mf_mrtg_default_model.py 文件源码

def load_data(in_file):
    # read csv file prepared by freddie_data_analysis module
    df = pd.read_csv(in_file)
    # drop unneeded columns
    columns = df.columns.tolist()
    for col in columns:
        if 'Unnamed' in col:
            df.drop(col, axis=1, inplace=True)
    df['published_date'] = pd.to_datetime(df['published_date'], errors='coerce')
    df.drop(['published_date'], axis=1, inplace=True)
    # replace nan values with 0
    df.replace([np.inf, -np.inf], np.nan, inplace=True)
    df.fillna(0, inplace=True)
    # apply get_dummies to particular columns
    df = pd.get_dummies(df, prefix=['state'], columns=['property_state'])
    df = pd.get_dummies(df, prefix=['ss'], columns=['special_servicer'])
    # return prepared dataframe
    return df