How to use the eemeter.features.compute_temperature_features function in eemeter

def test_compute_temperature_features_billing_bimonthly_bad_degree_days(
    il_electricity_cdd_hdd_billing_bimonthly
):
    meter_data = il_electricity_cdd_hdd_billing_bimonthly["meter_data"]
    temperature_data = il_electricity_cdd_hdd_billing_bimonthly["temperature_data"]
    with pytest.raises(ValueError):
        compute_temperature_features(
            meter_data.index,
            temperature_data,
            heating_balance_points=[60, 61],
            cooling_balance_points=[65, 66],
            degree_day_method="UNKNOWN",
        )

def test_compute_temperature_features_shorter_temperature_data(
    il_electricity_cdd_hdd_daily
):
    meter_data = il_electricity_cdd_hdd_daily["meter_data"]
    temperature_data = il_electricity_cdd_hdd_daily["temperature_data"]

    # drop some data
    temperature_data = temperature_data[:-200]

    df = compute_temperature_features(meter_data.index, temperature_data)
    assert df.shape == (810, 3)
    assert list(sorted(df.columns)) == [
        "n_days_dropped",
        "n_days_kept",
        "temperature_mean",
    ]
    assert round(df.temperature_mean.sum()) == 43958.0

def test_compute_temperature_features_empty_meter_data():
    index = pd.DatetimeIndex([], tz="UTC", name="dt", freq="H")
    temperature_data = pd.Series({"value": 0}, index=index)
    result_index = temperature_data.resample("D").sum().index
    meter_data_hack = pd.DataFrame({"value": []}, index=result_index)
    meter_data_hack.index.freq = None

    df = compute_temperature_features(
        meter_data_hack.index,
        temperature_data,
        heating_balance_points=[65],
        cooling_balance_points=[65],
        degree_day_method="daily",
        use_mean_daily_values=False,
    )
    assert df.shape == (0, 3)
    assert list(sorted(df.columns)) == [
        "n_days_dropped",
        "n_days_kept",
        "temperature_mean",
    ]
    assert round(df.temperature_mean.sum()) == 0

def test_compute_temperature_features_daily_daily_degree_days(
    il_electricity_cdd_hdd_daily, snapshot
):
    meter_data = il_electricity_cdd_hdd_daily["meter_data"]
    temperature_data = il_electricity_cdd_hdd_daily["temperature_data"]
    df = compute_temperature_features(
        meter_data.index,
        temperature_data,
        heating_balance_points=[60, 61],
        cooling_balance_points=[65, 66],
        temperature_mean=False,
        degree_day_method="daily",
    )
    assert df.shape == (810, 6)
    assert list(sorted(df.columns)) == [
        "cdd_65",
        "cdd_66",
        "hdd_60",
        "hdd_61",
        "n_days_dropped",
        "n_days_kept",
    ]

def test_compute_temperature_features_billing_monthly_bad_degree_day_method(
    il_electricity_cdd_hdd_billing_monthly
):
    meter_data = il_electricity_cdd_hdd_billing_monthly["meter_data"]
    temperature_data = il_electricity_cdd_hdd_billing_monthly["temperature_data"]
    with pytest.raises(ValueError):
        compute_temperature_features(
            meter_data.index,
            temperature_data,
            heating_balance_points=[60, 61],
            cooling_balance_points=[65, 66],
            degree_day_method="UNKNOWN",
        )

def test_compute_temperature_features_daily_daily_degree_days_use_mean_false(
    il_electricity_cdd_hdd_daily, snapshot
):
    meter_data = il_electricity_cdd_hdd_daily["meter_data"]
    temperature_data = il_electricity_cdd_hdd_daily["temperature_data"]
    df = compute_temperature_features(
        meter_data.index,
        temperature_data,
        heating_balance_points=[60, 61],
        cooling_balance_points=[65, 66],
        temperature_mean=False,
        degree_day_method="daily",
        use_mean_daily_values=False,
    )
    assert df.shape == (810, 6)
    assert list(sorted(df.columns)) == [
        "cdd_65",
        "cdd_66",
        "hdd_60",
        "hdd_61",
        "n_days_dropped",
        "n_days_kept",

def test_caltrack_merge_temperatures_insufficient_temperature_per_period(
    baseline_meter_data_billing, baseline_temperature_data
):
    baseline_temperature_data_missing = baseline_temperature_data.copy(deep=True)
    baseline_temperature_data_missing.iloc[: (4 * 24)] = np.nan

