modify

mix/mix_predict_600.py

@@ -2,6 +2,7 @@
 import numpy as np
 from keras.models import load_model
 import joblib
+import random
 
 
 def read_data(path):
@@ -17,26 +18,83 @@ def read_data(path):
     return np.array(train_x, dtype=np.float32),np.array(train_y, dtype=np.float32),lines
 
 
-def _score(fact, line):
+def _score(fact,):
     up_right = 0
     up_error = 0
 
+    # if fact[0] == 1:
+    #     up_right = up_right + 1.06
+    # elif fact[1] == 1:
+    #     up_error = up_error + 0.5
+    #     up_right = up_right + 0.98
+    # else:
+    #     up_error = up_error + 1
+    #     up_right = up_right + 0.93
     if fact[0] == 1:
-        up_right = up_right + 1.06
+        up_right = up_right + 1.1
     elif fact[1] == 1:
-        up_error = up_error + 0.3
-        up_right = up_right + 0.98
+        up_error = up_error + 0.4
+        up_right = up_right + 1.03
     else:
         up_error = up_error + 1
-        up_right = up_right + 0.94
+        up_right = up_right + 0.9
     return up_right,up_error
 
 
+def random_predict(file_path=''):
+    test_x,test_y,lines=read_data(file_path)
+    a=0
+    b=0
+    c=0
+    d=0
+    R=0
+
+    up_num = 0
+    up_error = 0
+    up_right = 0
+    down_num = 0
+    down_error = 0
+    down_right = 0
+    score = 0
+
+    for x in test_y:
+        xx = random.uniform(0, 3)
+        if xx > 2:
+            if x[0] == 1:
+                R = R + 1
+            if x[0] == 1:
+                up_right = up_right + 1
+                score = 3 + score
+            elif x[1] == 1:
+                score = 2 + score
+            else:
+                score = 1 + score
+            up_num = up_num + 1
+        elif xx > 1 and x[1] == 1:
+            R = R + 1
+        elif xx > 0 and x[2] == 1:
+            R = R + 1
+
+        if x[0] == 1:
+            a = a + 1
+        elif x[1] == 1:
+            b = b + 1
+        elif x[2] == 1:
+            c = c + 1
+
+    if up_num == 0:
+        up_num = 1
+    if down_num == 0:
+        down_num = 1
+
+    print(R/(a + b + c +d), score/up_num, up_right/up_num)
+
+
 def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1, row=18, col=20):
     test_x,test_y,lines=read_data(file_path)
 
     test_x_a = test_x[:,:row*col]
-    test_x_a = test_x_a.reshape(test_x.shape[0], row, col, 1)
+    test_x_a = test_x_a.reshape(test_x.shape[0], 1, row, col)
     # test_x_b = test_x[:, row*col:row*col+18*2]
     # test_x_b = test_x_b.reshape(test_x.shape[0], 18, 2, 1)
     test_x_c = test_x[:,row*col:]
@@ -56,22 +114,25 @@ def predict(file_path='', model_path='15min_dnn_seq.h5', idx=-1, row=18, col=20)
     win_dnn = []
     for r in result:
         fact = test_y[i]
+        xx = random.uniform(0, 3)
 
         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])
+            if r[0] > 0.7:
+            # if xx > 2:
+                tmp_right,tmp_error = _score(fact,)
                 up_right = tmp_right + up_right
                 up_error = tmp_error + up_error
                 up_num = up_num + 1
             elif r[2] > 0.5:
+            # elif xx < 2:
                 if fact[0] == 1:
                     down_error = down_error + 1
                     down_right = down_right + 1.04
                 elif fact[1] == 1:
-                    down_error = down_error + 0.3
+                    down_error = down_error + 0.5
                     down_right = down_right + 0.98
                 else:
                     down_right = down_right + 0.92
@@ -90,7 +151,7 @@ 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\\stock217_18d_train1.log', model_path='218_18d_mix_5D_ma5_s_seq.h5', row=18, col=18)
     # predict(file_path='D:\\data\\quantization\\stock400_18d_train1.log', model_path='400_18d_mix_5D_ma5_s_seq.h5', row=18, col=18)
-    predict(file_path='D:\\data\\quantization\\stock603_30d_train1.log', model_path='603_30d_mix_5D_ma5_s_seq.h5', row=30, col=19)
+    # predict(file_path='D:\\data\\quantization\\stock571_12d_train1.log', model_path='570_5d_mix_5D_ma5_s_seq.h5', row=5, col=31)
     # 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')
+    random_predict(file_path='D:\\data\\quantization\\stock578N_12d_train1.log')

mix/mix_predict_by_day_578A.py

@@ -4,12 +4,14 @@ from keras.models import load_model
 import joblib
 
 
+indent = -1
+
 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])
+            date = str(line[indent][-1])
             if date in day_lines:
                 day_lines[date].append(line)
             else:
@@ -40,21 +42,16 @@ def predict(file_path='', model_path='15min_dnn_seq', rows=18, cols=18):
         x4 = 0
 
         for line in lines:
-            train_x = np.array([line[:size - 1]])
-            train_x_a = train_x[:,:rows*cols]
-            train_x_a = train_x_a.reshape(train_x.shape[0], rows, cols, 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[:,rows*cols:]
+            train_x = np.array([line[:size + indent]])
 
