return result
def logloss(act, pred):
epsilon = 1e-15
pred = sp.maximum(epsilon, pred)
pred = sp.minimum(1 - epsilon, pred)
ll = sum(act * sp.log(pred) + sp.subtract(1, act) * sp.log(sp.subtract(1, pred)))
ll = ll * -1.0 / len(act)
return ll
if __name__ == '__main__':
debug = False
print('reading data...')
ad = Advertisement(Configure.ad_path, debug=debug)
app = App(Configure.app_categories_path, debug=debug)
data_set = Dataset(Configure.train_path, Configure.test_path, debug=debug)
position = Position(Configure.position_path, debug=debug)
user = User(Configure.user_path, debug=debug)
user_app_actions = User_App_Actions(Configure.user_app_actions_path, debug=debug)
# user_app_installed = User_App_Installed(Configure.user_installedapps_path, debug=debug)
data_set.add_to_position(position)
data_set.add_to_advertisement(ad)
data_set.add_to_app_cat(ad, app)
func_dict = {'creativeID': creative_dlist,
'adID': ad_dlist,
'camgaignID': camgaign_dlist,
'advertiserID': advertiser_dlist,
'appID': app_dlist,
'positionID': position_dlist}
path_dict = {'creativeID': Configure.creative_correlate,
import xgboost as xgb
from conf.configure import Configure
from reading.advertisement import Advertisement
from reading.app import App
from reading.dataset import Dataset
from reading.position import Position
from reading.user import User
from reading.user_app_actions import User_App_Actions
import matplotlib.pyplot as plt
import numpy as np
if __name__ == '__main__':
data_set = Dataset(Configure.train_path, Configure.test_path)
data_set.output_by_userid(Configure.dataset_sort_by_userid)