def date_week(match, other=None):
data = {k: int(v or 1) for k, v in match.groupdict().items()}
year = data['year']
week = data['week']
day = data['day']
ordinal = week * 7 + day - ((date_(year, 1, 4).weekday() + 1) + 3)
if ordinal < 1:
ordinal += days_in_year(year - 1)
year -= 1
elif ordinal > days_in_year(year):
ordinal -= days_in_year(year)
year += 1
return date_(year, 1, 1) + timedelta(days=(ordinal - 1))
def get_row_col(data,state,date):
col=data.index(state.lower())
date1=[]
date1=date.split("/")
d1=date_(int(str(date1[2])),int(str(date1[1])),int(str(date1[0])))
row=(d1-d0).days
row+=1
return row,col
def create_all_past_days():
today = date.today()
from datetime import date as date_
first_day = date_(2017, 9, 7)
day = first_day
while day < today:
store_day(day.strftime('%Y-%m-%d'))
day += timedelta(days=1)
def date(match, other=None):
data = {k: int(v) for k, v in match.groupdict().items() if v}
if other:
if isinstance(other, datetime):
return other.date().replace(**data)
elif isinstance(other, date_):
return other.replace(**data)
else:
raise ValueError('other must be datetime or date object.')
else:
return date_(data.get('year', 1), data.get('month', 1), data.get('day', 1))
def load_forces(src):
""" Load data into fox_forces """
session = model.Session()
for rowid, row in enumerate(csv2.DictReader(src, delimiter='\t')):
del row['cwsac']
for x in ['killed', 'wounded', 'missing', 'casualties']:
if row[x]:
row[x] = parse_human_integer(row[x])
for x in ['start', 'end']:
dateparts = [x + i for i in ('y', 'm', 'd')]
row['%s_date' % x] = date_(*[int(row[y]) for y in dateparts])
for y in dateparts:
del row[y]
row['aggrow'] = (row['aggrow'] == '1')
milforce = model.FoxForce(battle = rowid, **row)
session.add(milforce)
session.commit()
async def zipCode(self,
zipCode: str,
*,
date: Optional[Union[date_, datetime, str]] = None,
distance: Optional[int] = None) -> list:
'''Request current observation for zip code'''
params: dict = dict(zipCode=zipCode)
if date and isinstance(date, str):
y, m, d = date.split('-')
params['date'] = date_(int(y), int(m), int(d)).isoformat()
elif date and isinstance(date, datetime):
params['date'] = date.date().isoformat()
elif date and isinstance(date, date_):
params['date'] = date.isoformat()
if distance:
params['distance'] = distance
return await self._request('aq/forecast/zipCode', params=params)
async def latLong(
self,
latitude: Optional[Union[float, str]] = None,
longitude: Optional[Union[float, str]] = None,
*,
date: Optional[Union[date_, datetime, str]] = None,
distance: Optional[int] = None,
) -> None:
'''Request current observation for latitude/longitude'''
params: dict = dict(
latitude=str(latitude),
longitude=str(longitude),
)
if date and isinstance(date, str):
y, m, d = date.split('-')
params['date'] = date_(int(y), int(m), int(d)).isoformat()
elif date and isinstance(date, datetime):
params['date'] = date.date().isoformat()
elif date and isinstance(date, date_):
params['date'] = date.isoformat()
if distance:
params['distance'] = distance
return await self._request('aq/forecast/latLong', params=params)
def get_territory_currencies(territory, start_date=None, end_date=None,
tender=True, non_tender=False,
include_details=False):
"""Returns the list of currencies for the given territory that are valid for
the given date range. In addition to that the currency database
distinguishes between tender and non-tender currencies. By default only
tender currencies are returned.
The return value is a list of all currencies roughly ordered by the time
of when the currency became active. The longer the currency is being in
use the more to the left of the list it will be.