-            result = model.predict([train_x_c, train_x_a])
+            result = model.predict([train_x])
 
             ratio = 1
-            if train_x_c[0][-1] == 1:
-                ratio = 2
-            elif train_x_c[0][-2] == 1:
+            if train_x[0][-1] == 1:
+                ratio = 2.1
+            elif train_x[0][-2] == 1:
                 ratio = 1.6
-            elif train_x_c[0][-3] == 1:
+            elif train_x[0][-3] == 1:
                 ratio = 1.3
 
             if result[0][0]> 0.5:
@@ -62,29 +59,26 @@ def predict(file_path='', model_path='15min_dnn_seq', rows=18, cols=18):
             elif result[0][1] > 0.5:
                 up_num = up_num + 0.4*ratio
             elif result[0][2] > 0.5:
-                down_num = down_num + 0.4*ratio
-            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:
+            elif maxx - result[0][1] == 0:
                 x1 = x1 + 1
-            if maxx - result[0][2] == 0:
+            else:
                 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*1.5 + 2)/(up_num*1.2 + 2))
+        print(key, x0, x1, x2, (down_num*1.5 + 2)/(up_num*1.2 + 2))
 
 
 import datetime
 if __name__ == '__main__':
     today = datetime.datetime.now()
     today = today
-    today =  today.strftime('%Y%m%d')
+    today = today.strftime('%Y%m%d')
+    today = '20200512'
     # 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')
@@ -92,10 +86,10 @@ if __name__ == '__main__':
     # predict(file_path='D:\\data\\quantization\\stock196_18d_20200326.log', model_path='196_18d_mix_6D_ma5_s_seq')
 
 
-    # predict(file_path='D:\\data\\quantization\\stock321_28d_5D_20200429.log', model_path='321_28d_mix_5D_ma5_s_seq_2', rows=28, cols=20)
-
-    predict(file_path='D:\\data\\quantization\\stock327_28d_' + today + '.log', model_path='327_28d_mix_5D_ma5_s_seq', rows=28, cols=20)
+    # predict(file_path='D:\\data\\quantization\\stock578N_12d_train3.log', model_path='5d_578N_dnn_seq', rows=28, cols=20)
 
+    predict(file_path='D:\\data\\quantization\\stock578N_5d_' + today + '.log', model_path='5d_578N_dnn_seq', rows=28, cols=20)
+    #
 
 
     # predict(file_path='D:\\data\\quantization\\stock9_18_4.log', model_path='18d_dnn_seq.h5')

mix/mix_predict_everyday_600.py

@@ -44,7 +44,7 @@ def predict_today(file, day, model='10_18d', log=True):
         # print(result, line[-1])
         stock = code_table.find_one({'ts_code':line[-1][0]})
 
-        if result[0][0] > 0.85:
+        if result[0][0] > 0.8:
             if line[-1][0].startswith('688'):
                 continue
             # 去掉ST
@@ -78,10 +78,10 @@ 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) + ' ' + str(result[0][0]) + '\n')
 
-        elif result[0][1] > 0.5:
+        elif result[0][1] > 0.4:
             if stock['ts_code'] in holder_stock_list:
                 print(stock['ts_code'], stock['name'], '震荡评级')
-        elif result[0][2] > 0.5:
+        elif result[0][2] > 0.4:
             if stock['ts_code'] in holder_stock_list:
                 print(stock['ts_code'], stock['name'], '赶紧卖出')
 
