datapruning 1.0.2__tar.gz → 1.0.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {datapruning-1.0.2/datapruning.egg-info → datapruning-1.0.3}/PKG-INFO +1 -1
- {datapruning-1.0.2 → datapruning-1.0.3}/build_src/_core.c +11 -32
- {datapruning-1.0.2 → datapruning-1.0.3/datapruning.egg-info}/PKG-INFO +1 -1
- {datapruning-1.0.2 → datapruning-1.0.3}/pyproject.toml +1 -1
- {datapruning-1.0.2 → datapruning-1.0.3}/LICENSE +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/MANIFEST.in +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/README.md +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/datapruning/__init__.py +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/datapruning.egg-info/SOURCES.txt +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/datapruning.egg-info/dependency_links.txt +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/datapruning.egg-info/requires.txt +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/datapruning.egg-info/top_level.txt +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/setup.cfg +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/setup.py +0 -0
- {datapruning-1.0.2 → datapruning-1.0.3}/tests/test_simple.py +0 -0
|
@@ -21268,29 +21268,8 @@ static PyObject *__pyx_pf_5_core_4analyze_data(CYTHON_UNUSED PyObject *__pyx_sel
|
|
|
21268
21268
|
/* "_core.pyx":72
|
|
21269
21269
|
*
|
|
21270
21270
|
* if n_samples > MAX_FREE_ROWS:
|
|
21271
|
-
* raise ValueError( # <<<<<<<<<<<<<<
|
|
21272
|
-
* "Dataset exceeds 100,000 rows. "
|
|
21273
|
-
* "For larger datasets, visit https://www.datapruning.com "
|
|
21274
|
-
*/
|
|
21275
|
-
__pyx_t_3 = NULL;
|
|
21276
|
-
__pyx_t_4 = 1;
|
|
21277
|
-
{
|
|
21278
|
-
PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_mstate_global->__pyx_kp_u_Dataset_exceeds_100_000_rows_For};
|
|
21279
|
-
__pyx_t_2 = __Pyx_PyObject_FastCall((PyObject*)(((PyTypeObject*)PyExc_ValueError)), __pyx_callargs+__pyx_t_4, (2-__pyx_t_4) | (__pyx_t_4*__Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET));
|
|
21280
|
-
__Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0;
|
|
21281
|
-
if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 72, __pyx_L1_error)
|
|
21282
|
-
__Pyx_GOTREF(__pyx_t_2);
|
|
21283
|
-
}
|
|
21284
|
-
__Pyx_Raise(__pyx_t_2, 0, 0, 0);
|
|
21285
|
-
__Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
|
|
21286
|
-
__PYX_ERR(0, 72, __pyx_L1_error)
|
|
21287
|
-
|
|
21288
|
-
/* "_core.pyx":71
|
|
21289
|
-
* cdef int n_features = X.shape[1]
|
|
21290
|
-
*
|
|
21291
|
-
* if n_samples > MAX_FREE_ROWS: # <<<<<<<<<<<<<<
|
|
21292
21271
|
* raise ValueError(
|
|
21293
|
-
* "Dataset exceeds
|
|
21272
|
+
* "Dataset exceeds 300,000 rows. "
|
|
21294
21273
|
*/
|
|
21295
21274
|
}
|
|
21296
21275
|
|
|
@@ -27820,8 +27799,8 @@ __Pyx_RefNannySetupContext("PyInit__core", 0);
|
|
|
27820
27799
|
* import pandas as pd
|
|
27821
27800
|
* import gc # <<<<<<<<<<<<<<
|
|
27822
27801
|
*
|
|
27823
|
-
* MAX_FREE_ROWS =
|
|
27824
|
-
*/
|
|
27802
|
+
* MAX_FREE_ROWS = 300000
|
|
27803
|
+
*/
|
|
27825
27804
|
__pyx_t_1 = __Pyx_Import(__pyx_mstate_global->__pyx_n_u_gc, 0, 0, NULL, 0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 9, __pyx_L1_error)
|
