o \i>@sddlmZddlmZmZddlmZddlmZddlZ ddl m Z ddl mZddlmZmZmZdd lmZdd lmZGd d d eeZdS) )array)IterableMapping)Number) itemgetterN)metadata_routing) BaseEstimatorTransformerMixin _fit_context) check_array)check_is_fittedcseZdZUdZdejiZdegdgdgdZe e d<e j ddddd d Z dd d d d ddZeddd!ddZddZeddd!ddZe fddZddZd!ddZd"ddZfdd ZZS)#DictVectorizera Transforms lists of feature-value mappings to vectors. This transformer turns lists of mappings (dict-like objects) of feature names to feature values into Numpy arrays or scipy.sparse matrices for use with scikit-learn estimators. When feature values are strings, this transformer will do a binary one-hot (aka one-of-K) coding: one boolean-valued feature is constructed for each of the possible string values that the feature can take on. For instance, a feature "f" that can take on the values "ham" and "spam" will become two features in the output, one signifying "f=ham", the other "f=spam". If a feature value is a sequence or set of strings, this transformer will iterate over the values and will count the occurrences of each string value. However, note that this transformer will only do a binary one-hot encoding when feature values are of type string. If categorical features are represented as numeric values such as int or iterables of strings, the DictVectorizer can be followed by :class:`~sklearn.preprocessing.OneHotEncoder` to complete binary one-hot encoding. Features that do not occur in a sample (mapping) will have a zero value in the resulting array/matrix. For an efficiency comparison of the different feature extractors, see :ref:`sphx_glr_auto_examples_text_plot_hashing_vs_dict_vectorizer.py`. Read more in the :ref:`User Guide `. Parameters ---------- dtype : dtype, default=np.float64 The type of feature values. Passed to Numpy array/scipy.sparse matrix constructors as the dtype argument. separator : str, default="=" Separator string used when constructing new features for one-hot coding. sparse : bool, default=True Whether transform should produce scipy.sparse matrices. sort : bool, default=True Whether ``feature_names_`` and ``vocabulary_`` should be sorted when fitting. Attributes ---------- vocabulary_ : dict A dictionary mapping feature names to feature indices. feature_names_ : list A list of length n_features containing the feature names (e.g., "f=ham" and "f=spam"). See Also -------- FeatureHasher : Performs vectorization using only a hash function. sklearn.preprocessing.OrdinalEncoder : Handles nominal/categorical features encoded as columns of arbitrary data types. Examples -------- >>> from sklearn.feature_extraction import DictVectorizer >>> v = DictVectorizer(sparse=False) >>> D = [{'foo': 1, 'bar': 2}, {'foo': 3, 'baz': 1}] >>> X = v.fit_transform(D) >>> X array([[2., 0., 1.], [0., 1., 3.]]) >>> v.inverse_transform(X) == [{'bar': 2.0, 'foo': 1.0}, ... {'baz': 1.0, 'foo': 3.0}] True >>> v.transform({'foo': 4, 'unseen_feature': 3}) array([[0., 0., 4.]]) dict_type no_validationbooleandtype separatorsparsesort_parameter_constraints=TcCs||_||_||_||_dSNr)selfrrrrr/var/www/www-root/data/www/176.119.141.140/sports-predictor/venv/lib/python3.10/site-packages/sklearn/feature_extraction/_dict_vectorizer.py__init__js zDictVectorizer.__init__FNfitting transformingindicesvaluesc Cs|D]B} t| trd||j| f} d} n tdt| d|r/| |vr/t||| <|| |rD| |vrD||| ||| qdS)z)Add feature names for iterable of strings%s%s%szUnsupported type z; in iterable value. Only iterables of string are supported.N) isinstancestrr TypeErrortypelenappendr) rfv feature_namesvocabrr r!r"vv feature_namerrr_add_iterable_elementps     z$DictVectorizer._add_iterable_element)prefer_skip_nested_validationc Csg}i}|D]\}|D]U\}}t|trd||j|f}n0t|ts'|dur*|}n$t|tr?tdt|d|d|dt|trNd}| |||||dura||vrat |||<| |q q|j rs| ddt |D}||_||_|S) a)Learn a list of feature name -> indices mappings. Parameters ---------- X : Mapping or iterable over Mappings Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). .. versionchanged:: 0.24 Accepts multiple string values for one categorical feature. y : (ignored) Ignored parameter. Returns ------- self : object DictVectorizer class instance. r#NzUnsupported value type  for : z$. Mapping objects are not supported.cSsi|]\}}||qSrr).0ir+rrr sz&DictVectorizer.fit..)itemsr%r&rrrr'r(rr1r)r*r enumeratefeature_names_ vocabulary_) rXyr-r.xr+r,r0rrrfits>      zDictVectorizer.fitc CsNtdjdks Jd|j}|rg}i}n|j}|j}d}t|tr%|gn|}td}dg}g} |D]} | D]w\} } t| trLd| |j | f} d} n;t| t sU| durX| } n/t| tsrt| t rrd} |j | | |||||| dnt d t| d | d | d t| d | dur|r| |vrt||| <|| | |vr||| | || q8|t|q2t|dkrtdtj|tjd}t|dt|f}tj| ||f||d}|r|jr|tjt|tjd}t|D]\}} || ||<||| <q|dd|f}|jr|n|}|r%||_||_|S)Nr6zsizeof(int) != 4 on your platform; please report this at https://github.com/scikit-learn/scikit-learn/issues and include the output from platform.platform() in your bug reportTrr#r$rzUnsupported value Type r3r4z. z objects are not supported.zSample sequence X is empty.r)shaper)ritemsizerr:r;r%rr8r&rrrr1r'r(r)r* ValueErrornp frombufferintcsp csr_matrixremptyint32r9r sort_indicestoarray)rr<rrr-r.r r!indptrr"r>r+r,r0rB result_matrix map_indexnew_valrrr _transforms          zDictVectorizer._transformcCs|j|ddS)aLearn a list of feature name -> indices mappings and transform X. Like fit(X) followed by transform(X), but does not require materializing X in memory. Parameters ---------- X : Mapping or iterable over Mappings Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). .. versionchanged:: 0.24 Accepts multiple string values for one categorical feature. y : (ignored) Ignored parameter. Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. Tr)rR)rr<r=rrr fit_transform(szDictVectorizer.fit_transformc st|dt|ddgd}|jd}|j}fddt|D}t|r>t|D]\}}|||f||||<q+|St |D]!\}}t ||ddfD]\}} | dkrb|||f|||<qPqB|S) aWTransform array or sparse matrix X back to feature mappings. X must have been produced by this DictVectorizer's transform or fit_transform method; it may only have passed through transformers that preserve the number of features and their order. In the case of one-hot/one-of-K coding, the constructed feature names and values are returned rather than the original ones. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Sample matrix. dict_type : type, default=dict Constructor for feature mappings. Must conform to the collections.Mapping API. Returns ------- X_original : list of dict_type objects of shape (n_samples,) Feature mappings for the samples in X. r:csrcsc) accept_sparsercsg|]}qSrr)r5_rrr `sz4DictVectorizer.inverse_transform..N) r r rBr:rangerHissparsezipnonzeror9) rr<r n_samplesnamesdictsr6jdr,rrYrinverse_transformBs   z DictVectorizer.inverse_transformcCst|ddg|j|ddS)aTransform feature->value dicts to array or sparse matrix. Named features not encountered during fit or fit_transform will be silently ignored. Parameters ---------- X : Mapping or iterable over Mappings of shape (n_samples,) Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. r:r;FrS)r rR)rr<rrr transformmszDictVectorizer.transformcCsDt|dtdd|jDrdd|jD}n|j}tj|tdS)a^Get output feature names for transformation. Parameters ---------- input_features : array-like of str or None, default=None Not used, present here for API consistency by convention. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. r:css|] }t|t VqdSr)r%r&r5namerrr sz7DictVectorizer.get_feature_names_out..cSsg|]}t|qSr)r&rfrrrrZsz8DictVectorizer.get_feature_names_out..rA)r anyr:rEasarrayobject)rinput_featuresr-rrrget_feature_names_outs z$DictVectorizer.get_feature_names_outcCsjt|d|st|d}|j}i}|D] }t||||<q||_ddt|tddD|_|S)a=Restrict the features to those in support using feature selection. This function modifies the estimator in-place. Parameters ---------- support : array-like Boolean mask or list of indices (as returned by the get_support member of feature selectors). indices : bool, default=False Whether support is a list of indices. Returns ------- self : object DictVectorizer class instance. Examples -------- >>> from sklearn.feature_extraction import DictVectorizer >>> from sklearn.feature_selection import SelectKBest, chi2 >>> v = DictVectorizer() >>> D = [{'foo': 1, 'bar': 2}, {'foo': 3, 'baz': 1}] >>> X = v.fit_transform(D) >>> support = SelectKBest(chi2, k=2).fit(X, [0, 1]) >>> v.get_feature_names_out() array(['bar', 'baz', 'foo'], ...) >>> v.restrict(support.get_support()) DictVectorizer() >>> v.get_feature_names_out() array(['bar', 'foo'], ...) r:rcSsg|]\}}|qSrr)r5r+r6rrrrZsz+DictVectorizer.restrict..r$)key) r rEwherer:r)r;sortedr8r)rsupportr!r` new_vocabr6rrrrestricts !zDictVectorizer.restrictcst}d|j_d|j_|S)NTF)super__sklearn_tags__ input_tagsdict two_d_array)rtags __class__rrrus zDictVectorizer.__sklearn_tags__r)F)__name__ __module__ __qualname____doc__rUNUSED4_DictVectorizer__metadata_request__inverse_transformr&rrw__annotations__rEfloat64rr1r r?rRrTrdrermrsru __classcell__rrrzrrs0  M   5c  +  2r)rcollections.abcrrnumbersroperatorrnumpyrE scipy.sparserrH sklearn.utilsrbaser r r utilsr utils.validationr rrrrrs