def grabDataFromEpicast(self):
if self.region=='':
self.fludata = Epidata.fluview(self.state, [Epidata.range(201040,self.todaysEW)])
elif self.state=='':
self.fludata = Epidata.fluview(self.region, [Epidata.range(201040,self.todaysEW)])
else:
self.fludata = Epidata.fluview(self.region+self.state, [Epidata.range(201040,self.todaysEW)])
self.fludata_message = self.fludata['message']
self.fludata_data = self.fludata['epidata']
def EpiCallForData(year, week, region, lag):
if region == 'nat':
fluData = Epidata.fluview(regions=['nat'],
epiweeks=['{:04d}{:02d}'.format(year, week)],
lag=lag)
else:
region = int(region)
fluData = Epidata.fluview(regions=['HHS{:d}'.format(region)],
epiweeks=['{:04d}{:02d}'.format(year, week)],
lag=lag)
return fluData
def get_unstable_wILI(region, ew1, ew2):
weeks = Epidata.range(ew1, ew2)
epidata = AF_Utils._get(Epidata.fluview(region, weeks, issues=ew2))
data = [row['wili'] for row in epidata]
if len(data) != flu.delta_epiweeks(ew1, ew2) + 1:
raise Exception('missing data')
return data
def get_ili(location, issue, ew1, ew2):
result = {}
epiweeks = Epidata.range(ew1, ew2)
num_weeks = flu.delta_epiweeks(ew1, ew2) + 1
# try to get unstable, but gracefully fall back to stable
if issue is not None:
res = Epidata.fluview(location, epiweeks, issues=issue)
if res['result'] == 1:
for row in res['epidata']:
result[row['epiweek']] = row['wili']
# check to see if another API call is needed
if issue is None or res['result'] != 1 or len(res['epidata']) < num_weeks:
# get stable data
data = api_fetch(Epidata.fluview(location, epiweeks))
for row in data:
epiweek = row['epiweek']
if epiweek not in result:
result[epiweek] = row['wili']
# return a list of weekly data
return [[result[ew]] for ew in sorted(list(result.keys()))]
def get_fluview_data(states, start, end):
"""
return a dictionary of dataframe with the different epiweeks
"""
ilinet_raw = {}
for state in states:
print("State {}".format(state))
res = Epidata.fluview(
regions=state, #source
epiweeks=[Epidata.range(start, end)]) #range 2009 to 2016
if res['result'] == 1:
print(res['result'], res['message'], len(res['epidata']))
data = pd.DataFrame(res['epidata'])
ilinet_raw[state] = data
else:
print("(-2, u'no success')")
return ilinet_raw
def get_influenza_counts_df():
"""Load influenza counts from the CMU Delphi API, return a pandas dataframe"""
# Retrieves current date, formats it "YYYY-mm-dd", and converts it to epiweek
today_obj = datetime.today()
today_str = today_obj.strftime("%Y-%m-%d")
epiweek = DataLoader.get_approx_epiweek_from_date(today_str)
# Retrieves national fluview data for each "epiweek" from 2020:
results = Epidata.fluview(["nat"], [Epidata.range(202001, epiweek)])
results_df = pd.DataFrame.from_records(
results["epidata"]).sort_values(by=["epiweek"])
results_df = results_df[[
"epiweek", "lag", "num_ili", "num_patients", "num_providers",
"wili", "ili"
]]
# Convert epiweeks to approximate real date for graphing
results_df["date"] = results_df["epiweek"].apply(
DataLoader.get_approx_date_from_epiweek)
return results_df
return obs
unique_EWLagPairs= unique_EWLagPairs.apply(addLag,1)
return d.merge( unique_EWLagPairs, on = ['EW','lag'])
def timeStamp():
return datetime.datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
if __name__ == "__main__":
firstWeekOfSeason = datetime.datetime.strptime('2019-10-01',"%Y-%m-%d")
epiWeeks = computeEpiWeeksWithData(firstWeekOfSeason)
regions = createAllRegions()
mostRecentEpiData = {'EW':[],'region':[],'wili':[],'lag':[],'releaseDate':[],'releaseEW':[]}
for lag in np.arange(40,-1,-1):
fluData = Epidata.fluview(regions = regions ,epiweeks = epiWeeks,lag=lag)
if fluData['message'] != 'success':
print('could not download data-lag={:d}'.format(lag))
continue
print('Downloading data-lag={:d}'.format(lag))
for data in fluData['epidata']:
mostRecentEpiData['EW'].append(data['epiweek'])
mostRecentEpiData['region'].append(data['region'])
mostRecentEpiData['wili'].append(data['wili'])
mostRecentEpiData['lag'].append(lag)
mostRecentEpiData['releaseDate'].append(data['release_date'])
releasedateDT = datetime.datetime.strptime(data['release_date'],"%Y-%m-%d")
mostRecentEpiData['releaseEW'].append( fromDateTime2EW(releasedateDT ))
mostRecentEpiData = pd.DataFrame(mostRecentEpiData)
cur = cnx.cursor(buffered=True)
# Get ground truth
history = {}
regions = [
"nat", "hhs1", "hhs2", "hhs3", "hhs4", "hhs5", "hhs6", "hhs7", "hhs8",
"hhs9", "hhs10", "ga", "pa", "dc", "tx", "or"
]
# for 2017-18 season, 201744 is the first ground truth data we get after the competition starts (i.e., users forecasted for it in 201743)
#############################################################
season_start, season_end = 201744, 201820
for r in range(1, len(regions) + 1):
history[r] = {}
rows = Epidata.check(
Epidata.fluview(regions[r - 1], Epidata.range(season_start,
season_end)))
truth = [(row['epiweek'], row['wili']) for row in rows]
availableWeeks = [row[0] for row in truth]
for row in truth:
(epiweek, wili) = row
history[r][epiweek] = wili
print(regions[r - 1], epiweek, wili)
epiweek = availableWeeks[-1]
print("epiweek", epiweek)
if (epiweek == 201801): forecast_made = 201752
else: forecast_made = epiweek - 1
# debug print
print("availableWeeks", availableWeeks)
expected_weeks = epi_utils.delta_epiweeks(season_start, epiweek) + 1
def EpiCallForLag(year, week, region):
if region == 'nat':
return Epidata.fluview(['nat'], ['{:04d}{:02d}'.format(year, week)])
region = int(region)
return Epidata.fluview(['HHS{:d}'.format(region)],
['{:04d}{:02d}'.format(year, week)])
regions = ["nat", *["hhs" + str(i) for i in range(1, 11)]]
# NOTE Lag value
# A lag of 0 means that the data for each week collected will be
# as observed at that point in time.
# Pass None as lag will let us collect the most recent data
# available
df = {
"epiweek": [],
"region": [],
"wili": []
}
for region in regions:
res = Epidata.fluview(region, epiweek_range, lag=None)
for data in res["epidata"]:
df["epiweek"].append(data["epiweek"])
df["region"].append(data["region"])
df["wili"].append(data["wili"])
# Write to file
pd.DataFrame(df).to_csv(snakemake.output.actual_csv, index=False)
# Save baseline information
bdf = pd.read_csv(BASELINE_URL, index_col=0)
def rename_region(region: str) -> str:
if region == "National":
return "nat"
else:
