def run(self):
clean_data = CleanData()
clean_data.run()
calc_corr = CalcCorrMatrix()
calc_corr.run()
data_generator = DataGenerator()
train_feature, train_label, test_feature, test_label = data_generator.run()
return train_feature, train_label, test_feature, test_label
def run(self):
if self.preprocess == 1:
print "cleaning data...\n"
clean_data = CleanData(self.file_path)
clean_data.run()
print "cleaning data successfully\n"
print "calculating correlation matrix...\n"
calc_corr = CalcCorrMatrix()
corr_matrix = calc_corr.run()
print "calculatE successfully\n"
print "generating dataset...\n"
data_generator = DataGenerator('../data/', self.code, self.ratio,
corr_matrix, self.train_set_choice)
train_feature, train_label, test_feature, test_label = data_generator.run(
)
print "generate successfully\n"
return train_feature, train_label, test_feature, test_label, corr_matrix
args = parser.parse_args()
file_path = args.filepath
code = str(args.code)
method = args.method
# create pre processor
print args.preprocess
if args.preprocess:
data_cleaner = PreProcessor(file_path)
data_cleaner.run()
data_generator = DataGenerator(file_path,
code,
test_set_ratio=args.ratio,
ahead_num=11)
train_feature, train_label, test_feature, test_label = data_generator.run()
reg = LearningModel(method)
reg.fit(train_feature, train_label)
pred_label = reg.predict(test_feature)
# print type(pred_label)
# print type(test_label)
score = reg.score(test_feature, test_label)
print score
print reg.MSE(test_label, pred_label)
#
# score = reg.score(test_label, pred_label)
#
drawer = PicDrawer(file_path, code, train_label, test_label, pred_label)
drawer.run()