columns = ['A', 'B', 'C'] data_1 = [[2, 5, 3, 5], [8, 2, 4, 1], [6, 5, 9, 1]] data_1 = np.array(data_1).T df_1 = pd.DataFrame(data=data_1, columns=columns) print (df_1) A B C 0 2 8 6 1 5 2 5 2 3 4 9 3 5 1 1 columns = ['A', 'B', 'C'] data_2 = [[2, 5, 3, 5], [7, 1, 3, 0], [np.nan, np.nan, np.nan, np.nan]] data_2 = np.array(data_2).T df_2 = pd.DataFrame(data=data_2, columns=columns) print (df_2) A B C 0 2.0 7.0 NaN 1 5.0 1.0 NaN 2 3.0 3.0 NaN 3 5.0 0.0 NaN #right join NOT preserve order df1 = df_1.merge(df_2[['A', 'B']], on=['A', 'B'], how='right') print (df1) A B C 0 5 1 1.0 1 2 7 NaN 2 3 3 NaN 3 5 0 NaN 

 A B C 0 2 7 NaN 1 5 1 1 2 3 3 NaN 3 5 0 NaN #left join wpreserve order correct df2 = df_1.merge(df_2[['A', 'B']], on=['A', 'B'], how='left') print (df2) A B C 0 2 8 6 1 5 2 5 2 3 4 9 3 5 1 1 

print (pd.show_versions()) INSTALLED VERSIONS ------------------ commit: None python: 3.7.3.final.0 python-bits: 64 OS: Windows OS-release: 7 machine: AMD64 processor: Intel64 Family 6 Model 60 Stepping 3, GenuineIntel byteorder: little LC_ALL: None LANG: en LOCALE: None.None pandas: 0.24.2 pytest: 4.3.1 pip: 19.0.3 setuptools: 40.8.0 Cython: 0.29.6 numpy: 1.16.2 scipy: 1.2.1 pyarrow: None xarray: None IPython: 7.4.0 sphinx: 1.8.5 patsy: 0.5.1 dateutil: 2.8.0 pytz: 2018.9 blosc: None bottleneck: 1.2.1 tables: 3.5.1 numexpr: 2.6.9 feather: None matplotlib: 3.0.3 openpyxl: 2.6.1 xlrd: 1.2.0 xlwt: 1.3.0 xlsxwriter: 1.1.5 lxml.etree: 4.3.2 bs4: 4.7.1 html5lib: 1.0.1 sqlalchemy: 1.3.1 pymysql: None psycopg2: None jinja2: 2.10 s3fs: None fastparquet: None pandas_gbq: None pandas_datareader: None gcsfs: None None