preprocessing.exog_providers.CovidInfectionRateProvider

preprocessing.exog_providers.CovidInfectionRateProvider(
    data_home=None,
    csv_path=None,
    column='covid_infection_rate',
    fill_outside=0.0,
    max_gap=0,
    max_tail_gap=0,
    provider_window=None,
)

German national COVID-19 7-day incidence as an exogenous level regressor.

Reads the bundled, static RKI series (datasets/csv/covid_infection_rate_de.csv, CC-BY-4.0) and broadcasts the daily national 7-day incidence (per 100,000) onto the hourly target index: forward-filled within the data’s date span and filled with fill_outside (0.0 by default) before the first and after the last observed day, since outside the pandemic window there is no signal.

This is a slow socio-economic level input (a lockdown-stringency proxy). It carries the CR-3 release-lag caveat: the bundled file is the final published vintage, whereas on a true live path only the latest, lagged vintage is available. For training over historical data this is the standard treatment.

Parameters

Name	Type	Description	Default
data_home	`DataHome`	Unused (kept for a uniform provider signature); the dataset is package data, located via `get_package_data_home()`.	`None`
csv_path	Optional[Union[str, Path]]	Optional explicit path to the COVID CSV, overriding the bundled location.	`None`
column	str	Output column name. Defaults to `"covid_infection_rate"`.	`'covid_infection_rate'`
fill_outside	float	Value used outside the observed date span. Defaults to `0.0`.	`0.0`
max_gap	int	Maximum contiguous missing-value run healed by `_align_to_index`. See :func:`_align_to_index` for full semantics. Defaults to `0`.	`0`
max_tail_gap	int	Extended healing budget for the trailing-edge NaN run (the run containing `index[-1]`). The effective tail budget is `max(max_gap, max_tail_gap)`. See :func:`_align_to_index`. Defaults to `0`.	`0`
provider_window	Optional[pd.DatetimeIndex]	Validation index passed to `_align_to_index` as validate_index. See :func:`_align_to_index`. Defaults to `None`.	`None`

Examples

import pandas as pd
from spotforecast2_safe.preprocessing.exog_providers import (
    CovidInfectionRateProvider,
)

idx = pd.date_range("2021-12-01", periods=24, freq="h", tz="UTC")
out = CovidInfectionRateProvider().build(idx)
print(out.columns.tolist(), out.shape, bool(out.isna().any().any()))

['covid_infection_rate'] (24, 1) False

Methods

Name	Description
build	Return a single-column `float32` frame with the COVID incidence.

build

preprocessing.exog_providers.CovidInfectionRateProvider.build(index)

Return a single-column float32 frame with the COVID incidence.

Parameters

Name	Type	Description	Default
index	pd.DatetimeIndex	Hourly `DatetimeIndex` (tz-aware UTC) covering the training-plus-forecast window.	required

Returns

Name	Type	Description
	pd.DataFrame	pd.DataFrame: One column (`covid_infection_rate` by default), `float32`, indexed exactly by index. Values outside the pandemic date range are filled with `fill_outside` (0.0).

Raises

Name	Type	Description
	`ExogProviderError`	If the bundled CSV is absent or malformed.

Examples

import pandas as pd
from spotforecast2_safe.preprocessing.exog_providers import (
    CovidInfectionRateProvider,
)

idx = pd.date_range("2021-12-01", periods=24, freq="h", tz="UTC")
provider = CovidInfectionRateProvider()
out = provider.build(idx)
print(out.columns.tolist(), out.shape, out.dtypes.iloc[0].name)
assert out.shape == (24, 1)
assert not out.isna().any().any()

['covid_infection_rate'] (24, 1) float32