def get_shop_trend_zero_anomaly_filled(shop_id, continuous_zero_filled_threshold=5, consider_anomaly=True):
HOME = getHome()
source_folder = os.path.join(HOME, "Dropbox", "dataset", "Analysis", "PayTrend_Filled_threshold_%s_%s_anomaly" % (
continuous_zero_filled_threshold, "consider" if consider_anomaly else "not_consider"))
source_file = os.path.join(source_folder,"Customer_Flow_zeroFilled_shop_%s.csv"%shop_id)
if not os.path.exists(source_file):
#print 100101
print "Generating: %s\n"%source_file
sys.path.append(os.path.join(HOME, "Dropbox", "dataset", "Scripts"))
import TrendForEveryShop as tfes
tfes.get_Customer_flow_per_shop_missingdays_handled('mean', shop_id, continuous_zero_filled_threshold, consider_anomaly)
#print source_file
df = pd.read_csv(source_file, header=None, names=['time', 'orig_cnt', 'cnt'], parse_dates=[0])
df.drop('orig_cnt', inplace=True, axis=1)
df['day'] = df.apply(lambda row: row['time'].date(), axis=1)
df.drop('time', axis=1, inplace=True)
return df[['day','cnt']]
def inner_function(shop_id):
"""shop_static_info"""
FILE = os.path.join(getHome(), "Dropbox", "dataset", "Analysis", "Features", "shop_info_feature.csv")
df = pd.read_csv(FILE)
df = df[df['shop_id']==shop_id]
return df
def inner_function(shop_id):
FILE = os.path.join(getHome(), "Dropbox", "dataset", "Analysis", "Features", "shop_info_feature.csv")
return pd.read_csv(FILE)
def get_city_to_daily_aqi():
PKL_file = os.path.join(getHome(),'Dropbox','dataset','Scripts','weather','city_to_daily_aqi.pkl')
return pickle.load(open(PKL_file,'rb'))
def get_shop_2_city():
PKL_file = os.path.join(getHome(),'Dropbox','dataset','Scripts','weather','shop_2_city.pkl')
return pickle.load(open(PKL_file,'rb'))