|
27826
27805
|
__pyx_t_4 = __pyx_t_1;
|
|
27827
27806
|
__Pyx_GOTREF(__pyx_t_4);
|
|
@@ -27830,16 +27809,16 @@ __Pyx_RefNannySetupContext("PyInit__core", 0);
|
|
|
27830
27809
|
|
|
27831
27810
|
/* "_core.pyx":11
|
|
27832
27811
|
* import gc
|
|
27833
|
-
*
|
|
27834
|
-
* MAX_FREE_ROWS =
|
|
27812
|
+
*
|
|
27813
|
+
* MAX_FREE_ROWS = 300000 # <<<<<<<<<<<<<<
|
|
27835
27814
|
* SMALL_DATASET_THRESHOLD = 600
|
|
27836
|
-
*
|
|
27837
|
-
*/
|
|
27815
|
+
*
|
|
27816
|
+
*/
|
|
27838
27817
|
if (PyDict_SetItem(__pyx_mstate_global->__pyx_d, __pyx_mstate_global->__pyx_n_u_MAX_FREE_ROWS, __pyx_mstate_global->__pyx_int_100000) < (0)) __PYX_ERR(0, 11, __pyx_L1_error)
|
|
27839
27818
|
|
|
27840
27819
|
/* "_core.pyx":12
|
|
27841
|
-
*
|
|
27842
|
-
* MAX_FREE_ROWS =
|
|
27820
|
+
*
|
|
27821
|
+
* MAX_FREE_ROWS = 300000
|
|
27843
27822
|
* SMALL_DATASET_THRESHOLD = 600 # <<<<<<<<<<<<<<
|
|
27844
27823
|
*
|
|
27845
27824
|
*
|
|
@@ -28316,7 +28295,7 @@ const char* const cstring = "x\332\225VKw\323H\026\356\200\323I7\341\341$$\320pz
|
|
|
28316
28295
|
if (likely(bytes)); else { Py_DECREF(data); __PYX_ERR(0, 1, __pyx_L1_error) }
|
|
28317
28296
|
#endif
|
|
28318
28297
|
#else /* compression: none (5484 bytes) */
|
|
28319
|
-
const char* const bytes = ": All dimensions preceding dimension %d must be indexed and not slicedBuffer view does not expose stridesCan only create a buffer that is contiguous in memory.Cannot assign to read-only memoryviewCannot create writable memory view from read-only memoryviewCannot index with type 'Cannot transpose memoryview with indirect dimensionsColumn 'Dataset exceeds
|
|
28298
|
+
const char* const bytes = ": All dimensions preceding dimension %d must be indexed and not slicedBuffer view does not expose stridesCan only create a buffer that is contiguous in memory.Cannot assign to read-only memoryviewCannot create writable memory view from read-only memoryviewCannot index with type 'Cannot transpose memoryview with indirect dimensionsColumn 'Dataset exceeds 300,000 rows. For larger datasets, visit https://www.datapruning.com or contact datapruning@datapruning.comDimension %d is not directEmpty shape tuple for cython.arrayExpected a pandas DataFrameIndex out of bounds (axis %d)Indirect dimensions not supportedInvalid mode, expected 'c' or 'fortran', got Invalid shape in axis <MemoryView of Note that Cython is deliberately stricter than PEP-484 and rejects subclasses of builtin types. If you need to pass subclasses then set the 'annotation_typing' directive to False.Out of bounds on buffer access (axis Step may not be zero (axis %d)Unable to convert item to object.>')?add_note and at 0xcollections.abc<contiguous and direct><contiguous and indirect>_core.pyxdisableenablegc (got got differing extents in dimension isenableditemsize <= 0 for cython.arrayno default __reduce__ due to non-trivial __cinit__' not found in DataFramenumpy._core.multiarray failed to importnumpy._core.umath failed to import object><strided and direct><strided and direct or indirect><strided and indirect>unable to allocate array data.unable to allocate shape and strides.ASCIIAdamBatchNorm1dCCrossEntropyLossDataFrameEllipsisII_historyLinearMAX_FREE_ROWSMSELossModuleNetNet.