def get_high_low_points(self, stock_code_list):
msg = '''<html> <tr>Trend inverse reminder from H&L Model</tr> <table width="300" border="1" bordercolor="black" cellspacing="1">'''
bar_size = [5, 30, 60]
column_num = [5, 9, 13]
threshold = [0.03, 0.05, 0.15]
send_email_flag = False
for ii in range(len(bar_size)):
if bar_size[ii] == 60:
stock_intraday_data = LoadData.get_daily_stock_data(
stock_code_list, "20100101")
msg = msg + ''' <tr><td rowspan="2">''' + ''' daily </td>'''
else:
stock_intraday_data = LoadData.get_intraday_stock_data(
stock_code_list, bar_size=bar_size[ii], delta_days=365)
msg = msg + ''' <tr><td rowspan="2">''' + str(
bar_size[ii]) + ''' min </td>'''
high_point_index_list, high_point_list, high_point_time_list, low_point_index_list, low_point_list, low_point_time_list = HighLowPoint.get_high_low_points_list(
stock_intraday_data, threshold[ii])
fall_end_list = []
rise_end_lsit = []
fall_end_msg = ""
rise_end_msg = ""
for jj in range(len(stock_code_list)):
self.write_data_to_file(column_num[ii], jj,
high_point_list[jj][-1],
high_point_time_list[jj][-1],
low_point_list[jj][-1],
low_point_time_list[jj][-1])
temp_msg_fall_end, temp_msg_rise_end = self.judge_trend_inverse(
high_point_list[jj], low_point_list[jj],
self.current_price[jj])
if temp_msg_fall_end == True:
fall_end_list.append(stock_code_list[jj])
send_email_flag = True
if temp_msg_rise_end == True:
rise_end_lsit.append(stock_code_list[jj])
send_email_flag = True
for item in fall_end_list:
fall_end_msg = fall_end_msg + item + " "
for item in rise_end_lsit:
rise_end_msg = rise_end_msg + item + " "
msg = msg + "<td>" + "Falling End" + "</td><td>" + fall_end_msg + "</td></tr><tr><td> Rising End </td><td>" + rise_end_msg + "</td></tr> \n"
msg = msg + " </table></html>"
print msg
if send_email_flag == True:
a = SendEmail.Send_Email("Trend inverse reminder from H&L Model",
msg)
print a.isSend
def verify_account(self):
self.usernameError.setText('')
self.passwordError.setText('')
data = LoadData()
if self.usernameInput.text() != '' and self.passwordInput != '':
if self.usernameInput.text() == '':
self.usernameError.setText('Please enter a username')
self.usernameError.adjustSize()
if self.passwordInput.text() == '':
self.passwordError.setText('Please enter a password')
self.passwordError.adjustSize()
if self.usernameInput.text() not in data.username_list:
self.usernameError.setText('Please check your username')
self.usernameError.adjustSize()
else:
if self.passwordInput.text() not in data.password_list:
self.passwordError.setText('You got the wrong password')
self.passwordError.adjustSize()
else:
self.usernameError.setText('Please enter a username')
self.usernameError.adjustSize()
self.passwordError.setText('Please enter a password')
self.passwordError.adjustSize()
def __init__(self): input_file_path = "input/PriceVolume/bench_mark.xlsx" bench_mark_list,self.bench_mark_name_list = self.load_bench_mark_data(input_file_path) #bench_mark_list = ["000016.SH","000001.SH","000300.SH","399006.SZ","399905.SZ"] #self.bench_mark_name_list = [u"上证50",u"上证综指",u"沪深300",u"创业板指",u"中证500"] #bench_mark_list = ["0806.HK","QIHU.N"] #self.bench_mark_name_list = [u"惠理",u"奇虎"] stock_data_list = LoadData.get_daily_stock_data(bench_mark_list,"20110101") self.price_index = 4 self.volume_index = 5 self.trade_cost = 1-0.001 self.range_day = 1 self.regression_day = [2,5] # short flag = 1 表示可以做空 short_flag = 1 self.price_list = [] self.volume_list = [] for ii in range(len(bench_mark_list)): self.price_list.append(list(zip(*stock_data_list[ii])[self.price_index])) self.volume_list.append(list(zip(*stock_data_list[ii])[self.volume_index])) self.plot(self.price_list,bench_mark_list,self.range_day,short_flag) #self.run(bench_mark_list) print "done\n"
