पाइथन पांडास मर्जिंग: डेटा विश्लेषण के लिए डेटाफ़्रेम जॉइनिंग रणनीतियों में महारत हासिल करना

            import pandas as pd

# DataFrame 1: Customer Orders
df_orders = pd.DataFrame({
 'order_id': [1, 2, 3, 4, 5],
 'customer_id': [101, 102, 103, 104, 105],
 'product_id': [1, 2, 1, 3, 2],
 'quantity': [2, 1, 3, 1, 2]
})

# DataFrame 2: Customer Information
df_customers = pd.DataFrame({
 'customer_id': [101, 102, 103, 106],
 'customer_name': ['Alice', 'Bob', 'Charlie', 'David'],
 'country': ['USA', 'Canada', 'UK', 'Australia']
})

# Inner Join
df_inner = pd.merge(df_orders, df_customers, on='customer_id', how='inner')
print(df_inner)

            

              
                Copy
              
            
          

             order_id  customer_id  product_id  quantity customer_name country
0         1          101           1         2         Alice     USA
1         2          102           2         1           Bob  Canada
2         3          103           1         3       Charlie      UK

            

              
                Copy
              
            
          

            # Outer Join
df_outer = pd.merge(df_orders, df_customers, on='customer_id', how='outer')
print(df_outer)

            

              
                Copy
              
            
          

               order_id  customer_id  product_id  quantity customer_name    country
0       1.0          101         1.0       2.0         Alice        USA
1       2.0          102         2.0       1.0           Bob     Canada
2       3.0          103         1.0       3.0       Charlie         UK
3       4.0          104         3.0       1.0           NaN        NaN
4       5.0          105         2.0       2.0           NaN        NaN
5       NaN          106         NaN       NaN         David   Australia

            

              
                Copy
              
            
          

            # Left Join
df_left = pd.merge(df_orders, df_customers, on='customer_id', how='left')
print(df_left)

            

              
                Copy
              
            
          

               order_id  customer_id  product_id  quantity customer_name country
0         1          101           1         2         Alice     USA
1         2          102           2         1           Bob  Canada
2         3          103           1         3       Charlie      UK
3         4          104           3         1           NaN     NaN
4         5          105           2         2           NaN     NaN

            

              
                Copy
              
            
          

            # Right Join
df_right = pd.merge(df_orders, df_customers, on='customer_id', how='right')
print(df_right)

            

              
                Copy
              
            
          

               order_id  customer_id  product_id  quantity customer_name    country
0       1.0          101         1.0       2.0         Alice        USA
1       2.0          102         2.0       1.0           Bob     Canada
2       3.0          103         1.0       3.0       Charlie         UK
3       NaN          106         NaN       NaN         David   Australia

            

              
                Copy
              
            
          

            # DataFrame 1: Customer Orders with Customer ID as Index
df_orders_index = df_orders.set_index('customer_id')

# DataFrame 2: Customer Information with Customer ID as Index
df_customers_index = df_customers.set_index('customer_id')

# Join on Index (Left Join)
df_join_index = df_orders_index.join(df_customers_index, how='left')
print(df_join_index)

            

              
                Copy
              
            
          

               order_id  product_id  quantity customer_name country
customer_id                                        
101                 1           1         2         Alice     USA
102                 2           2         1           Bob  Canada
103                 3           1         3       Charlie      UK
104                 4           3         1           NaN     NaN
105                 5           2         2           NaN     NaN

            

              
                Copy
              
            
          

            # Joining on a column
df_join_column = df_orders.join(df_customers.set_index('customer_id'), on='customer_id', how='left')
print(df_join_column)

            

              
                Copy
              
            
          

               order_id  customer_id  product_id  quantity customer_name country
0         1          101           1         2         Alice     USA
1         2          102           2         1           Bob  Canada
2         3          103           1         3       Charlie      UK
3         4          104           3         1           NaN     NaN
4         5          105           2         2           NaN     NaN

            

              
                Copy
              
            
          

