ó ‡ˆ\c@s±dZddlZddlZddlZddlZddlZddlmZddl m Z ddl m Z m Z ddlmZdd lmZdd lmZdd lmZdd lmZmZmZmZmZmZmZmZm Z dd lm!Z!ej"Z"ej#Z#dZ$ee$ƒZ%e%ej&ƒZ&e%ej'ƒZ'e%ej(ƒZ(e%ej)ƒZ)e%dej*fd„ƒYƒZ*e%dej+fd„ƒYƒZ+dddddddddddddd d!d"ddd#d$d%d&d'gZ,ej-ƒd(kZ.d)ej/d*ƒd+kZ0d,e1fd-„ƒYZ2d.„Z3d/„Z4d0„Z5d1„Z6d2„Z7e8d3„Z9d4d5„Z:dd6„Z<d7„Z=d8„Z>ddd9„Z?d:„Z@dS(;s= The :mod:`sklearn.utils` module includes various utilities. iÿÿÿÿN(tissparsei(tmurmurhash3_32(tcompute_class_weighttcompute_sample_weight(t_joblibi(tDataConversionWarning(t _Sequence(t deprecated( tas_float_arraytassert_all_finitetcheck_random_statet column_or_1dt check_arraytcheck_consistent_lengtht check_X_yt indexabletcheck_symmetric(t get_configs£deprecated in version 0.20.1 to be removed in version 0.23. Please import this functionality directly from joblib, which can be installed with: pip install joblib.tMemorycBseZRS((t__name__t __module__(((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyR0stParallelcBseZRS((RR(((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyR5sRRR R R RRR t safe_indexingR RRRtindices_to_maskRt cpu_counttdelayedtparallel_backendtregister_parallel_backendthashteffective_n_jobstPyPyitPi tBunchcBs;eZdZd„Zd„Zd„Zd„Zd„ZRS(sòContainer object for datasets Dictionary-like object that exposes its keys as attributes. >>> b = Bunch(a=1, b=2) >>> b['b'] 2 >>> b.b 2 >>> b.a = 3 >>> b['a'] 3 >>> b.c = 6 >>> b['c'] 6 cKstt|ƒj|ƒdS(N(tsuperR t__init__(tselftkwargs((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyR"[scCs|||>> X = np.array([[1., 0.], [2., 1.], [0., 0.]]) >>> y = np.array([0, 1, 2]) >>> from scipy.sparse import coo_matrix >>> X_sparse = coo_matrix(X) >>> from sklearn.utils import resample >>> X, X_sparse, y = resample(X, X_sparse, y, random_state=0) >>> X array([[1., 0.], [2., 1.], [1., 0.]]) >>> X_sparse # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE <3x2 sparse matrix of type '<... 'numpy.float64'>' with 4 stored elements in Compressed Sparse Row format> >>> X_sparse.toarray() array([[1., 0.], [2., 1.], [1., 0.]]) >>> y array([0, 1, 0]) >>> resample(y, n_samples=2, random_state=0) array([0, 1]) See also -------- :func:`sklearn.utils.shuffle` t random_statetreplacet n_samplessUnexpected kw arguments: %riR8s@Cannot sample %d out of arrays with dim %d when replace is FalsetsizeiN(R tpoptNonetTrueRGR(tlenR6R8R trandintR1R7tshuffleRttocsrR( tarraystoptionsRMRNt max_n_samplestfirstRORKtatresampled_arrays((s5lib/python2.7/site-packages/sklearn/utils/__init__.pytresampleßs4J (     1"cOst|d>> X = np.array([[1., 0.], [2., 1.], [0., 0.]]) >>> y = np.array([0, 1, 2]) >>> from scipy.sparse import coo_matrix >>> X_sparse = coo_matrix(X) >>> from sklearn.utils import shuffle >>> X, X_sparse, y = shuffle(X, X_sparse, y, random_state=0) >>> X array([[0., 0.], [2., 1.], [1., 0.]]) >>> X_sparse # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE <3x2 sparse matrix of type '<... 'numpy.float64'>' with 3 stored elements in Compressed Sparse Row format> >>> X_sparse.toarray() array([[0., 0.], [2., 1.], [1., 0.]]) >>> y array([2, 1, 0]) >>> shuffle(y, n_samples=2, random_state=0) array([0, 1]) See also -------- :func:`sklearn.utils.resample` RN(tFalseR^(RXRY((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyRVOsC cCsut|ddddgdtƒ}t|ƒrT|rB|jƒ}n|jdC_n|rg|d}n |dC}|S(sdElement wise squaring of array-likes and sparse matrices. Parameters ---------- X : array like, matrix, sparse matrix copy : boolean, optional, default True Whether to create a copy of X and operate on it or to perform inplace computation (default behaviour). Returns ------- X ** 2 : element wise square t accept_sparsetcsrtcsctcoot ensure_2di(R R_RRFtdata(R9RF((s5lib/python2.7/site-packages/sklearn/utils/__init__.pytsafe_sqr–s!   iccs|d}xRtt||ƒƒD]:}||}|||krCqnt||ƒV|}qW||krxt||ƒVndS(s”Generator to create slices containing batch_size elements, from 0 to n. The last slice may contain less than batch_size elements, when batch_size does not divide n. Parameters ---------- n : int batch_size : int Number of element in each batch min_batch_size : int, default=0 Minimum batch size to produce. Yields ------ slice of batch_size elements Examples -------- >>> from sklearn.utils import gen_batches >>> list(gen_batches(7, 3)) [slice(0, 