dropout

stock/dnn_predict.py

@@ -0,0 +1,32 @@
+import keras
+# -*- encoding:utf-8 -*-
+import numpy as np
+from keras.models import Sequential
+from keras.layers import Dense,Dropout
+import random
+from keras.models import load_model
+
+def read_data(path):
+    lines = []
+    with open(path) as f:
+        for line in f.readlines()[:20]:
+            lines.append(eval(line.strip()))
+
+    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)
+
+test_x,test_y=read_data("D:\\data\\quantization\\stock_test.log")
+
+path="model_seq.h5"
+model=load_model(path)
+score = model.evaluate(test_x, test_y)
+print(score)
+
+result=model.predict(test_x)
+print(result)
+i = 0
+for x in test_y:
+    print(str(i) + ":" + str(x))
+    i = i + 1

stock/dnn_train.py

@@ -11,10 +11,10 @@ def read_data(path):
     train_y=[]
     lines = []
     with open(path) as f:
-        for x in range(100000):
+        for x in range(20000):
             lines.append(eval(f.readline().strip()))
     random.shuffle(lines)
-    lines = lines[:80000]
+    lines = lines[:8000]
     d=int(0.95*len(lines))
 
     size = len(lines[0])
@@ -30,13 +30,15 @@ model = Sequential()
 model.add(Dense(units=425, input_dim=166,  activation='relu'))
 model.add(Dense(units=325, activation='relu'))
 model.add(Dense(units=325, activation='relu'))
+model.add(Dropout(0.2))
 model.add(Dense(units=225, activation='relu'))
 model.add(Dense(units=225, activation='relu'))
 model.add(Dense(units=225, activation='relu'))
 model.add(Dense(units=225, activation='relu'))
-model.add(Dense(units=225, activation='relu'))
+model.add(Dropout(0.2))
 model.add(Dense(units=225, activation='relu'))
 model.add(Dense(units=125, activation='relu'))
+model.add(Dropout(0.2))
 model.add(Dense(units=125, activation='relu'))
 model.add(Dense(units=166, activation='relu'))
 # model.add(Dropout(0.2)(Dense(units=225, activation='relu')))
@@ -44,7 +46,7 @@ model.add(Dense(units=8, activation='softmax'))
 model.compile(loss='categorical_crossentropy', optimizer="adam",metrics=['accuracy'])
 
 print("Starting training ")
-h=model.fit(train_x, train_y, batch_size=32, epochs=8, shuffle=True)
+h=model.fit(train_x, train_y, batch_size=32, epochs=16, shuffle=True)
 score = model.evaluate(test_x, test_y)
 print(score)
 print('Test score:', score[0])