ó ‡ˆ\c@ sGddlmZddlZddlZddlZddlmZddlm Z ddl m Z m Z ddlmZddlmZdd lmZdd lmZmZdd lmZd d l mZd dlmZmZejjZddgZde e fd„ƒYZdefd„ƒYZ defd„ƒYZ!dS(iÿÿÿÿ(tdivisionN(tsparsei(t get_config(t BaseEstimatortTransformerMixin(tsix(t check_array(t deprecated(t_argmaxt_object_dtype_isnan(tcheck_is_fittedi(t_transform_selected(t_encodet_encode_check_unknownt OneHotEncodertOrdinalEncodert _BaseEncodercB s/eZdZd„Zdd„Zdd„ZRS(sm Base class for encoders that includes the code to categorize and transform the input features. cC s¨t|ddƒ}t|dƒ rRtj|jtjƒrRt|dtjƒ}n|}|jtjdƒkr¤tƒds¤t |ƒj ƒr¡t dƒ‚q¡q¤n|S(s Perform custom check_array: - convert list of strings to object dtype - check for missing values for object dtype data (check_array does not do that) tdtypetobjectt assume_finitesInput contains NaNN( RtNonethasattrtnpt issubdtypeRtstr_Rt _get_configR tanyt ValueError(tselftXtX_temp((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt_check_X's( terrorc C s||j|ƒ}|j\}}|jdkr°|jtkr‰xJ|jD]<}tjtj|ƒtj|ƒkƒsFt dƒ‚qFqFWnt |jƒ|kr°t dƒ‚q°ng|_ x¼t |ƒD]®}|dd…|f}|jdkrt |ƒ}ndtj|j|d|jƒ}|dkrdt||ƒ}|rddj||ƒ} t | ƒ‚qdn|j j|ƒqÆWdS(Ntautos>Unsorted categories are not supported for numerical categoriessMShape mismatch: if n_values is an array, it has to be of shape (n_features,).RR s5Found unknown categories {0} in column {1} during fit(Rtshapet _categoriesRRRtalltsorttarrayRtlent categories_trangeR R tformattappend( RRthandle_unknownt n_samplest n_featurestcatstitXitdifftmsg((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt_fit<s,'   c C s¤|j|ƒ}|j\}}tj|dtjƒ}tj|dtjƒ}xIt|ƒD];}|dd…|f}t||j |dt ƒ\} } tj | ƒs^|dkrÕdj | |ƒ} t | ƒ‚q^| |dd…|f<|j |jjd kr9|j |j|jkr9|j|j |jƒ}n |jƒ}|j |d|| lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt _transform[s,   "(t__name__t __module__t__doc__RR4RG(((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyR s  cB s×eZdZdddeejdd„Zee dƒd„ƒƒZ ee dƒd„ƒƒZ ee dƒd„ƒƒZ d „Z dd „Zd „Zdd „Zd „Zd„Zd„Zd„Zdd„ZRS(s5Encode categorical integer features as a one-hot numeric array. The input to this transformer should be an array-like of integers or strings, denoting the values taken on by categorical (discrete) features. The features are encoded using a one-hot (aka 'one-of-K' or 'dummy') encoding scheme. This creates a binary column for each category and returns a sparse matrix or dense array. By default, the encoder derives the categories based on the unique values in each feature. Alternatively, you can also specify the `categories` manually. The OneHotEncoder previously assumed that the input features take on values in the range [0, max(values)). This behaviour is deprecated. This encoding is needed for feeding categorical data to many scikit-learn estimators, notably linear models and SVMs with the standard kernels. Note: a one-hot encoding of y labels should use a LabelBinarizer instead. Read more in the :ref:`User Guide `. Parameters ---------- categories : 'auto' or a list of lists/arrays of values, default='auto'. Categories (unique values) per feature: - 'auto' : Determine categories automatically from the training data. - list : ``categories[i]`` holds the categories expected in the ith column. The passed categories should not mix strings and numeric values within a single feature, and should be sorted in case of numeric