InventoryDemandPre.py 文件源码

def parse_parameter_sweep(file='/Users/srinath/playground/data-science/BimboInventoryDemand/logs/xgboost_params-explore-case4.txt'):
    file = open(file,'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('Run ([0-9+]) XGBoost_nocv {(.*?)} .*?rmsle=([0-9.]+)')

    readings = []
    for match in p1.finditer(data):
        data_index = int(match.group(1))
        params_as_str = match.group(2)
        rmsle = float(match.group(3))
        print data_index, rmsle, params_as_str

        kvmap = parse_map_from_str(params_as_str)
        print kvmap
        readings.append([data_index, rmsle, kvmap['eta'], kvmap['max_depth'], kvmap['min_child_weight'], kvmap['gamma'],
                         kvmap['subsample'], kvmap['colsample_bytree']])

    df_data = np.row_stack(readings)
    para_sweep_df= pd.DataFrame(df_data, columns=['data_index' , 'rmsle', 'eta', 'max_depth', 'min_child_weight', 'gamma',
                         'subsample', 'colsample_bytree'])
    print para_sweep_df
    return para_sweep_df