0 C0 B0 C0
1 A1 B1 C1 B1 C5
2 A2 B2 C2 B6 C2

[ ]: pd.merge(left, right, how='outer', on='KEY')

[ ]: KEY B C D E
0 A0 B0 C0 B0 C0
1 A1 B1 C1 B1 C5
2 A2 B2 C2 B6 C2
3 A3 B3 C3 NaN NaN
4 A4 NaN NaN B3 C3

[ ]: left=pd.DataFrame({
'B': ['B0','B1', 'B2', 'B3'],
'C': ['C0','C1', 'C2', 'C3'],
}, index = ['A0','A1', 'A2' ,'A3'])
right=pd.DataFrame({
'D': ['D4','D5', 'D6', 'D7'],
'E' : ['E4', 'E5', 'E6', 'E7']}, index = ['A0','A1', 'A2'␣
,→,'A4'])

[ ]: print(left)

B C
A0 B0 C0
A1 B1 C1
A2 B2 C2
A3 B3 C3

[ ]: left.join(right)

[ ]: B C D E
A0 B0 C0 D4 E4
A1 B1 C1 D5 E5
A2 B2 C2 D6 E6
A3 B3 C3 NaN NaN

6
[ ]: right.join(left)

[ ]: D E B C
A0 D4 E4 B0 C0
A1 D5 E5 B1 C1
A2 D6 E6 B2 C2
A4 D7 E7 NaN NaN

[ ]: left.join(right, how ='outer')

[ ]: B C D E
A0 B0 C0 D4 E4
A1 B1 C1 D5 E5
A2 B2 C2 D6 E6
A3 B3 C3 NaN NaN
A4 NaN NaN D7 E7

[ ]: data=pd.DataFrame({'B': [1,2,1,3], 'C':[2,1,2,4]}, index = ['A0', 'A1','A2',␣

,→'A3'])

[ ]: data

[ ]: B C
A0 1 2
A1 2 1
A2 1 2
A3 3 4

[ ]: data['C'].unique()

[ ]: array([2, 1, 4])

[ ]: data['B'].nunique()

[ ]: 3

[ ]: data['C'].value_counts()

[ ]: 2 2
1 1
4 1
Name: C, dtype: int64

[ ]: data['B'].apply(lambda x: x*x)

[ ]: A0 1
A1 4

7
 A2 1
A3 9
Name: B, dtype: int64

[ ]: data.columns

[ ]: Index(['B', 'C'], dtype='object')

[ ]: data.index

[ ]: Index(['A0', 'A1', 'A2', 'A3'], dtype='object')

[ ]: data.sort_values('B')

[ ]: B C
A0 1 2
A2 1 2
A1 2 1
A3 3 4

3.1 Where is the Pandas Codebase?

The source code for Pandas is located at this github repository https://github.com/pandas-
dev/pandas
Latest version: 1.2.4
Release date: Apr 12, 2021.

[ ]: import pandas as pd

[ ]: data = pd.read_csv('/content/SAMPLE.csv')
print(data)

[ ]: data = pd.read_csv('/content/SAMPLE.csv')
print(data.to_string())

[ ]: d = pd.read_csv('/content/MODIFIED MID SEMESTER EXAMINATION MARKS.csv')

print(d.to_string())

[ ]: len(data)

[ ]: 12

[ ]: nd=pd.read_json('/content/sample_data/anscombe.json')
print(nd.to_string())

8
[ ]: pd.read_excel('/content/MID SEMESTER EXAMINATION.xlsx')

[ ]: data={"Name": ['Abhishek', 'Pawan','Kartik'],

"age": [31, 27, 3]}
v=pd.DataFrame(data)
print(v)

Name age
0 Abhishek 31
1 Pawan 27
2 Kartik 3

[ ]: v.to_csv('WRITECSV')

[ ]: view=pd.read_csv('/content/WRITECSV')
print(view)

[ ]: v.to_csv('WRITECSV', index=False)

[ ]: view=pd.read_csv('/content/WRITECSV')
view

[ ]: v.to_excel('WRITEEXCEL.xlsx', index=False)

[ ]: view=pd.read_excel('/content/WRITEEXCEL.xlsx')
view

[ ]: data = pd.read_csv('/content/SAMPLE.csv')
print(data.head(6))

[ ]: data = pd.read_csv('/content/SAMPLE.csv')
print(data.tail(6))

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
print(data.to_string())

S. No. ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS

PERCENTAGE
0 1 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0
75.0
1 2 0901IT181002 ADITYA JOSHI 05-25-2021 NaN
NaN
2 3 0901IT181003 AJAY GARG 25-May-21 16.0
80.0
3 4 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0
85.0
4 5 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0

