LASSO Regression (using Least-angle Regression algorithm) with built-in CV — ESMValTool 2.12.0.dev0+g93d6ff8.d20240704 documentation (2024)

Lasso Regression model with built-in CV using LARS algorithm.

Use mlr_model_type: lasso_lars_cv to use this MLR model in the recipe.

Classes:

class esmvaltool.diag_scripts.mlr.models.lasso_lars_cv.LassoLarsCVModel(input_datasets, **kwargs)[source]#

Bases: LinearModel

Lasso Regression model with built-in CV using LARS algorithm.

Attributes:

categorical_features	Categorical features.
data	Input data of the MLR model.
features	Features of the input data.
features_after_preprocessing	Features of the input data after preprocessing.
features_types	Types of the features.
features_units	Units of the features.
fit_kwargs	Keyword arguments for fit().
group_attributes	Group attributes of the input data.
label	Label of the input data.
label_units	Units of the label.
mlr_model_type	MLR model type.
numerical_features	Numerical features.
parameters	Parameters of the complete MLR model pipeline.
random_state	Random state instance.

Methods:

create(mlr_model_type,*args,**kwargs)	Create desired MLR model subclass (factory method).
efecv(**kwargs)	Perform exhaustive feature elimination using cross-validation.
export_prediction_data([filename])	Export all prediction data contained in self._data.
export_training_data([filename])	Export all training data contained in self._data.
fit()	Print final alpha after successful fitting.
get_ancestors([label,features,...])	Return ancestor files.
get_data_frame(data_type[,impute_nans])	Return data frame of specified type.
get_x_array(data_type[,impute_nans])	Return x data of specific type.
get_y_array(data_type[,impute_nans])	Return y data of specific type.
grid_search_cv(param_grid,**kwargs)	Perform exhaustive parameter search using cross-validation.
plot_1d_model([filename,n_points])	Plot lineplot that represents the MLR model.
plot_coefs([filename])	Plot linear coefficients of models.
plot_feature_importance([filename,color_coded])	Plot feature importance given by linear coefficients.
plot_partial_dependences([filename])	Plot partial dependences for every feature.
plot_prediction_errors([filename])	Plot predicted vs.
plot_residuals([filename])	Plot residuals of training and test (if available) data.
plot_residuals_distribution([filename])	Plot distribution of residuals of training and test data (KDE).
plot_residuals_histogram([filename])	Plot histogram of residuals of training and test data.
plot_scatterplots([filename])	Plot scatterplots label vs.
predict([save_mlr_model_error,...])	Perform prediction using the MLR model(s) and write *.nc files.
print_correlation_matrices()	Print correlation matrices for all datasets.
print_regression_metrics([logo])	Print all available regression metrics for training data.
register_mlr_model(mlr_model_type)	Add MLR model (subclass of this class) (decorator).
reset_pipeline()	Reset regressor pipeline.
rfecv(**kwargs)	Perform recursive feature elimination using cross-validation.
test_normality_of_residuals()	Perform Shapiro-Wilk test to normality of residuals.
update_parameters(**params)	Update parameters of the whole pipeline.

property categorical_features#

Categorical features.

Type:

numpy.ndarray

classmethod create(mlr_model_type, *args, **kwargs)#

Create desired MLR model subclass (factory method).

property data#

Input data of the MLR model.

Type:

dict

efecv(**kwargs)#

Perform exhaustive feature elimination using cross-validation.

Parameters:

**kwargs (keyword arguments, optional) – Additional options for esmvaltool.diag_scripts.mlr.custom_sklearn.cross_val_score_weighted().

export_prediction_data(filename=None)#

Export all prediction data contained in self._data.

Parameters:

filename (str, optional (default: '{data_type}_{pred_name}.csv')) – Name of the exported files.

export_training_data(filename=None)#

Export all training data contained in self._data.

Parameters:

filename (str, optional (default: '{data_type}.csv')) – Name of the exported files.

property features#

Features of the input data.

Type:

numpy.ndarray

property features_after_preprocessing#

Features of the input data after preprocessing.

Type:

numpy.ndarray

property features_types#

Types of the features.

