ɯwgU*dZddlZddlZddlZddlZddlZddlZddlZddlZddl Z ddl Z ddl m Z ddl mZddlmZmZddl mZddlmZddlmZmZmZmZmZmZgdZdZej>d vZ e jBjDd k(Z#e$e d Z%e&e d dduxre% Z'dBd Z(dZ)dZ*dZ+ dCdZ,dDdZ-dZ.dEdZ/dEdZ0 dFdddZ1dDdddZ2dGdZ3dDdZ4dZ5ddl6Z6Gdde6jnZ8e8dZ9d Z:dHd!Z;d"Z< dId#Z=dJd$Z>dKd%Z?dHd&Z@d'ZAd(ZBejdHd)ZDd*ZEejdHd+ZFd,ZGed-d.fd/ZHGd0d1eIZJejd2ZKejd3ZLGd4d5e jZNGd6d7ZOejdHd8ZPd9ZQd:ZRd;ZSd<ZTd=ZUd>ZVd?ZWd@ZXeXZYdAZZy)Lz* Utility function to facilitate testing. Nwraps)StringIO)mkdtempmkstemp)WarningMessage)arangeasarrayemptyfloat32intpndarray) assert_equalassert_almost_equalassert_approx_equalassert_array_equalassert_array_lessassert_string_equalassert_assert_array_almost_equal build_err_msgdecorate_methodsprint_assert_equalverboserassert_array_almost_equal_nulpassert_raises_regexassert_array_max_ulp assert_warnsassert_no_warningsassert_allcloseIgnoreExceptionclear_and_catch_warningstemppathtempdirIS_PYPY HAS_REFCOUNTIS_WASMsuppress_warningsassert_array_compareassert_no_gc_cycles break_cycles IS_PYSTON)wasm32wasm64pypypyston_version_info getrefcountchd}|s |}t|y#t$r|}Yt|wxYw)aI Assert that works in release mode. Accepts callable msg to allow deferring evaluation until failure. The Python built-in ``assert`` does not work when executing code in optimized mode (the ``-O`` flag) - no byte-code is generated for it. For documentation on usage, refer to the Python documentation. TN) TypeErrorAssertionError)valmsg__tracebackhide__smsgs _/home/mcse/projects/flask/flask-venv/lib/python3.12/site-packages/torch/_numpy/testing/utils.pyrrEsL  5DT""  DT"" s  11c,tj|SN)npisnanxs r9gisnanr@Y 88A;c,tj|Sr;)r<isfiniter>s r9 gisfiniterE]s ;;q>rBc,tj|Sr;)r<isinfr>s r9gisinfrHarArBcdd|zg}|rL|jddk(r't|dt|z kr |ddz|zg}n|j||rt|D]\}}t |t rt j } nt} | |} | jdd kDr'dj| jdd } | d z } |jd||d | dj|S#t$r&} dt|jd| d} Yd} ~ d} ~ wwxYw) N Or z[repr failed for : ]z...: )findlenappend enumerate isinstancer__repr__repr Exceptiontype__name__countjoin splitlines) arrayserr_msgheaderrnames precisionr6iar_funcrexcs r9rres4 &=/C <<  #G rCK7G(Gq6C<')*C JJw f% ,DAq!W%!)) E1Iwwt}q IIallnRa01U  JJ58*Bqc* + , 99S>  E(a)9)9(:#cU!D EsD D/ D**D/c  d}t|du|dug}|dk(rtd|d||dk(ryt|tjst|tjr||k(}|std|d|yt|t rt|t r||k(sJyt|t rt|t sttt|tt|t||||jD]4}||vrtt|t||||d|d||6yt|ttfrjt|ttfrTtt|t|||tt|D]}t||||d |d||yd d lm}m} m} m} m} m} t|| s t|| rt-||||St/||g|| } | |xs| |}|rS| |r| |}||}n|}d }| |r| |}||}n|}d } t||t||| || |k7r t| t5|}t5|}|r|rytj6|}tj6|}|d k(r!|d k(r| || |k(s t| ||k(s t|y#t0t2f$rd }YwxYw#t$r t|wxYw#t2t0t8f$rYXwxYw#t:t<f$r"}d|j>d vr t|d}~wwxYw)a Raises an AssertionError if two objects are not equal. Given two objects (scalars, lists, tuples, dictionaries or numpy arrays), check that all elements of these objects are equal. An exception is raised at the first conflicting values. When one of `actual` and `desired` is a scalar and the other is array_like, the function checks that each element of the array_like object is equal to the scalar. This function handles NaN comparisons as if NaN was a "normal" number. That is, AssertionError is not raised if both objects have NaNs in the same positions. This is in contrast to the IEEE standard on NaNs, which says that NaN compared to anything must return False. Parameters ---------- actual : array_like The object to check. desired : array_like The expected object. err_msg : str, optional The error message to be printed in case of failure. verbose : bool, optional If True, the conflicting values are appended to the error message. Raises ------ AssertionError If actual and desired are not equal. Examples -------- >>> np.testing.assert_equal([4,5], [4,6]) Traceback (most recent call last): ... AssertionError: Items are not equal: item=1 ACTUAL: 5 DESIRED: 6 The following comparison does not raise an exception. There are NaNs in the inputs, but they are in the same positions. >>> np.testing.assert_equal(np.array([1.0, 2.0, np.nan]), [1, 2, np.nan]) TNz Not equal: z != zkey=rJzitem=r)imag iscomplexobjisscalarrrealsignbit)rFzelementwise == comparison) sumr4rUr<DTypestrdictrWrYrrRkeyslisttuplerange torch._numpyrkrlrmrrnrorr ValueErrorr3r@r NotImplementedErrorDeprecationWarning FutureWarningargs)actualdesiredr_rr7 num_nonesresultkrkrlrmrrnror6 usecomplexactualractualidesiredrdesirediisdesnanisactnan array_actual array_desiredes r9rrsdVt^W_56IA~{6($wi@AA a&"((#z'288'D7" ;vhd7)!DE E'3Jvs$;   '4 &$' d6l!34 4S[#g,A RA$T!W-- GAJ$qe2gY0G Q R 'D%=)j$.OS[#g,As7|$ SA GAJ%uBwi0H' R SQQ&'"j'&B!&'7GDD )7G DC !&)B\'-B   6lG6lGGG  G}HG}HHH & ( + ( + HV,,S!! '?