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= 77 # size = 24000 #共68W file_path = 'D:\\data\\quantization\\week120_18d_train1.log' model_path = '120_18d_mix_3W_s_seqA.h5' row = 18 col = 9 col1 = 13 ''' 0 18-3 18*11 25,102,47-29 1 18W预测3周后最高价+pe 18*11 37,101,44-22 2 18*11 + 11*16 33,101,41-30 3 stripe=1,win=4-3 18*11 + 11*16 31,108,19-34 ----- 随机25,100,51-26 4 stripe=1,win=3 18*11 + 11*16 34,103,41-26 5 stripe=1,win=3 18*11 6 用ma来衡量 7 简化模型 8 ma5-大盘相关+alpha_6 18*11 + 11*16 ------25,96,69 9 ma5-大盘相关+alpha_44+alpha_2 51,96,68-07 10 ma5-大盘相关+alpha_53+alpha_18 48,97,61-06 11 high-大盘相关+alpha_53+alpha_18 35,103,39-37 12 high-大盘相关+alpha_53+alpha_18(每日) 18*11 + 11*17 33,101,46-30 13 high-大盘相关+alpha_53+alpha_18-dmi 18*6 + 11*16 37,105,33-32 14 high-大盘相关+alpha_53+alpha_18-dmi+result修改(自己对比) 18*6 + 11*16 17,97,59 15 high-大盘相关+alpha_53+alpha_18+result修改-波动-ma+dmi 18*9 + 11*14 26,99,53-22 !!! 16 high-pettm 18*9 + 11*13 29,99,54-26 17 high+大盘相关 18*9 + 11*13 26,98,54-27 18 high-大盘相关+alpha_53+alpha_18+result修改-波动-ma+dmi 8周后 18*9 + 11*14 19,111,8,55 16 ----- 随机24,100,49 19 high-大盘相关+alpha_53+alpha_18+result修改-波动-ma+dmi 4周后 18*9 + 11*14 26,113,2,22 73条数据 20 high-大盘相关+alpha_53+alpha_18+result修改-波动-ma+双dmi 4周后 18*9 + 11*13 32,110,11,26 大盘超好的时候可以用这种 ''' def read_data(path): lines = [] with open(path) as f: for x in f.readlines()[:]: #680000 line = eval(x.strip()) lines.append(line) # with open(path1) as f: # for x in f.readlines()[:]: #680000 # line = eval(x.strip()) # lines.append(line) random.shuffle(lines) print('读取数据完毕') d=int(0.95*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[:, row*col:row*col + 11*col1] train_x_b = train_x_b.reshape(train_x.shape[0], 11, col1, 1) train_x_c = train_x[:,row*col + 11*col1:] 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, strides=2): # 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=strides, 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=(4, col), size=66, regress=False, output=66) # 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(11, col1, 1, kernel_size=(3, col1), size=66, regress=False, output=66, strides=1) # 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, cnn_1.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, cnn_1.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_x_b], 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[:, row*col:row*col + 11*col1] test_x_b = test_x_b.reshape(test_x.shape[0],11, col1, 1) test_x_c = test_x[:,row*col + 11*col1:] # make predictions on the testing data print("[INFO] predicting house prices...") score = model.evaluate([test_x_c, test_x_a, test_x_b], test_y) print(score) print('Test score:', score[0]) print('Test accuracy:', score[1])