DegreeDayFeatures

class DegreeDayFeatures(base_temp: float = 65.0, tmax_col: str | None = None, tmin_col: str | None = None, tmean_col: str | None = None, return_tmean: bool = True, strict: bool = False, keep_original_columns: bool = False)[source]

Compute degree-day features (HDD/CDD) from daily temperatures.

Computes Heating Degree Days (HDD) and Cooling Degree Days (CDD) from daily temperature inputs.

Degree days convert temperature into a simple proxy for heating/cooling demand by measuring how far a day’s mean temperature is from a base (balance-point) temperature.

transform returns a DataFrame with column names hdd and cdd, indexed the same as the input. If return_tmean=True, also includes a tmean column.

Definitions (daily):

tmean = (tmax + tmin) / 2
hdd = max(0, base_temp - tmean)
cdd = max(0, tmean - base_temp)

Supports two input modes:

If no column names are provided via tmax_col, tmin_col, or tmean_col: 1 column is treated as mean temperature (tmean); 2+ columns use the first two columns as (tmax, tmin).
If column names are provided, the transformer uses those columns.

Parameters:

base_tempfloat, default=65.0: Base (balance-point) temperature in the same units as the input.
tmax_col, tmin_colstr or None, default=None: Column names for daily max/min temperature. If both provided, uses them.
tmean_colstr or None, default=None: Column name for mean temperature. If provided and present, uses it.
return_tmeanbool, default=True: If True, include tmean in the output.
strictbool, default=False: If True, raises when tmin > tmax; if False, auto-swaps those rows.
keep_original_columnsbool, default=False: If True, appends features to X. If False, returns only features.

Attributes:

is_fitted: Whether fit has been called.

Examples

Basic usage with explicit max/min temperature columns:

import pandas as pd from sktime.transformations.degree_day import DegreeDayFeatures X = pd.DataFrame( … {“high”: [60, 70, 90], “low”: [40, 60, 70]}, … index=pd.to_datetime([“2025-01-01”, “2025-01-02”, “2025-01-03”]), … ) tx = DegreeDayFeatures(base_temp=65.0, tmax_col=”high”, tmin_col=”low”) tx.fit_transform(X)[[“hdd”, “cdd”]].round(1)

hdd cdd

2025-01-01 15.0 0.0 2025-01-02 0.0 0.0 2025-01-03 0.0 15.0

Auto mode: if X has a single column, it is treated as mean temperature (tmean):

X_mean = pd.DataFrame( … {“temp”: [50.0, 65.0, 80.0]}, … index=pd.to_datetime([“2025-01-01”, “2025-01-02”, “2025-01-03”]), … ) DegreeDayFeatures(base_temp=65.0, return_tmean=False).fit_transform(X_mean)

hdd cdd

2025-01-01 15.0 0.0 2025-01-02 0.0 0.0 2025-01-03 0.0 15.0

Append features to the original data using keep_original_columns=True:

DegreeDayFeatures( … base_temp=65.0, tmax_col=”high”, tmin_col=”low”, keep_original_columns=True … ).fit_transform(X).columns.tolist() [‘high’, ‘low’, ‘tmean’, ‘hdd’, ‘cdd’]

Methods

`check_is_fitted`([method_name])	Check if the estimator has been fitted.
`clone`()	Obtain a clone of the object with same hyper-parameters and config.
`clone_tags`(estimator[, tag_names])	Clone tags from another object as dynamic override.
`create_test_instance`([parameter_set])	Construct an instance of the class, using first test parameter set.
`create_test_instances_and_names`([parameter_set])	Create list of all test instances and a list of names for them.
`fit`(X[, y])	Fit transformer to X, optionally to y.
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_class_tag`(tag_name[, tag_value_default])	Get class tag value from class, with tag level inheritance from parents.
`get_class_tags`()	Get class tags from class, with tag level inheritance from parent classes.
`get_config`()	Get config flags for self.
`get_fitted_params`([deep])	Get fitted parameters.
`get_param_defaults`()	Get object's parameter defaults.
`get_param_names`([sort])	Get object's parameter names.
`get_params`([deep])	Get a dict of parameters values for this object.
`get_tag`(tag_name[, tag_value_default, ...])	Get tag value from instance, with tag level inheritance and overrides.
`get_tags`()	Get tags from instance, with tag level inheritance and overrides.
`get_test_params`([parameter_set])	Return parameter settings for sktime's estimator checks.
`inverse_transform`(X[, y])	Inverse transform X and return an inverse transformed version.
`is_composite`()	Check if the object is composed of other BaseObjects.
`load_from_path`(serial)	Load object from file location.
`load_from_serial`(serial)	Load object from serialized memory container.
`reset`()	Reset the object to a clean post-init state.
`save`([path, serialization_format])	Save serialized self to bytes-like object or to (.zip) file.
`set_config`(**config_dict)	Set config flags to given values.
`set_params`(**params)	Set the parameters of this object.
`set_random_state`([random_state, deep, ...])	Set random_state pseudo-random seed parameters for self.
`set_tags`(**tag_dict)	Set instance level tag overrides to given values.
`transform`(X[, y])	Transform X and return a transformed version.
`update`(X[, y, update_params])	Update transformer with X, optionally y.