mix 相关

mix/mix_predict.py

@@ -19,7 +19,7 @@ def read_data(path):
 
 
 def _score(fact, line):
-    with open('dnn_predict_dmi_18d.txt', 'a') as f:
+    with open('mix_predict_dmi_18d.txt', 'a') as f:
         f.write(str([line[-2], line[-1]]) + "\n")
 
     up_right = 0
@@ -43,12 +43,13 @@ def _score(fact, line):
 
 def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
     test_x,test_y,lines=read_data(file_path)
+    print('Load data success')
 
     test_x_a = test_x[:,:18*18]
     test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
-    test_x_b = test_x[:, 18*18:18*18+2*18]
-    test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
-    test_x_c = test_x[:,18*18+2*18:]
+    test_x_b = test_x[:, 18*18:18*18+8*18]
+    test_x_b = test_x_b.reshape(test_x.shape[0], 18, 8, 1)
+    test_x_c = test_x[:,18*18+8*18:]
 
     model=load_model(model_path)
     score = model.evaluate([test_x_c, test_x_a, test_x_b], test_y)
@@ -70,12 +71,12 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
             if r[0] > 0.5 or r[1] > 0.5:
                 pass
         else:
-            if r[0] > 0.7 or r[1] > 0.7:
+            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] > 0.6 or r[4] > 0.6:
+            elif r[3] > 0.7 or r[4] > 0.7:
                 if fact[0] == 1:
                     down_error = down_error + 1
                     down_right = down_right + 1.12
@@ -83,6 +84,7 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
                     down_error = down_error + 1
                     down_right = down_right + 1.06
                 elif fact[2] == 1:
+                    down_error = down_error + 0.5
                     down_right = down_right + 1
                 elif fact[3] == 1:
                     down_right = down_right + 0.94
@@ -100,7 +102,7 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
 
 
 if __name__ == '__main__':
-    predict(file_path='D:\\data\\quantization\\stock18_18d_test.log', model_path='18_18d_mix_seq.h5')
+    predict(file_path='D:\\data\\quantization\\stock19_18d_test.log', model_path='19_18d_mix_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')

mix/mix_predict_by_day.py

@@ -0,0 +1,81 @@
+# -*- encoding:utf-8 -*-
+import numpy as np
+from keras.models import load_model
+import joblib
+
+
+def read_data(path):
+    day_lines = {}
+    with open(path) as f:
+        for line in f.readlines()[:]:
+            line = eval(line.strip())
+            date = str(line[-1][-1])
+            if date in day_lines:
+                day_lines[date].append(line)
+            else:
+                day_lines[date] = [line]
+    # print(len(day_lines['20191230']))
+    return day_lines
+
+
+def predict(file_path='', model_path='15min_dnn_seq'):
+    day_lines = read_data(file_path)
+    print('数据读取完毕')
+
+    models = []
+    for x in range(0, 12):
+        models.append(load_model(model_path + '_' + str(x) + '.h5'))
+    estimator = joblib.load('km_dmi_18.pkl')
+    print('模型加载完毕')
+
+    items = sorted(day_lines.keys())
+    for key in items:
+        # print(day)
+        lines = day_lines[key]
+
+        up_num = 0
+        down_num = 0
+        x = 24 # 每条数据项数
+        k = 18 # 周期
+        for line in lines:
+            v = line[1:x*k + 1]
+            v = np.array(v)
+            v = v.reshape(k, x)
+            v = v[:,4:8]
+            v = v.reshape(1, 4*k)
+            # print(v)
+            r = estimator.predict(v)
+
+            train_x = np.array([line[:-1]])
+            result = models[r[0]].predict(train_x)
+
+            if result[0][3] > 0.5 or result[0][4] > 0.5:
+                down_num = down_num + 1
+            elif result[0][1] > 0.5 or result[0][0] > 0.5:
+                up_num = up_num + 0.6  # 乐观调大 悲观调小
+
+            # if result[0][0] > 0.5 or result[0][1] > 0.5:
+            #     if r[0] in [0,2,3,4,5,9,10,11]:
+            #         up_num = up_num + 1
+            #     elif r[0] in [8]:
+            #         up_num = up_num + 0.6
+            #     else:
+            #         up_num = up_num + 0.4
+            # if result[0][3] > 0.5 or result[0][4] > 0.5:
+            #     if r[0] in [4,6,]:
+            #         down_num = down_num + 1
+            #     elif r[0] in [0,1,3,7,8,]:
+            #         down_num = down_num + 0.6
+            #     else:
+            #         down_num = down_num + 0.4
+
+        print(key, int(up_num), int(down_num), (down_num*1.2 + 2)/(up_num*1.2 + 2))
+
+
+if __name__ == '__main__':
+    # predict(file_path='D:\\data\\quantization\\stock6_5_test.log', model_path='5d_dnn_seq.h5')
+    # predict(file_path='D:\\data\\quantization\\stock9_18_20200220.log', model_path='18d_dnn_seq.h5')
+    # predict(file_path='D:\\data\\quantization\\stock9_18_2.log', model_path='18d_dnn_seq.h5')
+    predict(file_path='D:\\data\\quantization\\stock11_18d_20200229.log', model_path='11_18d_dnn_seq')
+    # predict(file_path='D:\\data\\quantization\\stock11_18d_20190103_20190604.log', model_path='14_18d_dnn_seq')
+    # predict(file_path='D:\\data\\quantization\\stock9_18_4.log', model_path='18d_dnn_seq.h5')

