machine_learn/mix/mix_train_400.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 imblearn.over_sampling import RandomOverSampler
# 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= 40
size = 440000 #共68W
file_path = 'D:\\data\\quantization\\stock417_30d_train2.log'
model_path = '417_30d_mix_5D_ma5_s_seq.h5'
file_path1='D:\\data\\quantization\\stock417_30d_test.log'
row = 30
col = 19
'''
0    roc 涨幅int表示  18*18             59,97,46                                       
1    dmi              24*20             59,98,41
2    roc              24*18             56,98,41
3    dmi              30*20             55,98,40       
3B   dmi    9
3A   dmi              30*20             53,97,44
4    roc              30*18             63,98,40
5    macd             30*19             64,98,39-24     !
5_1   macd   9                          62,98,41
5_2   macd   12                         58,98,43
9    rsi              30*17             50,97,43
15  macd+20ma占比     30*19             62,97,44
16  macd+beta1        30*19             62,98,37-27
17  macd+beta1+去掉阶段涨幅             61,98,41-28           
18  macd+资金/ma向量     30*21

6    dmi+大盘形态     30*20             52,98,39
7    roc+大盘形态     30*18             59,98,40
8    macd+大盘形态    30*19             
'''

def read_data(path, path1=file_path1):
    lines = []
    with open(path) as f:
        for x in range(size): #680000
            line = eval(f.readline().strip())
            lines.append(line)

    with open(path1) as f:
        for x in range(30000): #6w
            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, dtype=np.float32), np.array(train_y, dtype=np.float32))

    print('数据重采样完毕')

    return X_resampled,y_resampled,np.array(test_x, dtype=np.float32),np.array(test_y, dtype=np.float32)


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

train_x_a = train_x[:,:row*col]
train_x_a = train_x_a.reshape(train_x.shape[0], row, col, 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[:,row*col:]


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, 20, 1, kernel_size=(3, 3), size=90, regress=False, output=96)       # 31 97 46
cnn_0 = create_cnn(row, col, 1, kernel_size=(6, col), size=96, regress=False, output=96)         # 29 98 47
# cnn_0 = create_cnn(18, 20, 1, kernel_size=(9, 9), size=90, regress=False, output=96)         # 28 97 53
# cnn_0 = create_cnn(18, 20, 1, kernel_size=(3, 20), size=90, regress=False, output=96)
# cnn_1 = create_cnn(18, 20, 1, kernel_size=(18, 10), size=80, 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(3, 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[:,:row*col]
test_x_a = test_x_a.reshape(test_x.shape[0], row, col, 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[:,row*col:]

# 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])