&>  zz&)  7+ a>> np.testing.print_assert_equal('Test XYZ of func xyz', [0, 1], [0, 1]) # doctest: +SKIP >>> np.testing.print_assert_equal('Test XYZ of func xyz', [0, 1], [0, 2]) # doctest: +SKIP Traceback (most recent call last): ... AssertionError: Test XYZ of func xyz failed ACTUAL: [0, 1] DESIRED: [0, 2] TrNz failed ACTUAL: z DESIRED: )pprintrwriter4getvalue) test_stringr~rr7rr6s r9rr sw8 g j + '( fc" -  gs#S\\^,, rBc`d}ddlm}m}m}m}  |xs|} fd} | rW|r| } |} n} d} |r| }|}n}d} t | |t | |t|ttfst|ttfrtS tr tsSts tr'tr tst| yk(st| y t!z t#j$dd  zzk\rt| y#t $rd} YSwxYw#t$rt| wxYw#ttf$rY|wxYw) aV Raises an AssertionError if two items are not equal up to desired precision. .. note:: It is recommended to use one of `assert_allclose`, `assert_array_almost_equal_nulp` or `assert_array_max_ulp` instead of this function for more consistent floating point comparisons. The test verifies that the elements of `actual` and `desired` satisfy. ``abs(desired-actual) < float64(1.5 * 10**(-decimal))`` That is a looser test than originally documented, but agrees with what the actual implementation in `assert_array_almost_equal` did up to rounding vagaries. An exception is raised at conflicting values. For ndarrays this delegates to assert_array_almost_equal Parameters ---------- actual : array_like The object to check. desired : array_like The expected object. decimal : int, optional Desired precision, default is 7. err_msg : str, optional The error message to be printed in case of failure. verbose : bool, optional If True, the conflicting values are appended to the error message. Raises ------ AssertionError If actual and desired are not equal up to specified precision. See Also -------- assert_allclose: Compare two array_like objects for equality with desired relative and/or absolute precision. assert_array_almost_equal_nulp, assert_array_max_ulp, assert_equal Examples -------- >>> from torch._numpy.testing import assert_almost_equal >>> assert_almost_equal(2.3333333333333, 2.33333334) >>> assert_almost_equal(2.3333333333333, 2.33333334, decimal=10) Traceback (most recent call last): ... AssertionError: Arrays are not almost equal to 10 decimals ACTUAL: 2.3333333333333 DESIRED: 2.33333334 >>> assert_almost_equal(np.array([1.0,2.3333333333333]), ... np.array([1.0,2.33333334]), decimal=9) Traceback (most recent call last): ... AssertionError: Arrays are not almost equal to 9 decimals Mismatched elements: 1 / 2 (50%) Max absolute difference: 6.666699636781459e-09 Max relative difference: 2.8571569790287484e-09 x: torch.ndarray([1.0000, 2.3333], dtype=float64) y: torch.ndarray([1.0000, 2.3333], dtype=float64) Tr)rkrlrrnFc0dz}tg|S)N*Arrays are not almost equal to %d decimals)rr`)r)r`r~decimalrr_rs r9_build_err_msgz+assert_almost_equal.._build_err_msgs$=Gfg.QWXXrB)rN?$@)rxrkrlrrnryrr4rUrvrurrEr@rzr3absr<float64)r~rrr_rr7rkrlrrnrrrrrrs````` r9rrIsJ>> !&)B\'-B YY  6lG6lGGG  G}HG}HHH 3 7 C 7 C&7E401Z'5$'6)'7KK  '"y'8g&.wF6N()9:: &(()9:: (9 7V  37(1C+C DD^-..EY  . 3 !12 2 3&  +   s6E,-E>AFF, E;:E;>FF-,F-cd}ddl}tt||f\}}||k(ryd|j||j|zz}|jd|j |j |} ||z } ||z } t||g|d|z|} t|r t|sIt|s t|r"t|r t|s t| y||k(s t| y |j|| z |jd |d z k\r t| y#t$rd}YwxYw#t$rd} YwxYw#ttf$rYlwxYw) a Raises an AssertionError if two items are not equal up to significant digits. .. note:: It is recommended to use one of `assert_allclose`, `assert_array_almost_equal_nulp` or `assert_array_max_ulp` instead of this function for more consistent floating point comparisons. Given two numbers, check that they are approximately equal. Approximately equal is defined as the number of significant digits that agree. Parameters ---------- actual : scalar The object to check. desired : scalar The expected object. significant : int, optional Desired precision, default is 7. err_msg : str, optional The error message to be printed in case of failure. verbose : bool, optional If True, the conflicting values are appended to the error message. Raises ------ AssertionError If actual and desired are not equal up to specified precision. See Also -------- assert_allclose: Compare two array_like objects for equality with desired relative and/or absolute precision. assert_array_almost_equal_nulp, assert_array_max_ulp, assert_equal Examples -------- >>> np.testing.assert_approx_equal(0.12345677777777e-20, 0.1234567e-20) # doctest: +SKIP >>> np.testing.assert_approx_equal(0.12345670e-20, 0.12345671e-20, # doctest: +SKIP ... significant=8) >>> np.testing.assert_approx_equal(0.12345670e-20, 0.12345672e-20, # doctest: +SKIP ... significant=8) Traceback (most recent call last): ... AssertionError: Items are not equal to 8 significant digits: ACTUAL: 1.234567e-21 DESIRED: 1.2345672e-21 the evaluated condition that raises the exception is >>> abs(0.12345670e-20/1e-21 - 0.12345672e-20/1e-21) >= 10**-(8-1) True TrNg? gz-Items are not equal to %d significant digits:)r`rrri)numpymapfloatrpowerfloorlog10ZeroDivisionErrorrrEr@r4r3rz) r~r significantr_rr7r<scale sc_desired sc_actualr6s r9rrstEFG#45VW& 6266'?VRVVF^3 4E BHHR("((5/2 3Eu_ UN   >L  C  '"y'8g&.wF6N(-- &((-- (9rvvj9$%$+/8J)KKS!!L5    ( * +   s=>D7EA E,E7 EE EEE+*E+F)strictc  %&d} ddlm} m} m} m%m&m}m}| |}| |}d}||}}|df%fd } | r5|j|jk(xr|j|jk(}n;|jdk(xs|jdk(xs|j|jk(}|su|j|jk7rd|jd |jd }nd |jd |jd }t||g|zd  }t|%d}|r ||||d}|r$||||&fddz}||||&fddz}|jdkDr||||}}|jdk(ry|ry|||}t|tr |}| |g}n |j!}|j}|s|jt#|j%t&z }|jdk7r |jn |j}d|z|z }d|d|d|ddg}t)j*t,t.5t1||z }t3j4|jt2j6r&t1||z }t3j8|||||} |j;d|| j=z%|dk7}!| |!r | &}"n|||!t1||!z }"|j;d||"j=zdddddj?|zz t||gd  }t|y#1swY?xYw#t@$r;ddl!}#|#jE}$d|$d t||gd  }tA|wxYw)!NTr)allarrayr bool_infr=maxct|Sr;)rr)rds r9 array2stringz*assert_array_compare..array2string=s 1v rBnancXd}||}||}||k(jjdur%t||g d|dz d }t|t |t s|j dk(r|St |t s|j dk(r|S|S)zHandling nan/inf. Combine results of running func on x and y, checking that they are True at the same locations. Tz x and y z location mismatch:r?yrr`rarbr)ritemrr4rUboolndim) r?rfunchasvalr7x_idy_idr6rr_r`rbrs r9func_assert_same_posz2assert_array_compare..func_assert_same_posCs!AwAw DL    $ $ &d 2AJvh.ABB # C!