scdataloader 1.2.2__py3-none-any.whl → 1.6.4__py3-none-any.whl

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.
scdataloader/VERSION CHANGED
@@ -1 +1 @@
1
- 1.2.2
1
+ 1.6.4
scdataloader/data.py CHANGED
@@ -97,8 +97,8 @@ class Dataset(torchDataset):
97
97
  for clss in self.clss_to_pred:
98
98
  if clss not in self.hierarchical_clss:
99
99
  # otherwise it's already been done
100
- self.class_topred[clss] = self.mapped_dataset.get_merged_categories(
101
- clss
100
+ self.class_topred[clss] = set(
101
+ self.mapped_dataset.get_merged_categories(clss)
102
102
  )
103
103
  if (
104
104
  self.mapped_dataset.unknown_label
@@ -290,7 +290,7 @@ class DataModule(L.LightningDataModule):
290
290
  break
291
291
  else:
292
292
  self.test_datasets.append(
293
- self.dataset.mapped_dataset._path_list[i].path
293
+ self.dataset.mapped_dataset.path_list[i].path
294
294
  )
295
295
  cs += c
296
296
  len_test = cs
scdataloader/utils.py CHANGED
@@ -378,6 +378,169 @@ def load_genes(organisms: Union[str, list] = "NCBITaxon:9606"): # "NCBITaxon:10
378
378
  ]:
379
379
  if col in organismdf.columns:
380
380
  organismdf.drop(columns=[col], inplace=True)
381
+ # temp fix
382
+ drop = {
383
+ "ENSG00000112096",
384
+ "ENSG00000137808",
385
+ "ENSG00000161149",
386
+ "ENSG00000182230",
387
+ "ENSG00000203812",
388
+ "ENSG00000204092",
389
+ "ENSG00000205485",
390
+ "ENSG00000212951",
391
+ "ENSG00000215271",
392
+ "ENSG00000221995",
393
+ "ENSG00000224739",
394
+ "ENSG00000224745",
395
+ "ENSG00000225178",
396
+ "ENSG00000225932",
397
+ "ENSG00000226377",
398
+ "ENSG00000226380",
399
+ "ENSG00000226403",
400
+ "ENSG00000227021",
401
+ "ENSG00000227220",
402
+ "ENSG00000227902",
403
+ "ENSG00000228139",
404
+ "ENSG00000228206",
405
+ "ENSG00000228906",
406
+ "ENSG00000229352",
407
+ "ENSG00000231575",
408
+ "ENSG00000232196",
409
+ "ENSG00000232295",
410
+ "ENSG00000233776",
411
+ "ENSG00000236166",
412
+ "ENSG00000236673",
413
+ "ENSG00000236740",
414
+ "ENSG00000236886",
415
+ "ENSG00000236996",
416
+ "ENSG00000237133",
417
+ "ENSG00000237513",
418
+ "ENSG00000237548",
419
+ "ENSG00000237838",
420
+ "ENSG00000239446",
421
+ "ENSG00000239467",
422
+ "ENSG00000239665",
423
+ "ENSG00000244693",
424
+ "ENSG00000244952",
425
+ "ENSG00000249860",
426
+ "ENSG00000251044",
427
+ "ENSG00000253878",
428
+ "ENSG00000254561",
429
+ "ENSG00000254740",
430
+ "ENSG00000255633",
431
+ "ENSG00000255823",
432
+ "ENSG00000256045",
433
+ "ENSG00000256222",
434
+ "ENSG00000256374",
435
+ "ENSG00000256427",
436
+ "ENSG00000256618",
437
+ "ENSG00000256863",
438
+ "ENSG00000256892",
439
+ "ENSG00000258414",
440
+ "ENSG00000258808",
441
+ "ENSG00000258861",
442
+ "ENSG00000259444",
443
+ "ENSG00000259820",
444
+ "ENSG00000259834",
445
+ "ENSG00000259855",
446
+ "ENSG00000260461",
447
+ "ENSG00000261068",
448
+ "ENSG00000261438",
449
+ "ENSG00000261490",
450
+ "ENSG00000261534",
