creating empty dataframe

#import the pandas library and aliasing as pd
import pandas as pd
df = pd.DataFrame()
print df

_____________________________________

create dataframe from list

import pandas as pd
data = [1,2,3,4,5]
df = pd.DataFrame(data)
print df

______________________________________

create dataframe from list example 2

import pandas as pd
data = [['Alex',10],['Bob',12],['Clarke',13]]
df = pd.DataFrame(data,columns=['Name','Age'])
print df

________________________________________

example 3

import pandas as pd
data = [['Alex',10],['Bob',12],['Clarke',13]]
df = pd.DataFrame(data,columns=['Name','Age'],dtype=float)
print df

__________________________________________

Create a DataFrame from Dict of ndarrays / Lists

import pandas as pd
data = {'Name':['Tom', 'Jack', 'Steve', 'Ricky'],'Age':[28,34,29,42]}
df = pd.DataFrame(data)
print df

__________________________________________

example 2

import pandas as pd
data = {'Name':['Tom', 'Jack', 'Steve', 'Ricky'],'Age':[28,34,29,42]}
df = pd.DataFrame(data, index=['rank1','rank2','rank3','rank4'])
print df

_______________________________________________

Create a DataFrame from List of Dicts

example 1

import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]
df = pd.DataFrame(data)
print df

_____________________________________________

example 2

import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]
df = pd.DataFrame(data, index=['first', 'second'])
print df

______________________________________________

example 3

import pandas as pd
data = [{'a': 1, 'b': 2},{'a': 5, 'b': 10, 'c': 20}]

#With two column indices, values same as dictionary keys
df1 = pd.DataFrame(data, index=['first', 'second'], columns=['a', 'b'])

#With two column indices with one index with other name
df2 = pd.DataFrame(data, index=['first', 'second'], columns=['a', 'b1'])
print df1
print df2

________________________________________________

Create a DataFrame from Dict of Series

import pandas as pd

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

df = pd.DataFrame(d)
print df

_____________________________________________

Column Selection

import pandas as pd

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

df = pd.DataFrame(d)
print df ['one']
_________________________________________

adding a new column

import pandas as pd

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

df = pd.DataFrame(d)

# Adding a new column to an existing DataFrame object with column label by passing new series

print ("Adding a new column by passing as Series:")
df['three']=pd.Series([10,20,30],index=['a','b','c'])
print df

print ("Adding a new column using the existing columns in DataFrame:")
df['four']=df['one']+df['three']

print df

_______________________________________________

Column Deletion

# Using the previous DataFrame, we will delete a column
# using del function
import pandas as pd

d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']), 
   'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']), 
   'three' : pd.Series([10,20,30], index=['a','b','c'])}

df = pd.DataFrame(d)
print ("Our dataframe is:")
print df

# using del function
print ("Deleting the first column using DEL function:")
del df['one']
print df

# using pop function
print ("Deleting another column using POP function:")
df.pop('two')
print df

___________________________________________

Row Selection, Addition and Deletion

Selection by label

import pandas as pd

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

df = pd.DataFrame(d)
print df.loc['b']

__________________________________________

Selection by integer location

import pandas as pd

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

df = pd.DataFrame(d)
print df.iloc[2]

______________________________________________

Slice Rows

import pandas as pd

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

df = pd.DataFrame(d)
print df[2:4]

_____________________________________
Addition of Rows

import pandas as pd

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

df = df.append(df2)
print df

___________________________________________

Deletion of Rows

import pandas as pd

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

df = df.append(df2)

# Drop rows with label 0
df = df.drop(0)

print df

_________________________________________

iteritems()

import pandas as pd
import numpy as np
dc={2015:{'Qtr1':34500,'Qtr2':56000,'Qtr3':47000,'Qtr4':49000},2016:{'Qtr1':44900,'Qtr2':46100,'Qtr3':57000,'Qtr4':59000},2017:{'Qtr1':54500,'Qtr2':51000,'Qtr3':57000,'Qtr4':58500}}
df=pd.DataFrame(dc)
for key,value in df.iteritems():
   print(key,value)

