U mdN@sjddlmZddlZddlmZddlmZddlm Z m Z ddl m Z dd l mZGd d d eeZdS) )RealN) BaseEstimator) SelectorMixin)mean_variance_axis min_max_axis)check_is_fitted)Intervalc@sTeZdZUdZdeeddddgiZeed<dd d Z dd d Z d dZ ddZ dS)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_constraintscCs ||_dSN)r )selfr rf/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/feature_selection/_variance_threshold.py__init__LszVarianceThreshold.__init__c Cs||j|dtjdd}t|dr\t|dd\}|_|jdkrt|dd\}}||}n(tj |dd|_|jdkrtj |dd}|jdkrt |j|g}tj |dd|_t t|j|j|jkBrd}|jddkr|d 7}t||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. )ZcsrZcscz allow-nan)Z accept_sparseZdtypeZforce_all_finiteZtoarrayr)Zaxisz4No feature in X meets the variance threshold {0:.5f}rz (X contains only one sample))Z_validate_paramsZ_validate_datanpZfloat64hasattrr variances_r rZnanvarZptparrayZnanminallisfiniteshape ValueErrorformat) rXy_ZminsZmaxesZ peak_to_peaksZ compare_arrmsgrrrfitOs0      zVarianceThreshold.fitcCst||j|jkSr)r rr rrrr_get_support_masksz#VarianceThreshold._get_support_maskcCsddiS)N allow_nanTrr$rrr _more_tagsszVarianceThreshold._more_tags)r)N) __name__ __module__ __qualname____doc__r rrdict__annotations__rr#r%r'rrrrr s ;   2r )numbersrnumpyrbaser_baserZutils.sparsefuncsrrZutils.validationr Zutils._param_validationr r rrrrs