def load_standardized(df):
df = df[[
"date", "location", "new_cases", "new_deaths", "total_cases",
"total_deaths"
]]
df = inject_owid_aggregates(df)
df = discard_rows(df)
df = inject_weekly_growth(df)
df = inject_biweekly_growth(df)
df = inject_doubling_days(df)
df = inject_per_million(df, [
"new_cases", "new_deaths", "total_cases", "total_deaths",
"weekly_cases", "weekly_deaths", "biweekly_cases", "biweekly_deaths"
])
df = inject_rolling_avg(df)
df = inject_cfr(df)
df = inject_days_since(df)
df = inject_exemplars(df)
return df.sort_values(by=["location", "date"])
def load_standardized(filename):
df = _load_merged(filename) \
.drop(columns=[
'countriesAndTerritories', 'geoId',
'day', 'month', 'year',
]) \
.rename(columns={
'dateRep': 'date',
'cases': 'new_cases',
'deaths': 'new_deaths'
})
df = df[['date', 'location', 'new_cases', 'new_deaths']]
df = inject_owid_aggregates(df)
df = discard_rows(df)
df = inject_total_daily_cols(df, ['cases', 'deaths'])
df = inject_per_million(
df, ['new_cases', 'new_deaths', 'total_cases', 'total_deaths'])
df = inject_cfr(df)
df = inject_rolling_avg(df)
df = inject_days_since_all(df)
df = inject_exemplars(df)
return df.sort_values(by=['location', 'date'])