    # test without percent_hourly_coverage_per_billing_period constraint
    temperature_features_no_constraint = compute_temperature_features(
        baseline_meter_data_billing.index,
        baseline_temperature_data_missing,
        heating_balance_points=range(40, 81),
        cooling_balance_points=range(50, 91),
        data_quality=True,
        keep_partial_nan_rows=False,
        percent_hourly_coverage_per_billing_period=0,
    )

    assert temperature_features_no_constraint["n_days_kept"].isnull().sum() == 0

    # test with default percent_hourly_coverage_per_billing_period=0.9 constraint
    temperature_features_with_constraint = compute_temperature_features(
        baseline_meter_data_billing.index,
        baseline_temperature_data_missing,
        heating_balance_points=range(40, 81),

def test_compute_temperature_features_billing_monthly_daily_degree_days_use_mean_false(
    il_electricity_cdd_hdd_billing_monthly, snapshot
):
    meter_data = il_electricity_cdd_hdd_billing_monthly["meter_data"]
    temperature_data = il_electricity_cdd_hdd_billing_monthly["temperature_data"]
    df = compute_temperature_features(
        meter_data.index,
        temperature_data,
        heating_balance_points=[60, 61],
        cooling_balance_points=[65, 66],
        temperature_mean=False,
        degree_day_method="daily",
        use_mean_daily_values=False,
    )
    assert df.shape == (27, 6)
    assert list(sorted(df.columns)) == [
        "cdd_65",
        "cdd_66",
        "hdd_60",
        "hdd_61",
        "n_days_dropped",
        "n_days_kept",

Parameters
    ----------
    meter_data : :any:`pandas.DataFrame`
        Hourly meter data in eemeter format.
    temperature_data : :any:`pandas.Series`
        Hourly temperature data in eemeter format.

    Returns
    -------
    design_matrix : :any:`pandas.DataFrame`
        A design matrix with meter_value, hour_of_week, hdd_50, and cdd_65 features.
    """
    time_features = compute_time_features(
        meter_data.index, hour_of_week=True, hour_of_day=False, day_of_week=False
    )
    temperature_features = compute_temperature_features(
        meter_data.index,
        temperature_data,
        heating_balance_points=[50],
        cooling_balance_points=[65],
        degree_day_method="hourly",
    )
    design_matrix = merge_features(
        [meter_data.value.to_frame("meter_value"), temperature_features, time_features]
    )
    return design_matrix

Parameters
    ----------
    meter_data : :any:`pandas.DataFrame`
        Hourly meter data in eemeter format.
    temperature_data : :any:`pandas.Series`
        Hourly temperature data in eemeter format.

    Returns
    -------
    design_matrix : :any:`pandas.DataFrame`
        A design matrics with mean usage_per_day, hdd_30-hdd_90, and cdd_30-cdd_90
        features.
    """
    usage_per_day = compute_usage_per_day_feature(meter_data, series_name="meter_value")
    temperature_features = compute_temperature_features(
        meter_data.index,
        temperature_data,
        heating_balance_points=range(30, 91),
        cooling_balance_points=range(30, 91),
        data_quality=True,
        tolerance=pd.Timedelta(
            "35D"
        ),  # limit temperature data matching to periods of up to 35 days.
    )
    design_matrix = merge_features([usage_per_day, temperature_features])
    return design_matrix