def label_holidays2(frame: DataFrame, colname: str = "date") -> DataFrame:
"""Add a column indicating whether or not the column `colname`
is a holiday."""
# A more efficient implementation of `label_holidays`. Major downside is
# that the range of years needs to be known a priori. Put them in a config
# file or extract the range from the data beforehand.
holidays_be = holidays.BE(years=list(range(2015, 2020)))
return frame.withColumn("is_belgian_holiday",
col(colname)).isin(list(holidays_be.keys()))
def label_holidays3(frame: DataFrame, colname: str = "date") -> DataFrame:
"""Add a column indicating whether or not the column `colname`
is a holiday."""
# Another more efficient implementation of `label_holidays`. Same downsides
# as label_holidays2, but scales better.
holidays_be = holidays.BE(years=list(range(2015, 2020)))
spark = SparkSession.builder.getOrCreate()
holidays_frame = spark.createDataFrame(
data=[(day, True) for day in holidays_be.keys()],
schema=StructType([
StructField(colname, DateType(), False),
StructField("is_belgian_holiday", BooleanType(), False),
]),
)
return frame.join(holidays_frame, on=colname,
how="left").na.fill(False, ["is_belgian_holiday"])
def is_belgian_holiday(date: datetime.date):
belgian_holidays = holidays.BE()
return date in belgian_holidays
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 setUp(self):
self.holidays = holidays.BE()
"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(),
"SI": holidays.SI(),
"FI": holidays.FI(),
"CH": holidays.CH()
}
def get_holiday():
country = get_country_code()
if not country in country_holidays.keys():
return None
return country_holidays[country].get(datetime.now().date())
def topic_date(config):
return meta[app]['genre']
else:
return 'unknown'
tqdm.pandas(desc="Adding category", position=0, leave=True)
df['category'] = df.application.progress_apply(adding_category_row)
return df
##################################################
# Weekends, holidays, working hours, time of day #
##################################################
# Holidays --> complete with non-standard days
be_holidays = holidays.BE()
# Schedule
morning = (dt.time(8, 30), dt.time(12))
afternoon = (dt.time(13, 30), dt.time(16))
schedule = {
0: [morning, afternoon],
1: [morning, afternoon],
2: [morning],
3: [morning, afternoon],
4: [morning, afternoon]
}
def add_date_annotation(df: pd.DataFrame,