% % dD !TYY!^;  d #tyyA~; KrBz (shapes z, z mismatch)z (dtypes rrF)rrc|k(Sr;rxyrs r9z&assert_array_compare.. bSDjrBz+infc| k(Sr;rrs r9rz&assert_array_compare..rrBz-infdtypedzMismatched elements: z / z (z.3gz%))outzMax absolute difference: zMax relative difference: rJzerror during assertion: z )#rxrrr rrr=rshaperrr4rsizerUrravelintrpr contextlibsuppressr3 RuntimeErrorrr< issubdtypeunsignedintegerminimumrSrr\ry traceback format_exc)' comparisonr?rr_rr`rb equal_nan equal_infrr7rrr r=rroxoyrcondreasonr6flaggedr5reduced n_mismatch n_elementspercent_mismatchremarkserrorerror2 max_abs_errornonzero max_rel_errorrefmtrrs' ```` @@r9r)r)*sHHH A AB(-e&&Po 77agg%>> np.testing.assert_array_equal([1.0,2.33333,np.nan], ... [np.exp(0),2.33333, np.nan]) Use `assert_allclose` or one of the nulp (number of floating point values) functions for these cases instead: >>> np.testing.assert_allclose([1.0,np.pi,np.nan], ... [1, np.sqrt(np.pi)**2, np.nan], ... rtol=1e-10, atol=0) As mentioned in the Notes section, `assert_array_equal` has special handling for scalars. Here the test checks that each value in `x` is 3: >>> x = np.full((2, 5), fill_value=3) >>> np.testing.assert_array_equal(x, 3) Use `strict` to raise an AssertionError when comparing a scalar with an array: >>> np.testing.assert_array_equal(x, 3, strict=True) Traceback (most recent call last): ... AssertionError: Arrays are not equal (shapes (2, 5), () mismatch) x: torch.ndarray([[3, 3, 3, 3, 3], [3, 3, 3, 3, 3]]) y: torch.ndarray(3) The `strict` parameter also ensures that the array data types match: >>> x = np.array([2, 2, 2]) >>> y = np.array([2., 2., 2.], dtype=np.float32) >>> np.testing.assert_array_equal(x, y, strict=True) Traceback (most recent call last): ... AssertionError: Arrays are not equal (dtypes dtype("int64"), dtype("float32") mismatch) x: torch.ndarray([2, 2, 2]) y: torch.ndarray([2., 2., 2.]) TzArrays are not equal)r_rr`rN)r)operator__eq__)r?rr_rrr7s r9rrs,|  %rBc n d}ddlm mmm m  fd}t |||||dzy)a Raises an AssertionError if two objects are not equal up to desired precision. .. note:: It is recommended to use one of `assert_allclose`, `assert_array_almost_equal_nulp` or `assert_array_max_ulp` instead of this function for more consistent floating point comparisons. The test verifies identical shapes and that the elements of ``actual`` and ``desired`` satisfy. ``abs(desired-actual) < 1.5 * 10**(-decimal)`` That is a looser test than originally documented, but agrees with what the actual implementation did up to rounding vagaries. An exception is raised at shape mismatch or conflicting values. In contrast to the standard usage in numpy, NaNs are compared like numbers, no assertion is raised if both objects have NaNs in the same positions. Parameters ---------- x : array_like The actual object to check. y : array_like The desired, expected object. decimal : int, optional Desired precision, default is 6. err_msg : str, optional The error message to be printed in case of failure. verbose : bool, optional If True, the conflicting values are appended to the error message. Raises ------ AssertionError If actual and desired are not equal up to specified precision. See Also -------- assert_allclose: Compare two array_like objects for equality with desired relative and/or absolute precision. assert_array_almost_equal_nulp, assert_array_max_ulp, assert_equal Examples -------- the first assert does not raise an exception >>> np.testing.assert_array_almost_equal([1.0,2.333,np.nan], ... [1.0,2.333,np.nan]) >>> np.testing.assert_array_almost_equal([1.0,2.33333,np.nan], ... [1.0,2.33339,np.nan], decimal=5) Traceback (most recent call last): ... AssertionError: Arrays are not almost equal to 5 decimals Mismatched elements: 1 / 3 (33.3%) Max absolute difference: 5.999999999994898e-05 Max relative difference: 2.5713661239633743e-05 x: torch.ndarray([1.0000, 2.3333, nan], dtype=float64) y: torch.ndarray([1.0000, 2.3334, nan], dtype=float64) >>> np.testing.assert_array_almost_equal([1.0,2.33333,np.nan], ... [1.0,2.33333, 5], decimal=5) Traceback (most recent call last): ... AssertionError: Arrays are not almost equal to 5 decimals x and y nan location mismatch: x: torch.ndarray([1.0000, 2.3333, nan], dtype=float64) y: torch.ndarray([1.0000, 2.3333, 5.0000], dtype=float64) Tr)anyfloat_rnumber result_typec  t|s t|r]t|}t|}||k(jsy|j|jcxk(rdk(rnn||k(S||}||} |d}t ||}t ||z }|j s|j}|dd zzkS#ttf$rYdwxYw)NFrig?rr) rHrrr3rz asanyarrayrrastype) r?rxinfidyinfidrzrrrnpanyrrs r9comparez*assert_array_almost_equal..compares VAY5#3&(--/ 66QVV(q(6MvgJvgJ As# q%  AJ!''6* A37(++++./   sA C&C6 CC'&C'r)r_rr`rbN)rxrrrrrr)) r?rrr_rr7rrrrrrs ` @@@@@r9rrGs@ZRR,,4  >> np.testing.assert_array_less([1.0, 1.0, np.nan], [1.1, 2.0, np.nan]) >>> np.testing.assert_array_less([1.0, 1.0, np.nan], [1, 2.0, np.nan]) Traceback (most recent call last): ... AssertionError: Arrays are not less-ordered Mismatched elements: 1 / 3 (33.3%) Max absolute difference: 1.0 Max relative difference: 0.5 x: torch.ndarray([1., 1., nan], dtype=float64) y: torch.ndarray([1., 2., nan], dtype=float64) >>> np.testing.assert_array_less([1.0, 4.0], 3) Traceback (most recent call last): ... AssertionError: Arrays are not less-ordered Mismatched elements: 1 / 2 (50%) Max absolute difference: 2.0 Max relative difference: 0.6666666666666666 x: torch.ndarray([1., 4.], dtype=float64) y: torch.ndarray(3) >>> np.testing.assert_array_less([1.0, 2.0, 3.0], [4]) Traceback (most recent call last): ... AssertionError: Arrays are not less-ordered (shapes (3,), (1,) mismatch) x: torch.ndarray([1., 2., 3.], dtype=float64) y: torch.ndarray([4]) TzArrays are not less-orderedF)r_rr`rN)r)r__lt__)r?rr_rr7s r9rrs,X  ,rBc,d}ddl}t|tstt t |t|tstt t |||k(ryt |jj|jd|jd}g}|r-|jd}|jdr&|jdr|g}|jd}|jdr"|j||jd}|jdstt ||j||rF|jd} | jdr|j| n|jd| |dd|ddk(r |j|tt ||syd d j|j!