values. The used categories can be found in the ``categories_`` attribute. sparse : boolean, default=True Will return sparse matrix if set True else will return an array. dtype : number type, default=np.float Desired dtype of output. handle_unknown : 'error' or 'ignore', default='error'. Whether to raise an error or ignore if an unknown categorical feature is present during transform (default is to raise). When this parameter is set to 'ignore' and an unknown category is encountered during transform, the resulting one-hot encoded columns for this feature will be all zeros. In the inverse transform, an unknown category will be denoted as None. n_values : 'auto', int or array of ints, default='auto' Number of values per feature. - 'auto' : determine value range from training data. - int : number of categorical values per feature. Each feature value should be in ``range(n_values)`` - array : ``n_values[i]`` is the number of categorical values in ``X[:, i]``. Each feature value should be in ``range(n_values[i])`` .. deprecated:: 0.20 The `n_values` keyword was deprecated in version 0.20 and will be removed in 0.22. Use `categories` instead. categorical_features : 'all' or array of indices or mask, default='all' Specify what features are treated as categorical. - 'all': All features are treated as categorical. - array of indices: Array of categorical feature indices. - mask: Array of length n_features and with dtype=bool. Non-categorical features are always stacked to the right of the matrix. .. deprecated:: 0.20 The `categorical_features` keyword was deprecated in version 0.20 and will be removed in 0.22. You can use the ``ColumnTransformer`` instead. Attributes ---------- categories_ : list of arrays The categories of each feature determined during fitting (in order of the features in X and corresponding with the output of ``transform``). active_features_ : array Indices for active features, meaning values that actually occur in the training set. Only available when n_values is ``'auto'``. .. deprecated:: 0.20 The ``active_features_`` attribute was deprecated in version 0.20 and will be removed in 0.22. feature_indices_ : array of shape (n_features,) Indices to feature ranges. Feature ``i`` in the original data is mapped to features from ``feature_indices_[i]`` to ``feature_indices_[i+1]`` (and then potentially masked by ``active_features_`` afterwards) .. deprecated:: 0.20 The ``feature_indices_`` attribute was deprecated in version 0.20 and will be removed in 0.22. n_values_ : array of shape (n_features,) Maximum number of values per feature. .. deprecated:: 0.20 The ``n_values_`` attribute was deprecated in version 0.20 and will be removed in 0.22. Examples -------- Given a dataset with two features, we let the encoder find the unique values per feature and transform the data to a binary one-hot encoding. >>> from sklearn.preprocessing import OneHotEncoder >>> enc = OneHotEncoder(handle_unknown='ignore') >>> X = [['Male', 1], ['Female', 3], ['Female', 2]] >>> enc.fit(X) ... # doctest: +ELLIPSIS OneHotEncoder(categorical_features=None, categories=None, dtype=<... 