__init__.py 文件源码

def parse_feature_explore_output(file_name, feature_importance_map):
    #[IDF1] ['clients_combined_vh_Mean_x', 'clients_combined_vhci_x', 'clients_combined_vh_median_x', 'Producto_ID_Venta_hoy_Mean', 'Producto_ID_Venta_hoyci', 'Producto_ID_Venta_hoy_median', 'Producto_ID_Dev_proxima_Mean', 'Producto_ID_Dev_proximaci', 'Producto_ID_Dev_proxima_median', 'agc_product_Mean', 'agc_productci', 'agc_product_median'] XGB 0.584072902792

    file = open(file_name,'r')
    data =  file.read()

    data = data.replace('\n','')
    data = re.sub(r'\[=+\'\].*?s', '', data)
    #28. feature 27 =Producto_ID_Dev_proxima_StdDev (0.002047)

    p1 = re.compile('\[IDF1\] (\[.*?\]) XGB ([0-9.]+)')

    readings = []
    for match in p1.finditer(data):
        feature_set = match.group(1)
        rmsle = float(match.group(2))
        if 0.56 < rmsle < 0.57:
            for f in parse_list_from_str(feature_set):
                count = feature_importance_map.get(f, 0)
                count += 1
                feature_importance_map[f] = count
        readings.append([feature_set, rmsle])

    df_data = np.row_stack(readings)
    para_sweep_df= pd.DataFrame(df_data, columns=['feature_set' , 'rmsle'])
    return para_sweep_df