__init__Net.forwardPrunerPruner.__init__Pruner.prune__Pyx_PyDict_NextRefReLUSMALL_DATASET_THRESHOLDSequenceSequentialView.MemoryViewXX_mvX_npX_tX_trainabcabsacc_historyallocate_bufferanalyze_dataargmaxargsortarrayasarrayasyncio.coroutinesautogradaxisbackendsbackwardbasebase_batchbatch_sizebenchmarkccat__class____class_getitem__cline_in_tracebackclscollectcolumnscompute_I_dircopy_corecoscosine_similaritycountcudnncxddefault_rngdetermin""istic_dfdf_obj__dict__dim__doc__dropdtypedtype_is_objectencodeend_idxenergy__enter__enumerateerror__exit___filter_fallbackflagsfloatfloat32formatfortranforwardfrom_numpy__func__functionalgg1g2gaingc__getstate__gradhidden_dimiididxiloc__import__indexindices__init__input_dimint64is_classification_is_coroutineitemitemsitemsizekeepkeep_ratiolearning_gainlinalglonglossloss_fnlrm__main__manual_seedmeanmean_Imemview__metaclass__midmodemodel__module____mro_entries__nn_featuresn_rowsn_samplesn_trainname__name__nannan_to_numndimneginfnet__new__nnno_gradnonenormnpnum_splitsnum_stepsnumpyobjoffoptimoptimizerorderoutput_dimppackpandasparameterspdperfpermperm2popposinfpred__prepare__pruneprune_dataframe__pyx_checksum__pyx_state__pyx_type__pyx_unpickle_Enum__pyx_vtable____qualname__randomrandpermranked_all_indicesranked_train_indicesratioreached__reduce____reduce_cython____reduce_ex__reductionregisterreset_indexretain_graphrngsscorescore_mean_absscore_stdscoresseedselected_indicesself__set_name__set_seedsetdefault__setstate____setstate_cython__shapeshufflesisizesorted_splitssplit_sizesplits_Xsplits_ystartstdstepstopstructsumsupertarget_coltarget_keep__test__tolisttorchtorch.nntorch.optimtotal_energytrain_idxuniqueunique_valsunpackupdateval_idxval_sizevaluesviewwherexx1x2x_valxbxb_batchyy1y2y_mvy_npy_rawy_ty_trainy_valybyb_batchyb_splitzero_gradzeros\320\004 \320 0\260\001\330\010\017\210\177\230a\230t\2406\250\034\260\\\300\021\320\000\033\2301\330\004\n\210\"\210G\220<\230q\240\001\330\004\r\210R\210w\220a\220q\330\004\013\2102\210V\2201\220C\220q\230\004\230F\240!\330\004\017\210q\220\005\220T\230\022\230:\240R\240q\330\004\010\210\007\210q\330\010\014\210B\210c\220\021\330\010\r\210Q\210a\210q\330\010\013\2103\210a\210t\2202\220Q\330\014\020\220\001\220\025\220a\330\014\r\330\010\014\210B\210e\2201\220E\230\021\330\010\014\210B\210g\220U\230!\2303\230b\240\003\2405\250\001\330\010\r\210R\210x\220q\230\001\330\010\017\210q\220\003\2203\220a\220s\230!\2304\230r\240\021\330\010""\017\210s\220!\2204\220r\230\023\230C\230q\330\010\016\210b\220\006\220a\220r\230\021\230!\330\010\014\210A\210S\220\001\220\022\2201\220D\230\004\230B\230g\240Q\330\004\013\2102\210V\2201\220E\230\021\230!\200\001\330\004\t\210\032\2201\340\004\n\210%\210y\230\001\230\023\230A\230Q\330\004\r\210Q\210c\220\023\220A\220T\230\023\230A\340\004\t\210\022\2101\210C\210r\220\021\330\004\t\210\022\2101\210C\210q\220\001\340\004\t\210\022\2101\210C\210r\220\021\330\004\t\210\022\2101\210C\210q\220\001\340\004\007\200s\210!\2104\210s\220\"\220C\220s\230!