'numpy.float64'>, handle_unknown='ignore', n_values=None, sparse=True) >>> enc.categories_ [array(['Female', 'Male'], dtype=object), array([1, 2, 3], dtype=object)] >>> enc.transform([['Female', 1], ['Male', 4]]).toarray() array([[1., 0., 1., 0., 0.], [0., 1., 0., 0., 0.]]) >>> enc.inverse_transform([[0, 1, 1, 0, 0], [0, 0, 0, 1, 0]]) array([['Male', 1], [None, 2]], dtype=object) >>> enc.get_feature_names() array(['x0_Female', 'x0_Male', 'x1_1', 'x1_2', 'x1_3'], dtype=object) See also -------- sklearn.preprocessing.OrdinalEncoder : performs an ordinal (integer) encoding of the categorical features. sklearn.feature_extraction.DictVectorizer : performs a one-hot encoding of dictionary items (also handles string-valued features). sklearn.feature_extraction.FeatureHasher : performs an approximate one-hot encoding of dictionary items or strings. sklearn.preprocessing.LabelBinarizer : binarizes labels in a one-vs-all fashion. sklearn.preprocessing.MultiLabelBinarizer : transforms between iterable of iterables and a multilabel format, e.g. a (samples x classes) binary matrix indicating the presence of a class label. R cC s:||_||_||_||_||_||_dS(N(t categoriesRRR,tn_valuestcategorical_features(RRLRMRKRRR,((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt__init__s      s[The ``active_features_`` attribute was deprecated in version 0.20 and will be removed 0.22.cC st|dƒ|jS(NR((R t_active_features_(R((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pytactive_features_"s s[The ``feature_indices_`` attribute was deprecated in version 0.20 and will be removed 0.22.cC st|dƒ|jS(NR((R t_feature_indices_(R((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pytfeature_indices_)s sTThe ``n_values_`` attribute was deprecated in version 0.20 and will be removed 0.22.cC st|dƒ|jS(NR((R t _n_values_(R((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt n_values_0s cC s`|j|_t|ddƒ|_t|ddƒ|_|jdk sT|jdk r~t|_|jdk rq|j|_qqnó|jdk r¾|jdkr¾d}t j |t ƒt |_n³d|_|j dkrt|_d|_|jdkrqd}t j |t ƒqqn^yt|dtjƒ}Wn#tk rQt|_d|_n Xd}t j |tƒt |_|jdk rSt|jtjƒr·|jd kr·t j d t ƒn|jdk rÕtd ƒ‚nt j d t ƒ|jd }tj|dtƒ}t |tj|jƒlib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt_handle_deprecations7s^                  cC sŠ|jdkr0dj|jƒ}t|ƒ‚n|j|ƒ|jrlt||j|j|jdt ƒ|S|j |d|jƒ|SdS(síFit OneHotEncoder to X. Parameters ---------- X : array-like, shape [n_samples, n_features] The data to determine the categories of each feature. Returns ------- self R RVs=handle_unknown should be either 'error' or 'ignore', got {0}.RAR,N(R RV( R,R*RReRZR t_legacy_fit_transformRRUR=R4(RRtyR3((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pytfit”s     cC sˆt|dd ƒ}t|dtjƒ}tj|dkƒrKtdƒ‚n|j\}}t|j t j ƒrš|j dkrštj |ddƒd}nt|j t jƒrtj |ddƒ|j kjƒrétd|j ƒ‚ntj|dtjƒ}|j|j ƒn‡ytj|j dtƒ}Wn0ttfk rbtdt|j ƒƒ‚nX|jdksŒ|jd|jdkr›td ƒ‚n||_g|D]}tj|dd|ƒ^q«|_tjdg|gƒ}tj|ƒ}||_||d jƒ}tjtj|dtjƒ|ƒ} tj||ƒ} tj | | |ffd ||d fd|j!ƒj"ƒ} t|j t j ƒrq|j dkrqtj#| j$ddƒƒjƒdk} tj%| ƒd} | d d …| f} | |_&gt'|ƒD]S}|rFtj(|d d …|fƒj)|ƒntj(|d d …|fƒ^q|_n|jr~| S| j*ƒS( s-Assumes X contains only categorical features.Ris¿OneHotEncoder in legacy mode cannot handle categories encoded as negative integers. Please set categories='auto' explicitly to be able to use arbitrary integer values as category identifiers.R!taxisis%Feature out of bounds for n_values=%dsRWrong type for parameter `n_values`. Expected 'auto', int or array of ints, got %rsMShape mismatch: if n_values is