} ||k7r t| y) a Test if two strings are equal. If the given strings are equal, `assert_string_equal` does nothing. If they are not equal, an AssertionError is raised, and the diff between the strings is shown. Parameters ---------- actual : str The string to test for equality against the expected string. desired : str The expected string. Examples -------- >>> np.testing.assert_string_equal('abc', 'abc') # doctest: +SKIP >>> np.testing.assert_string_equal('abc', 'abcd') # doctest: +SKIP Traceback (most recent call last): File "", line 1, in ... AssertionError: Differences in strings: - abc+ abcd? + TrNz z- z? z+ rjzDifferences in strings: )difflibrUrrr4rWrYruDifferrr]pop startswithrSinsertextendr\rstrip) r~rr7rdiff diff_listd1ld2d3r6s r9rrs6 fc "T$v,/00 gs #T$w-011&   !2!24!8':L:LT:RS DI  XXa[ ==   == A!B}}T" XXa[==&$T"X.. HHRLXXa[==&HHRLKK2&!"vAB   Q  T"X&&  %bggi&8&?&?&A%B CC S!!rBceZdZdZy)_Dummycyr;r)selfs r9nopz _Dummy.nop`s rBN)rZ __module__ __qualname__r rrBr9r r _s rBr r c:d}tj||g|i|S)a assert_raises_regex(exception_class, expected_regexp, callable, *args, **kwargs) assert_raises_regex(exception_class, expected_regexp) Fail unless an exception of class exception_class and with message that matches expected_regexp is thrown by callable when invoked with arguments args and keyword arguments kwargs. Alternatively, can be used as a context manager like `assert_raises`. Notes ----- .. versionadded:: 1.9.0 T)_dassertRaisesRegex)exception_classexpected_regexpr}kwargsr7s r9rrgs'"   R4 R6 RRrBc|(tjdtjd}ntj|}|j}ddlm}|jDcgc] }||s |}}|D]_} t|dr |j}n |j}|j|s;|jdrMt||||aycc}w#t$rYswxYw)a  Apply a decorator to all methods in a class matching a regular expression. The given decorator is applied to all public methods of `cls` that are matched by the regular expression `testmatch` (``testmatch.search(methodname)``). Methods that are private, i.e. start with an underscore, are ignored. Parameters ---------- cls : class Class whose methods to decorate. decorator : function Decorator to apply to methods testmatch : compiled regexp or str, optional The regular expression. Default value is None, in which case the nose default (``re.compile(r'(?:^|[\b_\.%s-])[Tt]est' % os.sep)``) is used. If `testmatch` is a string, it is compiled to a regular expression first. Nz (?:^|[\\b_\\.z -])[Tt]estr) isfunctioncompat_func_name_)recompileossep__dict__inspectrvalueshasattrrrZAttributeErrorsearchrsetattr) cls decorator testmatchcls_attrr_mmethodsfunctionfuncnames r9rr|s.JJ-xzBC JJy) ||H#$OO-@bBr@G@ 8 x!34#44#,,   H %h.A.A#.F C9X#6 7 8 A   s$ C2C>%C"" C.-C.ctsyddl}ddl}|jdj dd}|}d}|j  t j|}tdD] }|||} tt j||k\|j~y#|jwxYw)zg Check that ufuncs don't mishandle refcount of object `1`. Used in a few regression tests. TrNi'rri) r&gcrr reshapedisablesysr1rwrenable) opr/r<bcrcrcjds r9_assert_valid_refcountr:s   )$$S#.A A ABJJL __Q r A1aA "b()    s AB**B=c d}fd} t|t|}}dddd} |r|j|jk(sJt| ||t||| y)a Raises an AssertionError if two objects are not equal up to desired tolerance. Given two array_like objects, check that their shapes and all elements are equal (but see the Notes for the special handling of a scalar). An exception is raised if the shapes mismatch or any values conflict. In contrast to the standard usage in numpy, NaNs are compared like numbers, no assertion is raised if both objects have NaNs in the same positions. The test is equivalent to ``allclose(actual, desired, rtol, atol)`` (note that ``allclose`` has different default values). It compares the difference between `actual` and `desired` to ``atol + rtol * abs(desired)``. .. versionadded:: 1.5.0 Parameters ---------- actual : array_like Array obtained. desired : array_like Array desired. rtol : float, optional Relative tolerance. atol : float, optional Absolute tolerance. equal_nan : bool, optional. If True, NaNs will compare equal. err_msg : str, optional The error message to be printed in case of failure. verbose : bool, optional If True, the conflicting values are appended to the error message. Raises ------ AssertionError If actual and desired are not equal up to specified precision. See Also -------- assert_array_almost_equal_nulp, assert_array_max_ulp Notes ----- When one of `actual` and `desired` is a scalar and the other is array_like, the function checks that each element of the array_like object is equal to the scalar. Examples -------- >>> x = [1e-5, 1e-3, 1e-1] >>> y = np.arccos(np.cos(x)) >>> np.testing.assert_allclose(x, y, rtol=1e-5, atol=0) Tc8tj||S)N)rtolatolr)r<isclose)r?rr>rr=s r9rz assert_allclose..compare szz!QT JJrBzNot equal to tolerance rtol=gz, atol=)r_rr`rN)rrr)rr) r~rr=r>rr_r check_dtyper7rr`s ``` r9r r swBK!