sg>ddlmZddlmZmZddlmZddlmZddlZ ddl m Z ddl mZddlmZmZmZdd lmZdd lmZGd d eeZy) )array)IterableMapping)Number) itemgetterN)metadata_routing) BaseEstimatorTransformerMixin _fit_context) check_array)check_is_fittedceZdZUdZdej iZdegdgdgdZe e d<e jddddd 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<||_||_||_||_yNr)selfrrrrs ^/var/www/html/venv/lib/python3.12/site-packages/sklearn/feature_extraction/_dict_vectorizer.py__init__zDictVectorizer.__init__js "  FNfitting transformingindicesvaluescN|D]} t| tr||j| } d} ntdt | d|r#| |vrt ||| <|j | |sh| |vsm|j || |j |j| y)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_elementps .B"c"+,dnnbA 'Rz2!!  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$. Mapping objects are not supported.)itemsr(r)rrrr*r+rr4r,r-r enumeratefeature_names_ vocabulary_) rXyr0r1xr.r/r3is rfitzDictVectorizer.fits?*  ;A  ;1a%/0$..!#DL6*qy#$L7+#1$q'; cA3'==  8,#'L..q!]EJ+#50.1-.@l+%,,\:% ; ;* 99    &/ &>?daQT?E?+  @s D!ctdjdk(sJd|j}|rg}i}n|j}|j}d}t |t r|gn|}td}dg}g} |D]8} | jD]\} } t | tr| |j| } d} n{t | ts| | } nft | t s,t | trd} |j| | |||||| n*tdt| d | d | d t| d | |r#| |vrt||| <|j!| | |vs|j!|| | j!|j|  |j!t|;t|dk(r t#d t%j&|t$j(}t|dz t|f}t+j,| ||f||}|rs|j.rg|j/t%j0t|t$j2}t5|D]\}} || ||<||| <|dd|f}|j6r|j9n|j;}|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 r7r8z. z objects are not supported.zSample sequence X is empty.r)shaper)ritemsizerr;r<r(rr9r)rrrr4r*r+r,r- ValueErrornp frombufferintcsp csr_matrixremptyint32r:r sort_indicestoarray)rr=r"rr0r1r#r$indptrr%r?r.r/r3rE result_matrix map_indexnew_vals r _transformzDictVectorizer._transforms Sz""a'  N '   ME //M$$E a)QCq*# (A 51a%/0$..!#DLA6*qy#$L#Aw/Jq(4K#'L..% '%1 '%/ $1$q'; cA3c7)#>@  + 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")rU)rr=r>s r fit_transformzDictVectorizer.fit_transform(s0q$//r ct|dt|ddg}|jd}|j}t |Dcgc] }| }}t j |r0t|jD]\}}|||f||||<|St|D]2\}} t||ddfD]\}} | dk7s |||f| ||<4|Scc}w)aNTransform array or sparse matrix X back to feature mappings. X must have been produced by this DictVectorizer's transform or fit_transform method; it may only have passed through transformers that preserve the number of features and their order. In the case of one-hot/one-of-K coding, the constructed feature names and values are returned rather than the original ones. Parameters ---------- X : {array-like, sparse matrix} of shape (n_samples, n_features) Sample matrix. dict_type : type, default=dict Constructor for feature mappings. Must conform to the collections.Mapping API. Returns ------- D : list of dict_type objects of shape (n_samples,) Feature mappings for the samples in X. r;csrcsc) accept_sparserN) rr rEr;rangerKissparsezipnonzeror:) rr=r n_samplesnames_dictsr@jdr/s rinverse_transformz DictVectorizer.inverse_transformBs. ./ % 8GGAJ ##&+I&6777 ;;q>QYY[) -1%&q!tWaq" - "%( .1%a1g..DAqAv&'1g%( . .  8sCcDt|ddg|j|dS)aTransform feature->value dicts to array or sparse matrix. Named features not encountered during fit or fit_transform will be silently ignored. Parameters ---------- X : Mapping or iterable over Mappings of shape (n_samples,) Dict(s) or Mapping(s) from feature names (arbitrary Python objects) to feature values (strings or convertible to dtype). Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. r;r<FrW)rrU)rr=s r transformzDictVectorizer.transformms'" /?@q%00r ct|dtd|jDr#|jDcgc] }t|}}n |j}t j |t Scc}w)a^Get output feature names for transformation. Parameters ---------- input_features : array-like of str or None, default=None Not used, present here for API consistency by convention. Returns ------- feature_names_out : ndarray of str objects Transformed feature names. r;c3>K|]}t|t ywr)r(r)).0names r z7DictVectorizer.get_feature_names_out..sIT:dC((IsrD)ranyr;r)rHasarrayobject)rinput_featuresrmr0s rget_feature_names_outz$DictVectorizer.get_feature_names_outsb ./ IT5H5HI I373F3FG4SYGMG //Mzz-v66HsA3c0t|d|stj|d}|j}i}|D]}t ||||<||_t |jtdDcgc]\}}| c}}|_|Scc}}w)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;rr')key) rrHwherer;r,r<sortedr9r)rsupportr$rb new_vocabr@r.s rrestrictzDictVectorizer.restrictsB ./hhw'*G##  1A"%i.IeAh  1% !2 1 F !QA   s; Bcht|}d|j_d|j_|S)NTF)super__sklearn_tags__ input_tagsdict two_d_array)rtags __class__s rr}zDictVectorizer.__sklearn_tags__s-w')#&+# r r)F)__name__ __module__ __qualname____doc__rUNUSED4_DictVectorizer__metadata_request__inverse_transformr)rr__annotations__rHfloat64rr4r rArUrXrgrirsrzr} __classcell__)rs@rrrsJZ.9:J:Q:Q,R)!U+ $D!# c$T.>5363jaF50602.2)V1(7(0dr r)rcollections.abcrrnumbersroperatorrnumpyrH scipy.sparserrK sklearn.utilsrbaser r r utilsr utils.validationrrr rrs9-*@@.x%}xr