def __init__(self): file_path = "input/HighLowPoint/user_data.xlsx" stock_code_list,stock_name_list,stock_buy_price_list,stock_sell_price_list = LoadUserData.load_user_data(file_path) stock_daily_data_list = LoadData.get_daily_stock_data(stock_code_list) self.fall_end_flag = [] self.rise_end_flag = [] print "begin running\n" self.run(stock_code_list,stock_buy_price_list,stock_sell_price_list)
def get_high_low_points(self,stock_code_list):
msg = '''<html> <tr>Trend inverse reminder from H&L Model</tr> <table width="300" border="1" bordercolor="black" cellspacing="1">'''
bar_size = [5,30,60]
column_num = [5,9,13]
threshold = [0.03,0.05,0.15]
send_email_flag = False
for ii in range(len(bar_size)):
if bar_size[ii]==60:
stock_intraday_data = LoadData.get_daily_stock_data(stock_code_list,"20100101")
msg = msg +''' <tr><td rowspan="2">''' + ''' daily </td>'''
else:
stock_intraday_data = LoadData.get_intraday_stock_data(stock_code_list,bar_size=bar_size[ii],delta_days = 365)
msg = msg +''' <tr><td rowspan="2">''' +str(bar_size[ii]) + ''' min </td>'''
high_point_index_list,high_point_list,high_point_time_list,low_point_index_list,low_point_list,low_point_time_list = HighLowPoint.get_high_low_points_list(stock_intraday_data,threshold[ii])
fall_end_list = []
rise_end_lsit = []
fall_end_msg = ""
rise_end_msg = ""
for jj in range(len(stock_code_list)):
self.write_data_to_file(column_num[ii],jj,high_point_list[jj][-1],high_point_time_list[jj][-1],low_point_list[jj][-1],low_point_time_list[jj][-1])
temp_msg_fall_end, temp_msg_rise_end = self.judge_trend_inverse(high_point_list[jj],low_point_list[jj],self.current_price[jj])
if temp_msg_fall_end ==True:
fall_end_list.append(stock_code_list[jj])
send_email_flag = True
if temp_msg_rise_end == True:
rise_end_lsit.append(stock_code_list[jj])
send_email_flag = True
for item in fall_end_list:
fall_end_msg = fall_end_msg + item + " "
for item in rise_end_lsit:
rise_end_msg = rise_end_msg + item +" "
msg = msg +"<td>" + "Falling End" + "</td><td>"+fall_end_msg +"</td></tr><tr><td> Rising End </td><td>"+rise_end_msg+"</td></tr> \n"
msg = msg +" </table></html>"
print msg
if send_email_flag == True:
a = SendEmail.Send_Email("Trend inverse reminder from H&L Model",msg)
print a.isSend
def __init__(self):
file_path = "input/HighLowPoint/user_data.xlsx"
stock_code_list, stock_name_list, stock_buy_price_list, stock_sell_price_list = LoadUserData.load_user_data(
file_path)
stock_daily_data_list = LoadData.get_daily_stock_data(stock_code_list)
self.fall_end_flag = []
self.rise_end_flag = []
print "begin running\n"
self.run(stock_code_list, stock_buy_price_list, stock_sell_price_list)
def run(self,stock_code_list,stock_buy_price_list,stock_sell_price_list): for ii in range(60): print "the " + str(ii) + " th is begining" self.current_price = LoadData.get_realtime_price(stock_code_list) print self.current_price self.get_high_low_points(stock_code_list) #self.stock_price_reminder(stock_code_list,stock_buy_price_list,stock_sell_price_list) print "the "+ str(ii) + " th is done." time.sleep(300)
def run(self, stock_code_list, stock_buy_price_list,
stock_sell_price_list):
for ii in range(60):
print "the " + str(ii) + " th is begining"
self.current_price = LoadData.get_realtime_price(stock_code_list)
print self.current_price
self.get_high_low_points(stock_code_list)
#self.stock_price_reminder(stock_code_list,stock_buy_price_list,stock_sell_price_list)
print "the " + str(ii) + " th is done."
