18个股 19大盘

mix/mix_kmeans_predict_1.py

@@ -3,9 +3,9 @@ import numpy as np
 from keras.models import load_model
 import joblib
 
-model_path = '161_18d_mix_5D_ma5_s_seq.h5' # 160roc分类 161dmi分类
-data_dir = 'D:\\data\\quantization\\dmi\\'
-args = 'stock160_18d_test_A'
+model_path = '160_18d_mix_6D_ma5_s_seq.h5' # 160roc分类 161dmi分类
+data_dir = 'D:\\data\\quantization\\macd\\'
+args = 'stock160_18d_train2_B'
 
 
 def read_data(path):
@@ -17,7 +17,7 @@ def read_data(path):
                 lines.append(line)
 
     size = len(lines[0])
-    train_x=[s[:size - 2] for s in lines]
+    train_x=[s[:size - 2 - 18*3] for s in lines]
     train_y=[s[size-1] for s in lines]
     return np.array(train_x),np.array(train_y),lines
 
@@ -69,7 +69,7 @@ def predict(file_path='', idx=-1):
     # test_x_b = test_x_b.reshape(test_x.shape[0], 18, 10, 1)
     test_x_c = test_x[:,18*24:]
 
-    model=load_model(model_path.split('.')[0] + '_' + str(idx) + '.h5')
+    model=load_model(model_path.split(".")[0] + '.h5')
     score = model.evaluate([test_x_c, test_x_a, ], test_y)
     print('MIX', score)
 

mix/mix_kmeans_train_1.py

@@ -16,8 +16,8 @@ from keras import regularizers
 from keras.models import Model
 
 epochs= 50
-model_path = '161_18d_mix_5D_ma5_s_seq.h5'
-data_dir = 'D:\\data\\quantization\\dmi\\'
+model_path = '164_18d_mix_6D_ma5_s_seq.h5'
+data_dir = 'D:\\data\\quantization\\dapan\\'
 args = 'stock160_18d_train_A_'
 
 
@@ -49,7 +49,7 @@ def read_data(path):
 
 
 def mul_train(name="10_18d"):
-    for x in range(8, 12):
+    for x in range(1, 5):
         score = train(data_dir + name + str(x) + ".log", x) # stock160_18d_trai_0
 
         with open(data_dir + name + '_mix.log', 'a') as f:

mix/mix_predict.py

@@ -47,12 +47,12 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
 
     test_x_tmp = test_x[:,:18*24]
     test_x_a = test_x_tmp.reshape(test_x.shape[0], 18, 24, 1)
-    test_x_b = test_x_tmp.reshape(test_x.shape[0], 18, 24)
+    # test_x_b = test_x_tmp.reshape(test_x.shape[0], 18, 24)
     # test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
     test_x_c = test_x[:,18*24:]
 
     model=load_model(model_path)
-    score = model.evaluate([test_x_c, test_x_a, test_x_b], test_y)
+    score = model.evaluate([test_x_c, test_x_a], test_y)
     print('MIX', score)
 
     up_num = 0
@@ -62,7 +62,7 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
     down_error = 0
     down_right = 0
     i = 0
-    result=model.predict([test_x_c, test_x_a, test_x_b])
+    result=model.predict([test_x_c, test_x_a])
     win_dnn = []
     for r in result:
         fact = test_y[i]
@@ -102,8 +102,8 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
 
 
 if __name__ == '__main__':
-    predict(file_path='D:\\data\\quantization\\stock160_18d_test.log', model_path='163_18d_mix_5D_ma5_s_seq.h5')
-    # predict(file_path='D:\\data\\quantization\\stock160_18d_train1.log', model_path='162_18d_mix_5D_ma5_s_seq.h5')
+    predict(file_path='D:\\data\\quantization\\stock160_18d_test.log', model_path='160_18d_mix_6D_ma5_s_seq.h5')
+    # predict(file_path='D:\\data\\quantization\\stock160_18d_train1.log', model_path='160_18d_mix_6D_ma5_s_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_1.py

