1/20/22, 9:59 PM 3a Data Frame - Jupyter Notebook

In [1]: # Pandas DataFrame

In [2]: # import packages

import pandas as pd
import numpy as np
​
test =[1,2,3,4,5]
test
​
​

Out[2]: [1, 2, 3, 4, 5]

In [2]: df1 = pd.Series(test)

df1
​

...

In [3]: df = pd.DataFrame(test)
df

...

In [3]: ## Creating a Table

table = [['srinu',25],['kishore',26],['mani',27],['ratna',28]]
​
table
​
​

...

In [4]: df = pd.DataFrame(table,columns =['Name','Age'])

​
df

...

In [3]: table1 = {'Name':['srinu','kishore','mani','ratna'],'Age':[25,26,27,28]}

​
df = pd.DataFrame(table1,index=[1,2,3,4])
​
df
​
​
​

...

localhost:8890/notebooks/3 Numpy and Pandas/3a Data Frame.ipynb 1/5

1/20/22, 9:59 PM 3a Data Frame - Jupyter Notebook

In [4]: ## Columns Selection , deletion , addition

df['weight'] = pd.Series([65,75,85,90],index = [1,2,3,4])
​
df
​

...

In [5]: df['height'] = pd.Series([150,151,152,153],index = [1,2,3,4])

df

...

In [3]: # creating the table

table12 = {'Name':['srinu','kishore','mani','ratna','ramu'],'Age':[25,26,27,28,29
table12
td = pd.DataFrame(table12,index=[1,2,3,4,5])
td
​

Out[3]: Name Age height weight

1 srinu 25 151 65

2 kishore 26 152 76

3 mani 27 153 78

4 ratna 28 154 87

5 ramu 29 155 88

In [4]: # deleting the column

del td['Age']
td
# other method to delete the column
#td.pop('two')

Out[4]: Name height weight

1 srinu 151 65

2 kishore 152 76

3 mani 153 78

4 ratna 154 87

5 ramu 155 88

In [5]: ​
td

...

localhost:8890/notebooks/3 Numpy and Pandas/3a Data Frame.ipynb 2/5

1/20/22, 9:59 PM 3a Data Frame - Jupyter Notebook

In [6]: # row selection

td.iloc[3:5]
# giving the index number to select the particular Row

...

In [13]: # multiple Selection

td[1:5]

...

In [9]: # Addition of Rows to existing

df = pd.DataFrame([[1,2],[3,4]],columns=['a','b'])

In [10]: df

...

In [11]: df2 = pd.DataFrame([[5,6],[7,8]],columns=['a','b'])

df2

...

In [12]: ## To add rows

df = df.append(df2)
df
​

...

In [13]: ​
df = pd.DataFrame([[1,2],[3,4]],columns=['a','b'])
df2 = pd.DataFrame([[5,6],[7,8]],columns=['a','b'])
df = df.append(df2)
df
​

...

In [19]: td
td.head(6)

Out[19]: Name height weight

1 srinu 151 65

2 kishore 152 76

3 mani 153 78

4 ratna 154 87

5 ramu 155 88

In [23]: td.tail(3)

...

localhost:8890/notebooks/3 Numpy and Pandas/3a Data Frame.ipynb 3/5

1/20/22, 9:59 PM 3a Data Frame - Jupyter Notebook

In [1]: import pandas as pd

In [14]: df1=pd.DataFrame(
{"emp_id":[1,2,5,4],'Name': ["Alex","John","Abhishek","Watson"], 'Age': [25,3

In [15]: df2=pd.DataFrame(
{"emp_id":[1,2,3,4],'Name': ["Alex","John","Krishna","Abhishek"], 'Weight': [

In [4]: df1

Out[4]: emp_id Name Age

0 1 Alex 25

1 2 John 30

2 5 Abhishek 24

3 4 Watson 20

In [5]: df2

Out[5]: emp_id Name Weight

0 1 Alex 60

1 2 John 65

2 3 Krishna 70

3 4 Abhishek 75

In [6]: pd.merge(df1,df2)

Out[6]: emp_id Name Age Weight

0 1 Alex 25 60

1 2 John 30 65

In [7]: pd.merge(df1,df2,how="outer")

Out[7]: emp_id Name Age Weight

0 1 Alex 25.0 60.0

1 2 John 30.0 65.0

2 5 Abhishek 24.0 NaN

3 4 Watson 20.0 NaN

4 3 Krishna NaN 70.0

5 4 Abhishek NaN 75.0

localhost:8890/notebooks/3 Numpy and Pandas/3a Data Frame.ipynb 4/5

1/20/22, 9:59 PM 3a Data Frame - Jupyter Notebook

In [8]: pd.merge(df1,df2,how="outer",on=["Name"])
​
# it will add the based on the name columns
​

Out[8]: emp_id_x Name Age emp_id_y Weight

0 1.0 Alex 25.0 1.0 60.0

1 2.0 John 30.0 2.0 65.0

2 5.0 Abhishek 24.0 4.0 75.0

3 4.0 Watson 20.0 NaN NaN

4 NaN Krishna NaN 3.0 70.0

In [ ]: ​

localhost:8890/notebooks/3 Numpy and Pandas/3a Data Frame.ipynb 5/5