merge in python code example

Example 1: pd merge on multiple columns

new_df = pd.merge(A_df, B_df,  how='left', left_on=['A_c1','c2'], right_on = ['B_c1','c2'])

Example 2: join on column pandas

# df1 as main df and use the feild from df2 and map it into df1

df1.merge(df2,on='columnName',how='left')

Example 3: Merge Sort python

def merge_sort(arr):
    # The last array split
    if len(arr) <= 1:
        return arr
    mid = len(arr) // 2
    # Perform merge_sort recursively on both halves
    left, right = merge_sort(arr[:mid]), merge_sort(arr[mid:])

    # Merge each side together
    return merge(left, right, arr.copy())


def merge(left, right, merged):

    left_cursor, right_cursor = 0, 0
    while left_cursor < len(left) and right_cursor < len(right):
      
        # Sort each one and place into the result
        if left[left_cursor] <= right[right_cursor]:
            merged[left_cursor+right_cursor]=left[left_cursor]
            left_cursor += 1
        else:
            merged[left_cursor + right_cursor] = right[right_cursor]
            right_cursor += 1
            
    for left_cursor in range(left_cursor, len(left)):
        merged[left_cursor + right_cursor] = left[left_cursor]
        
    for right_cursor in range(right_cursor, len(right)):
        merged[left_cursor + right_cursor] = right[right_cursor]

    return merged

Example 4: pandas merge python

import pandas as pd
df1 = pd.DataFrame({'lkey': ['foo', 'bar', 'baz', 'foo'],
                    'value': [1, 2, 3, 5]})
df2 = pd.DataFrame({'rkey': ['foo', 'bar', 'baz', 'foo'],
                    'value': [5, 6, 7, 8]})
df1.merge(df2, left_on='lkey', right_on='rkey')

Example 5: merge dataframe pandas

>>> df1.merge(df2, left_on='lkey', right_on='rkey')
  lkey  value_x rkey  value_y
0  foo        1  foo        5
1  foo        1  foo        8
2  foo        5  foo        5
3  foo        5  foo        8
4  bar        2  bar        6
5  baz        3  baz        7

Example 6: merge dataframe in python

In [1]: 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])
   ...: 

In [2]: 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])
   ...: 

In [3]: 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])
   ...: 

In [4]: frames = [df1, df2, df3]

In [5]: result = pd.concat(frames)