The start date defaults to today. If no end date is given it will be the
same as the start date. Otherwise a range can be defined. For instance
this can be used to find the currencies in use in Austria between 1995 and
2011:
>>> from datetime import date
>>> get_territory_currencies('AT', date(1995, 1, 1), date(2011, 1, 1))
['ATS', 'EUR']
Likewise it's also possible to find all the currencies in use on a
single date:
>>> get_territory_currencies('AT', date(1995, 1, 1))
['ATS']
>>> get_territory_currencies('AT', date(2011, 1, 1))
['EUR']
By default the return value only includes tender currencies. This
however can be changed:
>>> get_territory_currencies('US')
['USD']
>>> get_territory_currencies('US', tender=False, non_tender=True,
... start_date=date(2014, 1, 1))
['USN', 'USS']
.. versionadded:: 2.0
:param territory: the name of the territory to find the currency fo
:param start_date: the start date. If not given today is assumed.
:param end_date: the end date. If not given the start date is assumed.
:param tender: controls whether tender currencies should be included.
:param non_tender: controls whether non-tender currencies should be
included.
:param include_details: if set to `True`, instead of returning currency
codes the return value will be dictionaries
with detail information. In that case each
dictionary will have the keys ``'currency'``,
``'from'``, ``'to'``, and ``'tender'``.
"""
currencies = get_global('territory_currencies')
if start_date is None:
start_date = date_.today()
elif isinstance(start_date, datetime_):
start_date = start_date.date()
if end_date is None:
end_date = start_date
elif isinstance(end_date, datetime_):
end_date = end_date.date()
curs = currencies.get(territory.upper(), ())
# TODO: validate that the territory exists
def _is_active(start, end):
return (start is None or start <= end_date) and \
(end is None or end >= start_date)
result = []
for currency_code, start, end, is_tender in curs:
if start:
start = date_(*start)
if end:
end = date_(*end)
if ((is_tender and tender) or
(not is_tender and non_tender)) and _is_active(start, end):
if include_details:
result.append({
'currency': currency_code,
'from': start,
'to': end,
'tender': is_tender,
})
else:
result.append(currency_code)
return result
def get_territory_currencies(territory, start_date=None, end_date=None,
tender=True, non_tender=False,
include_details=False):
"""Returns the list of currencies for the given territory that are valid for
the given date range. In addition to that the currency database
distinguishes between tender and non-tender currencies. By default only
tender currencies are returned.
The return value is a list of all currencies roughly ordered by the time
of when the currency became active. The longer the currency is being in
use the more to the left of the list it will be.
The start date defaults to today. If no end date is given it will be the
same as the start date. Otherwise a range can be defined. For instance
this can be used to find the currencies in use in Austria between 1995 and
2011:
>>> from datetime import date
>>> get_territory_currencies('AT', date(1995, 1, 1), date(2011, 1, 1))
['ATS', 'EUR']
Likewise it's also possible to find all the currencies in use on a
single date:
>>> get_territory_currencies('AT', date(1995, 1, 1))
['ATS']
>>> get_territory_currencies('AT', date(2011, 1, 1))
['EUR']
By default the return value only includes tender currencies. This
however can be changed:
>>> get_territory_currencies('US')
['USD']
>>> get_territory_currencies('US', tender=False, non_tender=True,
... start_date=date(2014, 1, 1))
['USN', 'USS']
.. versionadded:: 2.0
:param territory: the name of the territory to find the currency for.
:param start_date: the start date. If not given today is assumed.
:param end_date: the end date. If not given the start date is assumed.
:param tender: controls whether tender currencies should be included.
:param non_tender: controls whether non-tender currencies should be
included.
:param include_details: if set to `True`, instead of returning currency
codes the return value will be dictionaries
with detail information. In that case each
dictionary will have the keys ``'currency'``,
``'from'``, ``'to'``, and ``'tender'``.