mix/mix_predict_by_stock.py

@@ -0,0 +1,128 @@
+# -*- encoding:utf-8 -*-
+import numpy as np
+from keras.models import load_model
+import joblib
+
+
+def read_data(path):
+    stock_lines = {}
+    with open(path) as f:
+        for line in f.readlines()[:]:
+            line = eval(line.strip())
+            stock = str(line[-2][0])
+
+            if stock in stock_lines:
+                stock_lines[stock].append(line)
+            else:
+                stock_lines[stock] = [line]
+    # print(len(day_lines['20191230']))
+    return stock_lines
+
+
+import pymongo
+from util.mongodb import get_mongo_table_instance
+code_table = get_mongo_table_instance('tushare_code')
+k_table = get_mongo_table_instance('stock_day_k')
+
+
+def predict(file_path='', model_path='15min_dnn_seq'):
+    stock_lines = read_data(file_path)
+    print('数据读取完毕')
+
+    models = []
+    models.append(load_model(model_path + '.h5'))
+    # estimator = joblib.load('km_dmi_18.pkl')
+    print('模型加载完毕')
+
+    total_money = 0
+    total_num = 0
+    items = sorted(stock_lines.keys())
+    for key in items:
+        # print(day)
+        lines = stock_lines[key]
+        init_money = 10000
+        last_price = 1
+
+        if lines[0][-2][0].startswith('6'):
+            continue
+
+        buy = 0 # 0空 1买入 2卖出
+        chiyou_0 = 0
+        high_price = 0
+
+        x = 24 # 每条数据项数
+        k = 18 # 周期
+        for line in lines:
+            # v = line[1:x*k + 1]
+            # v = np.array(v)
+            # v = v.reshape(k, x)
+            # v = v[:,6:10]
+            # v = v.reshape(1, 4*k)
+            # print(v)
+            # r = estimator.predict(v)
+
+            test_x = np.array([line[:-2]])
+            test_x_a = test_x[:,:18*24]
+            test_x_a = test_x_a.reshape(test_x.shape[0], 18, 24, 1)
+            test_x_b = test_x[:, 18*24:18*24+2*18]
+            test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
+            test_x_c = test_x[:,18*24+2*18:]
+
+            result = models[0].predict([test_x_c, test_x_a, test_x_b])
+
+            stock_name = line[-2]
+            today_price = list(k_table.find({'code':line[-2][0], 'tradeDate':{'$gt':int(line[-2][1])}}).sort('tradeDate',pymongo.ASCENDING).limit(1))
+            today_price = today_price[0]
+
+            if result[0][0] + result[0][1] > 0.7:
+                chiyou_0 = 0
+                if buy == 0:
+                    last_price = today_price['open']
+                    high_price = last_price
+                    print('首次买入', stock_name, today_price['open'])
+                    buy = 1
+                else:
+                    init_money = init_money * (today_price['close'] - last_price)/last_price + init_money
+                    last_price = today_price['close']
+                    print('买入+买入', stock_name, today_price['close'])
+                    buy = 1
+                    if last_price > high_price:
+                        high_price = last_price
+            elif buy == 1:
+                chiyou_0 = chiyou_0 + 1
+                if chiyou_0 > 2 and ((high_price - today_price['close'])/high_price*100 > 5):
+                    print('卖出', stock_name, today_price['close'])
+                    init_money = init_money * (today_price['close'] - last_price)/last_price + init_money
+                    buy = 0
+                    chiyou_0 = 0
+                if init_money < 9000:
+                    print('止损卖出', stock_name, today_price['close'])
+                    init_money = init_money * (today_price['close'] - last_price)/last_price + init_money
+                    buy = 0
+                    chiyou_0 = 0
+                else:
+                    print('继续持有', stock_name, today_price['close'])
+                    init_money = init_money * (today_price['close'] - last_price)/last_price + init_money
+                    buy = 1
+
+                last_price = today_price['close']
+                if last_price > high_price:
+                    high_price = last_price
+
+        print(key, init_money)
+
+        with open('D:\\data\\quantization\\stock_18_18d' + '_' +  'profit.log', 'a') as f:
+            if init_money > 10000:
+                f.write(str(key) + ' ' + str(init_money) + '\n')
+            elif init_money < 10000:
+                f.write(str(key) + ' ' + str(init_money) + '\n')
+
+        if init_money != 10000:
+            total_money = total_money + init_money
+            total_num = total_num + 1
+
+    print(total_money, total_num, total_money/total_num/10000)
+
+
+if __name__ == '__main__':
+    predict(file_path='D:\\data\\quantization\\stock18_18d_test.log', model_path='18_18d_mix_seq')

mix/mix_train.py

@@ -16,10 +16,13 @@ from keras import regularizers
 from keras.models import Model
 
