DATAFRAMES - MERGE & CONCAT | GRADE XII | 7 NOV

CONCATENATE DATAFRAMES

GRADE XII

#The concat() function is used to join more than one dataframe into one unit. 

#You can combine dataframes having similar structures.

import pandas as pd

'''

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])

df3 = pd.DataFrame(

    {

        "A": ["A8", "A9", "A10", "A11"],

        "B": ["B8", "B9", "B10", "B11"],

        "C": ["C8", "C9", "C10", "C11"],

        "D": ["D8", "D9", "D10", "D11"],

    },

    index=[8, 9, 10, 11])

frames = [df1, df2, df3]

result = pd.concat(frames)

print(result)

result1 = pd.concat([df1, df3], axis=1) # Concat Columnwise

print(result1)

print("*"*40)

result2 = pd.concat([df1, df3], axis=0) # concat row wise

print(result2)

print("*"*40)

result3 = pd.concat([df1, df3], ignore_index=True)

print(result3)

'''

'''

#You can add ignore_index = true to avoid using the same original index of dataframes. 

dt_sc=({'English':[74,79,48,53,68,44,65,67],

         'Physics':[76,78,80,76,73,55,49,60],

         'Chemistry':[57,74,55,89,70,50,60,80],})

xii_1=pd.DataFrame(dt_sc)

dt_co=({'English':[66,65,87,56,86,44,56,76],

         'Physics':[67,87,80,67,77,55,45,80],

         'Chemistry':[75,47,55,98,70,50,60,80],})

xii_2=pd.DataFrame(dt_co)

xii=pd.concat([xii_1,xii_2])

#print(xii)

#You can add ignore_index = true to avoid using the same 

#original index of dataframes

#observe the output

xii=pd.concat([xii_1,xii_2],ignore_index=True)

print(xii)

'''

#It is used to merge two dataframes that have some common values. 

#You can specify the fields as on parameter in the merge() function. 

#It follows the concept of RDBMS having parent column and child columns in the dataframe. 

#One column should have common data. 

p1=({'P_ID':[1,2,5,4,5],

         'First_Name':['Sachin','Saurav','Virendra','Mahendra Sinh','Gautam'],

         'Last_Name':['Tendulker','Ganguly','Sehvag','Dhoni','Gambhir']})

d1=pd.DataFrame(p1)

print(d1)

print("*"*40)

p2=({'P_ID':[1,2,3,4,5],

         'Runs':[18987,12120,11345,10345,12789]})

d2=pd.DataFrame(p2)

print(d2)

print("*"*40)

players=pd.merge(d1,d2)

print(players)

'''

# MERGING OF DATAFRAMES

left = pd.DataFrame(

    {

        "key": ["K0", "K1", "K2", "K3"],

        "A": ["A0", "A1", "A2", "A3"],

        "B": ["B0", "B1", "B2", "B3"],

    }

)

right = pd.DataFrame(

    {

        "key": ["K0", "K1", "K2", "K3"],

        "C": ["C0", "C1", "C2", "C3"],

        "D": ["D0", "D1", "D2", "D3"],

    }

)

#result = pd.merge(left, right, on="key")

result = pd.merge(left, right)

print(result)

# Define a dictionary containing employee data 

data1 = {'key': ['K0', 'K1', 'K2', 'K3'],

         'key1': ['K0', 'K1', 'K0', 'K1'],

         'Name':['Jai', 'Princi', 'Gaurav', 'Anuj'], 

        'Age':[27, 24, 22, 32],} 

   

# Define a dictionary containing employee data 

data2 = {'key': ['K0', 'K1', 'K2', 'K3'],

         'key1': ['K0', 'K0', 'K0', 'K0'],

         'Address':['Nagpur', 'Kanpur', 'Allahabad', 'Kannuaj'], 

        'Qualification':['Btech', 'B.A', 'Bcom', 'B.hons']} 

 

# Convert the dictionary into DataFrame  

df = pd.DataFrame(data1)

print("*"*40)

# Convert the dictionary into DataFrame  

df1 = pd.DataFrame(data2) 

print(df, "\n\n", df1) 

print("*"*40)

#Now we merge dataframe using multiple keys # merging dataframe using multiple keys

res1 = pd.merge(df, df1, on=['key', 'key1'])

print(res1)

#print("*"*40)

#res = pd.merge(df, df1, how='left', on=['key', 'key1'])

#print(res)

print("*"*40)

res = pd.merge(df, df1, how='right', on=['key', 'key1'])

print(res)

#In order to join dataframe, we use .

#join() function this function is used for combining the columns of two 

#potentially differently-indexed DataFrames into a single result DataFrame.

 # Define a dictionary containing employee data 

data1 = {'Name':['Jai', 'Princi', 'Gaurav', 'Anuj'], 

        'Age':[27, 24, 22, 32]} 

    

# Define a dictionary containing employee data 

data2 = {'Address':['Allahabad', 'Kannuaj', 'Allahabad', 'Kannuaj'], 

        'Qualification':['MCA', 'Phd', 'Bcom', 'B.hons']} 

  

# Convert the dictionary into DataFrame  

df = pd.DataFrame(data1,index=['K0', 'K1', 'K2', 'K3'])

# Convert the dictionary into DataFrame  

df1 = pd.DataFrame(data2, index=['K0', 'K2', 'K3', 'K4'])

# joining dataframe

res = df.join(df1)

print(res)

 print(df, "\n\n", df1)