an array, it has to be of shape (n_features,).iÿÿÿÿR"N(+RXRRRR:RRR"R_RWRR`tmaxtnumberstIntegraltemptytfillRbt TypeErrorttypetndimRStarangeR(thstacktcumsumRQtraveltrepeattint32tonesRt coo_matrixRttocsrR&RctwhereROR)tuniqueR@ttoarray(RRRR-R.RLtn_valtindicestcolumn_indicest row_indicestdatatouttmasktactive_featuresR0((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyRf°sV$) ,  ' icC s‚|jdkr0dj|jƒ}t|ƒ‚n|j|ƒ|jrht||j|j|jdt ƒS|j |ƒj |ƒSdS(smFit OneHotEncoder to X, then transform X. Equivalent to fit(X).transform(X) but more convenient. Parameters ---------- X : array-like, shape [n_samples, n_features] The data to encode. Returns ------- X_out : sparse matrix if sparse=True else a 2-d array Transformed input. R RVs=handle_unknown should be either 'error' or 'ignore', got {0}.RAN(R RV( R,R*RReRZR RfRRUR=Rht transform(RRRgR3((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt fit_transformës   c C sït|dtjƒ}tj|dkƒr9tdƒ‚n|j\}}|j}||jddkrŒtd|jdd|fƒ‚n||jkjƒ}tj|ƒr|j dkrÖtd|j ƒ‚n|j dkrtd |jƒ|ƒ‚qn||d jƒ|}tj tj |dtj ƒ|ƒ|}tj tj|ƒƒ}tj|||ffd ||d fd|jƒjƒ} t|jtjƒrØ|jd krØ| d d …|jf} n|jrå| S| jƒS(s-Assumes X contains only categorical features.Ris¿OneHotEncoder in legacy mode cannot handle categories encoded as negative integers. Please set categories='auto' explicitly to be able to use arbitrary integer values as category identifiers.is?X has different shape than during fitting. Expected %d, got %d.R RVs7handle_unknown should be either error or unknown got %ss8unknown categorical feature present %s during transform.iÿÿÿÿR"R!N(R RV(RRR:RRR"RQRSRuR,RvRrRwRxRcRRyRRzR_RWRR`ROR}( RRR-R.RR„R€RR‚Rƒ((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt_legacy_transforms6  cC st|ddƒ}t|dƒ rRtj|jtjƒrRt|dtjƒ}n|}|j\}}|j |d|j ƒ\}}|j ƒ}g|j D]}|jd^q›} tj dg| ƒ} tj| ƒ} || d j ƒ|} |jddƒjƒ} tj| ddƒ} tj||ƒ|} tj| | | fd|| dfd|jƒ}|jsy|jƒS|SdS( s-New implementation assuming categorical inputRR,iiÿÿÿÿRiiR"N(RRRRRRRRR"RGR,RuR(R&RtRctinsertRxRt csr_matrixR}(RRRR-R.RCRDR„R/RLtfeature_indicesRtindptrR‚Rƒ((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyt_transform_new4s(( #   cC sIt|dƒ|jr8t||j|j|jdtƒS|j|ƒSdS(s'Transform X using one-hot encoding. Parameters ---------- X : array-like, shape [n_samples, n_features] The data to encode. Returns ------- X_out : sparse matrix if sparse=True else a 2-d array Transformed input. R(RAN(R RZR RˆRRUR=R(RR((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyR†Rs   cC s5t|dƒt|ddƒ}|j\}}t|jƒ}tg|jD]}t|ƒ^qJƒ}d}|jd|kr t|j||jdƒƒ‚ntj g|jD]}|j ^q°gƒ} tj ||fd| ƒ} d} i} xåt |ƒD]×} t|j| ƒ}|dd…| | |…f}tj t|d dƒƒjƒ}|j| || dd…| f<|jd krÌtj |jd dƒdkƒjƒ}|jƒrÌ|| | lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pytinverse_transformgs8 ("+ !!' cC st|dƒ|j}|dkrNgtt|ƒƒD]}d|^q5}nEt|ƒt|jƒkr“tdjt|jƒt|ƒƒƒ‚ng}xYtt|ƒƒD]E}g||D]!}||dtj|ƒ^q½}|j |ƒq¬Wt j |dt ƒS(s‚Return feature names for output features. Parameters ---------- input_features : list of string, length n_features, optional String names for input features if available. By default, "x0", "x1", ... "xn_features" is used. Returns ------- output_feature_names : array of string, length n_output_features R(sx%dsJinput_features should have length equal to number of features ({}), got {}RBRN( R R(RR)R'RR*Rt text_typetextendRR&R(Rtinput_featuresR/R0t