指数预测

stock/dnn_predict_by_day.py

@@ -0,0 +1,77 @@
+# -*- 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.h5'):
+    day_lines = read_data(file_path)
+    print('数据读取完毕')
+
+    models = []
+    for x in range(0, 12):
+        models.append(load_model('18d_dnn_seq_' + 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 = 21 # 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)
+
+            if r[0] in [2,4,7,10]:
+                train_x = np.array([line[:-1]])
+
+                result = models[r[0]].predict(train_x)
+                if result[0][0] > 0.5 or result[0][1] > 0.5:
+                    up_num = up_num + 1
+
+            elif r[0] in [5,6,11]:
+                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
+
+            else:
+                train_x = np.array([line[:-1]])
+
+                result = models[r[0]].predict(train_x)
+                if result[0][0] > 0.5 or result[0][1] > 0.5:
+                    up_num = up_num + 1
+                elif result[0][3] > 0.5 or result[0][4] > 0.5:
+                    down_num = down_num + 1
+
+        print(key, up_num, down_num, (down_num*1.5 + 1)/(up_num*1.5 + 1))
+
+
+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_20200219.log', model_path='18d_dnn_seq.h5')