186 个股 196大盘

mix/mix_predict_200.py

@@ -90,7 +90,8 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1, row=18, col=20)
 
 if __name__ == '__main__':
     # predict(file_path='D:\\data\\quantization\\stock181_18d_test.log', model_path='181_18d_mix_6D_ma5_s_seq.h5')
-    predict(file_path='D:\\data\\quantization\\stock201_18d_train1.log', model_path='213_18d_mix_6D_ma5_s_seq.h5', row=18, col=20)
+    # predict(file_path='D:\\data\\quantization\\stock201_18d_train1.log', model_path='213_18d_mix_6D_ma5_s_seq.h5', row=18, col=20)
+    predict(file_path='D:\\data\\quantization\\stock301_18d_train1.log', model_path='301_18d_mix_6D_ma5_s_seq.h5', row=30, col=20)
     # 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')

mix/mix_train_190.py

@@ -76,8 +76,11 @@ train_x_c = train_x[:,18*18:]
 def create_mlp(dim, regress=False):
     # define our MLP network
     model = Sequential()
-    model.add(Dense(96, input_dim=dim, activation="relu"))
-    model.add(Dense(96, activation="relu"))
+    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:

mix/mix_train_300.py

@@ -18,16 +18,16 @@ from keras.callbacks import EarlyStopping
 
 early_stopping = EarlyStopping(monitor='accuracy', patience=5, verbose=2)
 
-epochs= 8
-size = 10000 #18W 60W
-file_path = 'D:\\data\\quantization\\stock300_18d_train2.log'
-model_path = '300_18d_mix_6D_ma5_s_seq.h5'
-file_path1='D:\\data\\quantization\\stock300_18d_test.log'
-col = 18
+epochs= 88
+size = 400000 #18W 60W
+file_path = 'D:\\data\\quantization\\stock302_18d_train2.log'
+model_path = '302_18d_mix_6D_ma5_s_seq.h5'
+file_path1='D:\\data\\quantization\\stock302_18d_test.log'
+col = 20
 '''
-ROC     30*18
-DMI     30*20
-MACD    30*19
+ROC     30*18           38,100,17
+DMI     30*20           39,101,13
+MACD    30*19           
 RSI     30*17
 
 '''
@@ -77,8 +77,10 @@ train_x_c = train_x[:,30*col:]
 def create_mlp(dim, regress=False):
     # define our MLP network
     model = Sequential()
-    model.add(Dense(128, input_dim=dim, activation="relu"))
+    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
@@ -149,9 +151,8 @@ x = Dense(1024, activation="relu", kernel_regularizer=regularizers.l1(0.003))(co
 x = Dropout(0.2)(x)
 x = Dense(1024, activation="relu")(x)
 x = Dense(1024, activation="relu")(x)
-x = Dense(1024, activation="relu")(x)
 # 在建设一层
-x = Dense(3, activation="softmax")(x)
+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