def add_predictor_columns(data):
"""
Will return predictive variables given a data-set with the 'TimeHour' column.
'TimeHour' can be created by applying the .replace() method on the 'TimeStamp'
column. The following variables will be added:
NAME ~~~~~~~~~~~~~~~ COLUMN ~~~~~~~ FORMAT
Hour of the day hour_XX Dummy, binary
Month of the year month_XX Dummy, binary
Holiday is_holiday Binary
Holiday is based on all holidays in the Netherlands in 2018, 2019.
"""
# Fetch holidays of given period
NL_holidays = [i[0] for i in holidays.Netherlands(years = [2018, 2019]).items()]
# Create dummies for hour of day and month of year
hour_dummies = pd.get_dummies(data["TimeHour"].apply(lambda i: i.hour), prefix="hour")
month_dummies = pd.get_dummies(data["TimeHour"].apply(lambda i: i.month), prefix="month")
# Check each date whether in holidays
is_holiday = data["TimeHour"].apply(lambda i: i.date() in NL_holidays).astype(int)
# Concatenate and add constant/intercept
X = pd.concat([hour_dummies, month_dummies, is_holiday], axis=1)
X["Constant"] = 1
return X
def SP_profile(SP_weekday,SP_dayoff):
""" Define Temperature SP for 1 days (24 hours).
Args:
SP_weekday: week day temperature profile
SP_dayoff: holiday or weekend temperature profile
Returns:
SP: Temperature SP profile for 8760 hours(year)
"""
base = datetime.datetime(2020, 1, 1)
date = np.array([base + datetime.timedelta(days=i) for i in range(365)])
nl_holidays = holidays.Netherlands(years = 2020)
temp2 = np.zeros((0,1))
# A years profile loop
for i in range(len(date)):
temp = SP_weekday[0:24]
if date[i].strftime("%A") == 'Saturday' or date[i].strftime("%A") == 'Sunday':
#print(i)
temp = SP_dayoff[0:24]
#print('------------------weekend------------------')
if nl_holidays.get(date[i]) != None:
#print(i)
temp = SP_dayoff[0:24]
#if i == 359:
#plt.plot(SP_weekday[0:23])
# plt.plot(temp[7:24])
temp2 = np.concatenate((temp2, temp))
SP = temp2[0:8760].flatten()
return SP
def is_holiday(date):
try:
import holidays
return date in holidays.Netherlands()
except:
return False
'FR': 64.610,
'LU': 0.502,
'NL': 16.570,
'PL': 38.53,
'SE': 9.341
}
holiday_op = [
('AT', holidays.Austria()), # holidays for each country
('BE', holidays.Belgium()), # implented this way because of bug in library
('CH', holidays.Switzerland()),
('CZ', holidays.Czech()),
('DE', holidays.Germany()),
('DK', holidays.Denmark()),
('FR', holidays.France()),
('LU', holidays.Luxembourg()),
('NL', holidays.Netherlands()),
('PL', holidays.Poland()),
('SE', holidays.Sweden())
]
def timedata(dt):
# create time data extra information for influxDB (makes sorting easier)
timestamp = datetime.fromtimestamp(dt)
year = timestamp.year
month = timestamp.month
hour = timestamp.hour
minute = timestamp.minute
weekday = timestamp.weekday()
# determine the holiday export weight
### STATIC VARIABLES today = date.today() australia_holidays = holidays.Australia() austria_holidays = holidays.Austria() canada_holidays = holidays.Canada() colombia_holidays = holidays.Colombia() czech_holidays = holidays.Czech() denmark_holidays = holidays.Denmark() england_holidays = holidays.England() europeancentralbank_holidays = holidays.EuropeanCentralBank() germany_holidays = holidays.Germany() ireland_holidays = holidays.Ireland() mexico_holidays = holidays.Mexico() netherlands_holidays = holidays.Netherlands() newzealand_holidays = holidays.NewZealand() northernireland_holidays = holidays.NorthernIreland() norway_holidays = holidays.Norway() portugal_holidays = holidays.Portugal() portugalext_holidays = holidays.PortugalExt() scotland_holidays = holidays.Scotland() spain_holidays = holidays.Spain() unitedkingdom_holidays = holidays.UnitedKingdom() unitedstates_holidays = holidays.UnitedStates() wales_holidays = holidays.Wales() def isDateHoliday(date, countryHolidays): return date in country def isTodayHoliday(countryHolidays):