Type:

pandas.Series

property features_units#

Units of the features.

Type:

pandas.Series

fit()[source]#

Print final alpha after successful fitting.

property fit_kwargs#

Keyword arguments for fit().

Type:

dict

get_ancestors(label=True, features=None, prediction_names=None, prediction_reference=False)#

Return ancestor files.

Parameters:

• label (bool, optional (default: True)) – Return label files.

• features (list of str, optional (default: None)) – Features for which files should be returned. If None, returnfiles for all features.

• prediction_names (list of str, optional (default: None)) – Prediction names for which files should be returned. If None,return files for all prediction names.

• prediction_reference (bool, optional (default: False)) – Return prediction_reference files if available for givenprediction_names.

Returns:

Ancestor files.

Return type:

list of str

Raises:

ValueError – Invalid feature or prediction_name given.

get_data_frame(data_type, impute_nans=False)#

Return data frame of specified type.

Parameters:

• data_type (str) – Data type to be returned. Must be one of 'all', 'train' or'test'.

• impute_nans (bool, optional (default: False)) – Impute nans if desired.

Returns:

Desired data.

Return type:

pandas.DataFrame

Raises:

TypeError – data_type is invalid or data does not exist (e.g. test data is not set).

get_x_array(data_type, impute_nans=False)#

Return x data of specific type.

Parameters:

• data_type (str) – Data type to be returned. Must be one of 'all', 'train' or'test'.

• impute_nans (bool, optional (default: False)) – Impute nans if desired.

Returns:

Desired data.

Return type:

numpy.ndarray

Raises:

TypeError – data_type is invalid or data does not exist (e.g. test data is not set).

get_y_array(data_type, impute_nans=False)#

Return y data of specific type.

Parameters:

• data_type (str) – Data type to be returned. Must be one of 'all', 'train' or'test'.

• impute_nans (bool, optional (default: False)) – Impute nans if desired.

Returns:

Desired data.

Return type:

numpy.ndarray

Raises:

TypeError – data_type is invalid or data does not exist (e.g. test data is not set).

grid_search_cv(param_grid, **kwargs)#

Perform exhaustive parameter search using cross-validation.

Parameters:

• param_grid (dict or list of dict) – Parameter names (keys) and ranges (values) for the search. Have tobe given for each step of the pipeline separated by twounderscores, i.e. s__p is the parameter p for step s.

• **kwargs (keyword arguments, optional) – Additional options forsklearn.model_selection.GridSearchCV.

Raises:

ValueError – Final regressor does not supply the attributes best_estimator_ or best_params_.

property group_attributes#

Group attributes of the input data.

Type:

numpy.ndarray

property label#

Label of the input data.

Type:

str

property label_units#

Units of the label.

Type:

str

property mlr_model_type#

MLR model type.

Type:

str

property numerical_features#

Numerical features.

Type:

numpy.ndarray

property parameters#

Parameters of the complete MLR model pipeline.

Type:

dict

plot_1d_model(filename=None, n_points=1000)#

Plot lineplot that represents the MLR model.

Note

This only works for a model with a single feature.

Parameters:

• filename (str, optional (default: '1d_mlr_model')) – Name of the plot file.

• n_points (int, optional (default: 1000)) – Number of sampled points for the single feature (using linearspacing between minimum and maximum value).

Raises:

• sklearn.exceptions.NotFittedError – MLR model is not fitted.

• ValueError – MLR model is built from more than 1 feature.

plot_coefs(filename=None)#

Plot linear coefficients of models.

Note

The features plotted here are not necessarily the real input features,but the ones after preprocessing.

Parameters:

filename (str, optional (default: 'coefs')) – Name of the plot file.

plot_feature_importance(filename=None, color_coded=True)#

Plot feature importance given by linear coefficients.

Note

The features plotted here are not necessarily the real input features,but the ones after preprocessing.

Parameters:

• filename (str, optional (default: 'feature_importance')) – Name of the plot file.

• color_coded (bool, optional (default: True)) – If True, mark positive (linear) correlations with red bars andnegative (linear) correlations with blue bars. If False, allbars are blue.

plot_partial_dependences(filename=None)#

Plot partial dependences for every feature.

