0fe6aafe48a44cf8ec6f5a86ac3d212622074150,recordlinkage/index.py,SortedNeighbourhood,_link_index,#SortedNeighbourhood#Any#Any#,250

Before Change

        data_right = df_b[listify(right_on) + block_right_on].dropna(
            axis=0, how="any", inplace=False
        )
        data_right.columns = ["sorting_key"] + \
            ["blocking_key_%d" % i for i, v in enumerate(block_right_on)]
        data_right["index_y"] = data_right.index

        // sorting_key_values is the terminology in Data Matching [Christen,
        // 2012]

After Change

            df_a[listify(left_on) + block_left_on], copy=False)
        data_left.columns = blocking_keys
        data_left["index_x"] = numpy.arange(len(df_a))
        data_left.dropna(axis=0, how="any", subset=blocking_keys, inplace=True)

        data_right = pandas.DataFrame(
            df_b[listify(right_on) + block_right_on], copy=False)
        data_right.columns = blocking_keys

Instances