def test_all_holidays_present(self):
at_2015 = holidays.AT(years=[2015])
all_holidays = [
"Neujahr",
"Heilige Drei Könige",
"Ostermontag",
"Staatsfeiertag",
"Christi Himmelfahrt",
"Pfingstmontag",
"Fronleichnam",
"Mariä Himmelfahrt",
"Nationalfeiertag",
"Allerheiligen",
"Mariä Empfängnis",
"Christtag",
"Stefanitag",
]
for holiday in all_holidays:
self.assertIn(holiday, at_2015.values())
def load(country, region, observed, expand, years):
# Erases existing holiday cache and makes a new one...
global dates
if country == "US":
dates = holidays.US(state=region,
observed=observed,
expand=expand,
years=years)
elif country == "CA":
dates = holidays.CA(prov=region,
observed=observed,
expand=expand,
years=years)
elif country == "MX":
dates = holidays.MX(observed=observed, expand=expand, years=years)
elif country == "NZ":
dates = holidays.NZ(prov=region,
observed=observed,
expand=expand,
years=years)
elif country == "AU":
dates = holidays.AU(prov=region,
observed=observed,
expand=expand,
years=years)
elif country == "AT":
dates = holidays.AT(prov=region,
observed=observed,
expand=expand,
years=years)
elif country == "DE":
dates = holidays.DE(prov=region,
observed=observed,
expand=expand,
years=years)
else:
print "UNKNOWN COUNTRY ", country
def judge_local_holiday(self, df):
country = df['geoNetwork_country']
date = df['visitId'].apply(lambda x: x.date())
judge_holiday = \
np.where(country.isin(
['United States','India','Canada','Germany',
'Japan','France','Mexico','Australia',
'Spain','Netherlands','Italy','Ireland',
'Sweden','Argentina','Colombia','Belgium',
'Switzerland','Czechia','Colombia','Belgium',
'New Zealand','South Africa','South Africa']),\
np.where((country=='United States')&
(date.isin(holidays.US())),1,
np.where((country=='India')&
(date.isin(holidays.India())),1,
np.where((country=='Canada')&
(date.isin(holidays.CA())),1,
np.where((country=='Germany')&
(date.isin(holidays.DE())),1,\
np.where((country=='Japan')&
(date.isin(holidays.JP())),1,
np.where((country=='France')&
(date.isin(holidays.FRA())),1,
np.where((country=='Mexico')&
(date.isin(holidays.MX())),1,
np.where((country=='Australia')&
(date.isin(holidays.AU())),1,\
np.where((country=='Spain')&
(date.isin(holidays.ES())),1,
np.where((country=='Netherlands')&
(date.isin(holidays.NL())),1,
np.where((country=='Italy')&
(date.isin(holidays.IT())),1,
np.where((country=='Ireland')&
(date.isin(holidays.IE())),1,\
np.where((country=='Sweden')&
(date.isin(holidays.SE())),1,
np.where((country=='Argentina')&
(date.isin(holidays.AR())),1,
np.where((country=='Colombia')&
(date.isin(holidays.CO())),1,
np.where((country=='Belgium')&
(date.isin(holidays.BE())),1,\
np.where((country=='Switzerland')&
(date.isin(holidays.CH())),1,
np.where((country=='Czechia')&
(date.isin(holidays.CZ())),1,
np.where((country=='Denmark')&
(date.isin(holidays.DK())),1,
np.where((country=='Austria')&
(date.isin(holidays.AT())),1,\
np.where((country=='Hungary')&
(date.isin(holidays.HU())),1,
np.where((country=='Portugal')&
(date.isin(holidays.PT())),1,
np.where((country=='Norway')&
(date.isin(holidays.NO())),1,
np.where((country=='Portugal')&
(date.isin(holidays.PT())),1,\
np.where((country=='New Zealand')&
(date.isin(holidays.NZ())),1,
np.where((country=='South Africa')&
(date.isin(holidays.ZA())),1,
np.where((country=='South Africa')&
(date.isin(holidays.ZA())),1,\
0))))))))))))))))))))))))))),np.nan).astype(int)
return judge_holiday
def ts_fit(self, suppress=False):
"""Fit Prophet to the time series data.
Parameters:
----------
suppress: bool
Suppress or not some of the output messages
"""
if self.hyper_params is not None:
self._gs.set_forecaster(self)
self._gs.set_hyper_params(self.hyper_params)
# a very important command here to avoid endless loop
self.hyper_params = None
self._prophet_logger.info("***** Starting grid search *****")
self._gs = self._gs.grid_search(suppress=suppress, show_plot=False)
#
self.best_model = self._gs.best_model
self.__dict__.update(self.best_model['forecaster'].__dict__)
self._prophet_logger.info("***** Finished grid search *****")
else:
self._prepare_fit()
self._model = None
self.ts_split()
ts_df = self._train_dt.copy()
ts_test_df = self._test_dt
# sanity check
if 'on_weekend' in ts_df.columns:
ts_df.drop(['on_weekend', 'off_weekend'], inplace=True, axis=1)
# ts_test_df.drop(['on_weekend', 'off_weekend'], inplace=True, axis=1)
# Fit
self._prophet_logger.info("Trying to fit the Prophet model....")
try:
if not suppress:
self._prophet_logger.info("...via using parameters\n")
print_attributes(self)
# diagnose on?
if self._diagnose:
try:
assert self._step is not None and self._horizon is not None
except (KeyError, AssertionError):
self._prophet_logger.warning("You want to diagnose the Prophet model. Please provide parameters "
"'step' and 'horizon' within object initialization!")