time.sleep(300)
def __init__(self,
ma_days=200,
start_date="19950101",
init_days=60,
short_flag=0):
input_file_path = "../input/DeviationFromMA/user_data.xlsx"
self.user_stock_code_list, self.user_stock_name_list = self.load_excel(
input_file_path)
self.user_stock_data_list = LoadData.get_daily_stock_data(
self.user_stock_code_list, start_date)
self.short_flag = short_flag
self.trade_cost = 1 - 0.001
self.ma_days = ma_days
self.user_stock_price_data_list = []
self.user_stock_uniform_price_list = []
self.user_stock_datetime_list = []
self.user_stock_price_data_old_list = []
for ii in range(len(self.user_stock_code_list)):
self.user_stock_price_data_list.append(
(list(zip(*self.user_stock_data_list[ii])[4]))[init_days:])
self.user_stock_price_data_old_list.append(
list(zip(*self.user_stock_data_list[ii])[4]))
self.user_stock_datetime_list.append(
(list(zip(*self.user_stock_data_list[ii])[0]))[init_days:])
self.user_stock_uniform_price_list.append(
CalcIndex.Uniform_Price(self.user_stock_price_data_list[ii]))
self.price_ma_list = CalcIndex.Calc_MA(
self.user_stock_price_data_old_list, int(ma_days), int(init_days))
self.diviation_from_ma_list, self.diviation_from_ma_std_list = self.calc_diviation_from_ma(
ma_days)
self.ma_dict = {60: 10, 120: 20, 200: 60, 250: 60}
self.diviation_ma_list = CalcIndex.Calc_MA(self.diviation_from_ma_list,
self.ma_dict[self.ma_days])
#self.plot(ma_days)
#self.eveluate_index(ma_days)
long_stand_deviation = {60: -0.5, 120: -0.1, 200: -0.15, 250: -0.2}
short_stand_deviation = {60: 0.5, 120: 0.1, 200: 0.15, 250: 0.2}
self.back_test_info = self.back_test(long_stand_deviation[ma_days],
short_stand_deviation[ma_days])
self.plot_back_test(ma_days)
print "done."
def __init__(self): file_path = "input/user_data.xlsx" self.user_stock_code_list,self.user_stock_name_list,user_stock_buy_point_list,user_stock_sell_point_list = LoadUserData.load_user_data(file_path) self.daily_stock_data_all = LoadData.get_daily_stock_data(self.user_stock_code_list,"20150101") #存放收盘价 self.daily_stock_data = [] for ii in range(len(self.daily_stock_data_all)): temp = [] for jj in range(len(self.daily_stock_data_all[ii])): temp.append(self.daily_stock_data_all[ii][jj][4]) self.daily_stock_data.append(temp) #print self.daily_stock_data[0][-1],self.daily_stock_data[1][-1] self.reminder_info= [] self.run()
def __init__(self):
file_path = "input/user_data.xlsx"
self.user_stock_code_list, self.user_stock_name_list, user_stock_buy_point_list, user_stock_sell_point_list = LoadUserData.load_user_data(
file_path)
self.daily_stock_data_all = LoadData.get_daily_stock_data(
self.user_stock_code_list, "20150101")
#存放收盘价
self.daily_stock_data = []
for ii in range(len(self.daily_stock_data_all)):
temp = []
for jj in range(len(self.daily_stock_data_all[ii])):
temp.append(self.daily_stock_data_all[ii][jj][4])
self.daily_stock_data.append(temp)
#print self.daily_stock_data[0][-1],self.daily_stock_data[1][-1]
self.reminder_info = []
self.run()
def __init__(self):
input_file_path = "input/PriceVolume/bench_mark.xlsx"
bench_mark_list, self.bench_mark_name_list = self.load_bench_mark_data(
input_file_path)
#bench_mark_list = ["000016.SH","000001.SH","000300.SH","399006.SZ","399905.SZ"]
#self.bench_mark_name_list = [u"上证50",u"上证综指",u"沪深300",u"创业板指",u"中证500"]
#bench_mark_list = ["0806.HK","QIHU.N"]
#self.bench_mark_name_list = [u"惠理",u"奇虎"]
stock_data_list = LoadData.get_daily_stock_data(
bench_mark_list, "20110101")
self.price_index = 4
self.volume_index = 5
self.trade_cost = 1 - 0.001
self.range_day = 1
self.regression_day = [2, 5]
# short flag = 1 表示可以做空
short_flag = 1
self.price_list = []
self.volume_list = []
for ii in range(len(bench_mark_list)):
self.price_list.append(
list(zip(*stock_data_list[ii])[self.price_index]))
self.volume_list.append(
list(zip(*stock_data_list[ii])[self.volume_index]))
self.plot(self.price_list, bench_mark_list, self.range_day, short_flag)