451
+ "ENSG00000261737",
452
+ "ENSG00000261773",
453
+ "ENSG00000261963",
454
+ "ENSG00000262668",
455
+ "ENSG00000263464",
456
+ "ENSG00000267637",
457
+ "ENSG00000268955",
458
+ "ENSG00000269028",
459
+ "ENSG00000269900",
460
+ "ENSG00000269933",
461
+ "ENSG00000269966",
462
+ "ENSG00000270188",
463
+ "ENSG00000270394",
464
+ "ENSG00000270672",
465
+ "ENSG00000271043",
466
+ "ENSG00000271409",
467
+ "ENSG00000271734",
468
+ "ENSG00000271870",
469
+ "ENSG00000272040",
470
+ "ENSG00000272196",
471
+ "ENSG00000272267",
472
+ "ENSG00000272354",
473
+ "ENSG00000272370",
474
+ "ENSG00000272551",
475
+ "ENSG00000272567",
476
+ "ENSG00000272880",
477
+ "ENSG00000272904",
478
+ "ENSG00000272934",
479
+ "ENSG00000273301",
480
+ "ENSG00000273370",
481
+ "ENSG00000273496",
482
+ "ENSG00000273576",
483
+ "ENSG00000273614",
484
+ "ENSG00000273837",
485
+ "ENSG00000273888",
486
+ "ENSG00000273923",
487
+ "ENSG00000276612",
488
+ "ENSG00000276814",
489
+ "ENSG00000277050",
490
+ "ENSG00000277077",
491
+ "ENSG00000277352",
492
+ "ENSG00000277666",
493
+ "ENSG00000277761",
494
+ "ENSG00000278198",
495
+ "ENSG00000278782",
496
+ "ENSG00000278927",
497
+ "ENSG00000278955",
498
+ "ENSG00000279226",
499
+ "ENSG00000279765",
500
+ "ENSG00000279769",
501
+ "ENSG00000279948",
502
+ "ENSG00000280058",
503
+ "ENSG00000280095",
504
+ "ENSG00000280250",
505
+ "ENSG00000280346",
506
+ "ENSG00000280374",
507
+ "ENSG00000280710",
508
+ "ENSG00000282080",
509
+ "ENSG00000282246",
510
+ "ENSG00000282965",
511
+ "ENSG00000283486",
512
+ "ENSG00000284299",
513
+ "ENSG00000284741",
514
+ "ENSG00000285106",
515
+ "ENSG00000285162",
516
+ "ENSG00000285476",
517
+ "ENSG00000285762",
518
+ "ENSG00000286065",
519
+ "ENSG00000286228",
520
+ "ENSG00000286601",
521
+ "ENSG00000286699",
522
+ "ENSG00000286949",
523
+ "ENSG00000286996",
524
+ "ENSG00000287116",
525
+ "ENSG00000287388",
526
+ "ENSG00000288541",
527
+ "ENSG00000288546",
528
+ "ENSG00000288630",
529
+ "ENSG00000288639",
530
+ "ENSMUSG00000069518",
531
+ "ENSMUSG00000073682",
532
+ "ENSMUSG00000075014",
533
+ "ENSMUSG00000075015",
534
+ "ENSMUSG00000078091",
535
+ "ENSMUSG00000094958",
536
+ "ENSMUSG00000095547",
537
+ "ENSMUSG00000095891",
538
+ "ENSMUSG00000096385",
539
+ "ENSMUSG00000096519",
540
+ "ENSMUSG00000096923",
541
+ "ENSMUSG00000097078",
542
+ }
543
+ organismdf = organismdf[~organismdf.index.isin(drop)]
381
544
  return organismdf
382
545
 
383
546
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.3
2
2
  Name: scdataloader
3
- Version: 1.2.2
3
+ Version: 1.6.4
4
4
  Summary: a dataloader for single cell data in lamindb
5
5
  Project-URL: repository, https://github.com/jkobject/scDataLoader
6
6
  Author-email: jkobject <jkobject@gmail.com>
@@ -11,6 +11,7 @@ Requires-Dist: anndata>=0.9.0
11
11
  Requires-Dist: biomart>=0.9.0
12
12
  Requires-Dist: cellxgene-census>=0.1.0
13
13
  Requires-Dist: django>=4.0.0
