scdataset.github.io/examples.html at main · scDataset/scdataset.github.io · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000

<!DOCTYPE html>


<html lang="en" data-content_root="./" >

  <head>
    <meta charset="utf-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />

    <title>Examples &#8212; scDataset Documentation</title>


  <script data-cfasync="false">
    document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
    document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
  </script>

  <!-- Loaded before other Sphinx assets -->
  <link href="_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />


  <link href="_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
  <link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />

    <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=8f2a1f02" />
    <link rel="stylesheet" type="text/css" href="_static/styles/sphinx-book-theme.css?v=eba8b062" />

  <!-- Pre-loaded scripts that we'll load fully later -->
  <link rel="preload" as="script" href="_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
  <script src="_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>

    <script src="_static/documentation_options.js?v=7f7c277e"></script>
    <script src="_static/doctools.js?v=9bcbadda"></script>
    <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
    <script src="_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
    <script>DOCUMENTATION_OPTIONS.pagename = 'examples';</script>
    <link rel="index" title="Index" href="genindex.html" />
    <link rel="search" title="Search" href="search.html" />
    <link rel="next" title="API Reference" href="scdataset.html" />
    <link rel="prev" title="Quick Start Guide" href="quickstart.html" />
  <meta name="viewport" content="width=device-width, initial-scale=1"/>
  <meta name="docsearch:language" content="en"/>
  </head>


  <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">


  <div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>

  <div id="pst-scroll-pixel-helper"></div>

  <button type="button" class="btn rounded-pill" id="pst-back-to-top">
    <i class="fa-solid fa-arrow-up"></i>Back to top</button>


  <input type="checkbox"
          class="sidebar-toggle"
          id="pst-primary-sidebar-checkbox"/>
  <label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>

  <input type="checkbox"
          class="sidebar-toggle"
          id="pst-secondary-sidebar-checkbox"/>
  <label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>

  <div class="search-button__wrapper">
    <div class="search-button__overlay"></div>
    <div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
      action="search.html"
      method="get">
  <i class="fa-solid fa-magnifying-glass"></i>
  <input type="search"
         class="form-control"
         name="q"
         id="search-input"
         placeholder="Search..."
         aria-label="Search..."
         autocomplete="off"
         autocorrect="off"
         autocapitalize="off"
         spellcheck="false"/>
  <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
  </div>

  <div class="pst-async-banner-revealer d-none">
  <aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>


    <header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
    </header>


  <div class="bd-container">
    <div class="bd-container__inner bd-page-width">


      <div class="bd-sidebar-primary bd-sidebar">


  <div class="sidebar-header-items sidebar-primary__section">


  </div>

    <div class="sidebar-primary-items__start sidebar-primary__section">
        <div class="sidebar-primary-item">


<a class="navbar-brand logo" href="index.html">


    <img src="https://github.com/scDataset/scDataset/raw/main/figures/scdataset.png" class="logo__image only-light" alt="scDataset Documentation - Home"/>
    <script>document.write(`<img src="https://github.com/scDataset/scDataset/raw/main/figures/scdataset.png" class="logo__image only-dark" alt="scDataset Documentation - Home"/>`);</script>


</a></div>
        <div class="sidebar-primary-item">

 <script>
 document.write(`
   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
    <i class="fa-solid fa-magnifying-glass"></i>
    <span class="search-button__default-text">Search</span>
    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
   </button>
 `);
 </script></div>
        <div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
    <div class="bd-toc-item navbar-nav active">
        <p aria-level="2" class="caption" role="heading"><span class="caption-text">Contents:</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="quickstart.html">Quick Start Guide</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Examples</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="scdataset.html">API Reference</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.scDataset.html">scdataset.scDataset</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.MultiIndexable.html">scdataset.MultiIndexable</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.strategy.SamplingStrategy.html">scdataset.strategy.SamplingStrategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.strategy.Streaming.html">scdataset.strategy.Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.strategy.BlockShuffling.html">scdataset.strategy.BlockShuffling</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.strategy.BlockWeightedSampling.html">scdataset.strategy.BlockWeightedSampling</a></li>
<li class="toctree-l2"><a class="reference internal" href="generated/scdataset.strategy.ClassBalancedSampling.html">scdataset.strategy.ClassBalancedSampling</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Additional Resources:</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="citation.html">Citation</a></li>
<li class="toctree-l1"><a class="reference internal" href="contributing.html">Contributing</a></li>
<li class="toctree-l1"><a class="reference internal" href="changelog.html">Changelog</a></li>
</ul>

    </div>
</nav></div>
    </div>


  <div class="sidebar-primary-items__end sidebar-primary__section">
  </div>

  <div id="rtd-footer-container"></div>


      </div>

      <main id="main-content" class="bd-main" role="main">


<div class="sbt-scroll-pixel-helper"></div>

          <div class="bd-content">
            <div class="bd-article-container">

              <div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">

    <div class="header-article-items__start">

        <div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
  <span class="fa-solid fa-bars"></span>
</button></div>

    </div>


    <div class="header-article-items__end">

        <div class="header-article-item">

<div class="article-header-buttons">


<div class="dropdown dropdown-source-buttons">
  <button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Source repositories">
    <i class="fab fa-github"></i>
  </button>
  <ul class="dropdown-menu">