#self.run(bench_mark_list)
print "done\n"
def __init__(self,ma_days=200,start_date="19950101",init_days = 60,short_flag =0):
input_file_path = "../input/DeviationFromMA/user_data.xlsx"
self.user_stock_code_list,self.user_stock_name_list = self.load_excel(input_file_path)
self.user_stock_data_list = LoadData.get_daily_stock_data(self.user_stock_code_list,start_date)
self.short_flag = short_flag
self.trade_cost = 1-0.001
self.ma_days = ma_days
self.user_stock_price_data_list = []
self.user_stock_uniform_price_list =[]
self.user_stock_datetime_list = []
self.user_stock_price_data_old_list =[]
for ii in range(len(self.user_stock_code_list)):
self.user_stock_price_data_list.append((list(zip(*self.user_stock_data_list[ii])[4]))[init_days:])
self.user_stock_price_data_old_list.append(list(zip(*self.user_stock_data_list[ii])[4]))
self.user_stock_datetime_list.append((list(zip(*self.user_stock_data_list[ii])[0]))[init_days:])
self.user_stock_uniform_price_list.append(CalcIndex.Uniform_Price(self.user_stock_price_data_list[ii]))
self.price_ma_list = CalcIndex.Calc_MA(self.user_stock_price_data_old_list,int(ma_days),int(init_days))
self.diviation_from_ma_list,self.diviation_from_ma_std_list = self.calc_diviation_from_ma(ma_days)
self.ma_dict ={60:10,120:20,200:60,250:60}
self.diviation_ma_list = CalcIndex.Calc_MA(self.diviation_from_ma_list,self.ma_dict[self.ma_days])
#self.plot(ma_days)
#self.eveluate_index(ma_days)
long_stand_deviation = {60:-0.5,120:-0.1,200:-0.15,250:-0.2}
short_stand_deviation = {60:0.5,120:0.1,200:0.15,250:0.2}
self.back_test_info = self.back_test(long_stand_deviation[ma_days],short_stand_deviation[ma_days])
self.plot_back_test(ma_days)
print "done."
def run(self,bench_mark_list,short_flag = 1,range_day =1):
realtime_price_list,realtime_volume_list = LoadData.get_realtime_price_and_volume(bench_mark_list)
print bench_mark_list
print realtime_price_list
print realtime_volume_list
reminder_info_flag_list = []
is_send_email = False
for ii in range(len(bench_mark_list)):
if float(datetime.today().hour) >=15:
self.price_list[ii].pop()
self.volume_list[ii].pop()
print "volume",self.volume_list[ii][-1]
old_action_len = []
for regression_day in self.regression_day:
old_action_len_per_rangeday = []
self.offset = range_day +regression_day -2
self.slope_price_list = PriceVolume.PriceVolume(self.price_list,range_day,regression_day)
self.slope_volume_list = PriceVolume.PriceVolume(self.volume_list,range_day,regression_day)
action_index_list,action_type_list,revenue_list = self.backtest(self.offset,short_flag)
for ii in range(len(action_type_list)):
old_action_len_per_rangeday.append(len(action_index_list[ii]))
old_action_len.append(old_action_len_per_rangeday)
for ii in range(len(bench_mark_list)):
self.price_list[ii].append(realtime_price_list[ii])
self.volume_list[ii].append(realtime_volume_list[ii])
print "volume new",self.volume_list[ii][-1]
for ii in range(len(self.regression_day)):
temp_reminder_info_flag = []
regression_day = self.regression_day[ii]
self.offset = range_day +regression_day -2
self.slope_price_list = PriceVolume.PriceVolume(self.price_list,range_day,regression_day)
self.slope_volume_list = PriceVolume.PriceVolume(self.volume_list,range_day,regression_day)
action_index_list,action_type_list,revenue_list = self.backtest(self.offset,short_flag)
for jj in range(len(action_index_list)):
print len(action_index_list[jj]),old_action_len[ii][jj]
if len(action_index_list[jj]) - old_action_len[ii][jj] ==1:
temp_reminder_info_flag.append(action_type_list[jj][-1])
is_send_email = True
else:
temp_reminder_info_flag.append("x")
reminder_info_flag_list.append(temp_reminder_info_flag)
print reminder_info_flag_list
if is_send_email == True:
msg= '''<html> <tr>Trade reminder from Price & Volume Model</tr> <table width="300" border="1" bordercolor="black" cellspacing="1">'''
for ii in range(len(reminder_info_flag_list)):