"""
currencies = get_global('territory_currencies')
if start_date is None:
start_date = date_.today()
elif isinstance(start_date, datetime_):
start_date = start_date.date()
if end_date is None:
end_date = start_date
elif isinstance(end_date, datetime_):
end_date = end_date.date()
curs = currencies.get(territory.upper(), ())
# TODO: validate that the territory exists
def _is_active(start, end):
return (start is None or start <= end_date) and \
(end is None or end >= start_date)
result = []
for currency_code, start, end, is_tender in curs:
if start:
start = date_(*start)
if end:
end = date_(*end)
if ((is_tender and tender) or
(not is_tender and non_tender)) and _is_active(start, end):
if include_details:
result.append({
'currency': currency_code,
'from': start,
'to': end,
'tender': is_tender,
})
else:
result.append(currency_code)
return result
import GetOldTweets3 as got
import pandas as pd
import tweepy
from datetime import date as date_
import requests
import csv
d0 = date_(2020, 3, 14) # date representing initial date from which data is there for corona cases
region=["KL","MH","RJ","KA","GA","MP","UP","GJ","TN","TS","BH","JK","PY","HR","AP","WB","CT","OR","JH","AS","HP","NL","SK","MN","AR","TR","ME","MI","UT"] #statecode corresponding to particular coordinates and radius
coordinates=["10.8505,76.2711","19.7515,75.7319","27.0238,74.2179","15.3173,75.7139","15.2993,74.1240","22.9734,78.6569","28.8467,80.9462","22.2587,71.1924","11.1271,78.6569","18.1124,79.0193","25.0961,85.3131","33.7782,76.5762","31.1471,75.3412","29.0588,76.0856","15.9129,79.7400","22.9868,87.8550","21.2787,81.8661","20.9517,85.0985","23.6102,85.2799","26.2006,92.9376","31.1048,77.1734","26.1584,94.5624","27.5330,88.5122","24.6637,93.9063","28.2180,94.7278","23.9408,91.9882","25.4670,91.3662","23.1645,92.9376","30.0668,79.0193"]
radius=["111.22","312.97","330.05","247.08","34.33","313.29","278.28","249.79","203.47","188.88","173.12","115.95","126.61","118.63","227.76","168.07","207.44","222.62","159.29","158.01","133.12","72.64","47.52","84.30","163.26","57.77","84.49","81.92","130.47"]
consumer_key="HBphkAktZUCXnzsETAL2DZDZ5"
consumer_secret="RVI25oLDDIHnwdlDTetMKkreG40tM0JLESP2rtMvjMr3SvbeQS"
access_token="1249603598545113089-JBOA1Bg2drujYFJbXL2ODAeL8lWX9v"
access_token_secret="TBZ2t8xOoHvdL2tuFArMsQrcjIFBOn33IO1v7Bs1FGP5r"
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)
f=open("dataset_actual.csv","w", encoding='utf-8')
w = csv.writer(f,lineterminator='\n')
data = pd.read_csv('data.csv', sep=',', header=None) #daily increase in corona cases dataset
def get_row_col(data,state,date):
col=data.index(state.lower())
date1=[]
date1=date.split("/")
d1=date_(int(str(date1[2])),int(str(date1[1])),int(str(date1[0])))
def load_from_xml(source):
session = model.Session()
context = iterparse(source, events=("start", "end", "start-ns"))
root = None
state = None
nevent = 1
for event, elem in context:
if event == "start":
if elem.tag == "div1" and elem.get('type') == "state":
state = elem.get("n")
elif elem.tag == "div2" and elem.get('type') == "year":
year = elem.get("n")
elif event == "end":
## Process a div3
if elem.tag == "div3" and elem.get('ana') == "interp-event":
head = elem.find("head")
## Parse Date
startDate = None
endDate = None
date = head.find("date")
if date is not None:
date_value = date.get("value")
if re.match("186[1-5]-00", date_value) is not None:
yyyy = int(date_value[:4])
if date.text == "Jan. to April":
startDate = date_(yyyy, 1, 1)
endDate = date_(yyyy, 4, 30)
else:
for k, v in _months.iteritems():
if date.text.startswith(k):
startDate = date_(yyyy, v, 1)
if v is not 12:
endDate = date_(yyyy, v + 1, 1) - timedelta(1)
else:
endDate = date_(yyyy, 12, 31)
break
else:
startDate = datetime_.strptime(date_value,
"%Y-%m-%d").date()
endDate = startDate
elif head.find("dateRange") is not None:
