2;ji>ddlmZddlmZmZddlmZddlmZddlZ ddl m Z ddl mZmZmZddlmZmZddlmZGd d eeZdS) )array)IterableMapping)Number) itemgetterN) BaseEstimatorTransformerMixin _fit_context) check_arraymetadata_routing)check_is_fittedceZdZUdZdejiZdegdgdgdZe e d<e j ddddd Z dd d d d d ZedddZdZedddZe fdZdZddZddZfdZxZS)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=Tc>||_||_||_||_dSNr)selfrrrrs e/root/voice-cloning/.venv/lib/python3.11/site-packages/sklearn/feature_extraction/_dict_vectorizer.py__init__zDictVectorizer.__init__hs" "  FNfitting transformingindicesvaluesc|D]} t| tr||j| } d} n tdt | d|r+| |vr't ||| <|| |rG| |vrC||| ||| dS)z)Add feature names for iterable of stringszUnsupported type z; in iterable value. Only iterables of string are supported.N) isinstancestrr TypeErrortypelenappendr) rfv feature_namesvocabr!r"r#r$vv feature_names r_add_iterable_elementz$DictVectorizer._add_iterable_elementns . .B"c"" +,1dnnbbA !R!!!  3 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. NzUnsupported value type  for : z$. Mapping objects are not supported.ci|]\}}|| Sr9).0ir-s r z&DictVectorizer.fit..s???daQ???r)itemsr'r(rrrr)r*rr3r+r,r enumeratefeature_names_ vocabulary_) rXyr/r0xr-r.r2s rfitzDictVectorizer.fits*  ; ;A  ; ;1a%% K/0q$..!!#DLL6** Kqy#$LL7++K#=$q''== ==$%===  8,,K#'L..q!]EJJJ+#500.1-.@.@l+%,,\:::% ;( 9 @    ??i &>&>???E+  rcFtdjdks Jd|j}|rg}i}n|j}|j}d}t |t r|gn|}td}dg}g} |D]v} | D];\} } t | tr| |j | } d} nt | ts| | } nt | t s5t | tr d} | | | |||||| n6tdt| d | d | d t| d | t|r+| |vr't||| <|| | |vrC||| | || =|t|xt|dkrt#d t%j|t$j}t|dz t|f}t+j| ||f||}|ry|jrr|t%jt|t$j}t5|D]\}} || ||<||| <|dd|f}|jr|n|}|r||_||_|S)Nr;zsizeof(int) != 4 on your platform; please report this at https://github.com/scikit-learn/scikit-learn/issues and include the output from platform.platform() in your bug reportTrr&r zUnsupported value Type r6r7z. z objects are not supported.zSample sequence X is empty.r)shaper)ritemsizerr?r@r'rr=r(rrrr3r)r*r+r, ValueErrornp frombufferintcsp csr_matrixremptyint32r>r sort_indicestoarray)rrAr!rr/r0r"r#indptrr$rCr-r.r2rH result_matrix map_indexnew_vals r _transformzDictVectorizer._transforms Szz"a''' N(''    %MEE /M$E a)) 0QCCq**# (# (A 5 51a%%/0q$..!!#DLAA6**qy#$LL#Aw//Jq(4K4K#'L..% '%1 '%/    $@$q''@@ @@$%@@77@@@  +; indices mappings and transform X. Like fit(X) followed by transform(X), but does not require materializing X in memory. Parameters ---------- X : Mapping or iterable over Mappings Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). .. versionchanged:: 0.24 Accepts multiple string values for one categorical feature. y : (ignored) Ignored parameter. Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. Tr!)rX)rrArBs r fit_transformzDictVectorizer.fit_transform&s0q$///rct|dt|ddg}|jd}|j}fdt |D}t j|r;t|D]\}}|||f||||<nMt|D]=\}}t||ddfD]\}} | dkr|||f|||<>|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_sparserc$g|] } Sr9r9)r:_rs r z4DictVectorizer.inverse_transform..^s777777rN) r r rHr?rangerNissparsezipnonzeror>) rrAr n_samplesnamesdictsr;jdr.s ` rinverse_transformz DictVectorizer.inverse_transform@s#. ./// % 8 8 8GAJ #7777eI&6&6777 ;q>> .QYY[[) - -1%&q!tWaq"" -"%(( . .1%a111g....DAqAvv&'1g%( . rcTt|ddg||dS)aTransform feature->value dicts to array or sparse matrix. Named features not encountered during fit or fit_transform will be silently ignored. Parameters ---------- X : Mapping or iterable over Mappings of shape (n_samples,) Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. r?r@FrZ)r rX)rrAs r transformzDictVectorizer.transformks0" /?@@@q%000rct|dtd|jDrd|jD}n|j}tj|t S)a^Get output feature names for transformation. Parameters ---------- input_features : array-like of str or None, default=None Not used, present here for API consistency by convention. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. r?c3BK|]}t|t VdSr)r'r(r:names r z7DictVectorizer.get_feature_names_out..s/IIT:dC(((IIIIIIrc,g|]}t|Sr9)r(rqs rrbz8DictVectorizer.get_feature_names_out..sGGG4SYYGGGrrG)r anyr?rKasarrayobject)rinput_featuresr/s rget_feature_names_outz$DictVectorizer.get_feature_names_outsl ./// IIT5HIII I I 0GG43FGGGMM /Mz-v6666rc6t|d|stj|d}|j}i}|D]}t ||||<||_dt |tdD|_|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?rcg|]\}}|Sr9r9)r:r-r;s rrbz+DictVectorizer.restrict..s)   !QA   rr&)key) r rKwherer?r+r@sortedr=r)rsupportr#rh new_vocabr;s rrestrictzDictVectorizer.restrictsB ./// +hw''*G#  1 1A"%i..IeAh  $   !2!2 1 FFF    rcxt}d|j_d|j_|S)NTF)super__sklearn_tags__ input_tagsdict two_d_array)rtags __class__s rrzDictVectorizer.__sklearn_tags__s1ww''))#&+# rr)F)__name__ __module__ __qualname____doc__r UNUSED4_DictVectorizer__metadata_request__inverse_transformr(rr__annotations__rKfloat64rr3r rDrXr[rlrnryrr __classcell__)rs@rrrsJJZ.9:J:Q,R)!U+ $$D!# c$T.....>\555333653jaaaF\5550006502.2))))V111(7777(0000drr)rcollections.abcrrnumbersroperatorrnumpyrK scipy.sparserrN sklearn.baserr r sklearn.utilsr r sklearn.utils.validationr rr9rrrs--------FFFFFFFFFF77777777444444xxxxx%}xxxxxr