\2304\230s\240!\330\010\017\210q\340\004\t\210\025\210i\220u\230A\230W\240A\240U\250!\2505\260\003\2605\270\004\270E\300\033\310D\320P]\320]^\330\004\t\210\025\210i\220u\230A\230W\240A\240U\250!\2505\260\003\2605\270\004\270E\300\033\310A\340\004\t\210\025\210d\220!\2201\220A\220U\230\"\230C\230t\2405\250\001\330\004\t\210\025\210d\220!\2201\220A\220U\230\"\230C\230t\2405\250\001\340\004\n\210\"\210K\320\027)\250\021\250$\250d\260$\260a\340\004\014\210B\210b\220\003\2205\230\004\230B\230a\200A\330\010\013\2104\210z\230\021\230(\240\"\240A\330\014\022\220)\2301\230A\330\010\014\210G\2201\200A\330\010\r\210R\210y\230\001\330\010\030\230\001\230\031\240%\240q\330\010\014\210G\2202\220[\240\001\330\014\016\210g\220Q\220k\240\021\330\014\016\210l\230!\2301\330\014\016\210e\2201\330\014\016\210g\220Q\220l\240!\200A\330\010\017\210t\2204\220q\230\001\200\r\210Q\330\004\t\210\034\220Q\220a\330\004\006\200g\210U\220!\2201\330\004\n\210%\210q\220\001\330\004\t\210\031\220&\320\030)\250\021\330\004\t\210\031\220&\230\r\240Q\320\000(\320(>\270a\330\004\007\200t\210:\220Q\220h\230b\240\001\330\010\016\210i\220q\230\001\330\004\007\200{\220'\230\026\230q\330\010\016\210j\230\001\230\032\2401\240A\340\004\026\220c\230\021\230!\340\004\013\2102\210X\220Q\220f\230E\240\021\240(\250!\250>\270\026\270r\300\031\310%\310q\320PV\320VW\330\004\013\2102\210X\220Q\220f\230A\230]\250&\260\002\260)\2705\300\001\300\026\300q\330\004\006\200k\220\021""\220&\230\005\230W\240D\250\005\250W\260E\270\027\300\001\340\004\007\200w\210b\220\001\330\010\022\320\022\"\240!\2406\250\026\250q\330\010\017\210v\220U\230!\2308\240<\250q\260\005\260Q\340\004\034\230A\330\004\031\230\021\340\004\016\210l\230!\2306\240\026\240{\260!\340\004\010\210\006\210f\220F\230!\330\004\006\200h\210a\340\004\013\2106\220\025\220a\220x\230|\2501\250E\260\021\320\000,\320,?\270q\340\004\014\210A\210Q\340\004\031\230\021\230&\240\001\240\021\330\004\032\230!\2306\240\021\240!\340\004\007\200z\220\022\2201\330\010\016\210j\230\001\330\014\r\360\n\000\005\013\210%\210{\230!\2302\230X\240Q\240c\250\026\250q\330\004\014\210B\210h\220a\220q\340\004\022\220\"\220G\2301\230A\330\004\030\230\003\2301\230M\250\022\2501\340\004\007\200q\330\010\016\210e\220;\230a\230v\240U\250!\330\010\025\220S\230\001\230\021\330\010\022\220\"\320\024%\240Q\240j\260\001\340\010\016\210e\220;\230a\230v\240V\2502\250U\260\"\260C\260q\330\010\025\220Q\330\010\022\220\"\220H\230A\230Z\240q\340\004\013\2105\220\t\230\021\230!\330\004\022\220!\2204\220s\230!\2305\240\002\240!\330\004\007\200y\220\003\2201\330\010\026\220a\220s\230*\240C\240q\340\004\016\210d\220\"\220A\330\004\014\210C\210q\220\001\330\004\014\210C\210q\220\001\340\004\020\220\004\220A\220Q\330\004\016\210c\220\021\220!\330\004\016\210c\220\021\220!\340\004\016\210c\220\021\220!\340\004\024\220A\220W\230D\240\010\250\003\2501\330\004\021\220\030\230\023\230A\340\004\021\220\021\340\004\014\210E\220\031\230!\2301\340\004\017\210q\330\004\017\210q\330\004\010\210\005\210U\220!\2201\330\010\022\220!