9
 60.0
5 6 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0
55.0
6 7 0901IT181007 ALOK KUMAR 05-25-2021 13.0
65.0
7 8 0901IT181008 AMAN DIXIT 25-05-2021 NaN
NaN
8 9 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0
60.0
9 10 0901IT181010 ANKIT KUMAR 25-05-2021 12.5
62.5
10 11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0
65.0
11 12 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0
65.0

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
newdata=data.dropna()
print(newdata.to_string())

S. No. ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS

PERCENTAGE
0 1 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0
75.0
2 3 0901IT181003 AJAY GARG 25-May-21 16.0
80.0
3 4 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0
85.0
4 5 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0
60.0
5 6 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0
55.0
6 7 0901IT181007 ALOK KUMAR 05-25-2021 13.0
65.0
8 9 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0
60.0
9 10 0901IT181010 ANKIT KUMAR 25-05-2021 12.5
62.5
10 11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0
65.0
11 12 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0
65.0

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
newdata=data.dropna(axis=1)
print(newdata.to_string())

10
[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
data.fillna(12)

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
data['MARKS'].fillna(12)

[ ]: 0 15.0
1 12.0
2 16.0
3 17.0
4 12.0
5 11.0
6 13.0
7 12.0
8 12.0
9 12.5
10 13.0
11 13.0
Name: MARKS, dtype: float64

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
data['MARKS'].fillna(12, inplace=True)
data

[ ]: S. No. ROLL. NO. … MARKS PERCENTAGE

0 1 0901IT181001 … 15.0 75.0
1 2 0901IT181002 … 12.0 NaN
2 3 0901IT181003 … 16.0 80.0
3 4 0901IT181004 … 17.0 85.0
4 5 0901IT181005 … 12.0 60.0
5 6 0901IT181006 … 11.0 55.0
6 7 0901IT181007 … 13.0 65.0
7 8 0901IT181008 … 12.0 NaN
8 9 0901IT181009 … 12.0 60.0
9 10 0901IT181010 … 12.5 62.5
10 11 0901IT181011 … 13.0 65.0
11 12 0901IT181011 … 13.0 65.0

[12 rows x 6 columns]

[ ]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
data = data.rename(columns= {'STUDENT_NAME':'NAME_STUDENT'})
print(data.to_string())

[ ]: data =pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
x = data["MARKS"].mean()
data["MARKS"].fillna(x, inplace=True)

11
 data

[ ]: S. No. ROLL. NO. … MARKS PERCENTAGE

0 1 0901IT181001 … 15.00 75.0
1 2 0901IT181002 … 13.45 NaN
2 3 0901IT181003 … 16.00 80.0
3 4 0901IT181004 … 17.00 85.0
4 5 0901IT181005 … 12.00 60.0
5 6 0901IT181006 … 11.00 55.0
6 7 0901IT181007 … 13.00 65.0
7 8 0901IT181008 … 13.45 NaN
8 9 0901IT181009 … 12.00 60.0
9 10 0901IT181010 … 12.50 62.5
10 11 0901IT181011 … 13.00 65.0
11 12 0901IT181011 … 13.00 65.0

[12 rows x 6 columns]

[ ]: data =pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
x = data["MARKS"].median()
data["MARKS"].fillna(x, inplace=True)
data

[ ]: S. No. ROLL. NO. … MARKS PERCENTAGE

0 1 0901IT181001 … 15.0 75.0
1 2 0901IT181002 … 13.0 NaN
2 3 0901IT181003 … 16.0 80.0
3 4 0901IT181004 … 17.0 85.0
4 5 0901IT181005 … 12.0 60.0
5 6 0901IT181006 … 11.0 55.0
6 7 0901IT181007 … 13.0 65.0
7 8 0901IT181008 … 13.0 NaN
8 9 0901IT181009 … 12.0 60.0
9 10 0901IT181010 … 12.5 62.5
10 11 0901IT181011 … 13.0 65.0
11 12 0901IT181011 … 13.0 65.0

[12 rows x 6 columns]

[ ]: data =pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')
x = data["MARKS"].mode()[0]
data["MARKS"].fillna(x, inplace=True)
data

[ ]: data.describe()

[ ]: data.info()

12
[2]: import pandas as pd

[6]: data =pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')

print(data.to_string())

ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0 75.0
1 0901IT181002 ADITYA JOSHI 05-25-2021 NaN NaN
2 0901IT181003 AJAY GARG 25-May-21 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0 85.0
4 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0 55.0
6 0901IT181007 ALOK KUMAR 05-25-2021 13.0 65.0
7 0901IT181008 AMAN DIXIT 25-05-2021 NaN NaN
8 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0 60.0
9 0901IT181010 ANKIT KUMAR 25-05-2021 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0
11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