            # DataFrame 1: Product Information
df_products1 = pd.DataFrame({
 'product_id': [1, 2, 3],
 'product_name': ['Product A', 'Product B', 'Product C'],
 'price': [10, 20, 15]
})

# DataFrame 2: Product Information (with potentially updated prices)
df_products2 = pd.DataFrame({
 'product_id': [1, 2, 4],
 'product_name': ['Product A', 'Product B', 'Product D'],
 'price': [12, 18, 25]
})

# Merge with suffixes
df_merged_suffixes = pd.merge(df_products1, df_products2, on='product_id', suffixes=('_old', '_new'))
print(df_merged_suffixes)

            

              
                Copy
              
            
          

               product_id product_name_old  price_old product_name_new  price_new
0           1      Product A         10       Product A         12
1           2      Product B         20       Product B         18

            

              
                Copy
              
            
          

            # Join with lsuffix and rsuffix
df_products1_index = df_products1.set_index('product_id')
df_products2_index = df_products2.set_index('product_id')
df_joined_suffixes = df_products1_index.join(df_products2_index, lsuffix='_old', rsuffix='_new', how='outer')
print(df_joined_suffixes)

            

              
                Copy
              
            
          

                      product_name_old  price_old product_name_new  price_new
product_id                                                     
1                 Product A       10.0        Product A       12.0
2                 Product B       20.0        Product B       18.0
3                 Product C       15.0            NaN        NaN
4                       NaN        NaN        Product D       25.0

            

              
                Copy
              
            
          

            # Sales Transactions Data
df_sales = pd.DataFrame({
 'transaction_id': [1, 2, 3, 4, 5],
 'product_id': [101, 102, 103, 101, 104],
 'quantity': [2, 1, 3, 1, 2],
 'sales_date': ['2023-01-15', '2023-02-20', '2023-03-10', '2023-04-05', '2023-05-01']
})

# Product Information Data
df_products = pd.DataFrame({
 'product_id': [101, 102, 103, 104],
 'product_name': ['Laptop', 'Mouse', 'Keyboard', 'Monitor'],
 'category': ['Electronics', 'Electronics', 'Electronics', 'Electronics'],
 'price': [1200, 25, 75, 300]
})

# Merge Sales Data with Product Information
df_sales_enriched = pd.merge(df_sales, df_products, on='product_id', how='left')
print(df_sales_enriched)

            

              
                Copy
              
            
          

               transaction_id  product_id  quantity sales_date product_name     category   price
0               1         101         2   2023-01-15       Laptop  Electronics  1200
1               2         102         1   2023-02-20        Mouse  Electronics    25
2               3         103         3   2023-03-10     Keyboard  Electronics    75
3               4         101         1   2023-04-05       Laptop  Electronics  1200
4               5         104         2   2023-05-01      Monitor  Electronics   300

            

              
                Copy
              
            
          

            # Customer Data
df_customers = pd.DataFrame({
 'customer_id': [1, 2, 3, 4, 5],
 'customer_name': ['Alice', 'Bob', 'Charlie', 'David', 'Eve'],
 'city': ['New York', 'London', 'Tokyo', 'Sydney', 'Berlin']
})

# Demographic Information Data
df_demographics = pd.DataFrame({
 'city': ['New York', 'London', 'Tokyo', 'Sydney', 'Berlin'],
 'population': [8419000, 8982000, 13960000, 5312000, 3769000],
 'average_income': [75000, 65000, 85000, 90000, 55000]
})

# Merge Customer Data with Demographic Information
df_customer_demographics = pd.merge(df_customers, df_demographics, on='city', how='left')
print(df_customer_demographics)

            

              
                Copy
              
            
          

               customer_id customer_name      city  population  average_income
0            1         Alice  New York     8419000           75000
1            2           Bob    London     8982000           65000
2            3       Charlie     Tokyo    13960000           85000
3            4         David    Sydney     5312000           90000
4            5           Eve    Berlin     3769000           55000

            