if ii ==0:
msg = msg + '''<tr><td> ''' + ''' </td>'''
for jj in range(len(reminder_info_flag_list[ii])):
msg = msg + ''' <td> ''' + str(bench_mark_list[jj])+ "</td>"
msg = msg + ''' </tr>\n'''
msg = msg + '''<tr><td>''' + str(self.regression_day[ii]) + ''' day </td>'''
for jj in range(len(reminder_info_flag_list[ii])):
if reminder_info_flag_list[ii][jj] =="b":
msg = msg + '''<td> long </td>'''
elif reminder_info_flag_list[ii][jj] =="s":
if short_flag ==1:
msg = msg + '''<td> short </td> '''
else:
msg = msg + '''<td> close previous long postion </td>'''
else:
msg = msg + '''<td> </td> '''
msg = msg + '''</tr> \n'''
msg = msg + '''</table></html> '''
send_email = SendEmail.Send_Email("Trade reminder from Price & Volume Model",msg)
print send_email.isSend
# # In[7]:
# class LabelTransform():
# def __init__(self, classes):
# self.classes = classes
# def transform(self, label):
# label = self.classes[label]
# return label
# In[10]:
path = './iris.csv'
classes = {"Iris-setosa": 0, "Iris-versicolor": 1, "Iris-virginica": 2}
labeltransform = LabelTransform(classes)
dataset_return = DatasetCSV(path, labeltransform)
load_data_obj = LoadData(dataset_return)
load_data_obj.prepare_data()
print()
# idxs = list(range(len(dataset_return)))
# random.shuffle(idxs)
# train_idx = int(len(dataset_return) * 0.6)
# cv_idx = train_idx + int(len(dataset_return) * 0.2)
# train = idxs[: train_idx]
# cv = idxs[train_idx: cv_idx]
# test = idxs[cv_idx:]
# # In[ ]:
# train_dataset = Subset(dataset_return, train)
# cv_dataset = Subset(dataset_return, cv)
from model import CreateModel
from data import LoadData
from keras.callbacks import ModelCheckpoint
import tensorflowjs as tfjs
import matplotlib.pyplot as plt
model = CreateModel()
model.compile(optimizer='sgd',
loss='binary_crossentropy',
metrics=['binary_accuracy'])
training_data, validation_data = LoadData()
#
## train model
#save_model = ModelCheckpoint('model.h5', save_best_only=True, save_weights_only=True, verbose=1)
#print(f'data generator length: {len(training_data)}')
#model.fit_generator(
# training_data,
# validation_data=validation_data,
# epochs=2,
# callbacks=[save_model])
#
## fine tuning
#for layer in base_model.layers[:-5]:
# layer.trainable = False
#model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['binary_accuracy'])
#model.fit_generator(
# training_data,
# validation_data=validation_data,
# epochs=2,
# callbacks=[save_model])
## save model
def train(configs):
"""
"""
#src = T.imatrix()
src = T.itensor3()
#tgt = T.ivector()
tgt = T.imatrix()
src_mask = T.ivector()
seg = segmentor_model(**configs)
seg.apply(src , src_mask , tgt)
cost = seg.cost
params = seg.params
params_regular = seg.L1 * 1e-6 + seg.L2 * 1e-6
grads = T.grad(cost + params_regular , params)
updates = adadelta(params , grads)
#train_fn = theano.function([src , src_mask , tgt] , [cost , seg.emb , seg.hidden_output ,
# seg.log_output , seg.src_mask , seg.tgt , seg.log] , updates=updates , on_unused_input='ignore')
train_fn = theano.function([src , src_mask , tgt] , [cost] , updates=updates , on_unused_input='ignore')
test_fn = theano.function([src , src_mask , tgt] , [cost , seg.log])
loadData = LoadData(**configs)
train_x , train_mask , train_y = loadData.loadTrain()
valid_x , valid_x_src , valid_x_length , valid_y = loadData.loadValid()
#test_x , test_y = loadData.loadTest()
#init some parameters
max_epochs = configs['finish_after']
batch_size = configs['batch_size']
window_size = configs['window_size']
iters = 0
valid_cost_best = -1
test_cost_best = -1
epoch_best = -1
iters_best = -1
cnt = 0
batch_x = []
batch_mask = []
batch_y = []
R , P , F1 = evaluate(loadData , test_fn , window_size , valid_x , valid_x_src , valid_x_length , valid_y , "valid")
print "R= " , R , " P= " , P , " F1= " , F1
for epoch in range(max_epochs):
for i , (x , mask , y) in enumerate(zip(train_x , train_mask , train_y)):
