ó ‡ˆ\c@sddlZddlZddljZddlmZddlmZddlm Z m Z ddl m Z ddl m Z ddlmZdd lmZdd lmZdd lmZejjZejjZd gZd „Zd„Ze dƒd e e fd„ƒYƒZdS(iÿÿÿÿN(tsparse(tstatsi(t BaseEstimatortTransformerMixin(t check_array(t deprecated(t _get_median(tcheck_is_fitted(t FLOAT_DTYPES(tsixtImputercCs6|dkstj|ƒr(tj|ƒS||kSdS(s-Compute the boolean mask X == missing_values.tNaNN(tnptisnan(tXt value_to_mask((s?lib/python2.7/site-packages/sklearn/preprocessing/imputation.pyt _get_masks cCs¯|jdkr=tj|ƒ}|dd}|dd}n d}d}|dkrh|dkrhtjS||krx|S||krˆ|S||kr«||kr¤|S|SndS(sCompute the most frequent value in a 1d array extended with [extra_value] * n_repeat, where extra_value is assumed to be not part of the array.iiN(tsizeRtmodeR tnan(tarrayt extra_valuetn_repeatRtmost_frequent_valuetmost_frequent_count((s?lib/python2.7/site-packages/sklearn/preprocessing/imputation.pyt_most_frequent$s     suImputer was deprecated in version 0.20 and will be removed in 0.22. Import impute.SimpleImputer from sklearn instead.cBsMeZdZdddded„Zd d„Zd„Zd„Zd„Z RS( s³Imputation transformer for completing missing values. Read more in the :ref:`User Guide `. Parameters ---------- missing_values : integer or "NaN", optional (default="NaN") The placeholder for the missing values. All occurrences of `missing_values` will be imputed. For missing values encoded as np.nan, use the string value "NaN". strategy : string, optional (default="mean") The imputation strategy. - If "mean", then replace missing values using the mean along the axis. - If "median", then replace missing values using the median along the axis. - If "most_frequent", then replace missing using the most frequent value along the axis. axis : integer, optional (default=0) The axis along which to impute. - If `axis=0`, then impute along columns. - If `axis=1`, then impute along rows. verbose : integer, optional (default=0) Controls the verbosity of the imputer. copy : boolean, optional (default=True) If True, a copy of X will be created. If False, imputation will be done in-place whenever possible. Note that, in the following cases, a new copy will always be made, even if `copy=False`: - If X is not an array of floating values; - If X is sparse and `missing_values=0`; - If `axis=0` and X is encoded as a CSR matrix; - If `axis=1` and X is encoded as a CSC matrix. Attributes ---------- statistics_ : array of shape (n_features,) The imputation fill value for each feature if axis == 0. Notes ----- - When ``axis=0``, columns which only contained missing values at `fit` are discarded upon `transform`. - When ``axis=1``, an exception is raised if there are rows for which it is not possible to fill in the missing values (e.g., because they only contain missing values). R tmeanicCs1||_||_||_||_||_dS(N(tmissing_valueststrategytaxistverbosetcopy(tselfRRRRR((s?lib/python2.7/site-packages/sklearn/preprocessing/imputation.pyt__init__ys     cCs÷dddg}|j|kr<tdj||jƒƒ‚n|jd krftdj|jƒƒ‚n|jdkrót|dd d tjd tƒ}tj |ƒrÌ|j ||j|j |jƒ|_ qó|j ||j|j |jƒ|_ n|S( sCFit the imputer on X. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) Input data, where ``n_samples`` is the number of samples and ``n_features`` is the number of features. Returns ------- self : Imputer Rtmediant most_frequents4Can only use these strategies: {0} got strategy={1}iis=Can only impute missing values on axis 0 and 1, got axis={0}t accept_sparsetcsctdtypetforce_all_finite(ii(Rt ValueErrortformatRRR tfloat64tFalseRtissparset _sparse_fitRt statistics_t _dense_fit(R Rtytallowed_strategies((s?lib/python2.7/site-packages/sklearn/preprocessing/imputation.pytfits*     cCsù|dkr|jƒ}n |jƒ}|dkrStj|j| dtƒ}n|j|tj|jƒ}|dkr¯|dkrU|}t|j |ƒ}tj |ƒ}|j j ƒ} d| |s$