def evaluate_model(model_path, code, output_dir, input_shape=[30, 61]):
extract_from_file("dataset/%s.csv" % code, output_dir, code)
train_set, test_set = read_feature(output_dir, input_shape, code)
saved_wp = WindPuller(input_shape).load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
[cr, cap] = calculate_cumulative_return(test_set.labels, pred)
# Output to a csv file
# Read in the date, close from original data file.
days_for_test = 700
tmp = pd.read_csv('dataset/%s.csv' % code, delimiter='\t')
# tmp.columns = ['date', 'open', 'high', 'low', 'close', 'volume']
date = tmp['date'][-days_for_test:]
close = tmp['close'][-days_for_test:]
output = pd.DataFrame(
{
'Return': test_set.labels,
'Position': pred.reshape(-1),
'Capital': cap.reshape(-1),
'Close': close.values
},
index=date,
columns=['Close', 'Return', 'Position', 'Capital'])
output.to_csv('output/%s.csv' % code)
def evaluate_model(model_path, code, input_shape=[30, 83]):
extract_from_file("dataset/%s.csv" % code, code)
train_set, test_set = read_feature(".", input_shape, code)
saved_wp = WindPuller(input_shape).load_model(model_path)
scores = saved_wp.evaluate(test_set.images, test_set.labels, verbose=0)
print('Test loss:', scores[0])
print('test accuracy:', scores[1])
pred = saved_wp.predict(test_set.images, 1024)
cr = calculate_cumulative_return(test_set.labels, pred)
print("changeRate\tpositionAdvice\tprincipal\tcumulativeReturn")
for i in range(len(test_set.labels)):
print(str(test_set.labels[i]) + "\t" + str(pred[i]) + "\t" + str(cr[i] + 1.) + "\t" + str(cr[i]))
def paper_test():
'''
逐个读取每一天的14：57的数据，与数据库中数据合并，生成新特征，读取训练好的模型，
预测出信号。
'''
merged_data_dir = './paper_merge'
signal_dir = './paper_signals'
date = get_date_list()
files = os.listdir(tsl_data_dir)
# 0. 加载模型
wp_buy = WindPuller(input_shape).load_model(model_path_buy)
wp_sell = WindPuller(input_shape).load_model(model_path_sell)
for (idx, d) in enumerate(date):
print('当前处理日期\t%s' % d)
for (idf, f) in enumerate(files):
# 1. 读取新的数据
f_path1 = os.path.join(tsl_data_dir, f)
df1 = pd.read_csv(f_path1)
# 获取某一天的数据
df1 = df1[df1['date'] == d]
df1['volume'] == df1['volume'] * 80 / 79
# 2. 读取原来的数据
f_path2 = os.path.join(data_dir, f)
df2 = pd.read_csv(f_path2)
# 3. 合并数据，删除原来数据多余部分，追加最新的一天的数据
df2 = df2.iloc[:int(np.flatnonzero(df2.date == d))]
df3 = df2.append(df1, ignore_index=True)
df3 = df3[df2.columns]
# 4. 保存数据
f_path_merged = os.path.join(merged_data_dir, f)
df3.to_csv(f_path_merged, index=False)
# 5. 提取1个特征，存入相应文件夹
output_prefix = f.split('.')[0]
extract_from_file(idx, f_path_merged, feature_dir, output_prefix,
1)
# 6. 读取提取完的特征
test_set = read_features(feature_dir, input_shape, output_prefix)
# 7. 训练模型
signal_buy = wp_buy.predict(test_set.images, 1024)
signal_buy = float(signal_buy[-1])
signal_sell = wp_sell.predict(test_set.images, 1024)
signal_sell = float(signal_sell[-1])
# 8. 保存结果
f_path_signal = os.path.join(signal_dir, f)
if idx == 0:
# 写入字段名
title = 'date,signal_buy,signal_sell'
with open(f_path_signal, 'a') as file:
file.write(title)
write = '%s,%.2f,%.2f\n' % (d, signal_buy, signal_sell)
with open(f_path_signal, 'a') as file:
file.write(write)
n_read = idx * len(files) + idf + 1
print('当前处理第%d个文件，剩余%d个文件，请耐心等待...' %
(n_read, len(files) * len(date) - n_read))
print('-' * 50)
print('\n全部处理完毕！')
print('=' * 80)