date_range = head.find("dateRange")
if date_range.text == "Feb. 14-29":
startDate = date_(1863, 2, 14)
endDate = date_(1863, 2, 28)
elif date_range.text == "Feb 6-8":
startDate = date_(1864, 2, 6)
endDate = date_(1864, 2, 8)
else:
startDate = datetime_.strptime(date_range.get("from"),
"%Y-%m-%d").date()
endDate = datetime_.strptime(date_range.get("to"),
"%Y-%m-%d").date()
# Event type
event_type = head.findtext("rs")
## head_text
event = tostring(head, encoding="utf8", method="text")
# Text
text = elem.findtext("p")
## Casualties
losses = parse_losses(text)
#print nevent, state, year, startDate, endDate, event_type
session.add(model.DyerBattle(battle = nevent,
event_type = unicode(event_type),
state = unicode(STATES[state]),
year = year,
battle_name = unicode(event, 'utf-8'),
start_date = startDate,
end_date = endDate,
text = unicode(text),
killed = losses['killed'],
wounded = losses['wounded'],
cap_missing = losses['capmiss'],
missing = losses['missing'],
casualties = losses['total']
))
nevent += 1
elem.clear()
session.commit()
def test_date():
assert parsers.date('2005-01-01') == parsers.date('2004-W53-6')
assert parsers.date('2005-01-02') == parsers.date('2004-W53-7')
assert parsers.date('2005-12-31') == parsers.date('2005-W52-6')
assert parsers.date('2007-01-01') == parsers.date('2007-W01-1')
assert parsers.date('2007-12-30') == parsers.date('2007-W52-7')
assert parsers.date('2007-12-31') == parsers.date('2008-W01-1')
assert parsers.date('2008-01-01') == parsers.date('2008-W01-2')
assert parsers.date('2008-12-28') == parsers.date('2008-W52-7')
assert parsers.date('2008-12-29') == parsers.date('2009-W01-1')
assert parsers.date('2008-12-30') == parsers.date('2009-W01-2')
assert parsers.date('2008-12-31') == parsers.date('2009-W01-3')
assert parsers.date('2009-01-01') == parsers.date('2009-W01-4')
assert parsers.date('2009-12-31') == parsers.date('2009-W53-4')
assert parsers.date('2010-01-01') == parsers.date('2009-W53-5')
assert parsers.date('2010-01-02') == parsers.date('2009-W53-6')
assert parsers.date('2010-01-03') == parsers.date('2009-W53-7')
assert parsers.date('2008-W39-6') == date_(2008, 9, 27)
assert parsers.date('2008W396') == date_(2008, 9, 27)
assert parsers.date('2016W431') == date_(2016, 10, 24)
assert parsers.date('2016-W43-1') == date_(2016, 10, 24)
assert parsers.date('2015-W30-4') == date_(2015, 7, 23)
assert parsers.date('1981-095') == date_(1981, 4, 5)
assert parsers.date('1981095') == date_(1981, 4, 5)
assert parsers.date('1981-04-05') == date_(1981, 4, 5)
assert parsers.date('19810405') == date_(1981, 4, 5)
assert parsers.date('--04-03') == date_(1, 4, 3)
assert parsers.date('--1001') == date_(1, 10, 1)
with pytest.raises(ValueError):
parsers.date('2008-W396')
with pytest.raises(ValueError):
parsers.date('2008W39-6')
with pytest.raises(ValueError):
parsers.date('198195')
with pytest.raises(ValueError):
parsers.date('1981-0405')
with pytest.raises(ValueError):
parsers.date('198104-05')
def xml_to_csv(source, writer, engagement_types):
context = iterparse(source, events=("start", "end", "start-ns"))
state = None
nevent = 1
for event, elem in context:
if event == "start":
if elem.tag == "div1" and elem.get('type') == "state":
state = elem.get("n")
elif elem.tag == "div2" and elem.get('type') == "year":
year = elem.get("n")
elif event == "end":
## Process a div3
if elem.tag == "div3" and elem.get('ana') == "interp-event":
head = elem.find("head")
## Parse Date
if nevent in MISSING_DATES:
date = MISSING_DATES[nevent]
startDate = date['start_date']
try:
endDate = date['end_date']
except KeyError:
endDate = startDate
else:
startDate = None
endDate = None
date = head.find("date")
if date is not None:
date_value = date.get("value")
if re.match("186[1-5]-00", date_value) is not None:
yyyy = int(date_value[:4])
if date.text == "Jan. to April":
startDate = date_(yyyy, 1, 1)
endDate = date_(yyyy, 4, 30)
