def prepare_train_data(self, data_feature, LabelColumnName):
firstloop = 1
print("get_data_feature")
#print(data_feature.items())
train_tickers_dict = get_all_target_dict()
train_symbols = train_tickers_dict.keys()
for ticker, data in data_feature.items():
# print(ticker, "n_feature", self.paras.n_features, len(data[0]))
# print("data[0]",data[0].head())
#print("data[0]", data[0].index)
if ticker not in train_symbols: continue
X, y = preprocessing_train_data(self.paras, data[0].copy(), LabelColumnName, ticker, train_tickers_dict, one_hot_label_proc=False)
# print(X.shape)
# X, y = reshape_input(self.paras.n_features, X, y)
X_train_temp, X_test_temp, y_train_temp, y_test_temp = train_test_split(X, y, test_size=0.2)
# print('Train shape X:', X_train_temp.shape, ',y:', y_train_temp.shape)
# print('Test shape X:', X_test_temp.shape, ',y:', y_test_temp.shape)
if firstloop == 1:
firstloop = 0
X_train = X_train_temp
X_test = X_test_temp
y_train = y_train_temp
y_test = y_test_temp
else:
X_train = np.append(X_train, X_train_temp, 0)
X_test = np.append(X_test, X_test_temp, 0)
y_train = np.append(y_train, y_train_temp, 0)
y_test = np.append(y_test, y_test_temp, 0)
# print('Train shape X:', X_train.shape, ',y:', y_train.shape)
# print('Test shape X:', X_test.shape, ',y:', y_test.shape)
return X_train, y_train, X_test, y_test
def prepare_train_data(self, data_feature, LabelColumnName):
firstloop = 1
print("get_data_feature")
#print(data_feature.items())
train_tickers_dict = get_all_target_dict()
train_symbols = train_tickers_dict.keys()
for ticker, data in data_feature.items():
if ticker not in train_symbols: continue
X, y = preprocessing_train_data(self.paras,
data[0].copy(),
LabelColumnName,
ticker,
train_tickers_dict,
one_hot_label_proc=False)
X_train_temp, X_test_temp, y_train_temp, y_test_temp = train_test_split(
X, y, test_size=0.2)
if firstloop == 1:
firstloop = 0
X_train = X_train_temp
X_test = X_test_temp
y_train = y_train_temp
y_test = y_test_temp
else:
X_train = np.append(X_train, X_train_temp, 0)
X_test = np.append(X_test, X_test_temp, 0)
y_train = np.append(y_train, y_train_temp, 0)
y_test = np.append(y_test, y_test_temp, 0)
return X_train, y_train, X_test, y_test