scikit-learn示例

scikit-learn示例

from joblib import parallel_backend, dump, load
import data.selectData as selectData
import time
import util_job.util as util
# from sklearn import svm
from sklearn.neural_network import MLPClassifier
# from sklearn.tree import DecisionTreeClassifier
# from sklearn.linear_model import LogisticRegression
from sklearn.svm import LinearSVC
import numpy as np
import data.insertData as insertData
from sklearn.metrics import accuracy_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import cross_val_predict
from sklearn.preprocessing import StandardScaler


# 预测
def run_sklearn(start_time, end_time, x, y):
    开始时间 = time.time()

    barData = selectData.show_10s_between_time_new(start_time, end_time)
    barData = util.sort_dataFrame(barData)
    barData.replace([np.inf, -np.inf, "", np.nan], 0, inplace=True)

    # x_train = np.array(barData[[x]])
    x_train = np.array(barData[x])

    # scaler = StandardScaler() 标准化数据，不准
    # scaler.fit(x_train)
    # x_train = scaler.transform(x_train)

    y_train = np.array(barData[y])
    print('开始')
    加载数据时间 = time.time()
    print('加载数据时间:', round((加载数据时间 - 开始时间) / 60, 2), '分钟')

    # 实例化 模型
    # clf = svm.SVC(C=0.6, kernel='rbf', gamma=0.001)
    # clf = svm.SVC()  # 相似度：71.75
    # clf = DecisionTreeClassifier()  # 相似度：61.48
    # clf = LogisticRegression()  # 相似度： 71.91

    clf = LinearSVC(max_iter=100000)  # 相似度：       max_iter=1000000
    # clf = MLPClassifier()  # 相似度：正 71.73 71.83  负 72.0129  max_iter=10000

    with parallel_backend('threading', n_jobs=-1):
        # 放入 数据学习
        clf.fit(x_train, y_train)
    print('训练完成!====', clf)
    print("LinearSVC 。 决策函数中的常数 intercept : ", clf.intercept_, " 。 唯一的类标签 classes_ : ", clf.classes_,
          " 。 所有类的最大迭代次数:n_iter_ : ", clf.n_iter_, " 。 系数：", clf.coef_)

    训练完成时间 = time.time()
    print('训练时间:', round((训练完成时间 - 加载数据时间) / 60, 2), '分钟')

    # 下载模型，持久化模型
    dump(clf, 'scikit_model.joblib')

    print('训练总时间:', round((训练完成时间 - 开始时间) / 60, 2), '分钟')
    return clf, x_train, y_train


# 交叉准确率
def scores(clf, x_train, y_train):
    开始时间 = time.time()

    with parallel_backend(backend='threading', n_jobs=-1):
        scores = cross_val_score(clf, x_train, y_train, cv=10)  # .astype('int')
        print('scores准确率:', scores)
        print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
        y_pred = cross_val_predict(clf, x_train, y_train, cv=10)
        print('y_pred准确率:', y_pred)

    结束时间 = time.time()
    print('交叉准确率时间:', round((开始时间 - 结束时间) / 60, 2), '分钟')

# 测试
def run_test(features_start_time, features_end_time, x, y):
    开始时间 = time.time()

    # 加载模型
    clf = load('scikit_model.joblib')

    # 加载测试数据
    features_barData = selectData.show_10s_between_time_new(features_start_time, features_end_time)
    features_barData = util.sort_dataFrame(features_barData)
    features = np.array(features_barData[x])
    加载数据时间 = time.time()
    print('加载测试数据时间:', round((加载数据时间 - 开始时间) / 60, 2), '分钟')
    # features = scaler.transform(features) 标准化数据

    with parallel_backend('threading', n_jobs=-1):
        # 预测 数据
        features_data = clf.predict(features)

    features_barData['未来价格走势'] = features_data
    insertData.run_features(features_barData)

    预测时间 = time.time()
    print('预测时间:', round((预测时间 - 加载数据时间) / 60, 2), '分钟')

    # 准确率
    acc = accuracy_score(np.array(features_barData[y]), features_data)
    time_end = time.time()
    print('计算准确率时间:', round((time_end - 预测时间) / 60, 2), '分钟')
    print('准确率:', acc)


def run_corr():
    barData = selectData.show_features_bar()
    corrr = barData['未来价格走势'].corr(barData['正价格走势'])
    print('相关性:', corrr)


def run():
    sk_start_time = "2018-01-01 09:00"
    sk_end_time = "2022-03-01 24:00"

    features_start_time = "2022-03-03 09:00"
    features_end_time = "2029-12-01 24:00"

    # todo 加上 价格趋势
    # x="买多_1r", "卖空_1r", "平多_1r", "平空_1r", "买多_5r", "卖空_5r", "平多_5r", "平空_5r", "买多_10r", "卖空_10r", "平多_10r", "平空_10r",  "买多_30r", "卖空_30r", "平多_30r", "平空_30r", "ask_1min", "bid_1min", "vr_1", "kdj_k_list", "kdj_d_list", "kdj_k-d", "diff", "dea","macd"
    x = ["买多_1r", "卖空_1r", "平多_1r", "平空_1r", "ask_1min", "bid_1min", "vr_1", "kdj_k_list", "kdj_d_list", "kdj_k-d",
         "diff",
         "dea", "macd"]
    # x = ["买多成交量", "卖空成交量", "平多成交量", "平空成交量", "ask_v_sum", "bid_v_sum", "volume_sum", "kdj_k_list", "kdj_d_list", "kdj_k-d", "diff", "dea", "macd"]  ,"hours","分钟"
    # x = ["ask_v_sum", "bid_v_sum", "volume_sum", "kdj_k_list", "kdj_d_list", "kdj_k-d", "diff", "dea", "macd"]
    y = "正价格走势"

    # 预测
    clf, x_train, y_train = run_sklearn(sk_start_time, sk_end_time, x, y)
    # 测试
    run_test(features_start_time, features_end_time, x, y)
    # 准确率
    scores(clf, x_train, y_train)
    # 相关性
    run_corr()