[5]: data['DATE OF EXAM']=pd.to_datetime(data['DATE OF EXAM'])

print(data.to_string())

ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 2021-05-25 15.0 75.0
1 0901IT181002 ADITYA JOSHI 2021-05-25 NaN NaN
2 0901IT181003 AJAY GARG 2021-05-25 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 2021-05-25 17.0 85.0
4 0901IT181005 AKSHAT KOTHAVADE 2021-05-25 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 2021-05-25 11.0 55.0
6 0901IT181007 ALOK KUMAR 2021-05-25 13.0 65.0
7 0901IT181008 AMAN DIXIT 2021-05-25 NaN NaN
8 0901IT181009 AMIT BAMNIYA 2021-05-25 12.0 60.0
9 0901IT181010 ANKIT KUMAR 2021-05-25 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 2021-05-25 13.0 65.0
11 0901IT181011 ANKIT RAJ TIRKEY 2021-05-25 13.0 65.0

[ ]: data['DATE OF EXAM'].apply(lambda x:pd.to_datetime(x).strftime('%m-%d-%y'))

[12]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')

data['MARKS'].fillna(21, inplace=True)
data

[12]: ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0 75.0
1 0901IT181002 ADITYA JOSHI 05-25-2021 21.0 NaN
2 0901IT181003 AJAY GARG 25-May-21 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0 85.0

13
 4 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0 55.0
6 0901IT181007 ALOK KUMAR 05-25-2021 13.0 65.0
7 0901IT181008 AMAN DIXIT 25-05-2021 21.0 NaN
8 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0 60.0
9 0901IT181010 ANKIT KUMAR 25-05-2021 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0
11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

[15]: for x in data.index:

if data.loc[x,'MARKS']>20:
data.loc[x, 'MARKS'] = 12
print(data.to_string())

ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0 75.0
1 0901IT181002 ADITYA JOSHI 05-25-2021 12.0 NaN
2 0901IT181003 AJAY GARG 25-May-21 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0 85.0
4 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0 55.0
6 0901IT181007 ALOK KUMAR 05-25-2021 13.0 65.0
7 0901IT181008 AMAN DIXIT 25-05-2021 12.0 NaN
8 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0 60.0
9 0901IT181010 ANKIT KUMAR 25-05-2021 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0
11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

[ ]: print(data.duplicated())

[ ]: data.drop_duplicates()

[ ]: data.corr()

[19]: import matplotlib.pyplot as plt

[20]: data =pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')

print(data.to_string())

ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0 75.0
1 0901IT181002 ADITYA JOSHI 05-25-2021 NaN NaN
2 0901IT181003 AJAY GARG 25-May-21 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0 85.0
4 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0 55.0
6 0901IT181007 ALOK KUMAR 05-25-2021 13.0 65.0

14
 7 0901IT181008 AMAN DIXIT 25-05-2021 NaN NaN
8 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0 60.0
9 0901IT181010 ANKIT KUMAR 25-05-2021 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0
11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

[21]: data.plot()
plt.show()

[22]: data = pd.read_csv('/content/SAMPLE_FOR_CLEANING.csv')

data['MARKS'].fillna(12, inplace=True)
data['PERCENTAGE'].fillna(60, inplace=True)
data

[22]: ROLL. NO. STUDENT_NAME DATE OF EXAM MARKS PERCENTAGE

0 0901IT181001 AADITYA KHANTAL 25-05-2021 15.0 75.0
1 0901IT181002 ADITYA JOSHI 05-25-2021 12.0 60.0
2 0901IT181003 AJAY GARG 25-May-21 16.0 80.0
3 0901IT181004 AKASH KACHHAWAY 25-05-2021 17.0 85.0
4 0901IT181005 AKSHAT KOTHAVADE 25-05-2021 12.0 60.0
5 0901IT181006 ALAKH NIRANJAN THAKURIYA 05-25-2021 11.0 55.0
6 0901IT181007 ALOK KUMAR 05-25-2021 13.0 65.0
7 0901IT181008 AMAN DIXIT 25-05-2021 12.0 60.0
8 0901IT181009 AMIT BAMNIYA 25-05-2021 12.0 60.0
9 0901IT181010 ANKIT KUMAR 25-05-2021 12.5 62.5
10 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

15
 11 0901IT181011 ANKIT RAJ TIRKEY 25-May-21 13.0 65.0

[ ]: data.plot()
plt.show()

[24]: data.plot(kind='bar')
plt.show()

16