machine_learn/mix/mix_train_190.py

import keras
# -*- encoding:utf-8 -*-
import numpy as np
from keras.models import Sequential
# 优化方法选用Adam(其实可选项有很多，如SGD)
from keras.optimizers import Adam
import random
from keras.models import load_model
from imblearn.over_sampling import RandomOverSampler
from keras.utils import np_utils
# 用于模型初始化，Conv2D模型初始化、Activation激活函数，MaxPooling2D是池化层
# Flatten作用是将多位输入进行一维化
# Dense是全连接层
from keras.layers import Conv2D, Activation, MaxPool2D, Flatten, Dense,Dropout,Input,MaxPooling2D,BatchNormalization,concatenate
from keras import regularizers
from keras.models import Model
from keras.callbacks import EarlyStopping

early_stopping = EarlyStopping(monitor='accuracy', patience=5, verbose=2)

epochs= 90
size = 400000 #18W 60W
file_path = 'D:\\data\\quantization\\stock199A_18d_train2.log'
model_path = '199A_18d_mix_5D_ma5_s_seq.h5'
file_path1='D:\\data\\quantization\\stock199A_18d_test.log'

'''
大盘预测
结果均用使用ma
6 ROC   cnn18*18                                             37,99,28
7 ROC + 窗口6*18+ cnn18*18                                   36,99,27     
8 after用5日                                                 40,99,22
9 after5 + roc in before 18*20                               40,99,23     
9A after5 + roc in before + beta                             40,100,21
9B after5 + roc in before + beta + 其他信息                  
9C 流通>5        
'''

def read_data(path, path1=file_path1):
    lines = []
    with open(path) as f:
        for x in range(size): #610000
            line = eval(f.readline().strip())
            lines.append(line)

    with open(path1) as f:
        for x in range(50000):
            line = eval(f.readline().strip())
            lines.append(line)

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

    d=int(0.85*len(lines))
    length = len(lines[0])

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


train_x,train_y,test_x,test_y=read_data(file_path)

train_x_a = train_x[:,:18*20]
train_x_a = train_x_a.reshape(train_x.shape[0], 18, 20, 1)
# train_x_b = train_x[:, 9*26:18*26]
# train_x_b = train_x_b.reshape(train_x.shape[0], 9, 26, 1)
train_x_c = train_x[:,18*20:]


def create_mlp(dim, regress=False):
    # define our MLP network
    model = Sequential()
    model.add(Dense(256, input_dim=dim, activation="relu"))
    model.add(Dropout(0.2))
    model.add(Dense(256, activation="relu"))
    model.add(Dense(256, activation="relu"))
    model.add(Dense(128, activation="relu"))

    # check to see if the regression node should be added
    if regress:
        model.add(Dense(1, activation="linear"))

    # return our model
    return model


def create_cnn(width, height, depth, size=48, kernel_size=(5, 6), regress=False, output=24):
    # initialize the input shape and channel dimension, assuming
    # TensorFlow/channels-last ordering
    inputShape = (width, height, 1)
    chanDim = -1

    # define the model input
    inputs = Input(shape=inputShape)
    # x = inputs
    # CONV => RELU => BN => POOL
    x = Conv2D(size, kernel_size, strides=2, padding="same")(inputs)
    x = Activation("relu")(x)
    x = BatchNormalization(axis=chanDim)(x)

    # y = Conv2D(24, (2, 8), strides=2, padding="same")(inputs)
    # y = Activation("relu")(y)
    # y = BatchNormalization(axis=chanDim)(y)

    # flatten the volume, then FC => RELU => BN => DROPOUT
    x = Flatten()(x)
    x = Dense(output)(x)
    x = Activation("relu")(x)
    x = BatchNormalization(axis=chanDim)(x)
    x = Dropout(0.2)(x)

    # apply another FC layer, this one to match the number of nodes
    # coming out of the MLP
    x = Dense(output)(x)
    x = Activation("relu")(x)

    # check to see if the regression node should be added
    if regress:
        x = Dense(1, activation="linear")(x)

    # construct the CNN
    model = Model(inputs, x)

    # return the CNN
    return model


# create the MLP and CNN models
mlp = create_mlp(train_x_c.shape[1], regress=False)
# cnn_0 = create_cnn(18, 21, 1, kernel_size=(3, 3), size=64, regress=False, output=128)       # 31 97 46
# cnn_0 = create_cnn(18, 21, 1, kernel_size=(6, 6), size=64, regress=False, output=128)         # 29 98 47
# cnn_0 = create_cnn(18, 21, 1, kernel_size=(9, 9), size=64, regress=False, output=128)         # 28 97 53
cnn_0 = create_cnn(18, 20, 1, kernel_size=(6, 20), size=96, regress=False, output=128)       #A23 99 33 A' 26 99 36 #B 34 98 43
# cnn_1 = create_cnn(18, 21, 1, kernel_size=(18, 11), size=96, regress=False, output=96)
# cnn_1 = create_cnn(9, 26, 1, kernel_size=(2, 14), size=36, regress=False, output=64)

# create the input to our final set of layers as the *output* of both
# the MLP and CNN
combinedInput = concatenate([mlp.output, cnn_0.output])

# our final FC layer head will have two dense layers, the final one
# being our regression head
x = Dense(1024, activation="relu", kernel_regularizer=regularizers.l1(0.003))(combinedInput)
x = Dropout(0.2)(x)
x = Dense(1024, activation="relu")(x)
x = Dense(1024, activation="relu")(x)
# 在建设一层
x = Dense(4, activation="softmax")(x)

# our final model will accept categorical/numerical data on the MLP
# input and images on the CNN input, outputting a single value (the
# predicted price of the house)
model = Model(inputs=[mlp.input, cnn_0.input,], outputs=x)


print("Starting training ")
# h = model.fit(train_x, train_y, batch_size=4096*2, epochs=500, shuffle=True)

# compile the model using mean absolute percentage error as our loss,
# implying that we seek to minimize the absolute percentage difference
# between our price *predictions* and the *actual prices*
opt = Adam(lr=1e-3, decay=1e-3 / 200)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=['accuracy'])

# train the model
print("[INFO] training model...")
model.fit(
    [train_x_c, train_x_a,], train_y,
    # validation_data=([testAttrX, testImagesX], testY),
    # epochs=int(3*train_x_a.shape[0]/1300),
    epochs=epochs,
    batch_size=2048, shuffle=True,
    callbacks=[early_stopping]
)

model.save(model_path)

test_x_a = test_x[:,:18*20]
test_x_a = test_x_a.reshape(test_x.shape[0], 18, 20, 1)
# test_x_b = test_x[:, 9*26:9*26+9*26]
# test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
test_x_c = test_x[:,18*20:]

# make predictions on the testing data
print("[INFO] predicting house prices...")
score  = model.evaluate([test_x_c, test_x_a], test_y)

print(score)
print('Test score:', score[0])
print('Test accuracy:', score[1])