      <li><a href="https://github.com/Kidara/scDataset" target="_blank"
   class="btn btn-sm btn-source-repository-button dropdown-item"
   title="Source repository"
   data-bs-placement="left" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fab fa-github"></i>
  </span>
<span class="btn__text-container">Repository</span>
</a>
</li>


      <li><a href="https://github.com/Kidara/scDataset/edit/main/docs/source/examples.rst" target="_blank"
   class="btn btn-sm btn-source-edit-button dropdown-item"
   title="Suggest edit"
   data-bs-placement="left" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fas fa-pencil-alt"></i>
  </span>
<span class="btn__text-container">Suggest edit</span>
</a>
</li>


      <li><a href="https://github.com/Kidara/scDataset/issues/new?title=Issue%20on%20page%20%2Fexamples.html&body=Your%20issue%20content%20here." target="_blank"
   class="btn btn-sm btn-source-issues-button dropdown-item"
   title="Open an issue"
   data-bs-placement="left" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fas fa-lightbulb"></i>
  </span>
<span class="btn__text-container">Open issue</span>
</a>
</li>

  </ul>
</div>


<div class="dropdown dropdown-download-buttons">
  <button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
    <i class="fas fa-download"></i>
  </button>
  <ul class="dropdown-menu">


      <li><a href="_sources/examples.rst" target="_blank"
   class="btn btn-sm btn-download-source-button dropdown-item"
   title="Download source file"
   data-bs-placement="left" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fas fa-file"></i>
  </span>
<span class="btn__text-container">.rst</span>
</a>
</li>


      <li>
<button onclick="window.print()"
  class="btn btn-sm btn-download-pdf-button dropdown-item"
  title="Print to PDF"
  data-bs-placement="left" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fas fa-file-pdf"></i>
  </span>
<span class="btn__text-container">.pdf</span>
</button>
</li>

  </ul>
</div>


<button onclick="toggleFullScreen()"
  class="btn btn-sm btn-fullscreen-button"
  title="Fullscreen mode"
  data-bs-placement="bottom" data-bs-toggle="tooltip"
>


<span class="btn__icon-container">
  <i class="fas fa-expand"></i>
  </span>

</button>


<script>
document.write(`
  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
  </button>
`);
</script>


<script>
document.write(`
  <button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
    <i class="fa-solid fa-magnifying-glass fa-lg"></i>
  </button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
    <span class="fa-solid fa-list"></span>
</button>
</div></div>

    </div>

</div>
</div>


<div id="jb-print-docs-body" class="onlyprint">
    <h1>Examples</h1>
    <!-- Table of contents -->
    <div id="print-main-content">
        <div id="jb-print-toc">

            <div>
                <h2> Contents </h2>
            </div>
            <nav aria-label="Page">
                <ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#single-cell-data-analysis">Single-Cell Data Analysis</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#working-with-anndata">Working with AnnData</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#class-balanced-training">Class-Balanced Training</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#multi-modal-data">Multi-Modal Data</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#large-scale-training">Large-Scale Training</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#memory-efficient-data-loading">Memory-Efficient Data Loading</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#subset-training-and-validation">Subset Training and Validation</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#custom-data-transformations">Custom Data Transformations</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#on-the-fly-normalization">On-the-Fly Normalization</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#data-augmentation">Data Augmentation</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#working-with-huggingface-datasets">Working with HuggingFace Datasets</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#basic-usage">Basic Usage</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#custom-processing-for-huggingface-data">Custom Processing for HuggingFace Data</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#working-with-multiindexable">Working with MultiIndexable</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#basic-multiindexable-usage">Basic MultiIndexable Usage</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#multi-modal-single-cell-data">Multi-Modal Single-Cell Data</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#subsetting-and-indexing">Subsetting and Indexing</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#integration-with-pytorch-lightning">Integration with PyTorch Lightning</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#advanced-sampling-strategies">Advanced Sampling Strategies</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#custom-weighted-sampling">Custom Weighted Sampling</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#temporal-sampling-for-time-series-data">Temporal Sampling for Time-Series Data</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#performance-benchmarking">Performance Benchmarking</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#tips-and-best-practices">Tips and Best Practices</a></li>
</ul>
            </nav>
        </div>
    </div>
</div>


<div id="searchbox"></div>
                <article class="bd-article">

  <section id="examples">
<h1>Examples<a class="headerlink" href="#examples" title="Link to this heading">#</a></h1>
<p>This section provides comprehensive examples of using <code class="docutils literal notranslate"><span class="pre">scDataset</span></code> in various scenarios.</p>
<section id="single-cell-data-analysis">
<h2>Single-Cell Data Analysis<a class="headerlink" href="#single-cell-data-analysis" title="Link to this heading">#</a></h2>
<section id="working-with-anndata">
<h3>Working with AnnData<a class="headerlink" href="#working-with-anndata" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">anndata</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">ad</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">scanpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">sc</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">scDataset</span><span class="p">,</span> <span class="n">BlockShuffling</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">torch.utils.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataLoader</span>

