def GET(self):
if librarian.is_traktor_running():
response = {"status": "error", "message": "Please quit Traktor first."}
else:
cleaner = Cleaner(Library.instance())
cleaner.remove_duplicates()
logger.debug(u"Duplicate removal complete")
response = cleaner.get_result()
response["status"] = "ok"
web.header("Cache-Control", "no-cache")
return json.dumps(response)
def main():
try:
lib = Library(conf.library_dir)
if conf.action == "clean":
cleaner = Cleaner(lib)
print("Removing duplicates..."),
cleaner.remove_duplicates()
print("DONE")
cleaner.report()
if not conf.test:
lib.flush()
print("\nTraktor library updated.")
else:
print("\nTest run. No changes made to the library.")
elif conf.action == "export":
exporter = Exporter(lib, conf.export_dir)
exporter.export()
except Exception as e:
logger.error(e, exc_info=False)
import os
congress_id = ""
if len(sys.argv) > 3 or len(sys.argv) < 2:
print("Please Enter valid parameter:")
print("Parameter: Congress term number")
print("Option: --skip, avoid data cleaning")
sys.exit()
if len(sys.argv) == 2:
congress_id = str(sys.argv[1])
if os.path.isfile("rawData/" + "speeches_" + congress_id +
".txt") and os.path.isfile("rawData/" + congress_id +
"_SpeakerMap.txt"):
print("cleaning ....")
data_cleaner = Cleaner([congress_id])
data_cleaner.clean_pipeline()
print("classifying ....")
congress_classifier = Classifier([congress_id])
congress_classifier.base_pipeline()
print("done.")
sys.exit()
else:
print(
"There are no speeches and speakerMap text file to process for congress "
+ congress_id)
print(
"Please put the target congress raw text data into rawData directory"
)
sys.exit()
[plot.fitted_histogram, y['LogSalePrice']],
# [plot.qq, y['SalePrice']],
# [plot.qq, y['Log1SalePrice']],
]
#plot.view(plots)
#y.to_csv('y.csv', index=False)
y_np = y.drop('SalePrice', axis=1).to_numpy()
train_id = x_train['Id']
test_id = x_test['Id']
x_train.drop('Id', axis=1, inplace=True)
x_test.drop('Id', axis=1, inplace=True)
cleaner = Cleaner(x_train, x_test)
cleaner.clean(variables)
#linear = regression.build('Linear')
#linear_cv = regression.cross_validate(linear, cleaner.x_train_np, y_np)
#print('LINEAR', linear_cv)
lasso = regression.build('Lasso', alpha=0.002)
lasso_cv = regression.cross_validate(lasso, cleaner.x_train_np, y_np)
elastic_net = regression.build('ElasticNet', alpha=0.002)
elastic_net_cv = regression.cross_validate(elastic_net, cleaner.x_train_np,
y_np)
kernel_ridge = regression.build('KernelRidge')
kernel_ridge_cv = regression.cross_validate(kernel_ridge, cleaner.x_train_np,
