cleaner.py 文件源码

def dummify(df):
    '''
        Given a dataframe, for all the columns which are not numericly typed already,
        create dummies. This will NOT remove one of the dummies which is required for
        linear regression.

        returns DataFrame -- a dataframe with all non-numeric columns swapped into dummy columns
    '''
    obj_cols = []
    for cname in df.columns:
        if df[cname].dtype == object:
            obj_cols.append(cname)

    df = pd.get_dummies(df, columns=obj_cols)
    # for cname in obj_cols:
    #     del df[cname]

    return df