def handle_ma(res, mapping):
tagged = {}
df = MaRawData(res[0])
tabs = ['DeathsReported (Report Date)', 'Testing2 (Report Date)',
'Cases (Report Date)', 'Hospitalization from Hospitals']
for tab in tabs:
# report the last row
partial = map_attributes(df[tab].iloc[-1], mapping, 'MA')
tagged.update(partial)
# positive pcr
tests = df['TestingByDate (Test Date)'].filter(like='All Positive')
tagged[Fields.SPECIMENS_POS.name] = tests.sum()['All Positive Molecular Tests']
hosp = df['RaceEthnicityLast2Weeks']
maxdate = hosp['Date'].max()
tagged[Fields.HOSP.name] = hosp[hosp['Date'] == maxdate].sum()['Ever Hospitaltized']
# weekly report:
df = MaRawData(res[0], "Weekly Public Health Report - Raw Data")
# recovered
rec = df['Quarantine and Isolation'].sort_values('Date')
recovered = rec[rec['Status'] == 'Total Cases Released from Isolation'].iloc[-1]['Residents']
tagged[Fields.RECOVERED.name] = recovered
antibody = df['Antibody'].sum()
tagged[Fields.ANTIBODY_TOTAL_PEOPLE.name] = antibody['Total Tests']
tagged[Fields.ANTIBODY_POS_PEOPLE.name] = antibody['Positive Tests']
return tagged
def handle_ma(res, mapping):
'''Returning a list of dictionaries (records)
'''
tagged = []
# break the mapping to {file -> {mapping}}
# not the most efficient, but the data is tiny
tab_mapping = build_leveled_mapping(mapping)
tabs = MaRawData(res[0])
for tabname in tab_mapping.keys():
df = tabs[tabname].rename(columns=tab_mapping[tabname])
df[DATE] = pd.to_datetime(df[DATE])
# TODO: FIX ME LATER
# drop NaT values
df = df.loc[df[DATE].notna()]
# expect it to always exist (we control the file list)
by_date = tab_mapping[tabname].pop(DATE_USED)
df = df[tab_mapping[tabname].values()]
# need to cumsum TestingByDate file
if tabname.startswith('TestingByDate'):
df = df.set_index(DATE).cumsum()
df[DATE] = df.index
df[DATE_USED] = by_date
tagged.extend(df.to_dict(orient='records'))
return tagged
def handle_ma(res, mapping):
'''Returning a list of dictionaries (records)
'''
tagged = []
# break the mapping to {file -> {mapping}}
# not the most efficient, but the data is tiny
tab_mapping = {
x.split(":")[0]: {}
for x in mapping.keys() if x.find(':') > 0
}
for k, v in mapping.items():
if k.find(':') < 0:
continue
tab, field = k.split(":")
tab_mapping[tab][field] = v
tabs = MaRawData(res[0])
for tabname in tab_mapping.keys():
if tabname.startswith('DateofDeath'):
date_field = 'Date of Death'
else:
date_field = 'Date'
df = tabs[tabname]
# handle dates
df[date_field] = pd.to_datetime(df[date_field])
# expect it to always exist (we control the file list)
by_date = tab_mapping[tabname].pop('BY_DATE')
df = df.rename(
columns=tab_mapping[tabname])[tab_mapping[tabname].values()]
# need to cumsum TestingByDate file
if tabname.startswith('TestingByDate'):
df = df.set_index('DATE').cumsum()
df['DATE'] = df.index
df['BY_DATE'] = by_date
tagged.extend(df.to_dict(orient='records'))
return tagged