def adapt(df, config):
"""
Adapt the line listing data to the desired dataframe format.
"""
# Extract the yaml config settings
date_low, date_high = get_date_low_high(config)
settings = config["CasesData"]
pillars = settings["pillars"]
measure = settings["measure"].casefold()
# this key might not be stored in the config file
# if it's not, we need to grab it using AreaCodeData
if "lad19cds" not in config:
_df = AreaCodeData.process(config)
areacodes = config["lad19cds"]
if settings["input"] == "processed":
return df
if settings["format"].lower() == "phe":
df = CasesData.adapt_phe(
df,
date_low,
date_high,
pillars,
measure,
areacodes,
)
elif (settings["input"] == "url") and (settings["format"] == "json"):
df = CasesData.adapt_gov_api(df, date_low, date_high, pillars,
measure, areacodes)
return df
def check(df, config):
"""
Check that data format seems correct
"""
nareas = len(config["lad19cds"])
date_low, date_high = get_date_low_high(config)
dates = pd.date_range(start=date_low, end=date_high, closed="left")
days = len(dates)
entries = days * nareas
if not (((dims[1] >= 3) & (dims[0] == entries))
| ((dims[1] == days) & (dims[0] == nareas))):
print(df)
raise ValueError("Incorrect CasesData dimensions")
if "date" in df:
_df = df
elif df.columns.name == "date":
_df = pd.DataFrame({"date": df.columns})
else:
raise ValueError("Cannot determine date axis")
check_date_bounds(df, date_low, date_high)
check_date_format(df)
check_lad19cd_format(df)
return True
def process_lancs(config):
global_settings = config["Global"]
settings = config["TierData"]
if "lad19cds" not in config:
_df = AreaCodeData.process(config)
areacodes = config["lad19cds"]
date_low, date_high = get_date_low_high(config)
if config["TierData"]["format"].lower() == "lancs_raw":
return LancsData.read_tier_restriction_data(
settings["address"], areacodes, date_low, date_high)
elif config["TierData"]["format"].lower() == "lancs_tidy":
return LancsData.read_challen_tier_restriction(
settings["address"], date_low, date_high, areacodes)
elif config["TierData"]["format"].lower() == "api":
raise NotImplementedError(f"Tier data api not implemented")
else:
raise NotImplementedError(
f'Format type {config["TierData"]["format"]} not implemented')
def adapt(df, config):
"""
Adapt the dataframe to the desired format.
"""
settings = config["TierData"]
# TODO this key might not be stored in the config file
# if it's not, we need to grab it using AreaCodeData
if "lad19cds" not in config:
areacodes = AreaCodeData.process(config)["lad19cd"]
else:
areacodes = config["lad19cds"]
# Below is assuming inference_period dates
date_low, date_high = get_date_low_high(config)
if settings["format"].lower() == "tidy":
xarray = TierData.adapt_xarray(df, date_low, date_high, areacodes,
settings)
elif settings["format"].lower() == "api":
xarray = TierData.adapt_api_xarray(df, date_low, date_high,
areacodes, settings)
return xarray