(*W*=GF+D874( CF||w}},,,G rBcd}ddl}|j|}|j|}||j|j||kD||z}|j|j||z |ksb|j |s|j |rd|z}t||j t||} d|| fz}t|y)a Compare two arrays relatively to their spacing. This is a relatively robust method to compare two arrays whose amplitude is variable. Parameters ---------- x, y : array_like Input arrays. nulp : int, optional The maximum number of unit in the last place for tolerance (see Notes). Default is 1. Returns ------- None Raises ------ AssertionError If the spacing between `x` and `y` for one or more elements is larger than `nulp`. See Also -------- assert_array_max_ulp : Check that all items of arrays differ in at most N Units in the Last Place. spacing : Return the distance between x and the nearest adjacent number. Notes ----- An assertion is raised if the following condition is not met:: abs(x - y) <= nulp * spacing(maximum(abs(x), abs(y))) Examples -------- >>> x = np.array([1., 1e-10, 1e-20]) >>> eps = np.finfo(x.dtype).eps >>> np.testing.assert_array_almost_equal_nulp(x, x*eps/2 + x) # doctest: +SKIP >>> np.testing.assert_array_almost_equal_nulp(x, x*eps + x) # doctest: +SKIP Traceback (most recent call last): ... AssertionError: X and Y are not equal to 1 ULP (max is 2) TrNzX and Y are not equal to %d ULPz+X and Y are not equal to %d ULP (max is %g)) rrspacingwhererrlr nulp_diffr4) r?rnulpr7r<axayrefr6max_nulps r9rrsb B B HBHHR"Wb"56 6C 266&"&&Q-3& ' 2??1 !33d:CS!!rvvi1o.H?4BRRCS!! (rBcd}ddl}t|||}|j||ks$td|dd|j|dd|S)a{ Check that all items of arrays differ in at most N Units in the Last Place. Parameters ---------- a, b : array_like Input arrays to be compared. maxulp : int, optional The maximum number of units in the last place that elements of `a` and `b` can differ. Default is 1. dtype : dtype, optional Data-type to convert `a` and `b` to if given. Default is None. Returns ------- ret : ndarray Array containing number of representable floating point numbers between items in `a` and `b`. Raises ------ AssertionError If one or more elements differ by more than `maxulp`. Notes ----- For computing the ULP difference, this API does not differentiate between various representations of NAN (ULP difference between 0x7fc00000 and 0xffc00000 is zero). See Also -------- assert_array_almost_equal_nulp : Compare two arrays relatively to their spacing. Examples -------- >>> a = np.linspace(0., 1., 100) >>> res = np.testing.assert_array_max_ulp(a, np.arcsin(np.sin(a))) # doctest: +SKIP TrNz"Arrays are not almost equal up to r@z ULP (max difference is z ULP))rrErr4r)rdr5maxulprr7r<rets r9rr]shT Aq% C 266#- 0 ;&&,bffSk!_E ;   JrBcddl|r)j||}j||}n$j|}j|}j||}j|sj|r t dj |g|}j |g|}j |j|<j |j|<|j|jk(s%td|jd|jfd}t|}t|}||||S)aFor each item in x and y, return the number of representable floating points between them. Parameters ---------- x : array_like first input array y : array_like second input array dtype : dtype, optional Data-type to convert `x` and `y` to if given. Default is None. Returns ------- nulp : array_like number of representable floating point numbers between each item in x and y. Notes ----- For computing the ULP difference, this API does not differentiate between various representations of NAN (ULP difference between 0x7fc00000 and 0xffc00000 is zero). Examples -------- # By definition, epsilon is the smallest number such as 1 + eps != 1, so # there should be exactly one ULP between 1 and 1 + eps >>> nulp_diff(1, 1 + np.finfo(x.dtype).eps) # doctest: +SKIP 1.0 rNrz'_nulp not implemented for complex arrayz$x and y do not have the same shape: z - cVj||z |}j|SNr)r r)rxryvdtrr<s r9_diffznulp_diff.._diffs)rzz"r'-rvvd|rB) rr common_typerlrzrrr=rry integer_repr)r?rrtrTrQrRr<s @r9rErEs6@ BJJq & BJJq & BJJqM BJJqMq!Arq_R__Q/!"KLL!AA!AAVVAhbhhqkNVVAhbhhqkN 77agg ?yAGG9UVV aB aB R rBc|j|}|jdk(s|||dkz ||dk<|S|dkr||z }|S)Nrir)viewr)r?rScomprQs r9 _integer_reprr[sT B GGqLBrAvJ&26 I 6B IrBcddl}|j|jk(r't||j|jdS|j|j k(r't||j |j dS|j|jk(r't||j|jdStd|j)zQReturn the signed-magnitude interpretation of the binary representation of x.rNiilzUnsupported dtype ) rrfloat16r[int16r int32rint64ry)r?r<s r9rVrVsww"**Q("((8*<== BJJ Q("((8*<== BJJ Q("((8*<==-aggY788rBc#Kd}t5}|j|}dt|dkDs|d|nd}td|z dddy#1swYyxYww)NTr when calling rzNo warning raised)r(recordrRr4) warning_classnamer7suprname_strs r9_assert_warns_contextrhsq  A JJ} % 1vz262Bv.H !4x!?@ @AAAs A ;A A AA c|s t|S|d}|dd}t||j5||i|cdddS#1swYyxYw)a+ Fail unless the given callable throws the specified warning. A warning of class warning_class should be thrown by the callable when invoked with arguments args and keyword arguments kwargs. If a different type of warning is thrown, it will not be caught. If called with all arguments other than the warning class omitted, may be used as a context manager: with assert_warns(SomeWarning): do_something() The ability to be used as a context manager is new in NumPy v1.11.0. .. versionadded:: 1.4.0 Parameters ---------- warning_class : class The class defining the warning that `func` is expected to throw. func : callable, optional Callable to test *args : Arguments Arguments for `func`. **kwargs : Kwargs Keyword arguments for `func`. Returns ------- The value returned by `func`. Examples -------- >>> import warnings >>> def deprecated_func(num): ... warnings.warn("Please upgrade", DeprecationWarning) ... return num*num >>> with np.testing.assert_warns(DeprecationWarning): ... assert deprecated_func(4) == 16 >>> # or passing a func >>> ret = np.testing.assert_warns(DeprecationWarning, deprecated_func, 4) >>> assert ret == 16 rriNre)rhrZ)rdr}rrs r9rrsWZ $]33 7D 8D }4== A%T$V$%%%s AA c#Kd}tjd5}tjddt|dkDr|d|nd}t d|d| dddy#1swYyxYww) NTrcalwaysrrbrz Got warningsrP)warningscatch_warnings simplefilterrRr4)rer7rrgs r9_assert_no_warnings_contextrq1s   -Ah' q6A:262Bv.H <zA3!?