sklearn: Detailed Description sklearn.feature_selection Raiders of SelectFromModel function, use it
About SelectFromModel function
Use SelectFromModel function
1, SelectFromModel native code
class SelectFromModel Found at: sklearn.feature_selection.from_model
class SelectFromModel(BaseEstimator, SelectorMixin, MetaEstimatorMixin):
"""Meta-transformer for selecting features based on importance weights.
.. versionadded:: 0.17
Parameters
----------
estimator : object
The base estimator from which the transformer is built.
This can be both a fitted (if ``prefit`` is set to True)
or a non-fitted estimator. The estimator must have either a
``feature_importances_`` or ``coef_`` attribute after fitting.
threshold : string, float, optional default None
The threshold value to use for feature selection. Features whose
importance is greater or equal are kept while the others are
discarded. If "median" (resp. "mean"), then the ``threshold`` value is
the median (resp. the mean) of the feature importances. A scaling
factor (e.g., "1.25*mean") may also be used. If None and if the
estimator has a parameter penalty set to l1, either explicitly
or implicitly (e.g, Lasso), the threshold used is 1e-5.
Otherwise, "mean" is used by default.
prefit : bool, default False
Whether a prefit model is expected to be passed into the constructor
directly or not. If True, ``transform`` must be called directly
and SelectFromModel cannot be used with ``cross_val_score``,
``GridSearchCV`` and similar utilities that clone the estimator.
Otherwise train the model using ``fit`` and then ``transform`` to do
feature selection.
norm_order : non-zero int, inf, -inf, default 1
Order of the norm used to filter the vectors of coefficients below
``threshold`` in the case where the ``coef_`` attribute of the
estimator is of dimension 2.
Attributes
----------
estimator_ : an estimator
The base estimator from which the transformer is built.
This is stored only when a non-fitted estimator is passed to the
``SelectFromModel``, i.e when prefit is False.
threshold_ : float
The threshold value used for feature selection.
"""
def __init__(self, estimator, threshold=None, prefit=False,
norm_order=1):
self.estimator = estimator
self.threshold = threshold
self.prefit = prefit
self.norm_order = norm_order
def _get_support_mask(self):
# SelectFromModel can directly call on transform.
if self.prefit:
estimator = self.estimator
elif hasattr(self, 'estimator_'):
estimator = self.estimator_
else:
raise ValueError(
'Either fit SelectFromModel before transform or set "prefit='
'True" and pass a fitted estimator to the constructor.')
scores = _get_feature_importances(estimator, self.norm_order)
threshold = _calculate_threshold(estimator, scores, self.threshold)
return scores >= threshold
def fit(self, X, y=None, **fit_params):
"""Fit the SelectFromModel meta-transformer.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The training input samples.
y : array-like, shape (n_samples,)
The target values (integers that correspond to classes in
classification, real numbers in regression).
**fit_params : Other estimator specific parameters
Returns
-------
self : object
Returns self.
"""
if self.prefit:
raise NotFittedError(
"Since 'prefit=True', call transform directly")
self.estimator_ = clone(self.estimator)
self.estimator_.fit(X, y, **fit_params)
return self
@property
def threshold_(self):
scores = _get_feature_importances(self.estimator_, self.norm_order)
return _calculate_threshold(self.estimator, scores, self.threshold)
@if_delegate_has_method('estimator')
def partial_fit(self, X, y=None, **fit_params):
"""Fit the SelectFromModel meta-transformer only once.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The training input samples.
y : array-like, shape (n_samples,)
The target values (integers that correspond to classes in
classification, real numbers in regression).
**fit_params : Other estimator specific parameters
Returns
-------
self : object
Returns self.
"""
if self.prefit:
raise NotFittedError(
"Since 'prefit=True', call transform directly")
if not hasattr(self, "estimator_"):
self.estimator_ = clone(self.estimator)
self.estimator_.partial_fit(X, y, **fit_params)
return self