14
+ Requires-Dist: harmonypy>=0.0.10
14
15
  Requires-Dist: ipykernel>=6.20.0
15
16
  Requires-Dist: lamindb[bionty]==0.76.12
16
17
  Requires-Dist: leidenalg>=0.8.0
@@ -49,6 +50,8 @@ Description-Content-Type: text/markdown
49
50
  [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
50
51
  [![DOI](https://img.shields.io/badge/DOI-10.1101%2F2024.07.29.605556-blue)](https://doi.org/10.1101/2024.07.29.605556)
51
52
 
53
+ <img src="scdataloader.png" width="600">
54
+
52
55
  This single cell pytorch dataloader / lighting datamodule is designed to be used with:
53
56
 
54
57
  - [lamindb](https://lamin.ai/)
@@ -0,0 +1,14 @@
1
+ scdataloader/VERSION,sha256=1-dHLCYhhLoNpJuXwyP9qKDsvu4z17NNtIQF76_WVd4,6
2
+ scdataloader/__init__.py,sha256=5y9VzRhOAUWeYMn2MrRRRlzgdiMjRFytr7gcn-I6IkE,147
3
+ scdataloader/__main__.py,sha256=VXrt2IykBypnIXWydwA7NfF7LtRGc-0Khjtm5OIBNpI,6527
4
+ scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
5
+ scdataloader/collator.py,sha256=gzHiuixUwK8JClhAbG12kgWMU_VTKkowibA-tDFpbwo,11341
6
+ scdataloader/config.py,sha256=rrW2DZxG4J2_pmpDbXXsaKJkpNC57w5dIlItiFbANYw,2905
7
+ scdataloader/data.py,sha256=1dF7B406dGYxmVb2ab6ROsaweHL-15CAcKrltuy1NIM,14912
8
+ scdataloader/datamodule.py,sha256=yGi0l4eY_j9IsPT_AGe196cT6ZmCHhpOpUrRPQ1wsKI,16935
9
+ scdataloader/preprocess.py,sha256=pH4EPrcRqH34o3t5X3A4kETiYdCZngih5SdP_PPfgOo,29178
10
+ scdataloader/utils.py,sha256=YLLMv_60K-TkW5kvJC7Ai7QCMleCBNVKUNrqYSzVllI,26919
11
+ scdataloader-1.6.4.dist-info/METADATA,sha256=OB_quKz5eCMXkhqIWkkuczKmrnFT0USYnVWqm0iL7uw,9875
12
+ scdataloader-1.6.4.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
13
+ scdataloader-1.6.4.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
14
+ scdataloader-1.6.4.dist-info/RECORD,,
@@ -1,14 +0,0 @@
1
- scdataloader/VERSION,sha256=xipcxhrEUlk1dT9ewoTAoFKksdpLOjWA3OK313ohVK4,6
2
- scdataloader/__init__.py,sha256=5y9VzRhOAUWeYMn2MrRRRlzgdiMjRFytr7gcn-I6IkE,147
3
- scdataloader/__main__.py,sha256=VXrt2IykBypnIXWydwA7NfF7LtRGc-0Khjtm5OIBNpI,6527
4
- scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
5
- scdataloader/collator.py,sha256=gzHiuixUwK8JClhAbG12kgWMU_VTKkowibA-tDFpbwo,11341
6
- scdataloader/config.py,sha256=rrW2DZxG4J2_pmpDbXXsaKJkpNC57w5dIlItiFbANYw,2905
7
- scdataloader/data.py,sha256=3dCp-lIAfOkCi76SH5W3iSqFmAWZslwARkN9v5mylz8,14907
8
- scdataloader/datamodule.py,sha256=B-udBevPSPF__hfy0pOz1dGovgE95K2pxPupjB7RblI,16936
9
- scdataloader/preprocess.py,sha256=pH4EPrcRqH34o3t5X3A4kETiYdCZngih5SdP_PPfgOo,29178
10
- scdataloader/utils.py,sha256=7tgt3sPj_XTKb-UlJDAZWvQr0_DG9VTC6ioiLdBWFFE,22498
11
- scdataloader-1.2.2.dist-info/METADATA,sha256=XMtKO9ImiyY--F92njvMUe69OaJgDx8C3xQtBAXqo8g,9800
12
- scdataloader-1.2.2.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
13
- scdataloader-1.2.2.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
14
- scdataloader-1.2.2.dist-info/RECORD,,