xx = contextwin(x , window_size)
if cnt >= batch_size - 1:
batch_x.append(xx)
batch_mask.append(mask)
batch_y.append(y)
# batch_x : batch_size * sentence_size * window_size
# batch_mask : batch_size
# batch_y : batch_size * sentence_size
# run_cost , k1 , k2 , k3 , k4 , k5 , k6 = train_fn(batch_x , batch_mask , batch_y)
run_cost = train_fn(batch_x , batch_mask , batch_y)
#print run_cost , k1.shape , k2.shape , k3.shape , k4.shape , k5.shape , k6
#print "epoch: " , epoch , " iters: " , iters , " cost: " , run_cost
cnt = 0
batch_x = []
batch_mask = []
batch_y = []
else:
batch_x.append(xx)
batch_mask.append(mask)
batch_y.append(y)
cnt += 1
iters += 1
if iters % configs['save_freq'] == 0:
R , P , F1 = evaluate(loadData , test_fn , window_size , valid_x , valid_x_src , valid_x_length , valid_y , "valid")
print "epoch: " , epoch , "R= " , R , " P= " , P , " F1= " , F1
lm.save()
if batch_x:
run_cost = train_fn(batch_x , batch_mask , batch_y)
print "epoch: " , epoch , " iters: " , iters , " cost: " , run_cost
batch_x = []
batch_mask = []
batch_y = []
cnt = 0
R , P , F1 = evaluate(loadData , test_fn , window_size , valid_x , valid_x_src , valid_x_length , valid_y , "valid")
print "epoch: " , epoch , "R= " , R , " P= " , P , " F1= " , F1
logger.info("Fold %i Accuracy: %.4f", i,
model.score(X[valid_idx], y[valid_idx]))
res[valid_idx, :] = model.predict_proba(X[valid_idx])
logger.info("Fold %i Log Loss: %.4f", i,
log_loss(y[valid_idx], res[valid_idx]))
i += 1
if short: break
if short: return -log_loss(y[valid_idx], res[valid_idx])
yhat = np.argmax(res, axis=1) + 1
Y = np.array([int(i[-1]) for i in y])
logger.info("CV Accuracy: %.5f", accuracy_score(Y, yhat))
logger.info("CV Log Loss: %.4f", log_loss(y, res))
return res, -log_loss(y, res)
_, y, _ = LoadData()
del _
def OptSVC(C, gamma):
model = SVC(C=C, gamma=gamma, probability=True)
return ReportPerfCV(model, "text", y)
def OptBTC(step_size=.5,
max_iterations=100,
row_subsample=.9,
column_subsample=.9,
max_depth=8):
model = BoostedTreesClassifier(step_size=step_size,
max_iterations=max_iterations,
def creepy_data_from_wind_to_local(self):
for ii in range(len(self.user_stock_name_list)):
self.path_is_exist(self.user_stock_name_list[ii])
data_base_path = sys.path[0] + "\\" + "data" + "\\" + "data_base"
stock_fold_path = data_base_path + "\\" + self.user_stock_name_list[
ii]
for data_type in self.data_type_list:
data_path = stock_fold_path + "\\" + data_type
latest_date = self.get_latest_date_in_fold(data_path)
print latest_date
temp_stock_name = []
temp_stock_name.append(self.user_stock_name_list[ii])
delta_day = (
datetime.now() -
datetime(int(latest_date[0:4]), int(latest_date[4:6]),
int(latest_date[6:8]))).days
print latest_date, delta_day, self.user_stock_name_list[ii]
pos = self.user_stock_name_list[ii].split(".")[1]
print pos
if data_type == "daily":
stock_daily_data = LoadData.get_daily_stock_data(
temp_stock_name, latest_date)
for jj in range(len(stock_daily_data[0])):
output_data_path = data_path + "\\" + stock_daily_data[
0][jj][0] + ".txt"
WriteToFile.write_to_file(output_data_path,
stock_daily_data[0][jj])
if pos != "SZ" and pos != "SH":
break
if float(delta_day) > 3 * 365:
delta_day = 1095
if data_type == "60min":
print "aaa"
stock_60_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=60, delta_days=delta_day)
date_60_min_index = self.get_day_sperate_index(
stock_60_min_data)
print stock_60_min_data
print date_60_min_index
for jj in range(len(date_60_min_index) - 1):
file_path = data_path + "\\" + stock_60_min_data[0][
date_60_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_60_min_data[0]
[date_60_min_index[jj]:date_60_min_index[jj + 1]])
elif data_type == "30min":
stock_30_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=30, delta_days=delta_day)
date_30_min_index = self.get_day_sperate_index(
stock_30_min_data)
for jj in range(len(date_30_min_index) - 1):