_____________________________________________________

iterrows

import pandas as pd
import numpy as np
dc={2015:{'Qtr1':34500,'Qtr2':56000,'Qtr3':47000,'Qtr4':49000},2016:{'Qtr1':44900,'Qtr2':46100,'Qtr3':57000,'Qtr4':59000},2017:{'Qtr1':54500,'Qtr2':51000,'Qtr3':57000,'Qtr4':58500}}
df=pd.DataFrame(dc)
for key,value in df.iterrows():
   print(key,value)

__________________________________________________________

loc function to get a value from dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.loc['Row_2', 'Name']

# Print the result 
print(result)
___________________________________________________

loc function to access multiple rows

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.loc['Row_2':'Row_4',:]

# Print the result
print(result)

___________________________________________________________

loc function to access selective columns

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.loc[:,'Name':'Age',]

# Print the result
print(result)

_________________________________________________________

loc function to access range of columns from a range of rows

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.loc["Row_1":"Row_3",'Name':'Age',]

# Print the result
print(result)

_____________________________________________________

iloc function to access rows and columns from dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.iloc[0:2,1:3]

# Print the result
print(result)

____________________________________________________

select or accessing individual value using column name

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.Weight[0]

# Print the result
print(result)

__________________________________________________________

access individual element using index and column name

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
result = df.Weight['Row_1']

# Print the result
print(result)

_____________________________________________________

modify column value in a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
df.Weight['Row_1']=90

print(df)
______________________________________________

modify row in a dataframe using at function

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
df.at['Row_1']=99

print(df)

____________________________________________________

modify row in a dataframe using loc function

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
df.loc['Row_1']=99

print(df)

_________________________________________________

adding column to a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
df['Class']=[12,11,10,9,9]

print(df)

________________________________________________________

delete a column from a dataframe using del statement

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


# return the value
del df["Weight"]

print(df)

__________________________________________

min function to get minimum values from a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.min())

________________________________________________

max function to get maximum values in a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.max())

__________________________________________________________

mode function to sort the records

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.mode())

__________________________________________________

mean function to find mean of values

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.mean())

________________________________________________________

median function to get median value

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.median())

____________________________________________________

count function

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.count())

___________________________________________________

sum function

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)


print(df.sum())

____________________________________________________

apply a function on a column

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df['Weight'].min())

______________________________________________

apply functions on multiple columns

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df[['Weight','Age']].min())

___________________________________________________

example 2 apply function on multiple columns

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df[['Weight','Age']].count())

______________________________________________________________

apply functions on a row of a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df.loc['Row_1':].max())

________________________________________

apply function on a range of rows of a dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df.loc['Row_1':'Row_3'].count())

_______________________________________________________

apply function to subset of dataframe

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)

print(df.loc['Row_1':'Row_2','Weight':'Age'].max())

____________________________________________________

pivot function

# importing pandas as pd
import pandas as pd
d1={'Tutor':['Tahira','Gurjyot','Anusha','Jacob','Venkat'],
'Classes':[28,36,41,32,40],
'Country':['USA','UK','Japan','USA','Brazil']
}
dfd=pd.DataFrame(d1)
print(dfd)
dfd2=dfd.pivot(index='Country',columns='Tutor',values='Classes')
print(dfd2)

_________________________________________________________

sort_values function

# importing pandas as pd
import pandas as pd
d1={'Tutor':['Tahira','Gurjyot','Anusha','Jacob','Venkat'],
'Classes':[28,36,41,32,40],
'Country':['USA','UK','Japan','USA','Brazil']
}
dfd=pd.DataFrame(d1)
print(dfd)
dfd2=dfd.sort_values('Country')
print(dfd2)

_________________________________________________

create histogram 

# importing pandas as pd
import pandas as pd
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame({'Weight':[45, 88, 56, 15, 71],
                   'Name':['Sam', 'Andrea', 'Alex', 'Robin', 'Kia'],
                   'Age':[14, 25, 55, 8, 21]},index=index_)
print(df)
import matplotlib.pyplot as plt
plt.interactive(True)

plt.show(df.hist(column='Age'))

_________________________________________________________

pipe function

import pandas as pd
import numpy as np
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']
# Creating the DataFrame
df = pd.DataFrame([45, 88, 56, 15, 71])
print(df)
df=df.pipe(np.add,30).pipe(np.multiply,3)
print(df)

