ó ‡ˆ\c@s½ddlmZddlmZddlZddljZddlm Z m Z ddl m Z ddl mZddlmZmZdd lmZd „Zd e e fd „ƒYZdS( iÿÿÿÿ(tarray(t itemgetterNi(t BaseEstimatortTransformerMixin(tsix(txrange(t check_arrayt tosequence(t_MappingcCs$t|tƒr|gSt|ƒSdS(s?Turn X into a sequence or ndarray, avoiding a copy if possible.N(t isinstancetMappingR(tX((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyt _tosequencestDictVectorizercBsqeZdZejdeed„Zd d„Zd„Z d d„Z e d„Z d„Z d„Zed „ZRS( sW 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". 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, 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. Read more in the :ref:`User Guide `. Parameters ---------- dtype : callable, optional The type of feature values. Passed to Numpy array/scipy.sparse matrix constructors as the dtype argument. separator : string, optional Separator string used when constructing new features for one-hot coding. sparse : boolean, optional. Whether transform should produce scipy.sparse matrices. True by default. sort : boolean, optional. Whether ``feature_names_`` and ``vocabulary_`` should be sorted when fitting. True by default. 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"). 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.]]) See also -------- FeatureHasher : performs vectorization using only a hash function. sklearn.preprocessing.OrdinalEncoder : handles nominal/categorical features encoded as columns of arbitrary data types. t=cCs(||_||_||_||_dS(N(tdtypet separatortsparsetsort(tselfRRRR((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyt__init__`s   cCsÜg}i}x…|D]}}xttj|ƒD]c\}}t|tjƒr`d||j|f}n||kr)|j|ƒt|ƒ|| 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). y : (ignored) Returns ------- self s%s%s%scss!|]\}}||fVqdS(N((t.0titf((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pys ‚s( Rt iteritemsR t string_typesRtappendtlenRtdictt enumeratetfeature_names_t vocabulary_(RR tyt feature_namestvocabtxRtv((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pytfitgs       cCsÜtdƒjdks!tdƒ‚|j}|r?g}i}n|j}|j}t|tƒri|gn|}tdƒ}tddgƒ}g}xï|D]ç} xËtj | ƒD]º\} } t| tj ƒríd| |j | f} d} n| |kr |j || ƒ|j || ƒƒq°|r°|j | ƒt |ƒ|| <|j || ƒ|j || ƒƒq°q°W|j t |ƒƒqšWt |ƒdkr¦tdƒ‚ntj|dtjƒ}tj|dtjƒ}t |ƒdt |ƒf} tj|||fd | d|ƒ} |r›|jr›|jƒtjt |ƒdtjƒ}x2t|ƒD]$\}} || ||<||| 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). y : (ignored) Returns ------- Xa : {array, sparse matrix} Feature vectors; always 2-d. R3(R:tTrue(RR R ((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyt fit_transformÕsc Cst|dddgƒ}|jd}|j}gt|ƒD]}|ƒ^q;}tj|ƒr¡x°t|jƒŒD](\}}|||f||||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, length = 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. R3Rs%s%s%siN(RR:tFalseRRR R*tzerosRRRRR RRtKeyError( RR RR"tXaRR#RR$((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyt transforms     '   cCs|jS(sÖReturns a list of feature names, ordered by their indices. If one-of-K coding is applied to categorical features, this will include the constructed feature names but not the original ones. (R(R((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pytget_feature_names8scCsš|stj|ƒd}n|j}i}x"|D]}t|ƒ|||>> 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() ['bar', 'baz', 'foo'] >>> v.restrict(support.get_support()) # doctest: +ELLIPSIS DictVectorizer(dtype=..., separator='=', sort=True, sparse=True) >>> v.get_feature_names() ['bar', 'foo'] itkeyi( R*twhereRRRtsortedRRR(RtsupportR4REt new_vocabRR((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pytrestrict@s!   (N(t__name__t __module__t__doc__R*tfloat64R;RtNoneR%R:R<RRJRORPRKRV(((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyR sD   " L  ) & (RtoperatorRtnumpyR*t scipy.sparseRR-tbaseRRt externalsRtexternals.six.movesRtutilsRRt utils.fixesRR R R (((sIlib/python2.7/site-packages/sklearn/feature_extraction/dict_vectorizer.pyts