@@ -26,32 +26,31 @@ def _score(fact, line):
     up_error = 0
 
     if fact[0] == 1:
-        up_right = up_right + 1.12
+        up_right = up_right + 1.1
     elif fact[1] == 1:
-        up_right = up_right + 1.06
+        up_right = up_right + 1.04
     elif fact[2] == 1:
         up_right = up_right + 1
-        up_error = up_error + 0.5
     elif fact[3] == 1:
         up_right = up_right + 0.94
         up_error = up_error + 1
     else:
         up_error = up_error + 1
-        up_right = up_right + 0.88
+        up_right = up_right + 0.90
     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_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*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*24:]
+    test_x_a = test_x[:,:18*21]
+    test_x_a = test_x_a.reshape(test_x.shape[0], 18, 21, 1)
+    # test_x_b = test_x[:, 9*26:9*26+9*26]
+    # test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+    test_x_c = test_x[:,18*21:]
 
     model=load_model(model_path)
-    score = model.evaluate([test_x_c, test_x_a], test_y)
+    score = model.evaluate([test_x_c, test_x_a, ], test_y)
     print('MIX', score)
 
     up_num = 0
@@ -61,7 +60,7 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
     down_error = 0
     down_right = 0
     i = 0
-    result=model.predict([test_x_c, test_x_a,])
+    result = model.predict([test_x_c, test_x_a, ])
     win_dnn = []
     for r in result:
         fact = test_y[i]
@@ -83,6 +82,7 @@ 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
@@ -100,8 +100,8 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1):
 
 
 if __name__ == '__main__':
-    # predict(file_path='D:\\data\\quantization\\stock160_18d_test.log', model_path='162_18d_mix_5D_ma5_s_seq.h5')
-    predict(file_path='D:\\data\\quantization\\stock160_18d_train1.log', model_path='162_18d_mix_5D_ma5_s_seq.h5')
+    predict(file_path='D:\\data\\quantization\\stock175_18d_test.log', model_path='175_18d_mix_6D_ma5_s_seq_2.h5')
+    # predict(file_path='D:\\data\\quantization\\stock175_18d_train1.log', model_path='175_18d_mix_6D_ma5_s_seq_2.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_180.py

@@ -0,0 +1,98 @@
+# -*- 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 + 1.1
+    elif fact[1] == 1:
+        up_right = up_right + 0.99
+        up_error = up_error + 0.2
+    else:
+        up_error = up_error + 1
+        up_right = up_right + 0.90
+    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_a = test_x[:,:18*18]
+    test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
+    # test_x_b = test_x[:, 9*26:9*26+9*26]
+    # test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+    test_x_c = test_x[:,18*18:]
+
+    model=load_model(model_path)
+    score = model.evaluate([test_x_c, test_x_a,], test_y)
+    print('MIX', 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_c, test_x_a,])
+    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
+        else:
+            if r[0] > 0.8:
+                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[2] > 0.6:
+                if fact[0] == 1:
+                    down_error = down_error + 1
+                    down_right = down_right + 1.1
+                elif fact[1] == 1:
+                    down_error = down_error + 0.2
+                    down_right = down_right + 0.99
+                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('MIX', 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
+
+
+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\\stock186A_18d_train1.log', model_path='186A_18d_mix_6D_ma5_s_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_190.py

