PrivacyScanData/target/Pseudonym/dataFrameAnonymizer_7.py

def build_anonymized_dataframe(self, df, partitions) -> DataFrame:
    aggregations = {}
    sensitive_columns = self.sensitive_attribute_columns
    feature_columns = self.feature_columns


    sa_len = len(sensitive_columns)
    for column in feature_columns:
        if self.format_to_str:
            aggregations[column] = self.__agg_column_str
        else:
            aggregations[column] = self.__agg_column_list

    rows = []
    for i, partition in enumerate(partitions):
        dfp = df.loc[partition]
        grouped_columns = dfp.agg(aggregations, squeeze=False)
        values = grouped_columns.to_dict()
        if self.avg_columns:
            # handle average columns and set average instead of interval
            # overwrite column with average
            for avg_col in self.avg_columns:
                col_name = avg_col + '_avg' if not self.AVG_OVERWRITE else avg_col
                if avg_col in feature_columns:
                    avg_val = dfp[avg_col].mean()
                    values.update({col_name: avg_val})

        grouped_sensitive_columns = dfp.groupby(sensitive_columns, as_index=False)
        for grouped_sensitive_value in grouped_sensitive_columns:
            for sensitive_column in sensitive_columns:
                if sa_len > 1:
                    # Value is tuple
                    sensitive_value = grouped_sensitive_value[0][sensitive_columns.index(sensitive_column)]
                else:
                    sensitive_value = grouped_sensitive_value[0]
                count = len(grouped_sensitive_value[1])
                values.update(
                    {
                        sensitive_column: sensitive_value,
                        sensitive_column + "_count": count,
                    }
                )
            rows.append(values.copy())
    return pd.DataFrame(rows)