U |h<@sddlmZddlmZmZddlmZddlmZddlZ ddl m Z ddl mZmZmZddlmZdd lmZGd d d eeZdS) )array)IterableMapping)Number) itemgetterN) BaseEstimatorTransformerMixin _fit_context) check_array)check_is_fittedc@seZdZUdZdegdgdgdZeed<ej dddddd Z dd d d d d dZ e ddd ddZ ddZe ddd!ddZefddZddZd"ddZd#ddZddZd S)$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 comparision 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.]]) Z no_validationbooleandtype separatorsparsesort_parameter_constraints=TcCs||_||_||_||_dSNr)selfrrrrrO/tmp/pip-unpacked-wheel-ig1s1lm8/sklearn/feature_extraction/_dict_vectorizer.py__init__fszDictVectorizer.__init__FNfitting transformingindicesvaluesc Cs|D]} t| tr(d||j| f} d} ntdt| d|r^| |kr^t||| <|| |r| |kr||| ||| 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_namesvocabrrrrvv feature_namerrr_add_iterable_elementls      z$DictVectorizer._add_iterable_element)Zprefer_skip_nested_validationc Csg}i}|D]}|D]\}}t|tr 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%rr.r&r'r enumeratefeature_names_ vocabulary_) rXyr*r+xr(r)r-rrrfits2    zDictVectorizer.fitc CsXtdjdkstd|j}|r*g}i}n |j}|j}d}t|trJ|gn|}td}dg}g} |D]} | D]\} } t| t rd| |j | f} d} nvt| t s| dkr| } n^t| tst| t rd} |j | | |||||| dn*td t| d | d | d t| d | dk rr|r>| |kr>t||| <|| | |krr||| | || qr|t|qdt|dkrtdtj|tjd}t|dt|f}tj| ||f||d}|r(|jr(|tjt|tjd}t|D]\}} || ||<||| <q|dd|f}|jr:|n|}|rT||_||_|S)Nr2zsizeof(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 r/r0z. z objects are not supported.zSample sequence X is empty.r)shaper)ritemsizeAssertionErrorrr6r7r"rr4r#rrrr.r$r%r&r' ValueErrornpZ frombufferZintcspZ csr_matrixremptyZint32r5rZ sort_indicesZtoarray)rr8rrr*r+rrZindptrrr:r(r)r-r>Z 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. TrrG)rr8r9rrr fit_transform$szDictVectorizer.fit_transformc st|ddgd}|jd}|j}fddt|D}t|rpt|D] \}}|||f||||<qLnLt|D]B\}}t||ddfD]$\}} | dkr|||f|||<qqx|S)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. ZcsrZcsc)Z accept_sparsercsg|] }qSrr)r1_ dict_typerr Zsz4DictVectorizer.inverse_transform..N) r r>r6rangerCissparsezipZnonzeror5) rr8rMZ n_samplesnamesZdictsr2jdr)rrLrinverse_transform>s  z DictVectorizer.inverse_transformcCs|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. FrHrI)rr8rrr transformgszDictVectorizer.transformcCsDt|dtdd|jDr0dd|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. r6css|]}t|t VqdSr)r"r#r1namerrr sz7DictVectorizer.get_feature_names_out..cSsg|] }t|qSr)r#rWrrrrNsz8DictVectorizer.get_feature_names_out..r=)r anyr6rBZasarrayobject)rZinput_featuresr*rrrget_feature_names_outzs z$DictVectorizer.get_feature_names_outcCs`|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'], ...) rcSsg|] \}}|qSrr)r1r(r2rrrrNsz+DictVectorizer.restrict..r!)key)rBwherer6r&r7sortedr4r)rZsupportrrRZ new_vocabr2rrrrestricts!zDictVectorizer.restrictcCs ddgiS)NZX_typesdictr)rrrr _more_tagsszDictVectorizer._more_tags)N)N)N)F)__name__ __module__ __qualname____doc__r#rra__annotations__rBZfloat64rr.r r;rGrJrUrVr\r`rbrrrrr s, M   5c  )  0r )rcollections.abcrrZnumbersroperatorrZnumpyrBZ scipy.sparserrCbaserr r utilsr Zutils.validationr r rrrrs