123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116 |
- # -*- 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 + 1.12
- elif fact[1] == 1:
- up_right = up_right + 1.06
- elif fact[2] == 1:
- up_right = up_right + 1
- 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
- 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 = test_x.reshape(test_x.shape[0], 1,6,77)
- model=load_model(model_path)
- score = model.evaluate(test_x, test_y)
- print('DNN', 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)
- 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] > 0.7 or r[1] > 0.7:
- 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:
- if fact[0] == 1:
- down_error = down_error + 1
- down_right = down_right + 1.12
- elif fact[1] == 1:
- down_error = down_error + 1
- down_right = down_right + 1.06
- elif fact[2] == 1:
- down_right = down_right + 1
- elif fact[3] == 1:
- down_right = down_right + 0.94
- 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('DNN', 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
- def multi_predict(model='14_18d'):
- r = 0;
- p = 0
- for x in range(0, 12): # 0,2,3,4,6,8,9,10,11
- # for x in [5,9,11,0,3,4,8]: #10_18,0没数据需要重新计算 [0,2,3,4,5,9,10,11]
- # for x in [0,1,10]:
- # for x in [2,4,7,10]: # 2表现最好 优秀的 0,8正确的反向指标,(9错误的反向指标 样本量太少)
- print(x)
- # for x in [0,2,5,6,7]: # 5表现最好
- win_dnn, up_ratio,down_ratio = predict(file_path='D:\\data\\quantization\\kmeans\\stock' + model + '_test_' + str(x) + '.log',
- model_path=model + '_dnn_seq_' + str(x) + '.h5', idx=x)
- r = r + up_ratio
- p = p + down_ratio
- print(r, p)
- if __name__ == '__main__':
- predict(file_path='D:\\data\\quantization\\stock16_18d_test.log', model_path='16_18d_cnn_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')
|