 
+epochs= 130
+size = 380000
+
 def read_data(path):
     lines = []
     with open(path) as f:
-        for x in range(300000): #380000
+        for x in range(size): #380000
             lines.append(eval(f.readline().strip()))
 
     random.shuffle(lines)
@@ -46,16 +49,16 @@ train_x,train_y,test_x,test_y=read_data("D:\\data\\quantization\\stock18_18d_tra
 
 train_x_a = train_x[:,:18*18]
 train_x_a = train_x_a.reshape(train_x.shape[0], 18, 18, 1)
-train_x_b = train_x[:, 18*18:18*18+2*18]
-train_x_b = train_x_b.reshape(train_x.shape[0], 18, 2, 1)
-train_x_c = train_x[:,18*18+2*18:]
+train_x_b = train_x[:, 18*18:18*18+8*18]
+train_x_b = train_x_b.reshape(train_x.shape[0], 18, 8, 1)
+train_x_c = train_x[:,18*18+8*18:]
 
 
 def create_mlp(dim, regress=False):
     # define our MLP network
     model = Sequential()
-    model.add(Dense(32, input_dim=dim, activation="relu"))
-    model.add(Dense(32, activation="relu"))
+    model.add(Dense(16, input_dim=dim, activation="relu"))
+    model.add(Dense(16, activation="relu"))
 
     # check to see if the regression node should be added
     if regress:
@@ -65,7 +68,7 @@ def create_mlp(dim, regress=False):
     return model
 
 
-def create_cnn(width, height, depth, filters=(4, 6), kernel_size=(5, 6), regress=False, output=24):
+def create_cnn(width, height, depth, filters=32, kernel_size=(5, 6), regress=False, output=24):
     # initialize the input shape and channel dimension, assuming
     # TensorFlow/channels-last ordering
     inputShape = (width, height, 1)
@@ -77,7 +80,7 @@ def create_cnn(width, height, depth, filters=(4, 6), kernel_size=(5, 6), regress
     x = inputs
 
     # CONV => RELU => BN => POOL
-    x = Conv2D(32, kernel_size, strides=2, padding="same")(x)
+    x = Conv2D(filters, kernel_size, strides=2, padding="same")(x)
     x = Activation("relu")(x)
     x = BatchNormalization(axis=chanDim)(x)
     # x = MaxPooling2D(pool_size=(2, 2))(x)
@@ -111,8 +114,8 @@ def create_cnn(width, height, depth, filters=(4, 6), kernel_size=(5, 6), regress
 
 # create the MLP and CNN models
 mlp = create_mlp(train_x_c.shape[1], regress=False)
-cnn_0 = create_cnn(18, 18, 1, kernel_size=(10, 6), regress=False, output=256)
-cnn_1 = create_cnn(18, 2, 1, kernel_size=(10,2), regress=False, output=36)
+cnn_0 = create_cnn(18, 18, 1, kernel_size=(5, 6), filters=48, regress=False, output=256)
+cnn_1 = create_cnn(18, 8, 1, kernel_size=(5, 6), filters=32, regress=False, output=128)
 
 # create the input to our final set of layers as the *output* of both
 # the MLP and CNN
@@ -120,10 +123,10 @@ 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(512, activation="relu", kernel_regularizer=regularizers.l1(0.003))(combinedInput)
+x = Dense(888, activation="relu", kernel_regularizer=regularizers.l1(0.003))(combinedInput)
 x = Dropout(0.2)(x)
-x = Dense(512, activation="relu")(x)
-x = Dense(512, activation="relu")(x)
+x = Dense(888, activation="relu")(x)
+x = Dense(888, activation="relu")(x)
 # 在建设一层
 x = Dense(5, activation="softmax")(x)
 
@@ -148,14 +151,14 @@ 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=100,
-    batch_size=2048, shuffle=True)
+    epochs=epochs,
+    batch_size=1024, shuffle=True)
 
 test_x_a = test_x[:,:18*18]
 test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
-test_x_b = test_x[:, 18*18:18*18+2*18]
-test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
-test_x_c = test_x[:,18*18+2*18:]
+test_x_b = test_x[:, 18*18:18*18+8*18]
+test_x_b = test_x_b.reshape(test_x.shape[0], 18, 8, 1)
+test_x_c = test_x[:,18*18+8*18:]
 
 # make predictions on the testing data
 print("[INFO] predicting house prices...")
@@ -165,6 +168,6 @@ print(score)
 print('Test score:', score[0])
 print('Test accuracy:', score[1])
 
-path="18_18d_mix_seq.h5"
+path="19_18d_mix_seq.h5"
 model.save(path)
 model=None