Question

我找不到与自己的问题有关的任何问题，因此无法解决。刚开始在数据分析中使用并行计算。我正在使用随机森林进行预测。当我使用for循环运行它时，它可以很好地工作，但是会花费更长的时间。但是使用池进行多处理，速度更快，但即使它们应该有所不同，也可以继续为我提供相同的结果。我在做什么错。

import data_process as imb
import datetime
import os
import pandas as pd
import numpy as np
from multiprocessing import Pool
from functools import partial
from myModels import RandomForest


def Average(lst):
    return sum(lst) / len(lst)


def split_imbal_process(df, a):
    pred_start = datetime.datetime(2018, 6, 1)
    start_data = pred_start - datetime.timedelta(days=a)
    df = df[start_data.strftime('%Y-%m-%d'):]
    d = [i.strftime('%Y-%m-%d') for i in df.dropna().index]
    n_train = 48 * a
    n_records = len(d)
    feature_list = list(df.drop('price', axis=1).columns)
    data = [(i, j * 48) for j, i in enumerate(range(n_train, n_records, 48))]
    pool = Pool(os.cpu_count() - 2)
    func = partial(process_model, d, df, feature_list)
    result = pool.starmap(func, data)
    pool.close()
    pool.join()
    mape = Average([i[0] for i in result])
    error = Average([i[1] for i in result])
    print(mape, error)
    return mape, error


def process_model(d, df, feature_list, i, j):
    train_index, test_index = d[j: i], d[i: i + 48 * 5]
    train_data = df[train_index[0]: train_index[-1]]
    test_data = df[test_index[0]: test_index[-1]]
    train_features = np.array(train_data.drop('price', axis=1))
    train_target = np.array(train_data['price'])

    test_features = np.array(test_data.drop('price', axis=1))
    test_target = np.array(test_data['price'])
    index_test = test_data.index
    mape, errors = RandomForest(
        train_features,
        train_target,
        test_features,
        test_target,
        feature_list,
        index_test)
    return mape, errors


if __name__ == '__main__':
    df = imb.imbalance_feature()[:'2018-06-30'].drop('date', axis=1)
    a = int(len(df[:'2018-05-31']) / 48)
    d = pd.DataFrame()
    for i in range(a, 7, -40):
        d_mape, d_error = split_imbal_process(df, a)
        print(d_mape, d_error)

使用池进行多处理时我在做什么错

0 个答案: