def pd_read_csv_kwargs()

in src/datasets/packaged_modules/csv/csv.py [0:0]

• 55 lines of code
• 14 McCabe index (conditional complexity)

    def pd_read_csv_kwargs(self):
        pd_read_csv_kwargs = {
            "sep": self.sep,
            "header": self.header,
            "names": self.names,
            "index_col": self.index_col,
            "usecols": self.usecols,
            "prefix": self.prefix,
            "mangle_dupe_cols": self.mangle_dupe_cols,
            "engine": self.engine,
            "converters": self.converters,
            "true_values": self.true_values,
            "false_values": self.false_values,
            "skipinitialspace": self.skipinitialspace,
            "skiprows": self.skiprows,
            "nrows": self.nrows,
            "na_values": self.na_values,
            "keep_default_na": self.keep_default_na,
            "na_filter": self.na_filter,
            "verbose": self.verbose,
            "skip_blank_lines": self.skip_blank_lines,
            "thousands": self.thousands,
            "decimal": self.decimal,
            "lineterminator": self.lineterminator,
            "quotechar": self.quotechar,
            "quoting": self.quoting,
            "escapechar": self.escapechar,
            "comment": self.comment,
            "encoding": self.encoding,
            "dialect": self.dialect,
            "error_bad_lines": self.error_bad_lines,
            "warn_bad_lines": self.warn_bad_lines,
            "skipfooter": self.skipfooter,
            "doublequote": self.doublequote,
            "memory_map": self.memory_map,
            "float_precision": self.float_precision,
            "chunksize": self.chunksize,
            "encoding_errors": self.encoding_errors,
            "on_bad_lines": self.on_bad_lines,
            "date_format": self.date_format,
        }

        # some kwargs must not be passed if they don't have a default value
        # some others are deprecated and we can also not pass them if they are the default value
        for pd_read_csv_parameter in _PANDAS_READ_CSV_NO_DEFAULT_PARAMETERS + _PANDAS_READ_CSV_DEPRECATED_PARAMETERS:
            if pd_read_csv_kwargs[pd_read_csv_parameter] == getattr(CsvConfig(), pd_read_csv_parameter):
                del pd_read_csv_kwargs[pd_read_csv_parameter]

        # Remove 1.3 new arguments
        if not (datasets.config.PANDAS_VERSION.major >= 1 and datasets.config.PANDAS_VERSION.minor >= 3):
            for pd_read_csv_parameter in _PANDAS_READ_CSV_NEW_1_3_0_PARAMETERS:
                del pd_read_csv_kwargs[pd_read_csv_parameter]

        # Remove 2.0 new arguments
        if not (datasets.config.PANDAS_VERSION.major >= 2):
            for pd_read_csv_parameter in _PANDAS_READ_CSV_NEW_2_0_0_PARAMETERS:
                del pd_read_csv_kwargs[pd_read_csv_parameter]

        # Remove 2.2 deprecated arguments
        if datasets.config.PANDAS_VERSION.release >= (2, 2):
            for pd_read_csv_parameter in _PANDAS_READ_CSV_DEPRECATED_2_2_0_PARAMETERS:
                if pd_read_csv_kwargs[pd_read_csv_parameter] == getattr(CsvConfig(), pd_read_csv_parameter):
                    del pd_read_csv_kwargs[pd_read_csv_parameter]

        return pd_read_csv_kwargs