def regressor_dev_test(self, dev_set, dev_value_set, dev_date_set, dev_stock_id_set, save_clsfy_path="mlp_trade_regressor", is_cv=False, include_top_list = None):
# test mode
if not include_top_list:
include_top_list = [1]
mlp_regressor = self.mlp_regressor
pred_value_list = np.array(mlp_regressor.predict(dev_set))
actual_value_list = np.array(dev_value_set)
mrse = calculate_rmse(actual_value_list, pred_value_list)
date_list = dev_date_set
stock_id_list = dev_stock_id_set
avg_price_change_tuple, var_tuple, std_tuple = get_avg_price_change(pred_value_list, actual_value_list,
date_list, stock_id_list,
include_top_list=
include_top_list)
# count how many predicted value has the same polarity as actual value
polar_list = [1 for x, y in zip(pred_value_list, actual_value_list) if x * y >= 0]
polar_count = len(polar_list)
polar_percent = polar_count / len(pred_value_list)
#
# <uncomment for debugging>
if not is_cv:
print("----------------------------------------------------------------------------------------")
print("actual_value_list, ", actual_value_list)
print("pred_value_list, ", pred_value_list)
print("polarity: {}".format(polar_percent))
print("mrse: {}".format(mrse))
print("avg_price_change: {}".format(avg_price_change_tuple))
print("----------------------------------------------------------------------------------------")
else:
pass
# print("Testing complete! Testing Set size: {}".format(len(self.r_dev_value_set)))
# <uncomment for debugging>
# ------------------------------------------------------------------------------------------------------------------
return mrse, avg_price_change_tuple[0], polar_percent
def regressor_dev(self, save_clsfy_path="mlp_trade_regressor", is_cv=False, include_top_list = None):
# test mode
if not include_top_list:
include_top_list = [1]
mlp_regressor = pickle.load(open(save_clsfy_path, "rb"))
pred_value_list = np.array(mlp_regressor.predict(self.dev_set))
actual_value_list = np.array(self.dev_value_set)
date_list = self.dev_date_set
stock_id_list = self.dev_stock_id_set
avg_price_change_tuple, var_tuple, std_tuple = get_avg_price_change(pred_value_list, actual_value_list,
date_list, stock_id_list,
include_top_list=
include_top_list)
# compute accuracy in terms of positive and negative
# (3.) get the pred label for each week
pred_label_dict_by_week = collections.defaultdict(lambda :[])
golden_label_dict_by_week = collections.defaultdict(lambda :[])
pred_value_dict_by_week = collections.defaultdict(lambda :[])
golden_value_dict_by_week = collections.defaultdict(lambda :[])
pred_label_list = ['pos' if x >= 0 else 'neg' for x in pred_value_list ]
actual_label_list = ['pos' if x >= 0 else 'neg' for x in actual_value_list ]
for i, pred_label in enumerate(pred_label_list):
date = self.dev_date_set[i]
# classification
pred_label_dict_by_week[date].append(pred_label)
golden_label = actual_label_list[i]
golden_label_dict_by_week[date].append(golden_label)
#
# regression
predict_value = pred_value_list[i]
golden_value = actual_value_list[i]
pred_value_dict_by_week[date].append(predict_value)
golden_value_dict_by_week[date].append(golden_value)
week_average_f1_list = []
week_average_accuracy_list = []
week_average_rmse = []
dev_label_dict = collections.defaultdict(lambda: 0)
pred_label_dict = collections.defaultdict(lambda: 0)
label_f1_list_all = []
# (4.) compute the f1, accuracy for each week in 1 validation set
for date, pred_label_list_for_1_week in pred_label_dict_by_week.items():
pred_label_list = pred_label_list_for_1_week
golden_label_list = golden_label_dict_by_week[date]
# (3.) compute the average f-measure
_,average_f1 = compute_average_f1(pred_label_list, golden_label_list)
week_average_f1_list.append(average_f1)
#average_f1 = f1_list[0] # using F-measure
#
# (4.) compute accuracy
correct = 0
for i, pred_label in enumerate(pred_label_list):
if pred_label == golden_label_list[i]:
correct += 1
accuracy = correct / len(golden_label_list)
week_average_accuracy_list.append(accuracy)
#
# (5.) count the occurrence for each label
for dev_label in golden_label_list:
dev_label_dict[dev_label] += 1
for pred_label in pred_label_list:
pred_label_dict[pred_label] += 1
#
# # (6.) save rmse
pred_value_list1 = pred_value_dict_by_week[date]
actual_value_list1 = golden_value_dict_by_week[date]
rmse = calculate_rmse(actual_value_list1, pred_value_list1)
week_average_rmse.append(rmse)
week_average_f1 = np.average(week_average_f1_list)
week_average_accuracy = np.average(week_average_accuracy_list)
week_average_rmse = np.average(week_average_rmse)
# <uncomment for debugging>
if not is_cv:
print("----------------------------------------------------------------------------------------")
print("actual_value_list, ", actual_value_list)
print("pred_value_list, ", pred_value_list)
print("week_average_accuracy: {}".format(week_average_accuracy))
print("week_average_f1: {}".format(week_average_f1))
print("week_average_rmse: {}".format(week_average_rmse))
print("week_average_price_change: {}".format(avg_price_change_tuple))
print("----------------------------------------------------------------------------------------")
else:
pass
# print("Testing complete! Testing Set size: {}".format(len(self.r_dev_value_set)))
# <uncomment for debugging>
# ------------------------------------------------------------------------------------------------------------------
return week_average_rmse, avg_price_change_tuple, week_average_accuracy, week_average_f1