@ @ AAAsA3AA' A3'A0,A3c|s tS|d}|dd}t|j5||i|cdddS#1swYyxYw)a: Fail if the given callable produces any warnings. If called with all arguments omitted, may be used as a context manager: with assert_no_warnings(): do_something() The ability to be used as a context manager is new in NumPy v1.11.0. .. versionadded:: 1.7.0 Parameters ---------- func : callable The callable to test. \*args : Arguments Arguments passed to `func`. \*\*kwargs : Kwargs Keyword arguments passed to `func`. Returns ------- The value returned by `func`. rriNrj)rqrZr}rrs r9rr<sR6 *,, 7D 8D $$-- 8%T$V$%%%s ?Abinaryc #& Kd}d}tdD]w t dzt dz|D]T |dk(r̈ fd}t f d}||| d fzf|}||| d fzf|d d|dd | d z d z d fzf|dd |d d| d z d z d fzf|dd |d d| d z d z d fzf|d d|dd | d z d z d fzf|dk(sۈ fd}|} t f d}||| | d fzf|}||| | dfzf| }|||| dfzf|d d|dd | dd | d z d z d fzf|dd |d d| dd | d z d z d fzf|dd |dd | d d| d z d z d fzf|d d|dd | dd | d z d z d fzf|dd |d d| dd | d z d z d fzf|dd |dd | d d| d z d z d fzfWzyw)a generator producing data with different alignment and offsets to test simd vectorization Parameters ---------- dtype : dtype data type to produce type : string 'unary': create data for unary operations, creates one input and output array 'binary': create data for unary operations, creates two input and output array max_size : integer maximum size of data to produce Returns ------- if type is 'unary' yields one output, one input array and a message containing information on the data if type is 'binary' yields one output array, two input array and a message containing information on the data z,unary offset=(%d, %d), size=%d, dtype=%r, %sz1binary offset=(%d, %d, %d), size=%d, dtype=%r, %srOrjunaryc$tdSrPr rossr9inpz _gen_alignment_data..inp!!51!"55rBrNz out of placezin placerirKaliasedrtc$tdSrPryrzsr9inp1z!_gen_alignment_data..inp1r~rBz in place1z in place2)rwrr ) rrYmax_sizeufmtbfmtr}rr9rinp2r{r|s ` @@r9_gen_alignment_datar`s*2 :D >D 1XVq1uc!a%23U Aw6QD.qr235$!Q5.)I"IIIEDAq!UJ#????!"gsuSbz4EE" 3,#2hab 4EE" 3,eCRj#%)TQAq1ueY4W-WWWeABisTQUAq1ueY4W-WWWx6QD.qr2464641aAun2U+UUUFDFDAq!Q{+K$KKKFDAq!Q{+K$KKK!"gtvcr{DF3BKEE" A:#2hqr DF3BKEE" A:#2hs TVABZEE" A:fQRj$&"+tvcr{DEE D=fSbk46!":tvcr{DEE D=fSbk46#2;qr DEE D=]U Vs D JFJceZdZdZy)r!z/Ignoring this exception due to disabled featureN)rZrr__doc__rrBr9r!r!s5rBr!c/Kt|i|} |tj|y#tj|wxYww)zContext manager to provide a temporary test folder. All arguments are passed as this to the underlying tempfile.mkdtemp function. N)rshutilrmtree)r}rtmpdirs r9r$r$s9d %f %F  f fs A)AAAc/Kt|i|\}}tj| |tj|y#tj|wxYww)aContext manager for temporary files. Context manager that returns the path to a closed temporary file. Its parameters are the same as for tempfile.mkstemp and are passed directly to that function. The underlying file is removed when the context is exited, so it should be closed at that time. Windows does not allow a temporary file to be opened if it is already open, so the underlying file must be closed after opening before it can be opened again. N)rrcloseremove)r}rfdpaths r9r#r#sF''HBHHRL  $ $s$AAAAAc<eZdZdZdZdfd ZfdZfdZxZS)r"aMContext manager that resets warning registry for catching warnings Warnings can be slippery, because, whenever a warning is triggered, Python adds a ``__warningregistry__`` member to the *calling* module. This makes it impossible to retrigger the warning in this module, whatever you put in the warnings filters. This context manager accepts a sequence of `modules` as a keyword argument to its constructor and: * stores and removes any ``__warningregistry__`` entries in given `modules` on entry; * resets ``__warningregistry__`` to its previous state on exit. This makes it possible to trigger any warning afresh inside the context manager without disturbing the state of warnings outside. For compatibility with Python 3.0, please consider all arguments to be keyword-only. Parameters ---------- record : bool, optional Specifies whether warnings should be captured by a custom implementation of ``warnings.showwarning()`` and be appended to a list returned by the context manager. Otherwise None is returned by the context manager. The objects appended to the list are arguments whose attributes mirror the arguments to ``showwarning()``. modules : sequence, optional Sequence of modules for which to reset warnings registry on entry and restore on exit. To work correctly, all 'ignore' filters should filter by one of these modules. Examples -------- >>> import warnings >>> with np.testing.clear_and_catch_warnings( # doctest: +SKIP ... modules=[np.core.fromnumeric]): ... warnings.simplefilter('always') ... warnings.filterwarnings('ignore', module='np.core.fromnumeric') ... # do something that raises a warning but ignore those in ... # np.core.fromnumeric rct|j|j|_i|_t ||y)Nrl)setunion class_modulesmodules_warnreg_copiessuper__init__)r rcr __class__s r9rz!clear_and_catch_warnings.