else:
for k, v in _months.items():
if date.text.startswith(k):
startDate = date_(yyyy, v, 1)
if v is not 12:
endDate = date_(yyyy, v + 1, 1) - timedelta(1)
else:
endDate = date_(yyyy, 12, 31)
break
else:
startDate = datetime_.strptime(date_value,
"%Y-%m-%d").date()
endDate = startDate
elif head.find("dateRange") is not None:
date_range = head.find("dateRange")
startDate = datetime_.strptime(date_range.get("from"),
"%Y-%m-%d").date()
endDate = datetime_.strptime(date_range.get("to"),
"%Y-%m-%d").date()
# Event type
if nevent in MISSING_EVENTS:
event_type = MISSING_EVENTS[nevent]
else:
event_type = engagement_types[head.findtext("rs")]
## head_text
event = tostring(head, method = "text", encoding = 'utf-8').\
decode('utf-8')
# Text
text = elem.findtext("p").strip()
## Casualties
losses = parse_losses(text)
#print nevent, state, year, startDate, endDate, event_type
data = {'battle_id' : nevent,
'event_type' : event_type,
'state' :STATES[state],
'year' : year,
'battle_name' : event,
'start_date' : startDate,
'end_date' : endDate,
'text' : text.strip(),
'casualties' : losses['kwm'],
'killed' : losses['k'],
'wounded' : losses['w'],
'killed_wounded' : losses['kw'],
'missing_captured' : losses['m']
}
writer.writerow(data)
nevent += 1
def date_ordinal(match, other=None):
data = {k: int(v) for k, v in match.groupdict().items() if v}
days = (date_(data.get('year', 1), 1, 1) - date_(1, 1, 1)).days
return date_.fromordinal(days + data.get('day', 0))
def xml_to_csv(source, writer):
context = iterparse(source, events=("start", "end", "start-ns"))
state = None
nevent = 1
for event, elem in context:
if event == "start":
if elem.tag == "div1" and elem.get('type') == "state":
state = elem.get("n")
elif elem.tag == "div2" and elem.get('type') == "year":
year = elem.get("n")
elif event == "end":
## Process a div3
if elem.tag == "div3" and elem.get('ana') == "interp-event":
head = elem.find("head")
## Parse Date
startDate = None
endDate = None
date = head.find("date")
if date is not None:
date_value = date.get("value")
if re.match("186[1-5]-00", date_value) is not None:
yyyy = int(date_value[:4])
if date.text == "Jan. to April":
startDate = date_(yyyy, 1, 1)
endDate = date_(yyyy, 4, 30)
else:
for k, v in _months.items():
if date.text.startswith(k):
startDate = date_(yyyy, v, 1)
if v is not 12:
endDate = date_(yyyy, v + 1, 1) - timedelta(1)
else:
endDate = date_(yyyy, 12, 31)
break
else:
startDate = datetime_.strptime(date_value,
"%Y-%m-%d").date()
endDate = startDate
elif head.find("dateRange") is not None:
date_range = head.find("dateRange")
if date_range.text == "Feb. 14-29":
startDate = date_(1863, 2, 14)
endDate = date_(1863, 2, 28)
elif date_range.text == "Feb 6-8":
startDate = date_(1864, 2, 6)
endDate = date_(1864, 2, 8)
else:
startDate = datetime_.strptime(date_range.get("from"),
"%Y-%m-%d").date()
endDate = datetime_.strptime(date_range.get("to"),
"%Y-%m-%d").date()
# Event type
event_type_tmp = head.findtext("rs")
if event_type_tmp in ENGAGEMENT_TYPES:
event_type = ENGAGEMENT_TYPES[event_type_tmp]
else:
if nevent == 4319:
event_type = "Reoccupation" # Re-occupation of New Madrid
elif nevent == 6348:
event_type = "Reopening" # Oct. 26-29: Re-opening, Tennessee River
else:
event_type = ""
## head_text
event = tostring(head, method = "text", encoding = 'utf-8').decode('utf-8')
# Text
text = elem.findtext("p").strip()
## Casualties
losses = parse_losses(text)
#print nevent, state, year, startDate, endDate, event_type
data = {'battle' : nevent,
'event_type' : event_type,
'state' :STATES[state],
'year' : year,
'battle_name' : event,
'start_date' : startDate,
'end_date' : endDate,
'text' : text.strip(),
'killed' : losses['killed'],
'wounded' : losses['wounded'],
'cap_missing' : losses['capmiss'],
'missing' : losses['missing'],
'casualties' : losses['total']
}
writer.writerow(data)
nevent += 1