def baseline_reg_dev(self, target_folder):
file1 = os.listdir(target_folder)[0]
file1_path = os.path.join(target_folder, file1)
with open(file1_path, 'r') as f:
feature_list = f.readlines()[0].strip().split(',')[::2]
key_index = feature_list.index('percent_change_price')
print ("key_index: ", key_index)
pred_value_list = []
for dev_sample in self.dev_set:
percent_change_price = float(dev_sample[key_index])*0.01
pred_value_list.append(percent_change_price)
actual_value_list = np.array(self.dev_value_set)
date_list = self.dev_date_set
stock_id_list = self.dev_stock_id_set
include_top_list = [1]
avg_price_change_tuple, var_tuple, std_tuple = get_avg_price_change(pred_value_list, actual_value_list,
date_list, stock_id_list,
include_top_list=
include_top_list)
date_actual_avg_priceChange_list = get_chosen_stock_return(pred_value_list, actual_value_list, date_list,
stock_id_list, include_top_list=None)
# compute accuracy in terms of positive and negative
# (3.) get the pred label for each week
pred_label_dict_by_week = collections.defaultdict(lambda :[])
golden_label_dict_by_week = collections.defaultdict(lambda :[])
pred_value_dict_by_week = collections.defaultdict(lambda :[])
golden_value_dict_by_week = collections.defaultdict(lambda :[])
pred_label_list = ['pos' if x >= 0 else 'neg' for x in pred_value_list ]
actual_label_list = ['pos' if x >= 0 else 'neg' for x in actual_value_list ]
for i, pred_label in enumerate(pred_label_list):
date = self.dev_date_set[i]
# classification
pred_label_dict_by_week[date].append(pred_label)
golden_label = actual_label_list[i]
golden_label_dict_by_week[date].append(golden_label)
#
# regression
predict_value = pred_value_list[i]
golden_value = actual_value_list[i]
pred_value_dict_by_week[date].append(predict_value)
golden_value_dict_by_week[date].append(golden_value)
week_average_f1_list = []
week_average_accuracy_list = []
week_average_rmse = []
dev_label_dict = collections.defaultdict(lambda: 0)
pred_label_dict = collections.defaultdict(lambda: 0)
label_f1_list_all = []
# (4.) compute the f1, accuracy for each week in 1 validation set
for date, pred_label_list_for_1_week in pred_label_dict_by_week.items():
pred_label_list = pred_label_list_for_1_week
golden_label_list = golden_label_dict_by_week[date]
# (3.) compute the average f-measure
_,average_f1 = compute_average_f1(pred_label_list, golden_label_list)
week_average_f1_list.append(average_f1)
#average_f1 = f1_list[0] # using F-measure
#
# (4.) compute accuracy
correct = 0
for i, pred_label in enumerate(pred_label_list):
if pred_label == golden_label_list[i]:
correct += 1
accuracy = correct / len(golden_label_list)
week_average_accuracy_list.append(accuracy)
#
# (5.) count the occurrence for each label
for dev_label in golden_label_list:
dev_label_dict[dev_label] += 1
for pred_label in pred_label_list:
pred_label_dict[pred_label] += 1
#
# # (6.) save rmse
pred_value_list1 = pred_value_dict_by_week[date]
actual_value_list1 = golden_value_dict_by_week[date]
rmse = calculate_rmse(actual_value_list1, pred_value_list1)
week_average_rmse.append(rmse)
week_average_f1 = np.average(week_average_f1_list)
week_average_accuracy = np.average(week_average_accuracy_list)
week_average_rmse = np.average(week_average_rmse)
# # <uncomment for debugging>
# print("----------------------------------------------------------------------------------------")
# print("actual_value_list, ", actual_value_list)
# print("pred_value_list, ", pred_value_list)
# print("week_average_accuracy: {}".format(week_average_accuracy))
# print("week_average_f1: {}".format(week_average_f1))
# print("week_average_rmse: {}".format(week_average_rmse))
# print("week_average_price_change: {}".format(avg_price_change_tuple))
# print("----------------------------------------------------------------------------------------")
# ------------------------------------------------------------------------------------------------------------------
return week_average_rmse, avg_price_change_tuple, week_average_accuracy, week_average_f1, \
date_actual_avg_priceChange_list
pred_value_list, actual_value_list, date_list, stock_id_list = rnn1.reg_dev_for_moving_window_test(
)
#
#print ("date_list: ", date_list)
pred_label_list_temp = [
'pos' if x >= 0 else 'neg' for x in pred_value_list
]
actual_label_list_temp = [
'pos' if x >= 0 else 'neg' for x in actual_value_list
]
pred_label_list.extend(pred_label_list_temp)
actual_label_list.extend(actual_label_list_temp)
data_list_for_classification.extend(date_list)
#
rmse = calculate_rmse(actual_value_list, pred_value_list)
avg_price_change_tuple, var_tuple, std_tuple = get_avg_price_change(
pred_value_list, actual_value_list, date_list, stock_id_list)
chosen_stock_return_list_temp = get_chosen_stock_return(
pred_value_list, actual_value_list, date_list, stock_id_list)
avg_price_change_1 = avg_price_change_tuple[
0] # Strategy: choose the top 1 stock each week
var_1 = var_tuple[0]
std_1 = std_tuple[0]
avg_price_change_list.append(avg_price_change_1)
print("chosen_stock_return_list_temp: ", chosen_stock_return_list_temp)
var_list.append(var_1)
std_list.append(std_1)
chosen_stock_return_list.extend(chosen_stock_return_list_temp)
rmse_list.append(rmse)
# date set