__init__*s77|))$*<*<= ! 'rBc|jD]H}t|ds|j}|j|j|<|j Jt |SN__warningregistry__)rr!rcopyrclearr __enter__)r modmod_regrs r9rz"clear_and_catch_warnings.__enter__/s[<< Cs1211,3LLN$$S)   w ""rBct|||jD]_}t|dr|jj ||j vs8|jj|j |ayr)r__exit__rr!rrrupdate)r exc_inforrs r9rz!clear_and_catch_warnings.__exit__7so (#<< JCs12''--/d***''..t/C/CC/HI  JrB)Fr) rZrrrrrrr __classcell__)rs@r9r"r"s&(TM( #JJrBr"cheZdZdZddZdZedddfdZeddfdZeddfd Z d Z d Z dd d Z dZ y)r(a Context manager and decorator doing much the same as ``warnings.catch_warnings``. However, it also provides a filter mechanism to work around https://bugs.python.org/issue4180. This bug causes Python before 3.4 to not reliably show warnings again after they have been ignored once (even within catch_warnings). It means that no "ignore" filter can be used easily, since following tests might need to see the warning. Additionally it allows easier specificity for testing warnings and can be nested. Parameters ---------- forwarding_rule : str, optional One of "always", "once", "module", or "location". Analogous to the usual warnings module filter mode, it is useful to reduce noise mostly on the outmost level. Unsuppressed and unrecorded warnings will be forwarded based on this rule. Defaults to "always". "location" is equivalent to the warnings "default", match by exact location the warning warning originated from. Notes ----- Filters added inside the context manager will be discarded again when leaving it. Upon entering all filters defined outside a context will be applied automatically. When a recording filter is added, matching warnings are stored in the ``log`` attribute as well as in the list returned by ``record``. If filters are added and the ``module`` keyword is given, the warning registry of this module will additionally be cleared when applying it, entering the context, or exiting it. This could cause warnings to appear a second time after leaving the context if they were configured to be printed once (default) and were already printed before the context was entered. Nesting this context manager will work as expected when the forwarding rule is "always" (default). Unfiltered and unrecorded warnings will be passed out and be matched by the outer level. On the outmost level they will be printed (or caught by another warnings context). The forwarding rule argument can modify this behaviour. Like ``catch_warnings`` this context manager is not threadsafe. Examples -------- With a context manager:: with np.testing.suppress_warnings() as sup: sup.filter(DeprecationWarning, "Some text") sup.filter(module=np.ma.core) log = sup.record(FutureWarning, "Does this occur?") command_giving_warnings() # The FutureWarning was given once, the filtered warnings were # ignored. All other warnings abide outside settings (may be # printed/error) assert_(len(log) == 1) assert_(len(sup.log) == 1) # also stored in log attribute Or as a decorator:: sup = np.testing.suppress_warnings() sup.filter(module=np.ma.core) # module must match exactly @sup def some_function(): # do something which causes a warning in np.ma.core pass cLd|_g|_|dvr td||_y)NF>oncermmodulelocationzunsupported forwarding rule.)_entered _suppressionsry_forwarding_rule)r forwarding_rules r9rzsuppress_warnings.__init__s0   "J J;< < /rBcttdrtjy|jD])}t|ds|jj +y)N_filters_mutatedr)r!rnr _tmp_modulesrr)r rs r9_clear_registriesz#suppress_warnings._clear_registriessR 8/ 0  % % ' '' 3Fv45**002 3rBrNFc4|rg}nd}|jr|tjd||nc|jj dddz}tjd||||j j ||j|jj||tj|tj||f|S|jj||tj|tj||f|S)Nrmcategorymessage.\.$rrr)rrnfilterwarningsrZreplaceraddr_tmp_suppressionsrSrr IGNORECASEr)r rrrrc module_regexs r9_filterzsuppress_warnings._filters FF ==~''8WU%66sEBSH ''x!!%%f-&&(  " " ) )7BJJw $FPVW     % %7BJJw $FPVW  rBc.|j|||dy)a Add a new suppressing filter or apply it if the state is entered. Parameters ---------- category : class, optional Warning class to filter message : string, optional Regular expression matching the warning message. module : module, optional Module to filter for. Note that the module (and its file) must match exactly and cannot be a submodule. This may make it unreliable for external modules. Notes ----- When added within a context, filters are only added inside the context and will be forgotten when the context is exited. FrrrrcNrr rrrs r9filterzsuppress_warnings.filters( hu UrBc,|j|||dS)ai Append a new recording filter or apply it if the state is entered. All warnings matching will be appended to the ``log`` attribute. Parameters ---------- category : class, optional Warning class to filter message : string, optional Regular expression matching the warning message. module : module, optional Module to filter for. Note that the module (and its file) must match exactly and cannot be a submodule. This may make it unreliable for external modules. Returns ------- log : list A list which will be filled with all matched warnings. Notes ----- When added within a context, filters are only added inside the context and will be forgotten when the context is exited. Trrrs r9rczsuppress_warnings.records#6||wvd  rBc|jr tdtj|_tj |_|j ddt_d|_g|_t|_ t|_ g|_ |jD]}\}}}}}||dd=|tjd||+|jjdddz}tjd||||jj!