________________________________________________________________________

apply function

import pandas as pd;
def fun(num):
  
    if num<200: 
        return "Low"
  
    elif num>= 200 and num<400: 
        return "Normal"
  
    else: 
        return "High"

src=pd.Series([1000,20,300,400]);
print(src);
new=src.apply(fun)
print(new)

________________________________________________________

applymap

import pandas as pd;
src=pd.DataFrame(['abc','xyx','xyz']);
src=src.applymap(lambda x: str(x) + '_X')
print(src)

_______________________________________________________________

group by function

import pandas as pd

# Define a dictionary containing employee data
data1 = {'Name':['Jai', 'Anuj', 'Jai', 'Princi',
                 'Gaurav', 'Anuj', 'Princi', 'Abhi'],
        'Age':[27, 24, 22, 32,
               33, 36, 27, 32],
        'Address':['Nagpur', 'Kanpur', 'Allahabad', 'Kannuaj',
                   'Jaunpur', 'Kanpur', 'Allahabad', 'Aligarh'],
        'Qualification':['Msc', 'MA', 'MCA', 'Phd',
                         'B.Tech', 'B.com', 'Msc', 'MA']}


# Convert the dictionary into DataFrame
df = pd.DataFrame(data1)

print(df)

df.groupby('Name')
print(df.groupby('Name').groups) 

____________________________________________________________________

agg function


# importing pandas module
import pandas as pd

# importing numpy module
import numpy as np

# creating random arr of 10 elements
arr=np.random.randn(10)

# creating series from array
series=pd.Series(arr)

# calling .agg() method 
result=series.agg(lambda num : num + 2)

# display
print('Array before operation: \n', series,
      '\n\nArray after operation: \n',result)

______________________________________________________

transform function

import pandas as pd

# Creating the DataFrame
df = pd.DataFrame({"A":[12, 4, 5, None, 1],
                   "B":[7, 2, 54, 3, None],
                   "C":[20, 16, 11, 3, 8],
                   "D":[14, 3, None, 2, 6]})

# Create the index
index_ = ['Row_1', 'Row_2', 'Row_3', 'Row_4', 'Row_5']

# Set the index
df.index = index_

# Print the DataFrame
print(df)


# add 10 to each element of the dataframe
result = df.transform(func = lambda x : x + 10)

# Print the result
print(result)

_____________________________________________________

rename function

import pandas as pd

d = {'one' : pd.Series([1, 2, 3], index=['a', 'b', 'c']),
   'two' : pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']),
   'three' : pd.Series([10,20,30], index=['a','b','c'])}

df = pd.DataFrame(d)
print ("Our dataframe is:")
print(df)
df.rename(index = {"a": "A",
                     "b":"B","c":"C","d":"D"},
                                 inplace = True)

print(df)

_______________________________________________

reindex function


# importing pandas as pd
import pandas as pd

# Creating the dataframe
df = pd.DataFrame({"A":[1, 5, 3, 4, 2],
                   "B":[3, 2, 4, 3, 4],
                   "C":[2, 2, 7, 3, 4],
                   "D":[4, 3, 6, 12, 7]},
                   index =["first", "second", "third", "fourth", "fifth"])

# Print the dataframe
print(df)
df=df.reindex(["first", "dues", "trois", "fourth", "fifth"])
print(df)

_________________________________________________________________

reindex_like function

# importing pandas as pd
import pandas as pd

# Creating the first dataframe
df1 = pd.DataFrame({"A":[1, 5, 3, 4, 2],
                    "B":[3, 2, 4, 3, 4],
                    "C":[2, 2, 7, 3, 4],
                    "D":[4, 3, 6, 12, 7]},
                    index =["A1", "A2", "A3", "A4", "A5"])

# Creating the second dataframe
df2 = pd.DataFrame({"A":[10, 11, 7, 8, 5],
                    "B":[21, 5, 32, 4, 6],
                    "C":[11, 21, 23, 7, 9],
                    "D":[1, 5, 3, 8, 6]},
                     index =["A1", "A3", "A4", "A7", "A8"])

# Print the first dataframe
print(df1)

# Print the second dataframe
print(df2)


# find matching indexes
df1=df1.reindex_like(df2)

print(df1)
____________________________________________________________