Curso Manipulación de datos con Pandas

Por

Ing. Catalina Urdaneta

MERGE

MERGE

LEFT JOIN

UNION ALL

RIGHT JOIN

INNER JOIN

RESULTADO

INNER JOIN

import pandas as pd

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})
  
result = pd.merge(left, right, how='inner', on=['key1', 'key2'])

print(result)

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})


right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})
  

result = pd.merge(left, right, on=['key1', 'key2'])

RESULTADO

LEFT JOIN

import pandas as pd

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})
  
result = pd.merge(left, right, how='left', on=['key1', 'key2'])

print(result)

RESULTADO

RIGHT JOIN

import pandas as pd

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})
  
result = pd.merge(left, right, how='right', on=['key1', 'key2'])

print(result)

RESULTADO

UNION ALL

import pandas as pd

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                     'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})
  
result = pd.merge(left, right, how='outer', on=['key1', 'key2'])

print(result)

BONUS!

Chequear llaves repetidas

Indicador de fusión

Tipo de dato

import pandas as pd

left = pd.DataFrame({'A' : [1,2], 'B' : [1, 2]})
right = pd.DataFrame({'A' : [4,5,6], 'B': [2, 2, 2]})
result = pd.merge(left, right, on='B', how='outer', validate="one_to_one")
pd.merge(left, right, on='B', how='outer', validate="one_to_many")

df1 = pd.DataFrame({'col1': [0, 1], 'col_left': ['a', 'b']})
df2 = pd.DataFrame({'col1': [1, 2, 2], 'col_right': [2, 2, 2]})
pd.merge(df1, df2, on='col1', how='outer', indicator=True)

left = pd.DataFrame({'key': [1], 'v1': [10]})
right = pd.DataFrame({'key': [1, 2], 'v1': [20, 30]})
result = pd.merge(left, right, how='outer')
types = pd.merge(left, right, how='outer').dtypes
print(result)
print(types)

Gracias

https://slides.com/curdanetab/python-merge

Ing. Catalina Urdaneta