Parameters:

filename (str, optional (default: 'partial_dependece_{feature}')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

plot_prediction_errors(filename=None)#

Plot predicted vs. true values.

Parameters:

filename (str, optional (default: 'prediction_errors')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

plot_residuals(filename=None)#

Plot residuals of training and test (if available) data.

Parameters:

filename (str, optional (default: 'residuals')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

plot_residuals_distribution(filename=None)#

Plot distribution of residuals of training and test data (KDE).

Parameters:

filename (str, optional (default: 'residuals_distribution')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

plot_residuals_histogram(filename=None)#

Plot histogram of residuals of training and test data.

Parameters:

filename (str, optional (default: 'residuals_histogram')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

plot_scatterplots(filename=None)#

Plot scatterplots label vs. feature for every feature.

Parameters:

filename (str, optional (default: 'scatterplot_{feature}')) – Name of the plot file.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

predict(save_mlr_model_error=None, save_lime_importance=False, save_propagated_errors=False, **kwargs)#

Perform prediction using the MLR model(s) and write *.nc files.

Parameters:

• save_mlr_model_error (str or int, optional) – Additionally saves estimated squared MLR model error. This errorrepresents the uncertainty of the prediction caused by the MLRmodel itself and not by errors in the prediction input data (errorsin that will be considered by including datasets with var_typeset to prediction_input_error and settingsave_propagated_errors to True). If the option is set to'test', the (constant) error is estimated as RMSEP using a(hold-out) test data set. Only possible if test data is available,i.e. the option test_size is not set to False during classinitialization. If the option is set to 'logo', the (constant)error is estimated as RMSEP using leave-one-group-outcross-validation using the group_attributes. Only possible ifgroup_datasets_by_attributes is given. If the option is set toan integer n (!= 0), the (constant) error is estimated as RMSEPusing n-fold cross-validation.

• save_lime_importance (bool, optional (default: False)) – Additionally saves local feature importance given by LIME (LocalInterpretable Model-agnostic Explanations).

• save_propagated_errors (bool, optional (default: False)) – Additionally saves propagated errors fromprediction_input_error datasets. Only possible when these areavailable.

• **kwargs (keyword arguments, optional) – Additional options for the final regressors predict() function.

Raises:

• RuntimeError – return_var and return_cov are both set to True.

• sklearn.exceptions.NotFittedError – MLR model is not fitted.

• ValueError – An invalid value for save_mlr_model_error is given.

• ValueError – save_propagated_errors is True and no prediction_input_error data is available.

print_correlation_matrices()#

Print correlation matrices for all datasets.

print_regression_metrics(logo=False)#

Print all available regression metrics for training data.

Parameters:

logo (bool, optional (default: False)) – Print regression metrics usingsklearn.model_selection.LeaveOneGroupOut cross-validation.Only possible when group_datasets_by_attributes was given duringclass initialization.

property random_state#

Random state instance.

Type:

numpy.random.RandomState

classmethod register_mlr_model(mlr_model_type)#

Add MLR model (subclass of this class) (decorator).

reset_pipeline()#

Reset regressor pipeline.

rfecv(**kwargs)#

Perform recursive feature elimination using cross-validation.

Note

This only works for final estimators that provide information aboutfeature importance either through a coef_ attribute or through afeature_importances_ attribute.

Parameters:

**kwargs (keyword arguments, optional) – Additional options for sklearn.feature_selection.RFECV.

Raises:

RuntimeError – Final estimator does not provide coef_ or feature_importances_ attribute.

test_normality_of_residuals()#

Perform Shapiro-Wilk test to normality of residuals.

Raises:

sklearn.exceptions.NotFittedError – MLR model is not fitted.

update_parameters(**params)#

Update parameters of the whole pipeline.

Note

Parameter names have to be given for each step of the pipelineseparated by two underscores, i.e. s__p is the parameter p forstep s.

Parameters:

**params (keyword arguments, optional) – Parameters for the pipeline which should be updated.

Raises:

ValueError – Invalid parameter for pipeline given.