def get_encoded_calendar_df(data_final):
# Load school holidays for France
fr_holidays = SchoolHolidayDates()
df_vacances = pd.DataFrame()
for year in list(set(data_final['year'])):
df_vacances = pd.concat([df_vacances, pd.DataFrame.from_dict(fr_holidays.holidays_for_year(year)).T])
# Load bank holidays for France
df_jf = pd.DataFrame()
for year in list(set(data_final['year'])):
df_jf = pd.concat([df_jf, pd.DataFrame([
{'date': el[0], 'jour_ferie': el[1]} for el in sorted(holidays.FRA(years=year).items())])])
# Merge school and bank holidays
df_holidays = pd.merge(df_vacances, df_jf, how='outer', on='date')
# Create features from df_holidays dataframes (school holidays and bank holidays):
# - 3 binary features for school holidays, taking 1 if the given zone is on holiday, else 0 (vacances_zone_a,
# vacances_zone_b, vacances_zone_c)
# Definition of a dictionary to encode boolean into numeric
dict_map_vac = {
True: 1,
False: 0
}
# Apply dictionary to each holiday column for the three zones (A, B, C)
df_holidays['vacances_zone_a'] = df_holidays['vacances_zone_a'].map(dict_map_vac)
df_holidays['vacances_zone_b'] = df_holidays['vacances_zone_b'].map(dict_map_vac)
df_holidays['vacances_zone_c'] = df_holidays['vacances_zone_c'].map(dict_map_vac)
# - 1 binary feature for bank holiday, taking 1 if it is a bank holiday, else 0
# The column "jour ferie" contains either the name of the holiday or a missing value (NaN)
# The idea is to put a '1' when it's a holiday (i.e. when the value is different from nan, else 0)
df_holidays['jour_ferie'] = df_holidays['jour_ferie'].map(lambda x: 1 if str(x) != 'nan' else 0)
# - To go further: Try to create a combined feature with school and bank holidays
df_holidays['holiday'] = df_holidays['vacances_zone_a'] + df_holidays['vacances_zone_b'] + df_holidays[
'vacances_zone_c'] + df_holidays['jour_ferie']
df_holidays['date'] = df_holidays['date'].map(lambda x: str(x))
data_final_cal = pd.merge(data_final, df_holidays, how='left', left_on='release_date', right_on='date').fillna(0)
data_final_cal['month'] = data_final_cal['release_date'].map(lambda x: int(x[5:7]))
data_final_cal = apply_cos(data_final_cal, 'month', 'cos_month', 12)
return data_final_cal
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 test_read_working_days_from_contract_by_month_by_user(
client: TestClient, normal_user_token_headers: dict,
db: Session) -> None:
r = client.get(f"{settings.API_V1_STR}/users/me",
headers=normal_user_token_headers)
user_id = r.json()["id"]
contract = create_random_contract(db, user_id=user_id)
working_days = []
next_days = +1
working_days.insert(
0,
create_random_working_day(db,
contract_id=contract.id,
day=str(contract.start +
relativedelta(days=+next_days * 1))))
working_days.insert(
1,
create_random_working_day(db,
contract_id=contract.id,
day=str(contract.start +
relativedelta(days=+next_days * 2))))
working_days.insert(
2,
create_random_working_day(db,
contract_id=contract.id,
day=str(contract.start +
relativedelta(days=+next_days * 5))))
# Month N
month_date = str(contract.start)
year = str(month_date).split("-")[0]
month = str(month_date).split("-")[1]
response = client.get(
f"{settings.API_V1_STR}/contracts/{contract.id}/working_days?year={year}&month={month}",
headers=normal_user_token_headers,
)
assert response.status_code == 200
content = response.json()
assert isinstance(content, list)
holidays_fra = [
datetime.strftime(x[0], "%Y-%m-%d")
for x in holidays.FRA(years=int(year)).items()
if x[0] >= datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date()
and x[0] < datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date() +
relativedelta(months=+1)
]
weekmask = contract.weekdays
startDay = datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date()
endDay = datetime.strptime(f"{year}-{month}-01",