@@ -0,0 +1,103 @@
+# -*- 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 + 1.1
+    elif fact[1] == 1:
+        up_right = up_right + 0.99
+    elif fact[2] == 1:
+        up_right = up_right + 0.96
+        up_error = up_error + 0.5
+    else:
+        up_error = up_error + 1
+        up_right = up_right + 0.90
+    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_a = test_x[:,:18*18]
+    test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
+    # test_x_b = test_x[:, 9*26:9*26+9*26]
+    # test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+    test_x_c = test_x[:,18*18:]
+
+    model=load_model(model_path)
+    score = model.evaluate([test_x_c, test_x_a,], test_y)
+    print('MIX', 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_c, test_x_a,])
+    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
+        else:
+            if r[0] > 0.5:
+                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[2] > 0.5:
+                if fact[0] == 1:
+                    down_error = down_error + 1
+                    down_right = down_right + 1.06
+                elif fact[1] == 1:
+                    down_error = down_error + 0.3
+                    down_right = down_right + 1
+                elif fact[2] == 1:
+                    down_right = down_right + 0.96
+                else:
+                    down_right = down_right + 0.9
+                down_num = down_num + 1
+
+        i = i + 1
+    if up_num == 0:
+        up_num = 1
+    if down_num == 0:
+        down_num = 1
+    print('MIX', 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
+
+
+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\\stock196_18d_train1.log', model_path='196_18d_mix_6D_ma5_s_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

@@ -41,18 +41,20 @@ def predict(file_path='', model_path='15min_dnn_seq'):
 
         for line in lines:
             train_x = np.array([line[:size - 1]])
-            train_x_a = train_x[:,:18*24]
-            train_x_a = train_x_a.reshape(train_x.shape[0], 18, 24, 1)
+            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*24:]
+            train_x_c = train_x[:,18*18:]
 
             result = model.predict([train_x_c, train_x_a])
 
-            if result[0][3] + result[0][4] > 0.5:
+            if result[0][2]> 0.5:
                 down_num = down_num + 1
-            elif result[0][1] + result[0][0] > 0.5:
-                up_num = up_num + 0.6
+            elif result[0][0] > 0.5:
+                up_num = up_num + 1
+            elif result[0][1] > 0.5:
+                up_num = up_num + 0.2
             # else:
             #     up_num = up_num + 0.4 # 乐观调大 悲观调小
             #     down_num = down_num + 0.6
@@ -64,13 +66,9 @@ def predict(file_path='', model_path='15min_dnn_seq'):
                 x1 = x1 + 1
             if maxx - result[0][2] == 0:
                 x2 = x2 + 1
-            if maxx - result[0][3] == 0:
-                x3 = x3 + 1
-            if maxx - result[0][4] == 0:
-                x4 = x4 + 1
 
         # print(key, int(up_num), int(down_num), (down_num*1.2 + 2)/(up_num*1.2 + 2), )
-        print(key, x0, x1, x2,x3,x4)
+        print(key, x0, x1, x2, (down_num*1.2 + 2)/(up_num*1.2 + 2))
 
 
 if __name__ == '__main__':
@@ -78,5 +76,5 @@ if __name__ == '__main__':
     # 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\\stock16_18d_20200310.log', model_path='16_18d_mix_seq')
-    predict(file_path='D:\\data\\quantization\\stock160_18d_10D_20200313.log', model_path='160_18d_mix_10D_ma5_s_seq')
+    predict(file_path='D:\\data\\quantization\\stock186_18d_20191211.log', model_path='186_18d_mix_6D_ma5_s_seq')
     # predict(file_path='D:\\data\\quantization\\stock9_18_4.log', model_path='18d_dnn_seq.h5')