file_path = data_path + "\\" + stock_30_min_data[0][
date_30_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_30_min_data[0]
[date_30_min_index[jj]:date_30_min_index[jj + 1]])
elif data_type == "15min":
stock_15_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=15, delta_days=delta_day)
date_15_min_index = self.get_day_sperate_index(
stock_15_min_data)
for jj in range(len(date_15_min_index) - 1):
file_path = data_path + "\\" + stock_15_min_data[0][
date_15_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_15_min_data[0]
[date_15_min_index[jj]:date_15_min_index[jj + 1]])
elif data_type == "5min":
stock_5_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=5, delta_days=delta_day)
date_5_min_index = self.get_day_sperate_index(
stock_5_min_data)
for jj in range(len(date_5_min_index) - 1):
file_path = data_path + "\\" + stock_5_min_data[0][
date_5_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_5_min_data[0]
[date_5_min_index[jj]:date_5_min_index[jj + 1]])
def creepy_data_from_wind_to_local(self):
for ii in range(len(self.user_stock_name_list)):
self.path_is_exist(self.user_stock_name_list[ii])
data_base_path = sys.path[0] + "\\" + "data" + "\\" + "data_base"
stock_fold_path = data_base_path + "\\" + self.user_stock_name_list[ii]
for data_type in self.data_type_list:
data_path = stock_fold_path + "\\" + data_type
latest_date = self.get_latest_date_in_fold(data_path)
print latest_date
temp_stock_name = []
temp_stock_name.append(self.user_stock_name_list[ii])
delta_day = (
datetime.now() - datetime(int(latest_date[0:4]), int(latest_date[4:6]), int(latest_date[6:8]))
).days
print latest_date, delta_day, self.user_stock_name_list[ii]
pos = self.user_stock_name_list[ii].split(".")[1]
print pos
if data_type == "daily":
stock_daily_data = LoadData.get_daily_stock_data(temp_stock_name, latest_date)
for jj in range(len(stock_daily_data[0])):
output_data_path = data_path + "\\" + stock_daily_data[0][jj][0] + ".txt"
WriteToFile.write_to_file(output_data_path, stock_daily_data[0][jj])
if pos != "SZ" and pos != "SH":
break
if float(delta_day) > 3 * 365:
delta_day = 1095
if data_type == "60min":
print "aaa"
stock_60_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=60, delta_days=delta_day
)
date_60_min_index = self.get_day_sperate_index(stock_60_min_data)
print stock_60_min_data
print date_60_min_index
for jj in range(len(date_60_min_index) - 1):
file_path = data_path + "\\" + stock_60_min_data[0][date_60_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_60_min_data[0][date_60_min_index[jj] : date_60_min_index[jj + 1]]
)
elif data_type == "30min":
stock_30_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=30, delta_days=delta_day
)
date_30_min_index = self.get_day_sperate_index(stock_30_min_data)
for jj in range(len(date_30_min_index) - 1):
file_path = data_path + "\\" + stock_30_min_data[0][date_30_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_30_min_data[0][date_30_min_index[jj] : date_30_min_index[jj + 1]]
)
elif data_type == "15min":
stock_15_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=15, delta_days=delta_day
)
date_15_min_index = self.get_day_sperate_index(stock_15_min_data)
for jj in range(len(date_15_min_index) - 1):
file_path = data_path + "\\" + stock_15_min_data[0][date_15_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_15_min_data[0][date_15_min_index[jj] : date_15_min_index[jj + 1]]
)
elif data_type == "5min":
stock_5_min_data = LoadData.get_intraday_stock_data(
temp_stock_name, bar_size=5, delta_days=delta_day
)
date_5_min_index = self.get_day_sperate_index(stock_5_min_data)
for jj in range(len(date_5_min_index) - 1):
file_path = data_path + "\\" + stock_5_min_data[0][date_5_min_index[jj]][0][0:8] + ".txt"
WriteToFile.write_list_to_file(
file_path, stock_5_min_data[0][date_5_min_index[jj] : date_5_min_index[jj + 1]]
)
def load_data(self):
print('Loading Dataset...')
