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'])

import pandas as pd
from functools import reduce

# compile the list of dataframes you want to merge
data_frames = [df1, df2, df3]
df_merged = reduce(lambda  left,right: pd.merge(left,right,on=['key_col'],
                                            how='outer'), data_frames)

# 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)]

m = {'left_only': 'df1', 'right_only': 'df2', 'both': 'df1, df2'}

result = df1.merge(df2, on=['A'], how='outer', indicator='B')
result['B'] = result['B'].map(m)

result