||j"t_|j%|S) Nz%cannot enter suppress_warnings twice.Trmrrrrr)rrrn showwarning _orig_showfilters_filtersrrr _forwardedlogrrrZrr _showwarningr)r catmessrrrrs r9rzsuppress_warnings.__enter__s ==FG G".. (( ==+ !#E%&*&8&8 + "Cq#sF{''3M"||33C?#E ''sD!!%%c* + $00   rBc|jt_|jt_|j d|_|`|`y)NF)rrnrrrrr)r rs r9rzsuppress_warnings.__exit__s7#==   O MrB) use_warnmsgc|j|jzdddD]\}} } } } t||s| j|jd5| ?| ;t ||||fi|} |j j| | j| y| jj|s| ;t ||||fi|} |j j| | j| y|jdk(r.||j||||g|i|y|j|y|jdk(r|j|f}n>|jdk(r|j||f}n|jdk(r|j|||f}|jvry|jj|||j||||g|i|y|j|y)NrKrrmrrr)rr issubclassmatchr}rrrS__file__rrr _orig_showmsgrr)r rrfilenamelinenorr}rrrpatternrrecr6 signatures r9rzsuppress_warnings._showwarnings+/*<*.new_funcQs( -T,V, - - -sr)r rrs`` r9__call__zsuppress_warnings.__call__Ks" t -  -rB)rm)rZrrrrrWarningrrrcrrrrrrBr9r(r(@s\HT0 3 '44&r$V,&r$ >>GK2,h rBr(c #>Kd}tsdyttjtjtj } t dD]}tjdk(sn tdtjtjdtj}tjdd}tjdd=tj|tj|rE|d|nd}tdj||t|dj!d|Dy#tjdd=tj|tjwxYww) NTrrz]Unable to fully collect garbage - perhaps a __del__ method is creating more reference cycles?rbrzXReference cycles were found{}: {} objects were collected, of which {} are shown below:{}c 3K|]V}djt|jt|t j |j ddXyw)z {} object with id={}: {}rJz N)formatrYrZidrpformatr).0r{s r9 z/_assert_no_gc_cycles_context..sR  8>>Q((1q)11$AsAA)r&rr/ isenabledr1 get_debugrwcollectr set_debug DEBUG_SAVEALLgarbager3r4rrRr\)rer7gc_debugrcn_objects_in_cyclesobjects_in_cyclesrgs r9_assert_no_gc_cycles_contextrYsM   BLLNJJL||~Hs Azz|q  5  R%%& !jjlJJqM JJqM X .2.>^D6*B --3V#%& /  .   JJqM X s&AF%EFFc|s tS|d}|dd}t|j5||i|dddy#1swYyxYw)a3 Fail if the given callable produces any reference cycles. If called with all arguments omitted, may be used as a context manager: with assert_no_gc_cycles(): do_something() .. versionadded:: 1.15.0 Parameters ---------- func : callable The callable to test. \*args : Arguments Arguments passed to `func`. \*\*kwargs : Kwargs Keyword arguments passed to `func`. Returns ------- Nothing. The result is deliberately discarded to ensure that all cycles are found. rriNrj)rrZrss r9r*r*sR4 +-- 7D 8D %4== 9 dfs ?ActjtrQtjtjtjtjyy)a1 Break reference cycles by calling gc.collect Objects can call other objects' methods (for instance, another object's __del__) inside their own __del__. On PyPy, the interpreter only runs between calls to gc.collect, so multiple calls are needed to completely release all cycles. N)r/rr%rrBr9r+r+s9JJL    rBcddlfd}|S)z:Decorator to skip a test if not enough memory is availablerNc4tfd}|S)Nct}|j| |i|S#t$rjdYywxYw)NzMemoryError raised)check_free_memoryskip MemoryErrorxfail)rdkwr6 free_bytesrpytests r9wrapperz3requires_memory..decorator..wrappersM#J/C C  3Q~"~% 3 12 3s)AAr)rrrrs` r9r&z"requires_memory..decorators t 3  3rB)r)rr&rs` @r9requires_memoryrs  rBc d}tjj|}| t|}|dz d|d}nt }|d}d }n|dz d |dz d }||kr|SdS#t$r}t d|d|d}~wwxYw) z Check whether `free_bytes` amount of memory is currently free. Returns: None if enough memory available, otherwise error message NPY_AVAILABLE_MEMNzInvalid environment variable rPgeAz@ GB memory required, but environment variable NPY_AVAILABLE_MEM=z setzCould not determine available memory; set NPY_AVAILABLE_MEM environment variable (e.g. NPY_AVAILABLE_MEM=16GB) to run the test.rKz GB memory required, but z GB available)renvironget _parse_sizery_get_mem_available)renv_var env_valuemem_freergr6s r9rrs "G w'I "9-H#~!!* 4 1 &'    Hc>"";HSL>W Z'31T11 /y3%@  s A$$ B-A>>Bcdddddddddddddd d }tjd jd j|j tj }|j |j}|r|jd |vrtd|dtt|jd||jd zS)z3Convert memory size strings ('12 GB' etc.) to floatriii@Biʚ;lJ)ii@l)rr5rmr@rWkbmbgbtbkibmibgibtibz^\s*(\d+|\d+\.\d+)\s*({})\s*$|rjzvalue z not a valid size) rrrr\rtrrlowergroupryrr)size_strsuffixessize_rers r9r r s      H"jj(//0IJ G  hnn&'A  (*6(->?@@ uQWWQZ 8AGGAJ#77 88rBc ddl}|jjS#ttf$rYnwxYwt j jdri}td5}|D]F}|j}t|ddz||djdj<H dddn #1swYnxYwd|vr|dS|d |d zSy) z5Return available memory in bytes, or None if unknown.rNlinuxz /proc/meminforir: memavailablememfreecached) psutilvirtual_memory available ImportErrorr"r2platformropensplitrstripr)r%infoflineps r9r r  s $$&000  (    ||w' / " Aa AJJL03AaD D0@QqTZZ_**,- A A A A T !' ' ?T(^3 3 s 22!A B77CcRttdsStfd}|S)z Decorator to temporarily turn off tracing for the duration of a test. Needed in tests that check refcounting, otherwise the tracing itself influences the refcounts gettracectj} tjd|i|tj|S#tj|wxYwr;)r2r2settrace)r}roriginal_tracers r9rz_no_tracing..wrapper? sE \\^N - T"T,V, ^, ^,s A A )r!r2r)rrs` r9 _no_tracingr65 s3 3 #  t -  -rBc tjdjdd}|S#t$r }d}Yd}~|Sd}~wwxYw)NCS_GNU_LIBC_VERSIONrMri0.0)rconfstrrsplitrX)verinsts r9_get_glibc_versionr>K sIjj./66s;A> J  Js'+ A<Ac*tdk7xr t|kS)Nr9) _glibcverr>s r9_glibc_older_thanrAW s   /)a-/rB)r)zItems are not equal:T)ACTUALDESIRED)rT)rT)rTrTT)rFrTr;)gHz>rTrTF)ri)riN)[rrr/rrr)rrrr2rn functoolsriortempfilerrrrx_numpyr<r r rr r r r__all__rmachiner'implementationrer%r!r,getattrr&rr@rErHrrrrrr)rrrrunittestTestCaser rrrr:r rrrEr[rVcontextmanagerrhrrqrrrXr!r$r#ror"r(rr*r+rrr r r6r>r@rArrBr9rRs   %#UU F  (    4 4   ! !V + C. / sM40<NY #( "   DVr&-Rz/za"P   p pfggTrjUpE"P X    E]S*, ^ <    Tn="@3l<~  9 AA3%l AA!%H&Hrqh6i6    *@Jx66@JFVVr 1 1 h F$,"2J9<2,  0rB