machine_learn/stock/kmeans.py

# -*- encoding:utf-8 -*-
from sklearn.cluster import KMeans
import numpy as np
# from annoy import AnnoyIndex
import joblib

def read_data(path):
    lines = []
    with open(path) as f:
        for x in range(20000):
            line = eval(f.readline().strip())
            # if line[-1][0] == 1 or line[-1][1] == 1:
            lines.append(line)

    return lines


length = 18  # 周期是多少
j = 20
def class_fic(file_path=''):
    lines = read_data(file_path)
    print('读取数据完毕')
    size = len(lines[0])
    x_list = []
    for s in lines:
        tmp_list = []
        for x in range(0, length):
            tmp_list = tmp_list + s[x*j+5:x*j+9]
        x_list.append(tmp_list)
    train_x = np.array(x_list)
    # train_x = np.array([s[5:9] + s[j+5:j+9] + s[j*2+5:j*2+9] + s[j*3+5:j*3+9] + s[j*4+5:j*4+9] + s[j*5+5:j*5+9] + s[j*6+5:j*6+9]
    #                     + s[j*7+5:j*7+9] + s[j*8+5:j*8+9] + s[j*9+5:j*9+9] + s[j*10+5:j*10+9] + s[j*11+5:j*11+9] + s[j*12+5:j*12+9] + s[j*13+5:j*13+9]
    #                     + s[j*14+5:j*14+9] + s[j*15+5:j*15+9] + s[j*9+5:j*9+9] + s[j*10+5:j*10+9] + s[j*11+5:j*11+9] + s[j*12+5:j*12+9] + s[j*13+5:j*13+9]
    #                     for s in lines])
    # train_y = [s[size - 1] for s in lines]
    v_x = train_x.reshape(train_x.shape[0], 4*length)
    stock_list = [s[size - 2] for s in lines]

    estimator = KMeans(n_clusters=12, random_state=129)
    estimator.fit(v_x)
    label_pred = estimator.labels_  # 获取聚类标签
    centroids = estimator.cluster_centers_
    joblib.dump(estimator , 'km_dmi_18.pkl')

    print(estimator.predict(v_x[:10]))

    estimator = joblib.load('km_dmi_18.pkl')
    print(estimator.predict(v_x[10:20]))
    # annoy_sim(v_x)
    # print('save数据完毕')
    # return find_annoy(train_y, stock_list)

def annoy_sim(lines):
    tree = 30
    t = AnnoyIndex(length*4, metric="angular") # 24是向量维度

    i = 0
    for stock in lines:
        t.add_item(i, stock)
        i = i + 1

    t.build(tree)
    t.save('stock_20d.ann')


def find_annoy(lines, stock_list):
    t = AnnoyIndex(length*4, metric="angular")
    t.load('stock_20d.ann')
    num = 0
    right = 0

    win_dnn = []
    for i in range(len(lines)):
        index, distance = t.get_nns_by_item(i, 10, include_distances=True)
        # print(index, distance)

        # 预测
        total = 0
        g = 0
        for j in range(1, len(index)):
            if distance[j] < 0.4:
                total = total + 1
                if lines[j][0] == 1:
                    g = g + 1
                elif lines[j][1] == 1:
                    g = g + 1
                elif lines[j][2] == 1:
                    g = g + 0.5
        if total > 1 and g / total > 0.38:
            right = right + 1
            if stock_list[i][1] > 20181101:
                print(stock_list[i])
                win_dnn.append([stock_list[i], lines[i]])


        # 计算
        # if lines[i][0] == 1:
        #     g = 0
        #     total = 0
        #     for j in range(1,len(index)):
        #         if distance[j] < 0.4:
        #             total = total + 1
        #             if lines[j][0] == 1:
        #                 g = g+1
        #             elif lines[j][1] == 1:
        #                 g = g+1
        #     if total > 1 and g/total > 0.21:
        #         right = right + 1
        #     if total > 1:
        #         num = num + 1

    print(right, num)
    print('find数据完毕')
    return win_dnn


if __name__ == '__main__':
    # class_fic(file_path="D:\\data\\quantization\\stock2_10.log")
    class_fic(file_path="D:\\data\\quantization\\stock9_18.log")