mix/mix_predict_by_day_190.py

@@ -0,0 +1,85 @@
+# -*- 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')
+
+    model=load_model(model_path + '.h5')
+    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
+        size = len(lines[0])
+        x0 = 0
+        x1 = 0
+        x2 = 0
+        x3 = 0
+        x4 = 0
+
+        for line in lines:
+            train_x = np.array([line[:size - 1]])
+            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:]
+
+            result = model.predict([train_x_c, train_x_a])
+
+            ratio = 1
+            if train_x_c[0][-1] == 1:
+                ratio = 1.2
+
+            if result[0][0]> 0.5:
+                up_num = up_num + ratio
+            elif result[0][1] > 0.5:
+                up_num = up_num + 0.3
+            elif result[0][2] > 0.5:
+                down_num = down_num + 0.3
+            else:
+                down_num = down_num + ratio
+
+            maxx = max(result[0])
+            if maxx - result[0][0] == 0:
+                x0 = x0 + 1
+            if maxx - result[0][1] == 0:
+                x1 = x1 + 1
+            if maxx - result[0][2] == 0:
+                x2 = x2 + 1
+            if maxx - result[0][3] == 0:
+                x3 = x3 + 1
+
+        # print(key, int(up_num), int(down_num), (down_num*1.2 + 2)/(up_num*1.2 + 2), )
+        print(key, x0, x1, x2,x3, (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\\stock16_18d_20200310.log', model_path='16_18d_mix_seq')
+    predict(file_path='D:\\data\\quantization\\stock196_18d_20200325.log', model_path='196_18d_mix_6D_ma5_s_seq')
+    # predict(file_path='D:\\data\\quantization\\stock9_18_4.log', model_path='18d_dnn_seq.h5')

mix/mix_predict_everyday.py

@@ -5,10 +5,21 @@ import joblib
 
 
 holder_stock_list = [
-                        '000063.SZ', '002093.SZ'
-                        '300253.SZ', '300807.SZ',
+                        # 医疗
+                        '000150.SZ', '300300.SZ', '603990.SH', '300759.SZ', '300347.SZ', '300003.SZ', '300253.SZ',
+                        # 5G
+                        '300698.SZ', '600498.SH', '300310.SZ', '600353.SH', '603912.SH', '603220.SH', '300602.SZ', '600260.SH',
+                        # 车联网
+                        '002369.SZ', '002920.SZ', '300020.SZ', '002373.SZ', '002869.SZ',
+                        # 工业互联网
+                        '002184.SZ', '002364.SZ','300310.SZ', '300670.SZ', '300166.SZ', '002169.SZ', '002380.SZ',
+                        # 特高压
+                        '300341.SZ', '300670.SZ', '300018.SZ', '600268.SH', '002879.SZ',
+                        # 基础建设
+                        '300041.SZ', '603568.SH', '000967.SZ', '603018.SH',
+                        # B
+                        '002555.SZ', '002174.SZ'
 
-                         # b账户
 
     ]
 
@@ -82,17 +93,16 @@ def predict_today(file, day, model='10_18d', log=True):
 
     for line in lines:
         train_x = np.array([line[:size - 1]])
-        train_x_a = train_x[:,:18*24]
-        train_x_a = train_x_a.reshape(train_x.shape[0], 18, 24, 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*24:]
+        train_x_tmp = train_x[:,:18*18]
+        train_x_a = train_x_tmp.reshape(train_x.shape[0], 18, 18, 1)
+        # train_x_b = train_x_tmp.reshape(train_x.shape[0], 18, 24)
+        train_x_c = train_x[:,18*18:]
 
-        result = model.predict([train_x_c, train_x_a])
+        result = model.predict([train_x_c, train_x_a, ])
         # print(result, line[-1])
         stock = code_table.find_one({'ts_code':line[-1][0]})
 
-        if result[0][0] + result[0][1] > 0.5:
+        if result[0][0] > 0.5:
             if line[-1][0].startswith('688'):
                 continue
             # 去掉ST
@@ -141,11 +151,11 @@ def predict_today(file, day, model='10_18d', log=True):
                 with open('D:\\data\\quantization\\predict\\' + str(day) + '_mix.txt', mode='a', encoding="utf-8") as f:
                     f.write(str(line[-1]) + ' ' + stock['name'] + ' ' + stock['sw_industry'] + ' ' + str(concept_detail_list) + ' buy' + '\n')
 
-        elif result[0][2] > 0.5:
+        elif result[0][1] > 0.5:
             if stock['ts_code'] in holder_stock_list:
                 print(stock['ts_code'], stock['name'], '震荡评级')
 