@@ -124,6 +124,6 @@ if __name__ == '__main__':
     # multi_predict()
     # predict_today("D:\\data\\quantization\\stock405_30d_20200413.log", 20200413, model='405_30d_mix_5D_ma5_s_seq.h5', log=True)
     # 模型 下跌趋势，没大涨的不要买
-    predict_today("D:\\data\\quantization\\stock578A_5d_20200430.log", 20200430, model='5d_578A_dnn_seq.h5', log=True)
+    predict_today("D:\\data\\quantization\\stock578A_5d_20200512.log", 20200430, model='5d_578A_dnn_seq.h5', log=True)
     # join_two_day(20200305, 20200305)
     # check_everyday(20200311, 20200312)

mix/stock_source.py

@@ -19,7 +19,8 @@ zixuan_stock_list = [
     '603568.SH', '000967.SZ', '603018.SH','002062.SZ','600452.SH',
     # 华为
     '300687.SZ','002316.SZ','300339.SZ','300378.SZ','300020.SZ','300634.SZ','002570.SZ', '300766.SZ',
-
+    # hsgt
+    '603713.SH',
 ]
 
 zeng_stock_list = [
@@ -27,7 +28,7 @@ zeng_stock_list = [
     '300097.SZ', '000625.SZ', '000876.SZ', '603258.SH', '002973.SZ', '300390.SZ', '002030.SZ', '002041.SZ', '000767.SZ', '002214.SZ', '002869.SZ',
     '300541.SZ', '002185.SZ',
     '002555.SZ','600585.SH','600276.SH','002415.SZ','000651.SZ',
-    '601800.SH', '601108.SH', '601186.SH',
+    '601800.SH', '601186.SH',
 ]
 
 ROE_stock_list =   [                      # ROE
@@ -49,12 +50,12 @@ ROE_stock_list =   [                      # ROE
 
 
 holder_stock_list = [
-    '002415.SZ','002214.SZ', '002459.SZ'
+    '002415.SZ','002214.SZ', '002459.SZ', '002035.SZ', '000963.SZ',
 
-    '300639.SZ','300003.SZ', '300185.SZ',
+    '300639.SZ','300185.SZ', '601162.SH',
 
-    '600196.SH', '601108.SH', '600057.SH',
-    '601211.SH', '600452.SH', '603638.SH',
+    '600196.SH', '600057.SH',
+    '603638.SH',
 ]
 
 

stock/dnn_predict_by_day.py

@@ -35,13 +35,13 @@ def predict(file_path='', model_path='15min_dnn_seq'):
 
         up_num = 0
         down_num = 0
-        x = 16 # 每条数据项数
+        x = 24 # 每条数据项数
         k = 18 # 周期
         for line in lines:
-            v = line[0:x*k]
+            v = line[1:x*k+1]
             v = np.array(v)
             v = v.reshape(k, x)
-            v = v[:,6:10]
+            v = v[:,4:8]
             v = v.reshape(1, 4*k)
             # print(v)
             r = estimator.predict(v)
@@ -52,22 +52,7 @@ def predict(file_path='', model_path='15min_dnn_seq'):
             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 + 0.5  # 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
+                up_num = up_num + 0.6  # 乐观调大 悲观调小
 
         print(key, int(up_num), int(down_num), (down_num*1.2 + 2)/(up_num*1.2 + 2))
 
@@ -76,6 +61,6 @@ 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\\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\\stock19_18d_20200309.log', model_path='19_18d_dnn_seq')
+    predict(file_path='D:\\data\\quantization\\stock16_18d_20200311.log', model_path='16_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')

stock/dnn_predict_dmi_everyday.py

@@ -6,13 +6,13 @@ import joblib
 
 holder_stock_list = [
                      '000063.SZ',
-                     '002796.SZ',
                      '002373.SZ',
                      '300253.SZ',
                      '300059.SZ',
                     # b账户
                      '002373.SZ',
                      '300422.SZ',
+                     '300468.SZ',
     ]
 
 
@@ -91,6 +91,7 @@ def predict_today(day, model='10_18d', log=True):
 
     x = 24 # 每条数据项数
     k = 18 # 周期
+    shift = 1
     for line in lines:
         # print(line)
         v = line[1:x*k + 1]
@@ -107,7 +108,7 @@ def predict_today(day, model='10_18d', log=True):
         # print(result, line[-1])
         stock = code_table.find_one({'ts_code':line[-1][0]})
 
-        if result[0][0] > 0.6 or result[0][1] > 0.6:
+        if result[0][0] > 0.5 or result[0][1] > 0.5:
             if line[-1][0].startswith('688'):
                 continue
             # 去掉ST
@@ -132,29 +133,29 @@ def predict_today(day, model='10_18d', log=True):
             concept_detail_list = []
 
