module `mlmodel.interval_regressor`#

Short summary#

module mlinsights.mlmodel.interval_regressor

Implements a piecewise linear regression.

Classes#

class	truncated documentation
`IntervalRegressor`	Trains multiple regressors to provide a confidence interval on prediction. It only works for single regression. …

Properties#

property	truncated documentation
`_repr_html_`	HTML representation of estimator. This is redundant with the logic of _repr_mimebundle_. The latter should …
`n_estimators_`	Returns the number of estimators = the number of buckets the data was split in.

Methods#

method	truncated documentation
`__init__`
`fit`	Trains the binner and an estimator on every bucket.
`predict`	Computes the average predictions.
`predict_all`	Computes the predictions for all estimators.
`predict_sorted`	Computes the predictions for all estimators. Sorts them for all observations.

Documentation#

Implements a piecewise linear regression.

source on GitHub

class mlinsights.mlmodel.interval_regressor.IntervalRegressor(estimator=None, n_estimators=10, n_jobs=None, alpha=1.0, verbose=False)#

Bases: BaseEstimator, RegressorMixin

Trains multiple regressors to provide a confidence interval on prediction. It only works for single regression. Every training is made with a new sample of the training data, parameter alpha let the user choose the size of this sample. A smaller alpha increases the variance of the predictions. The current implementation draws sample by random but keeps the weight associated to each of them. Another way could be to draw a weighted sample but give them uniform weights.

source on GitHub

Parameters:

estimator – predictor trained on every bucket
n_estimators – number of estimators to train
n_jobs – number of parallel jobs (for training and predicting)
alpha – proportion of samples resampled for each training
verbose – boolean or use 'tqdm' to use tqdm to fit the estimators

source on GitHub

__init__(estimator=None, n_estimators=10, n_jobs=None, alpha=1.0, verbose=False)#

Parameters:

estimator – predictor trained on every bucket
n_estimators – number of estimators to train
n_jobs – number of parallel jobs (for training and predicting)
alpha – proportion of samples resampled for each training
verbose – boolean or use 'tqdm' to use tqdm to fit the estimators

source on GitHub

fit(X, y, sample_weight=None)#

Trains the binner and an estimator on every bucket.

Parameters:

X – features, X is converted into an array if X is a dataframe
y – target
sample_weight – sample weights

Returns:

self: returns an instance of self.

Fitted attributes:

binner_: binner
estimators_: dictionary of estimators, each of them
mapped to a leave to the tree
mean_estimator_: estimator trained on the whole
datasets in case the binner can find a bucket for a new observation
dim_: dimension of the output
mean_: average targets