\2201\220A\220R\220q\230\016\240b\250\002\250+\260R\260w\270a\330\010\016\210e\2201\220A\220Q\220k\240\021\330\010\020\220\007\220q\230\007\230q\240\001\330\010\020\220\007\220q\230\007\230q\240\001\340\004\r\210R\210v\220Q\220l\240&\250\002\250!\340\004\010\210\005\210U\220!\2201\330\010\014\210H\220A\220Q\330\010\023\2208\2301\230A\340\010\020\220\003\2201\220L\240\001\330\010\024\220E\230\025\230a\230u\240K\250t""\2603\260a\340\010\027\220q\330\010\023\2201\340\010\026\220a\330\010\024\220A\340\010\030\230\001\320\031)\250\023\250C\250q\260\003\2603\260a\340\010\014\210H\220E\230\021\230!\330\014\022\220%\220y\240\001\240\023\240A\240S\250\002\250!\330\014\027\220q\230\001\230\021\330\014\027\220x\230q\240\001\340\014\020\220\r\230Q\230g\240Y\250j\270\001\330\014\025\220W\230A\230Q\340\014\023\2205\230\001\230\021\330\014\023\2207\230!\2306\240\031\250%\250q\340\014\025\220Z\230q\330\014\020\220\t\230\021\340\014\025\220Q\330\014\020\220\005\220U\230+\240Q\330\020\023\2201\220F\230'\240\021\330\024\037\230q\240\005\240R\240r\250\024\250R\250u\260A\340\014\034\230A\330\014\025\220U\230!\340\021\026\220h\230a\330\020\023\2201\330\024\034\230E\240\021\240&\250\007\250q\260\003\2603\260f\270F\300\"\300E\310\022\3105\320PQ\340\024\033\2301\230G\2401\240E\250\021\250(\260&\270\005\270R\270u\300A\330\020\033\2307\240!\2401\340\014\017\210x\220t\2302\230T\240\023\240A\240]\260\"\260A\330\020\027\220{\240\"\240C\240r\250\033\260B\260a\330\020\027\220s\230!\230;\240b\250\005\250R\250q\330\020\024\220E\230\022\2306\240\022\2401\330\024\036\230a\340\010\030\230\013\2402\240S\250\002\250+\260Q\260a\330\010\021\220\025\220a\220r\230\025\230a\230q\340\010\021\220\036\230s\240-\250r\260\027\270\003\2702\270R\270q\330\010\016\210a\210u\220A\340\004\024\220B\220h\230a\230w\240d\250!\340\004\033\2301\330\004\010\210\005\210Q\330\010\022\220!\2201\220A\220R\220q\230\016\240b\250\002\250+\260R\260w\270a\330\010\016\210e\2201\220A\220Q\220k\240\021\330\010\034\230G\2401\240I\250Q\250d\260'\270\021\340\004\031\230\027\240\007\240s\250\"\250A\340\004\020\220\002\220$\220a\220q\330\004\025\220R\220t\2301\230B\230e\2401\240I\250R\250q\330\004\010\210\n\220\"\320\024$\240B\240a\330\010\016\210h\220a\220q\340\004\025\220Q\220c\230\023\230A\230Z\240r\250\021\330\004\027\320\027)\250\022\2501\340\004\013\2102\210V\2201\320\024&\240f\250B\250aO";
|
|
28320
28299
|
PyObject *data = NULL;
|
|
28321
28300
|
CYTHON_UNUSED_VAR(__Pyx_DecompressString);
|
|
28322
28301
|
#endif
|
|
@@ -28381,7 +28360,7 @@ const char* const bytes = ": All dimensions preceding dimension %d must be index
|
|
|
28381
28360
|
PyObject **numbertab = __pyx_mstate->__pyx_number_tab + 6;
|
|
28382
28361
|
int8_t const cint_constants_1[] = {0,-1,1,2,42};
|
|
28383
28362
|
int16_t const cint_constants_2[] = {300,600,1500,2000};
|
|
28384
|
-
int32_t const cint_constants_4[] = {
|
|
28363
|
+
int32_t const cint_constants_4[] = {300000L,136983863L};
|
|
28385
28364
|
for (int i = 0; i < 11; i++) {
|
|
28386
28365
|
numbertab[i] = PyLong_FromLong((i < 5 ? cint_constants_1[i - 0] : (i < 9 ? cint_constants_2[i - 5] : cint_constants_4[i - 9])));
|
|
28387
28366
|
if (unlikely(!numbertab[i])) __PYX_ERR(0, 1, __pyx_L1_error)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|