self.x_right, self.x_left, self.y_train = LoadData().load()
# -*- coding: utf-8 -*- # File Name: main.py # Author: Changsheng Zhang # mail: [email protected] # Created Time: Tue Jul 7 10:09:08 2015 ######################################################################### import os import sys import strategy.test as test import data.LoadData as LoadData if __name__ == '__main__': b = LoadData.get_daily_stock_data(["600000.SH"]) print b[0][0]
# Global variables
l_value = [4]
thresholds = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
split = [10, 20, 30, 40, 50, 60, 70, 80, 90]
m = 0
train1 = []
train0 = []
data_vector = []
test1 = []
test0 = []
weights = []
weights_history = []
dev_data = []
temp = []
data = LoadData()
def logistic_function(x, w): # sigmoid function
return expit(
np.dot(w, x[:-1])
) # same as 1.0/(1 + np.exp(-np.dot(weights, x[:-1]))) without overflow warning
# last element of x[] = category (or y)
def train(train_total): # train
global train0, train1, m, data_vector, weights, dev_data, temp
if len(temp) == 0:
data.createDictionary()
def run(self, bench_mark_list, short_flag=1, range_day=1):
realtime_price_list, realtime_volume_list = LoadData.get_realtime_price_and_volume(
bench_mark_list)
print bench_mark_list
print realtime_price_list
print realtime_volume_list
reminder_info_flag_list = []
is_send_email = False
for ii in range(len(bench_mark_list)):
if float(datetime.today().hour) >= 15:
self.price_list[ii].pop()
self.volume_list[ii].pop()
print "volume", self.volume_list[ii][-1]
old_action_len = []
for regression_day in self.regression_day:
old_action_len_per_rangeday = []
self.offset = range_day + regression_day - 2
self.slope_price_list = PriceVolume.PriceVolume(
self.price_list, range_day, regression_day)
self.slope_volume_list = PriceVolume.PriceVolume(
self.volume_list, range_day, regression_day)
action_index_list, action_type_list, revenue_list = self.backtest(
self.offset, short_flag)
for ii in range(len(action_type_list)):
old_action_len_per_rangeday.append(len(action_index_list[ii]))
old_action_len.append(old_action_len_per_rangeday)
for ii in range(len(bench_mark_list)):
self.price_list[ii].append(realtime_price_list[ii])
self.volume_list[ii].append(realtime_volume_list[ii])
print "volume new", self.volume_list[ii][-1]
for ii in range(len(self.regression_day)):
temp_reminder_info_flag = []
regression_day = self.regression_day[ii]
self.offset = range_day + regression_day - 2
self.slope_price_list = PriceVolume.PriceVolume(
self.price_list, range_day, regression_day)
self.slope_volume_list = PriceVolume.PriceVolume(
self.volume_list, range_day, regression_day)
action_index_list, action_type_list, revenue_list = self.backtest(
self.offset, short_flag)
for jj in range(len(action_index_list)):
print len(action_index_list[jj]), old_action_len[ii][jj]
if len(action_index_list[jj]) - old_action_len[ii][jj] == 1:
temp_reminder_info_flag.append(action_type_list[jj][-1])
is_send_email = True
else:
temp_reminder_info_flag.append("x")
reminder_info_flag_list.append(temp_reminder_info_flag)
print reminder_info_flag_list
if is_send_email == True:
msg = '''<html> <tr>Trade reminder from Price & Volume Model</tr> <table width="300" border="1" bordercolor="black" cellspacing="1">'''
for ii in range(len(reminder_info_flag_list)):
if ii == 0:
msg = msg + '''<tr><td> ''' + ''' </td>'''
for jj in range(len(reminder_info_flag_list[ii])):
msg = msg + ''' <td> ''' + str(
bench_mark_list[jj]) + "</td>"
msg = msg + ''' </tr>\n'''
msg = msg + '''<tr><td>''' + str(
self.regression_day[ii]) + ''' day </td>'''
for jj in range(len(reminder_info_flag_list[ii])):
if reminder_info_flag_list[ii][jj] == "b":
msg = msg + '''<td> long </td>'''
elif reminder_info_flag_list[ii][jj] == "s":
if short_flag == 1:
msg = msg + '''<td> short </td> '''
else:
msg = msg + '''<td> close previous long postion </td>'''
else:
msg = msg + '''<td> </td> '''
msg = msg + '''</tr> \n'''
msg = msg + '''</table></html> '''
send_email = SendEmail.Send_Email(
"Trade reminder from Price & Volume Model", msg)
print send_email.isSend