sys.exit("STOP")
ts_df = ts_df.reset_index()
ts_df.columns = self._ts_df_cols
if ts_test_df is not None and not ts_test_df.empty:
ts_test_df = ts_test_df.reset_index()
ts_test_df.columns = self._ts_df_cols
#
weekly_s = self._weekly_seasonality
if self._weekend_seasonality:
# force to False
weekly_s = False
#
if not self._consider_holidays:
self._model = Prophet(interval_width=self._prophet_interval_width,
yearly_seasonality=self._yearly_seasonality,
weekly_seasonality=weekly_s,
daily_seasonality=self._daily_seasonality,
changepoint_range=self._changepoint_range,
changepoint_prior_scale=self._changepoint_prior_scale)
else:
try:
assert self._country in ['AT', 'DE', 'US']
except AssertionError:
self._prophet_logger.exception("Assrtion exception occurred. Right now, Austria (AT), "
"Germany(DE) and USA (US) supported.")
sys.exit("STOP")
else:
holi = None
if self._country == 'AT':
holi = holidays.AT(state=None, years=list(np.unique(np.asarray(self.ts_df.index.year))))
elif self._country == 'DE':
holi = holidays.DE(state=None, years=list(np.unique(np.asarray(self.ts_df.index.year))))
elif self._country == 'US':
holi = holidays.US(state=None, years=list(np.unique(np.asarray(self.ts_df.index.year))))
#
holi_dict = dict()
for date, name in sorted(holi.items()):
holi_dict[date] = name
df_holi = pd.DataFrame.from_dict(data=holi_dict, orient='index').reset_index()
df_holi.columns = ['ds', 'holiday']
df_holi['lower_window'] = 0
df_holi['upper_window'] = 0
self._model = Prophet(interval_width=self._prophet_interval_width,
yearly_seasonality=self._yearly_seasonality,
weekly_seasonality=weekly_s,
daily_seasonality=self._daily_seasonality,
changepoint_range=self._changepoint_range,
changepoint_prior_scale=self._changepoint_prior_scale,
holidays=df_holi)
if self._monthly_seasonality:
self._model.add_seasonality(name='monthly', period=30.5, fourier_order=20)
if not suppress:
self._prophet_logger.info("Added monthly seasonality.")
if self._quarterly_seasonality:
self._model.add_seasonality(name='quarterly', period=91.5, fourier_order=20)
if not suppress:
self._prophet_logger.info("Added quarterly seasonality.")
if self._weekend_seasonality:
ts_df['on_weekend'] = ts_df['ds'].apply(self.we_season)
ts_df['off_weekend'] = ~ts_df['ds'].apply(self.we_season)
self._train_dt = ts_df.copy()
self._train_dt.set_index('ds', inplace=True)
#
if ts_test_df is not None and not ts_test_df.empty:
ts_test_df['on_weekend'] = ts_test_df['ds'].apply(self.we_season)
ts_test_df['off_weekend'] = ~ts_test_df['ds'].apply(self.we_season)
self._test_dt = ts_test_df.copy()
self._test_dt.set_index('ds', inplace=True)
# and add
self._model.add_seasonality(name='weekend_on_season', period=7,
fourier_order=5, condition_name='on_weekend')
self._model.add_seasonality(name='weekend_off_season', period=7,
fourier_order=5, condition_name='off_weekend')
if not suppress:
self._prophet_logger.info("Added week-end seasonality.")
# tic
start = time()
self.model_fit = self._model.fit(ts_df)
# toc
if not suppress:
self._prophet_logger.info("Time elapsed: {} sec.".format(time() - start))
except (Exception, ValueError):
self._prophet_logger.exception("Prophet error...")
return -1
else:
self._prophet_logger.info("Model successfully fitted to the data!")
# Fitted values
self._prophet_logger.info("Computing fitted values and residuals...")
# in-sample predict
try:
self.fittedvalues = self._model.predict(ts_df.drop('y', axis=1))
except (Exception, ValueError):
self._prophet_logger.exception("Prophet predict error...")
# Residuals
try:
# use fittedvalues to fill in the model dictionary
self.residuals = pd.Series(np.asarray(ts_df.y) - np.asarray(self.fittedvalues['yhat']),
index=self._train_dt.index)
except (KeyError, AttributeError):
self._prophet_logger.exception("Model was not fitted or ts has other structure...")
#
self.lower_conf_int = pd.Series(np.asarray(self.fittedvalues['yhat_lower']), index=self._train_dt.index)
self.upper_conf_int = pd.Series(np.asarray(self.fittedvalues['yhat_upper']), index=self._train_dt.index)
self._prophet_logger.info("Done.")
return self
settings["country_last_updated"] = now
settings["country_last"] = country_last
settings.flush()
return country_last
country_holidays = {
"CA": holidays.CA(),
"CO": holidays.CO(),
"MX": holidays.MX(),
"US": holidays.US(),
"NZ": holidays.NZ(),
"AU": holidays.AU(),
"DE": holidays.DE(),
"AT": holidays.AT(),
"DK": holidays.DK(),
"UK": holidays.UK(),
"IE": holidays.IE(),
"ES": holidays.ES(),
"CZ": holidays.CZ(),
"SK": holidays.SK(),
"PL": holidays.PL(),
"PT": holidays.PT(),
"NL": holidays.NL(),
"NO": holidays.NO(),
"IT": holidays.IT(),
"SE": holidays.SE(),
"JP": holidays.JP(),
"BE": holidays.BE(),
"ZA": holidays.ZA(),
def setUp(self):
self.holidays = holidays.AT()
