spark_histogrammar_filler.py 文件源码

def get_data_type(self, df, col):
        """Get data type of dataframe column

        :param df: input data frame
        :param str col: column
        """
        if col not in df.columns:
            raise KeyError('column "{0:s}" not in input dataframe'.format(col))
        dt = dict(df.dtypes)[col]
        # spark conversions to numpy or python equivalent
        if dt == 'string':
            dt = 'str'
        elif dt == 'timestamp':
            dt = np.datetime64
        return np.dtype(dt)