             # 处理行业
-            if stock['industry'] in hangye_map:
-                i_c = hangye_map[stock['industry']]
-                hangye_map[stock['industry']] = i_c + 1
+            if stock['sw_industry'] in hangye_map:
+                i_c = hangye_map[stock['sw_industry']]
+                hangye_map[stock['sw_industry']] = i_c + 1
             else:
-                hangye_map[stock['industry']] = 1
-
-            if len(concept_code_list) > 0:
-                for concept in concept_code_list:
-                    for c in all_concept_code_list:
-                        if c['code'] == concept['concept_code']:
-                            concept_detail_list.append(c['name'])
-
-                            if c['name'] in gainian_map:
-                                g_c = gainian_map[c['name']]
-                                gainian_map[c['name']] = g_c + 1
-                            else:
-                                gainian_map[c['name']] = 1
-
-            print(line[-1], stock['name'], stock['industry'], str(concept_detail_list), 'buy', k_table_list[0]['pct_chg'])
+                hangye_map[stock['sw_industry']] = 1
+
+            # if len(concept_code_list) > 0:
+            #     for concept in concept_code_list:
+            #         for c in all_concept_code_list:
+            #             if c['code'] == concept['concept_code']:
+            #                 concept_detail_list.append(c['name'])
+            #
+            #                 if c['name'] in gainian_map:
+            #                     g_c = gainian_map[c['name']]
+            #                     gainian_map[c['name']] = g_c + 1
+            #                 else:
+            #                     gainian_map[c['name']] = 1
+
+            print(line[-1], stock['name'], stock['sw_industry'], str(concept_detail_list), 'buy', k_table_list[0]['pct_chg'])
 
             if log is True:
                 with open('D:\\data\\quantization\\predict\\' + str(day) + '.txt', mode='a', encoding="utf-8") as f:
-                    f.write(str(line[-1]) + ' ' + stock['name'] + ' ' + stock['industry'] + ' ' + str(concept_detail_list) + ' buy' + '\n')
+                    f.write(str(line[-1]) + ' ' + stock['name'] + ' ' + stock['sw_industry'] + ' ' + str(concept_detail_list) + ' buy' + '\n')
 
 
             # concept_list = list(stock_concept_table.find({'ts_code':stock['ts_code']}))
@@ -196,5 +197,5 @@ 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(20200303, model='11_18d', log=True)
-    join_two_day(20200303, 20200303)
+    # predict_today(20200305, model='11_18d', log=True)
+    join_two_day(20200311, 20200311)

stock/dnn_train.py

@@ -18,9 +18,9 @@ def read_data(path):
         for line in f.readlines()[:]:
             lines.append(eval(line.strip()))
 
-    # with open("D:\\data\\quantization\\stock578A_12d_train1.log") as f:
-    #     for line in f.readlines()[:]:
-    #         lines.append(eval(line.strip()))
+    with open("D:\\data\\quantization\\stock578N_12d_train3.log") as f:
+        for line in f.readlines()[:]:
+            lines.append(eval(line.strip()))
 
     random.shuffle(lines)
     print('读取数据完毕')
@@ -119,7 +119,6 @@ def train(result_class=3, file_path="D:\\data\\quantization\\stock6.log", model_
 
 568 3d-3 input_dim=  >0.7 35,97,64   
 569 4d-3 input_dim=  >0.7 33,100,52   >0.9 33,100.3,50
-570 5d-3 input_dim=  >0.9 32,102,42   随机45,99,56
 571 6d-3 >0.7 37,100,48
 572 5d-3 + macd+roc 37,101,46
 573 +index  32,101,44
@@ -129,11 +128,27 @@ def train(result_class=3, file_path="D:\\data\\quantization\\stock6.log", model_
 577 加上r0_ratio 34,100,48
 578 570修正 30,101,47 
 578A 38,101.7 44
-578B 4class 38,101.7 44
-574A >0.8 34,98,59
+578B 4class 
+578C 加上指数 38,99,52
+578D 指数涨幅 34,100,50
+578E 涨停数 39,100,51
+578F 加上是否最高最低 34,,100.9,48
+579G 换成dmi 32 100.9 47
+579H 回退 去掉roc等  39,101.5,45
+579I 加上是否最高最低 30,100,50
+579J 加上DMI 34，101，47
+
+574A >0.8 34,98,59           36,1.86,25  
+570 5d-3 input_dim=  >0.9                       32,102,42   随机45,99,56
+
+578K 用上日收盘价 39,101,46
+578L 仅ROC   41,101.6,43     41,2.036,29
+578M 仅macd  41,101.7,43     41,2.035,28
+578N 仅DMI                   42,2.079,33  随机45,1.82,20
+578O 都去掉                  41,2.013,29
 '''
 if __name__ == '__main__':
     # train(input_dim=176, result_class=5, file_path="D:\\data\\quantization\\stock6_5.log", model_name='5d_dnn_seq.h5')
-    train(result_class=4, file_path="D:\\data\\quantization\\stock578B_12d_train2.log", model_name='5d_578B_dnn_seq.h5')
+    train(result_class=3, file_path="D:\\data\\quantization\\stock578N_12d_train2.log", model_name='5d_578N_dnn_seq.h5')
     # resample('D:\\data\\quantization\\stock8_14.log')
     # mul_train()