feature_namestttnames((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pytget_feature_namesªs   , 2N(RHRIRJRR=Rtfloat64RNtpropertyRRPRRRTReRhRfR‡RˆRR†RžR¥(((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyR€s&”   ]  ;  ,   CcB s>eZdZdejd„Zdd„Zd„Zd„Z RS(s©Encode categorical features as an integer array. The input to this transformer should be an array-like of integers or strings, denoting the values taken on by categorical (discrete) features. The features are converted to ordinal integers. This results in a single column of integers (0 to n_categories - 1) per feature. Read more in the :ref:`User Guide `. Parameters ---------- categories : 'auto' or a list of lists/arrays of values. Categories (unique values) per feature: - 'auto' : Determine categories automatically from the training data. - list : ``categories[i]`` holds the categories expected in the ith column. The passed categories should not mix strings and numeric values, and should be sorted in case of numeric values. The used categories can be found in the ``categories_`` attribute. dtype : number type, default np.float64 Desired dtype of output. Attributes ---------- categories_ : list of arrays The categories of each feature determined during fitting (in order of the features in X and corresponding with the output of ``transform``). Examples -------- Given a dataset with two features, we let the encoder find the unique values per feature and transform the data to an ordinal encoding. >>> from sklearn.preprocessing import OrdinalEncoder >>> enc = OrdinalEncoder() >>> X = [['Male', 1], ['Female', 3], ['Female', 2]] >>> enc.fit(X) ... # doctest: +ELLIPSIS OrdinalEncoder(categories='auto', dtype=<... 'numpy.float64'>) >>> enc.categories_ [array(['Female', 'Male'], dtype=object), array([1, 2, 3], dtype=object)] >>> enc.transform([['Female', 3], ['Male', 1]]) array([[0., 2.], [1., 0.]]) >>> enc.inverse_transform([[1, 0], [0, 1]]) array([['Male', 1], ['Female', 2]], dtype=object) See also -------- sklearn.preprocessing.OneHotEncoder : performs a one-hot encoding of categorical features. sklearn.preprocessing.LabelEncoder : encodes target labels with values between 0 and n_classes-1. R!cC s||_||_dS(N(RKR(RRKR((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyRNs cC s|j|_|j|ƒ|S(sóFit the OrdinalEncoder to X. Parameters ---------- X : array-like, shape [n_samples, n_features] The data to determine the categories of each feature. Returns ------- self (RKR#R4(RRRg((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyRh s  cC s+|j|ƒ\}}|j|jdtƒS(sTransform X to ordinal codes. Parameters ---------- X : array-like, shape [n_samples, n_features] The data to encode. Returns ------- X_out : sparse matrix or a 2-d array Transformed input. RA(RGR@RRY(RRRCRB((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyR† sc C st|dƒt|ddƒ}|j\}}t|jƒ}d}|jd|krxt|j||jdƒƒ‚ntjg|jD]}|j ^qˆgƒ}tj ||fd|ƒ}xTt |ƒD]F} |dd…| fj dƒ} |j| | |dd…| flib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyRž1s "+%N( RHRIRJRR¦RNRRhR†Rž(((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyRËs ;  ("t __future__RRkR[tnumpyRtscipyRtRRtbaseRRt externalsRtutilsRRt utils.fixesRR tutils.validationR R tlabelR R tmovesR)t__all__RRR(((s>lib/python2.7/site-packages/sklearn/preprocessing/_encoders.pyts*     `ÿÿM