-        elif result[0][3] + result[0][4] > 0.5:
+        elif result[0][2] > 0.5:
             if stock['ts_code'] in holder_stock_list:
                 print(stock['ts_code'], stock['name'], '赶紧卖出')
         else:
@@ -202,6 +212,6 @@ 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\\stock6_test.log', model_path='15m_dnn_seq.h5')
     # multi_predict()
-    predict_today("D:\\data\\quantization\\stock160_18d_20200316.log", 20200316, model='160_18d_mix_5D_ma5_s_seq.h5', log=True)
+    predict_today("D:\\data\\quantization\\stock186_18d_20200325.log", 20200325, model='186_18d_mix_6D_ma5_s_seq.h5', log=True)
     # join_two_day(20200305, 20200305)
     # check_everyday(20200311, 20200312)

mix/mix_train_1.py

@@ -14,29 +14,37 @@ from keras.utils import np_utils
 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
 
-epochs= 440
-size = 580000
-file_path = 'D:\\data\\quantization\\stock160_18d_train.log'
-model_path = '160_18d_mix_5D_ma5_s_seq.h5'
+early_stopping = EarlyStopping(monitor='accuracy', patience=5, verbose=2)
 
+epochs= 108
+size = 450000 #18W 60W
+file_path = 'D:\\data\\quantization\\stock175_18d_train2.log'
+model_path = '175_18d_mix_6D_ma5_s_seq_2.h5'
 
-def read_data(path):
+
+def read_data(path, path1="D:\\data\\quantization\\stock175_18d_train1.log"):
     lines = []
     with open(path) as f:
-        i = 0
         for x in range(size): #610000
             line = eval(f.readline().strip())
             lines.append(line)
 
+    with open(path1) as f:
+        for x in range(50000):
+            line = eval(f.readline().strip())
+            lines.append(line)
+
     random.shuffle(lines)
     print('读取数据完毕')
 
-    d=int(0.7*len(lines))
+    d=int(0.85*len(lines))
+    length = len(lines[0])
 
-    train_x=[s[:-2] for s in lines[0:d]]
+    train_x=[s[:length - 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_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')
@@ -51,18 +59,18 @@ def read_data(path):
 
 train_x,train_y,test_x,test_y=read_data(file_path)
 
-train_x_a = train_x[:,:18*24]
-train_x_a = train_x_a.reshape(train_x.shape[0], 18, 24, 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*24:]
+train_x_a = train_x[:,:18*19]
+train_x_a = train_x_a.reshape(train_x.shape[0], 18, 19, 1)
+# train_x_b = train_x[:, 9*26:18*26]
+# train_x_b = train_x_b.reshape(train_x.shape[0], 9, 26, 1)
+train_x_c = train_x[:,18*19:]
 
 
 def create_mlp(dim, regress=False):
     # define our MLP network
     model = Sequential()
-    model.add(Dense(64, input_dim=dim, activation="relu"))
-    model.add(Dense(64, activation="relu"))
+    model.add(Dense(96, input_dim=dim, activation="relu"))
+    model.add(Dense(96, activation="relu"))
 
     # check to see if the regression node should be added
     if regress:
@@ -72,7 +80,7 @@ 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, size=48, kernel_size=(5, 6), regress=False, output=24):
     # initialize the input shape and channel dimension, assuming
     # TensorFlow/channels-last ordering
     inputShape = (width, height, 1)
@@ -80,18 +88,15 @@ def create_cnn(width, height, depth, filters=(4, 6), kernel_size=(5, 6), regress
 