              
                Copy
              
            
          

            # Supplier Data
df_suppliers = pd.DataFrame({
 'supplier_id': [1, 2, 3],
 'supplier_name': ['GlobalTech', 'EuroParts', 'AsiaSource'],
 'location': ['Taiwan', 'Germany', 'China']
})

# Shipping Data
df_shipments = pd.DataFrame({
 'shipment_id': [101, 102, 103, 104],
 'supplier_id': [1, 2, 3, 1],
 'destination': ['USA', 'Canada', 'Australia', 'Japan'],
 'shipment_date': ['2023-01-10', '2023-02-15', '2023-03-20', '2023-04-25']
})


# Merge Supplier and Shipment Data
df_supply_chain = pd.merge(df_shipments, df_suppliers, on='supplier_id', how='left')

print(df_supply_chain)

            

              
                Copy
              
            
          

               shipment_id  supplier_id destination shipment_date supplier_name location
0          101            1         USA    2023-01-10     GlobalTech   Taiwan
1          102            2      Canada    2023-02-15      EuroParts  Germany
2          103            3   Australia    2023-03-20     AsiaSource    China
3          104            1       Japan    2023-04-25     GlobalTech   Taiwan

            

              
                Copy
              
            
          

            # DataFrame 1
df1 = pd.DataFrame({
 'product_id': [1, 1, 2, 2],
 'color': ['red', 'blue', 'red', 'blue'],
 'quantity': [10, 15, 20, 25]
})

# DataFrame 2
df2 = pd.DataFrame({
 'product_id': [1, 1, 2, 2],
 'color': ['red', 'blue', 'red', 'blue'],
 'price': [5, 7, 8, 10]
})

# Merge on multiple columns
df_merged_multiple = pd.merge(df1, df2, on=['product_id', 'color'], how='inner')
print(df_merged_multiple)

            

              
                Copy
              
            
          

               product_id color  quantity  price
0           1   red        10      5
1           1  blue        15      7
2           2   red        20      8
3           2  blue        25     10

            

              
                Copy
              
            
          

            # DataFrame 1
df1 = pd.DataFrame({
 'product_id': [1, 2, 3],
 'product_name': ['Product A', 'Product B', 'Product C']
})

# DataFrame 2
df2 = pd.DataFrame({
 'id': [1, 2, 4],
 'price': [10, 20, 25]
})

# Merge with different column names
df_merged_different = pd.merge(df1, df2, left_on='product_id', right_on='id', how='left')
print(df_merged_different)

            

              
                Copy
              
            
          

               product_id product_name   id   price
0           1    Product A  1.0    10.0
1           2    Product B  2.0    20.0
2           3    Product C  NaN     NaN

            

              
                Copy
              
            
          

            # Merge with indicator
df_merged_indicator = pd.merge(df_orders, df_customers, on='customer_id', how='outer', indicator=True)
print(df_merged_indicator)

            

              
                Copy
              
            
          

               order_id  customer_id  product_id  quantity customer_name    country      _merge
0       1.0          101         1.0       2.0         Alice        USA        both
1       2.0          102         2.0       1.0           Bob     Canada        both
2       3.0          103         1.0       3.0       Charlie         UK        both
3       4.0          104         3.0       1.0           NaN        NaN   left_only
4       5.0          105         2.0       2.0           NaN        NaN   left_only
5       NaN          106         NaN       NaN         David   Australia  right_only

            

              
                Copy
              
            
          

            # Example with one-to-one validation
df_users = pd.DataFrame({
 'user_id': [1, 2, 3],
 'username': ['john_doe', 'jane_smith', 'peter_jones']
})

df_profiles = pd.DataFrame({
 'user_id': [1, 2, 3],
 'profile_description': ['Software Engineer', 'Data Scientist', 'Project Manager']
})

# Performing a one-to-one merge with validation
merged_df = pd.merge(df_users, df_profiles, on='user_id', validate='one_to_one')

print(merged_df)

            

              
                Copy