cnn

stock/cnn_predict_dmi.py

@@ -0,0 +1,126 @@
+# -*- encoding:utf-8 -*-
+import numpy as np
+from keras.models import load_model
+import joblib
+
+
+def read_data(path):
+    lines = []
+    with open(path) as f:
+        for line in f.readlines()[:]:
+            line = eval(line.strip())
+            if line[-2][0].startswith('0') or line[-2][0].startswith('3'):
+                lines.append(line)
+
+    size = len(lines[0])
+    train_x=[s[:size - 2] for s in lines]
+    train_y=[s[size-1] for s in lines]
+    return np.array(train_x),np.array(train_y),lines
+
+
+def _score(fact, line):
+    with open('dnn_predict_dmi_18d.txt', 'a') as f:
+        f.write(str([line[-2], line[-1]]) + "\n")
+
+    up_right = 0
+    up_error = 0
+
+    if fact[0] == 1:
+        up_right = up_right + 1.12
+    elif fact[1] == 1:
+        up_right = up_right + 1.06
+    elif fact[2] == 1:
+        up_right = up_right + 1
+    elif fact[3] == 1:
+        up_right = up_right + 0.94
+    else:
+        up_error = up_error + 1
+        up_right = up_right + 0.88
+    return up_right,up_error
+
+
+def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
+    test_x,test_y,lines=read_data(file_path)
+    test_x = test_x.reshape(test_x.shape[0], 1,6,77)
+
+    model=load_model(model_path)
+    score = model.evaluate(test_x, test_y)
+    print('DNN', score)
+
+    up_num = 0
+    up_error = 0
+    up_right = 0
+    down_num = 0
+    down_error = 0
+    down_right = 0
+    i = 0
+    result=model.predict(test_x)
+    win_dnn = []
+    for r in result:
+        fact = test_y[i]
+
+        if idx in [-2]:
+            if r[0] > 0.5 or r[1] > 0.5:
+                pass
+                # if fact[0] == 1:
+                #     up_right = up_right + 1.12
+                # elif fact[1] == 1:
+                #     up_right = up_right + 1.06
+                # elif fact[2] == 1:
+                #     up_right = up_right + 1
+                # elif fact[3] == 1:
+                #     up_right = up_right + 0.94
+                # else:
+                #     up_error = up_error + 1
+                #     up_right = up_right + 0.88
+                # up_num = up_num + 1
+        else:
+            if r[0] > 0.6 or r[1] > 0.6:
+                tmp_right,tmp_error = _score(fact, lines[i])
+                up_right = tmp_right + up_right
+                up_error = tmp_error + up_error
+                up_num = up_num + 1
+            elif r[3] > 0.5 or r[4] > 0.5:
+                if fact[0] == 1:
+                    down_error = down_error + 1
+                    down_right = down_right + 1.12
+                elif fact[1] == 1:
+                    down_right = down_right + 1.06
+                elif fact[2] == 1:
+                    down_right = down_right + 1
+                elif fact[3] == 1:
+                    down_right = down_right + 0.94
+                else:
+                    down_right = down_right + 0.88
+                down_num = down_num + 1
+
+        i = i + 1
+    if up_num == 0:
+        up_num = 1
+    if down_num == 0:
+        down_num = 1
+    print('DNN', up_right, up_num, up_right/up_num, up_error/up_num, down_right/down_num, down_error/down_num)
+    return win_dnn,up_right/up_num,down_right/down_num
+
+
+def multi_predict(model='14_18d'):
+    r = 0;
+    p = 0
+    for x in range(0, 12): # 0,2,3,4,6,8,9,10,11
+    # for x in [5,9,11,0,3,4,8]: #10_18,0没数据需要重新计算 [0,2,3,4,5,9,10,11]
+    # for x in [0,1,10]:
+    # for x in [2,4,7,10]: # 2表现最好 优秀的 0,8正确的反向指标,(9错误的反向指标 样本量太少)
+        print(x)
+    # for x in [0,2,5,6,7]: # 5表现最好
+        win_dnn, up_ratio,down_ratio = predict(file_path='D:\\data\\quantization\\kmeans\\stock' + model + '_test_' + str(x) + '.log',
+                                               model_path=model + '_dnn_seq_' + str(x) + '.h5', idx=x)
+        r = r + up_ratio
+        p = p + down_ratio
+    print(r, p)
+
+
+if __name__ == '__main__':
+    predict(file_path='D:\\data\\quantization\\stock16_18d_test.log', model_path='16_18d_cnn_seq.h5')
+    # predict(file_path='D:\\data\\quantization\\stock6_test.log', model_path='15m_dnn_seq.h5')
+    # multi_predict(model='15_18d')
+    # predict_today(20200229, model='11_18d')

stock/cnn_train_dmi.py

@@ -0,0 +1,106 @@
+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
+from keras import regularizers
+
+
+def read_data(path):
+    lines = []
+    with open(path) as f:
+        for x in range(200000):
+            lines.append(eval(f.readline().strip()))
+
+    random.shuffle(lines)
+    print('读取数据完毕')
+
+    d=int(0.75*len(lines))
+
+    train_x=[s[:-2] for s in lines[0:d]]
+    train_y=[s[-1] for s in lines[0:d]]
+    test_x=[s[:-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("D:\\data\\quantization\\stock16_18d_train.log")
+train_x = train_x.reshape(train_x.shape[0], 1,6,77)
+test_x = test_x.reshape(test_x.shape[0], 1,6, 77)
+
+
+
+model = Sequential()
+
+# 模型卷积层设计
+model.add(Conv2D(
+    nb_filter=32,  # 第一层设置32个滤波器
+    nb_row=10,
+    nb_col=6,  # 设置滤波器的大小为5*5
+    padding='same',  # 选择滤波器的扫描方式，即是否考虑边缘
+    input_shape=(1,6,77),  # 设置输入的形状
+    # batch_input_shape=(64, 1, 28, 28),
+))
+# 选择激活函数
+model.add(Activation('relu'))
+
+# 设置下采样(池化层）
+model.add(MaxPool2D(
+    pool_size=(4,1),  # 下采样格为2*2
+    strides=(2,2),  # 向右向下的步长
+    padding='same', # padding mode is 'same'
+))
+
+# 使用Flatten函数，将输入数据扁平化（因为输入数据是一个多维的形式，需要将其扁平化）
+model.add(Flatten())  # 将多维的输入一维化
+model.add(Dense(units=777, activation='relu', kernel_regularizer=regularizers.l1(0.003)))
+model.add(Dropout(0.2))
+model.add(Dense(units=777, activation='relu'))
+model.add(Dense(units=777, activation='relu'))
+model.add(Dense(units=777, activation='relu',kernel_regularizer=regularizers.l1(0.002)))
+model.add(Dropout(0.2))
+model.add(Dense(units=1024, activation='relu'))
+
+# 在建设一层
+model.add(Dense(5))  # 输入是个类别
+model.add(Activation('softmax'))  # 用于分类的softmax函数
+
+adam = Adam()  # 学习速率lr=0.0001
+
+model.compile(optimizer=adam,
+    loss='categorical_crossentropy',
+    metrics=['accuracy'])
+
+print("Starting training ")
+h=model.fit(train_x, train_y, batch_size=4096*2, epochs=150, shuffle=True)
+score = model.evaluate(test_x, test_y)
+print(score)
+print('Test score:', score[0])
+print('Test accuracy:', score[1])
+
+path="16_18d_cnn_seq.h5"
+model.save(path)
+model=None
+
+
+model=load_model(path)
+result=model.predict(test_x)
+print(result)
+print(test_y)