3, None), slice(3, 6, None), slice(6, 7, None)] >>> list(gen_batches(6, 3)) [slice(0, 3, None), slice(3, 6, None)] >>> list(gen_batches(2, 3)) [slice(0, 2, None)] >>> list(gen_batches(7, 3, min_batch_size=0)) [slice(0, 3, None), slice(3, 6, None), slice(6, 7, None)] >>> list(gen_batches(7, 3, min_batch_size=2)) [slice(0, 3, None), slice(3, 7, None)] iN(trangetinttslice(tnt batch_sizetmin_batch_sizetstartt_tend((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyt gen_batches²s    ccsµd}|dkr%td|ƒ‚nx‰t|ƒD]{}||}|||kr_|d7}n|dkr2||}|dk r“t||ƒ}nt||dƒV|}q2q2WdS(s¹Generator to create n_packs slices going up to n. Parameters ---------- n : int n_packs : int Number of slices to generate. n_samples : int or None (default = None) Number of samples. Pass n_samples when the slices are to be used for sparse matrix indexing; slicing off-the-end raises an exception, while it works for NumPy arrays. Yields ------ slice Examples -------- >>> from sklearn.utils import gen_even_slices >>> list(gen_even_slices(10, 1)) [slice(0, 10, None)] >>> list(gen_even_slices(10, 10)) #doctest: +ELLIPSIS [slice(0, 1, None), slice(1, 2, None), ..., slice(9, 10, None)] >>> list(gen_even_slices(10, 5)) #doctest: +ELLIPSIS [slice(0, 2, None), slice(2, 4, None), ..., slice(8, 10, None)] >>> list(gen_even_slices(10, 3)) [slice(0, 4, None), slice(4, 7, None), slice(7, 10, None)] iis+gen_even_slices got n_packs=%s, must be >=1N(RGRgRRtminRi(Rjtn_packsRORmtpack_numtthis_nRo((s5lib/python2.7/site-packages/sklearn/utils/__init__.pytgen_even_slicesÝs       cCs@t|tjƒrtj|ƒSt|tƒr2|St|ƒSdS(spCast iterable x to a Sequence, avoiding a copy if possible. Parameters ---------- x : iterable N(t isinstanceR1tndarrayR2tSequencetlist(tx((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyt tosequence s  cCsJ|tj|ƒkr$tdƒ‚ntj|dtjƒ}t||<|S(sRConvert list of indices to boolean mask. Parameters ---------- indices : list-like List of integers treated as indices. mask_length : int Length of boolean mask to be generated. This parameter must be greater than max(indices) Returns ------- mask : 1d boolean nd-array Boolean array that is True where indices are present, else False. Examples -------- >>> from sklearn.utils import indices_to_mask >>> indices = [1, 2 , 3, 4] >>> indices_to_mask(indices, 5) array([False, True, True, True, True]) s-mask_length must be greater than max(indices)R4(R1tmaxRGR=tboolRS(RKt mask_lengthR:((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyRs  cCs‹|dkrtƒd}nt|d|ƒ}|dk rNt||ƒ}n|dkr‡tjd|tj|d ƒfƒd}n|S( s¢Calculates how many rows can be processed within working_memory Parameters ---------- row_bytes : int The expected number of bytes of memory that will be consumed during the processing of each row. max_n_rows : int, optional The maximum return value. working_memory : int or float, optional The number of rows to fit inside this number of MiB will be returned. When None (default), the value of ``sklearn.get_config()['working_memory']`` is used. Returns ------- int or the value of n_samples Warns ----- Issues a UserWarning if ``row_bytes`` exceeds ``working_memory`` MiB. tworking_memoryiiisOCould not adhere to working_memory config. Currently %.0fMiB, %.0fMiB required.iìÿÿÿNig°>(RRRRhRqRHRIR1tceil(t row_bytest max_n_rowsRt chunk_n_rows((s5lib/python2.7/site-packages/sklearn/utils/__init__.pytget_chunk_n_rows9s     cCs.tt|tjtjfƒo*tj|ƒƒS(sçTests if x is NaN This function is meant to overcome the issue that np.isnan does not allow non-numerical types as input, and that np.nan is not np.float('nan'). Parameters ---------- x : any type Returns ------- boolean Examples -------- >>> is_scalar_nan(np.nan) True >>> is_scalar_nan(float("nan")) True >>> is_scalar_nan(None) False >>> is_scalar_nan("") False >>> is_scalar_nan([np.nan]) False (R}RvtnumberstRealR1tfloatingtisnan(Rz((s5lib/python2.7/site-packages/sklearn/utils/__init__.pyt is_scalar_nan`s (AR/R…tplatformtstructRHtnumpyR1t scipy.sparseRt murmurhashRt class_weightRRtRt exceptionsRtfixesRRxt deprecationRt validationRR R R R R RRRRRRtmsgt deprecateRRRRRRt__all__tpython_implementationtIS_PYPYtcalcsizet _IS_32BITtdictR R<R?RR^RVRSRfRpRRRuR{RR„R‰(((s5lib/python2.7/site-packages/sklearn/utils/__init__.pytsf     @     .  # - p G  + -   &