     # define the model input
     inputs = Input(shape=inputShape)
-
-    x = inputs
-
+    # x = inputs
     # CONV => RELU => BN => POOL
-    x = Conv2D(32, kernel_size, strides=2, padding="same")(x)
+    x = Conv2D(size, kernel_size, strides=2, padding="same")(inputs)
     x = Activation("relu")(x)
     x = BatchNormalization(axis=chanDim)(x)
-    # x = MaxPooling2D(pool_size=(2, 2))(x)
-    # if width > 2:
-    #     x = Conv2D(32, (10, 6), padding="same")(x)
-    #     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)
@@ -118,8 +123,11 @@ 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, 24, 1, kernel_size=(6, 6), regress=False, output=256)
-# cnn_1 = create_cnn(18, 2, 1, kernel_size=(6,2), regress=False, output=36)
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(3, 3), size=64, regress=False, output=128)       # 31 97 46
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(6, 6), size=64, regress=False, output=128)         # 29 98 47
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(9, 9), size=64, regress=False, output=128)         # 28 97 53
+cnn_0 = create_cnn(18, 19, 1, kernel_size=(3, 19), size=96, regress=False, output=128)        #A 28 98 40 #B 38 97 51 #A 24 98 41  #b 33 97 48 #B
+# 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
@@ -127,10 +135,10 @@ combinedInput = concatenate([mlp.output, cnn_0.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(1024, 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(1024, activation="relu")(x)
+x = Dense(1024, activation="relu")(x)
 # 在建设一层
 x = Dense(5, activation="softmax")(x)
 
@@ -156,13 +164,17 @@ model.fit(
     # validation_data=([testAttrX, testImagesX], testY),
     # epochs=int(3*train_x_a.shape[0]/1300),
     epochs=epochs,
-    batch_size=2048, shuffle=True)
+    batch_size=2048, shuffle=True,
+    callbacks=[early_stopping]
+)
 
-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*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*24:]
+model.save(model_path)
+
+test_x_a = test_x[:,:18*19]
+test_x_a = test_x_a.reshape(test_x.shape[0], 18, 19, 1)
+# test_x_b = test_x[:, 9*26:9*26+9*26]
+# test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+test_x_c = test_x[:,18*19:]
 
 # make predictions on the testing data
 print("[INFO] predicting house prices...")
@@ -170,6 +182,4 @@ score  = model.evaluate([test_x_c, test_x_a], test_y)
 
 print(score)
 print('Test score:', score[0])
-print('Test accuracy:', score[1])
-
-model.save(model_path)
+print('Test accuracy:', score[1])

mix/mix_train_180.py

@@ -0,0 +1,202 @@
+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,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= 138
+size = 400000 #18W 60W
+file_path = 'D:\\data\\quantization\\stock186B_18d_train2.log'
+model_path = '186B_18d_mix_6D_ma5_s_seq.h5'
+file_path1='D:\\data\\quantization\\stock186B_18d_test.log'
+'''
+1 MACD                      
+4 MACD不在cnn范围内         50,97,43
+2 DMI                       
+5 DMI不在cnn范围内          49,97,42
+3 ROC
+6 ROC不在cnn范围内          50,98,40
+8 RSI                       49,98,42
+'''
+'''
+a 加上大盘涨停和个股统计 涨停/跌停/创业板涨停跌停   39,98,39
+b 加上大盘涨停和个股统计 t1,t2,t3....    
+c MACD + ROC
+d DMI + ROC
+e RSI + ROC           
+'''
+
+def read_data(path, path1=file_path1):
+    lines = []
+    with open(path) as f:
+        for x in range(size): #610000
+            line = eval(f.readline().strip())
+            lines.append(line)
+
+    with open(path1) as f:
+        for x in range(50000):
+            line = eval(f.readline().strip())
+            lines.append(line)
+
+    random.shuffle(lines)
+    print('读取数据完毕')
+
+    d=int(0.85*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), 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(file_path)
+
+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[:, 9*26:18*26]
+# train_x_b = train_x_b.reshape(train_x.shape[0], 9, 26, 1)
+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"))
+
+    # 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):
+    # 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=2, 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, 21, 1, kernel_size=(3, 3), size=64, regress=False, output=128)       # 31 97 46
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(6, 6), size=64, regress=False, output=128)         # 29 98 47
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(9, 9), size=64, regress=False, output=128)         # 28 97 53
+cnn_0 = create_cnn(18, 18, 1, kernel_size=(3, 18), size=96, regress=False, output=96)       #A23 99 33 A' 26 99 36 #B 34 98 43
+# cnn_1 = create_cnn(18, 21, 1, kernel_size=(18, 11), size=96, regress=False, output=96)
+# 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])
+
+# 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(3, 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,], 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_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[:,:18*18]
+test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
+# test_x_b = test_x[:, 9*26:9*26+9*26]
+# test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+test_x_c = test_x[:,18*18:]
+
+# make predictions on the testing data
+print("[INFO] predicting house prices...")
+score  = model.evaluate([test_x_c, test_x_a], test_y)
+
+print(score)
+print('Test score:', score[0])
+print('Test accuracy:', score[1])

