machine_learn/stock/dnn_train.py

import keras
# -*- encoding:utf-8 -*-
import numpy as np
from keras.models import Sequential
from keras.layers import Dense,Dropout
import random
from keras import regularizers
from keras.models import load_model
from imblearn.over_sampling import RandomOverSampler
import joblib


def read_data(path):
    lines = []
    with open(path) as f:
        # for x in range(30000):
        # lines.append(eval(f.readline().strip()))
        for line in f.readlines()[:]:
            lines.append(eval(line.strip()))

    random.shuffle(lines)
    print('读取数据完毕')

    d=int(0.95*len(lines))

    size = len(lines[0])
    train_x=[s[:size - 2] for s in lines[0:d]]
    train_y=[s[size-1] for s in lines[0:d]]
    test_x=[s[:size - 2] for s in lines[d:]]
    test_y=[s[size-1] for s in lines[d:]]

    print('转换数据完毕')

    ros = RandomOverSampler(random_state=0)
    X_resampled, y_resampled = ros.fit_sample(np.array(train_x), np.array(train_y))

    print('数据重采样完毕')

    return X_resampled,y_resampled,np.array(test_x),np.array(test_y)


def resample(path):
    lines = []
    with open(path) as f:
        for x in range(160000):
            lines.append(eval(f.readline().strip()))
    estimator = joblib.load('km.pkl')

    x = 17
    for line in lines:
        v = line[1:x*10 + 1]
        v = np.array(v)
        v = v.reshape(10, x)
        v = v[:,0:4]
        v = v.reshape(1, 40)
        # print(v)
        r = estimator.predict(v)
        with open('D:\\data\\quantization\\kmeans\\stock2_10_' + str(r[0]) + '.log', 'a') as f:
            f.write(str(line) + '\n')


def mul_train():
    # for x in range(0, 16):
    for x in [7,9,12,14,15]:
        train(input_dim=176, result_class=5, file_path="D:\\data\\quantization\\kmeans\\stock2_10_" + str(x) + ".log",
              model_name='5d_dnn_seq_' + str(x) + '.h5')


def train(input_dim=400, result_class=3, file_path="D:\\data\\quantization\\stock6.log", model_name=''):
    train_x,train_y,test_x,test_y=read_data(file_path)

    model = Sequential()
    model.add(Dense(units=120+input_dim, input_dim=input_dim,  activation='relu'))
    model.add(Dense(units=120+input_dim, activation='relu',kernel_regularizer=regularizers.l1(0.001)))
    model.add(Dense(units=120+input_dim, activation='relu'))
    model.add(Dense(units=120 + input_dim, activation='relu'))
    model.add(Dropout(0.1))
    model.add(Dense(units=60+input_dim, activation='selu'))
    # model.add(Dropout(0.2))
    # model.add(Dense(units=60+input_dim, activation='selu'))
    # model.add(Dropout(0.2))
    model.add(Dense(units=512, activation='relu'))

    model.add(Dense(units=result_class, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer="adam",metrics=['accuracy'])

    print("Starting training ")
    model.fit(train_x, train_y, batch_size=32, epochs=117 + int(len(train_x)/900), shuffle=True)
    score = model.evaluate(test_x, test_y)
    print(score)
    print('Test score:', score[0])
    print('Test accuracy:', score[1])

    model.save(model_name)

    # model=None
    # model=load_model(model_name)
    # result=model.predict(test_x)
    # print(result)
    # print(test_y)


if __name__ == '__main__':
    # train(input_dim=86, result_class=5, file_path="D:\\data\\quantization\\stock6_5.log", model_name='5d_dnn_seq.h5')
    # train(input_dim=400, result_class=3, file_path="D:\\data\\quantization\\stock6.log", model_name='15m_dnn_seq.h5')
    # resample('D:\\data\\quantization\\stock6_5.log')
    mul_train()