示例#1
0
def clean_demographics(df: SparkDataFrame) -> SparkDataFrame:
    """Clean demographics data

    :param df: demographic data frame to be cleaned.
    :return: cleaned demographic data frame
    """

    int_cols = [
        'count', 'male_population', 'female_population', 'total_population',
        'number_of_veterans', 'foreign_born'
    ]
    float_cols = ['median_age', 'average_household_size']
    df = convert_column_type(df, 'integer', int_cols)
    df = convert_column_type(df, 'float', float_cols)
    df = df.fillna(0, [*int_cols, *float_cols])
    return df
示例#2
0
 def run(self, dataframe: DataFrame) -> DataFrame:
     """Execute the hook."""
     return dataframe.fillna(0)