mix/mix_train_190.py

@@ -0,0 +1,191 @@
+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,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= 88
+size = 400000 #18W 60W
+file_path = 'D:\\data\\quantization\\stock196_18d_train2.log'
+model_path = '196_18d_mix_6D_ma5_s_seq.h5'
+file_path1='D:\\data\\quantization\\stock196_18d_test.log'
+
+'''
+结果均用使用ma
+4 ROC         
+'''
+
+def read_data(path, path1=file_path1):
+    lines = []
+    with open(path) as f:
+        for x in range(size): #610000
+            line = eval(f.readline().strip())
+            lines.append(line)
+
+    # with open(path1) as f:
+    #     for x in range(50000):
+    #         line = eval(f.readline().strip())
+    #         lines.append(line)
+
+    random.shuffle(lines)
+    print('读取数据完毕')
+
+    d=int(0.85*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), 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(file_path)
+
+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[:, 9*26:18*26]
+# train_x_b = train_x_b.reshape(train_x.shape[0], 9, 26, 1)
+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"))
+
+    # 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):
+    # 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=2, 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, 21, 1, kernel_size=(3, 3), size=64, regress=False, output=128)       # 31 97 46
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(6, 6), size=64, regress=False, output=128)         # 29 98 47
+# cnn_0 = create_cnn(18, 21, 1, kernel_size=(9, 9), size=64, regress=False, output=128)         # 28 97 53
+cnn_0 = create_cnn(18, 18, 1, kernel_size=(3, 18), size=96, regress=False, output=96)       #A23 99 33 A' 26 99 36 #B 34 98 43
+# cnn_1 = create_cnn(18, 21, 1, kernel_size=(18, 11), size=96, regress=False, output=96)
+# 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])
+
+# 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,], 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_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[:,:18*18]
+test_x_a = test_x_a.reshape(test_x.shape[0], 18, 18, 1)
+# test_x_b = test_x[:, 9*26:9*26+9*26]
+# test_x_b = test_x_b.reshape(test_x.shape[0], 9, 26, 1)
+test_x_c = test_x[:,18*18:]
+
+# make predictions on the testing data
+print("[INFO] predicting house prices...")
+score  = model.evaluate([test_x_c, test_x_a], test_y)
+
+print(score)
+print('Test score:', score[0])
+print('Test accuracy:', score[1])

mix/mix_train_2.py

@@ -16,10 +16,10 @@ from keras.layers import LSTM
 from keras import regularizers
 from keras.models import Model
 
-epochs= 440
+epochs= 100
 size = 440000
 file_path = 'D:\\data\\quantization\\stock160_18d_train.log'
-model_path = '163_18d_mix_5D_ma5_s_seq.h5'
+model_path = '170_18d_mix_5D_ma5_s_seq.h5'
 
 
 def read_data(path):
@@ -184,7 +184,6 @@ model.fit(
 test_x_tmp = test_x[:,:18*24]
 test_x_a = test_x_tmp.reshape(test_x.shape[0], 18, 24, 1)
 test_x_b = test_x_tmp.reshape(test_x.shape[0], 18, 24)
-# test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
 test_x_c = test_x[:,18*24:]
 
 # make predictions on the testing data