"%Y-%m-%d").date() + relativedelta(months=+1)
workingdays_list = [x.day for x in working_days]
business_days_inherited_pandas = pandas.bdate_range(
start=startDay,
end=endDay,
freq="C",
weekmask=weekmask,
holidays=holidays_fra + workingdays_list).format()
working_days2 = working_days + [dict(day=x) for x in holidays_fra] + [
dict(day=x) for x in business_days_inherited_pandas
]
assert len(content) == len(working_days2)
for i in content:
assert "id" in dict(i).keys()
assert "day" in dict(i).keys()
assert "start" in dict(i).keys()
assert "end" in dict(i).keys()
assert "contract_id" in dict(i).keys()
assert "day_type_id" in dict(i).keys()
lookup_month = {
1: "January",
2: "February",
3: "March",
4: "April",
5: "May",
6: "June",
7: "July",
8: "August",
9: "September",
10: "October",
11: "November",
12: "December"
}
fr_holidays = holidays.FRA()
df = pd.DataFrame({"date": pd.date_range('2000-01-01', '2050-12-31')})
df["year"] = df.date.dt.year
df["semester"] = (df.date.dt.quarter + 1) // 2
df["quarter"] = df.date.dt.quarter
df["monthofyear"] = df.date.dt.month
df["name_of_month"] = df["monthofyear"].apply(lambda x: lookup_month[x])
df["week"] = df.date.dt.weekofyear
df["dayofyear"] = df.date.dt.dayofyear
df["dayofweek"] = df.date.dt.dayofweek + 1
df["name_of_day"] = df.date.dt.weekday_name
df["holiday"] = df["date"].apply(lambda x: x in fr_holidays)
print(df.head(10))
df.to_csv("lookup_date.csv", index=False)
def is_holidays():
"""
Détermine si lejour courant est un jour ferié
:return:
"""
return datetime.datetime.today() in holidays.FRA()
def read_working_days(
*,
db: Session = Depends(deps.get_db),
id: int,
year: str = Query(None, regex="^[2][0-9]{3}", min_length=4, max_length=4),
month: str = Query(None, regex="^[01]?[0-9]", min_length=1, max_length=2),
current_user: models.User = Depends(deps.get_current_active_user),
) -> Any:
"""
Retrieve working_days by contract.
"""
contract = crud.contract.get(db=db, id=id)
if not contract:
raise HTTPException(status_code=404, detail="Contract not found")
if (not crud.user.is_superuser(current_user)
and (contract.user_id != current_user.id)):
raise HTTPException(status_code=400, detail="Not enough permissions")
if year and month:
month_date = datetime.strptime(f"{year}-{month}", "%Y-%m").date()
next_month_date = month_date + relativedelta(months=+1, days=-1)
working_days = crud.working_day.get_multi_by_contract_by_date(
db=db, contract_id=id, start=month_date, end=next_month_date)
else:
working_days = crud.working_day.get_multi_by_contract(db=db,
contract_id=id)
holidays_fra = [
datetime.strftime(x[0], "%Y-%m-%d")
for x in holidays.FRA(years=int(year)).items()
if x[0] >= datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date()
and x[0] < datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date() +
relativedelta(months=+1)
]
workingdays_list = [x.day for x in working_days]
weekmask = contract.weekdays
startDay = datetime.strptime(f"{year}-{month}-01", "%Y-%m-%d").date()
endDay = datetime.strptime(f"{year}-{month}-01",
"%Y-%m-%d").date() + relativedelta(months=+1)
business_days_inherited_pandas = pandas.bdate_range(
start=startDay,
end=endDay,
freq="C",
weekmask=weekmask,
holidays=holidays_fra + workingdays_list).format()
result = working_days + [
schemas.WorkingDay(
day=x,
day_type_id=51,
contract_id=contract.id,
id=0,
start=datetime.strptime(f"09:00:00", "%H:%M:%S").time(),
end=datetime.strptime(f"18:00:00", "%H:%M:%S").time(),
) for x in holidays_fra
] + [
schemas.WorkingDay(
day=x,
day_type_id=50,
contract_id=contract.id,
id=0,
start=datetime.strptime(f"09:00:00", "%H:%M:%S").time(),
end=(datetime.strptime(f"09:00:00", "%H:%M:%S") +
relativedelta(hours=+int(contract.hours))).time(),
) for x in business_days_inherited_pandas
]
result.sort(key=lambda x: x.day)
return result