join two pandas df code example

Example 1: Joins with another DataFrame

# Joins with another DataFrame

df.join(df2, df.name == df2.name, 'outer').select(
  df.name, df2.height).collect()
# [Row(name=None, height=80), Row(name=u'Bob', height=85), Row(
#   name=u'Alice', height=None)]

df.join(df2, 'name', 'outer').select('name', 'height').collect()
# [Row(name=u'Tom', height=80), Row(name=u'Bob', height=85), Row(
#   name=u'Alice', height=None)]

cond = [df.name == df3.name, df.age == df3.age]
df.join(df3, cond, 'outer').select(df.name, df3.age).collect()
# [Row(name=u'Alice', age=2), Row(name=u'Bob', age=5)]

df.join(df2, 'name').select(df.name, df2.height).collect()
# Row(name=u'Bob', height=85)]

df.join(df4, ['name', 'age']).select(df.name, df.age).collect()
# [Row(name=u'Bob', age=5)]

Example 2: concat two dataframe pandas 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)