sgxddlmZddlZddlmZmZddlmZddl m Z m Z ddl m Z mZdd lmZGd d eeZy) )RealN) BaseEstimator _fit_context)Interval)mean_variance_axis min_max_axis)check_is_fitted validate_data) SelectorMixinczeZdZUdZdeedddgiZeed<ddZ e d dd Z d Z fd Z xZS)VarianceThresholdatFeature selector that removes all low-variance features. This feature selection algorithm looks only at the features (X), not the desired outputs (y), and can thus be used for unsupervised learning. Read more in the :ref:`User Guide `. Parameters ---------- threshold : float, default=0 Features with a training-set variance lower than this threshold will be removed. The default is to keep all features with non-zero variance, i.e. remove the features that have the same value in all samples. Attributes ---------- variances_ : array, shape (n_features,) Variances of individual features. n_features_in_ : int Number of features seen during :term:`fit`. .. versionadded:: 0.24 feature_names_in_ : ndarray of shape (`n_features_in_`,) Names of features seen during :term:`fit`. Defined only when `X` has feature names that are all strings. .. versionadded:: 1.0 See Also -------- SelectFromModel: Meta-transformer for selecting features based on importance weights. SelectPercentile : Select features according to a percentile of the highest scores. SequentialFeatureSelector : Transformer that performs Sequential Feature Selection. Notes ----- Allows NaN in the input. Raises ValueError if no feature in X meets the variance threshold. Examples -------- The following dataset has integer features, two of which are the same in every sample. These are removed with the default setting for threshold:: >>> from sklearn.feature_selection import VarianceThreshold >>> X = [[0, 2, 0, 3], [0, 1, 4, 3], [0, 1, 1, 3]] >>> selector = VarianceThreshold() >>> selector.fit_transform(X) array([[2, 0], [1, 4], [1, 1]]) thresholdrNleft)closed_parameter_constraintsc||_yN)r)selfrs `/var/www/html/venv/lib/python3.12/site-packages/sklearn/feature_selection/_variance_threshold.py__init__zVarianceThreshold.__init__Ns "T)prefer_skip_nested_validationct||dtjd}t|dr:t |d\}|_|j dk(rXt|d\}}||z }nBtj|d|_|j dk(rtj|d}|j dk(r=tj|j g}tj|d|_tjtj|j |j |j kzr=d}|jddk(r|d z }t|j!|j |S) aLearn empirical variances from X. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) Data from which to compute variances, where `n_samples` is the number of samples and `n_features` is the number of features. y : any, default=None Ignored. This parameter exists only for compatibility with sklearn.pipeline.Pipeline. Returns ------- self : object Returns the instance itself. )csrcscz allow-nan) accept_sparsedtypeensure_all_finitetoarrayr)axisz4No feature in X meets the variance threshold {0:.5f}r z (X contains only one sample))r npfloat64hasattrr variances_rr nanvarptparraynanminallisfiniteshape ValueErrorformat) rXy_minsmaxes peak_to_peaks compare_arrmsgs rfitzVarianceThreshold.fitQs4&   (**)   1i !3AA!> At~~"*115 e %  ii2DO~~" "qq 1 >>Q ((DOO]#CDK ii !rQs,..@= } }}r