<span class="c1"># Load single-cell data</span>
<span class="n">adata</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">pbmc3k_processed</span><span class="p">()</span>

<span class="c1"># Create custom fetch function for AnnData</span>
<span class="k">def</span><span class="w"> </span><span class="nf">fetch_anndata</span><span class="p">(</span><span class="n">adata</span><span class="p">,</span> <span class="n">indices</span><span class="p">):</span>
    <span class="c1"># Get expression matrix and convert to dense if sparse</span>
    <span class="n">data</span> <span class="o">=</span> <span class="n">adata</span><span class="p">[</span><span class="n">indices</span><span class="p">]</span><span class="o">.</span><span class="n">X</span>
    <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="s1">&#39;toarray&#39;</span><span class="p">):</span>
        <span class="n">data</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">toarray</span><span class="p">()</span>
    <span class="k">return</span> <span class="n">data</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>

<span class="c1"># Create dataset with block shuffling</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">adata</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
    <span class="n">fetch_callback</span><span class="o">=</span><span class="n">fetch_anndata</span>
<span class="p">)</span>

<span class="c1"># Use with DataLoader</span>
<span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>

<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">loader</span><span class="p">:</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Processing batch of shape: </span><span class="si">{</span><span class="n">batch</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
    <span class="c1"># Your model training code here</span>
    <span class="k">break</span>
</pre></div>
</div>
</section>
<section id="class-balanced-training">
<h3>Class-Balanced Training<a class="headerlink" href="#class-balanced-training" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pandas</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pd</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">ClassBalancedSampling</span>

<span class="c1"># Assume you have cell type annotations</span>
<span class="n">cell_types</span> <span class="o">=</span> <span class="n">adata</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="s1">&#39;cell_type&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>

<span class="c1"># Create balanced sampling strategy</span>
<span class="n">strategy</span> <span class="o">=</span> <span class="n">ClassBalancedSampling</span><span class="p">(</span>
    <span class="n">cell_types</span><span class="p">,</span>
    <span class="n">total_size</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span>  <span class="c1"># Generate 10k balanced samples per epoch</span>
    <span class="n">block_size</span><span class="o">=</span><span class="mi">8</span>
<span class="p">)</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span><span class="n">adata</span><span class="p">,</span> <span class="n">strategy</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">fetch_callback</span><span class="o">=</span><span class="n">fetch_anndata</span><span class="p">)</span>

<span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>

<span class="c1"># Training loop with balanced batches</span>
<span class="k">for</span> <span class="n">epoch</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">10</span><span class="p">):</span>
    <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">loader</span><span class="p">:</span>
        <span class="c1"># Each batch will be class-balanced</span>
        <span class="n">train_step</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="multi-modal-data">
<h3>Multi-Modal Data<a class="headerlink" href="#multi-modal-data" title="Link to this heading">#</a></h3>
<p>For multi-modal single-cell data (e.g., gene expression + protein measurements),
you can use the <code class="xref py py-class docutils literal notranslate"><span class="pre">MultiIndexable</span></code> class to keep different data modalities
synchronized during indexing:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">scDataset</span><span class="p">,</span> <span class="n">BlockShuffling</span><span class="p">,</span> <span class="n">MultiIndexable</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">torch.utils.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataLoader</span>

<span class="c1"># Simulate multi-modal data</span>
<span class="n">n_cells</span> <span class="o">=</span> <span class="mi">1000</span>
<span class="n">gene_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">n_cells</span><span class="p">,</span> <span class="mi">2000</span><span class="p">)</span>     <span class="c1"># Gene expression</span>
<span class="n">protein_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">n_cells</span><span class="p">,</span> <span class="mi">100</span><span class="p">)</span>   <span class="c1"># Protein measurements</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">n_cells</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>        <span class="c1"># Cell metadata</span>

<span class="c1"># Method 1: Using keyword arguments</span>
<span class="n">multimodal_data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span>
    <span class="n">genes</span><span class="o">=</span><span class="n">gene_data</span><span class="p">,</span>
    <span class="n">proteins</span><span class="o">=</span><span class="n">protein_data</span><span class="p">,</span>
    <span class="n">metadata</span><span class="o">=</span><span class="n">metadata</span>
<span class="p">)</span>

<span class="c1"># Method 2: Using dictionary as positional argument</span>
<span class="n">data_dict</span> <span class="o">=</span> <span class="p">{</span>
    <span class="s1">&#39;genes&#39;</span><span class="p">:</span> <span class="n">gene_data</span><span class="p">,</span>
    <span class="s1">&#39;proteins&#39;</span><span class="p">:</span> <span class="n">protein_data</span><span class="p">,</span>
    <span class="s1">&#39;metadata&#39;</span><span class="p">:</span> <span class="n">metadata</span>
<span class="p">}</span>
<span class="n">multimodal_data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span><span class="n">data_dict</span><span class="p">)</span>

<span class="c1"># Create dataset - all modalities will be indexed together</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">multimodal_data</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span>
<span class="p">)</span>

<span class="c1"># Use with DataLoader</span>
<span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>

<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">loader</span><span class="p">:</span>
    <span class="n">genes</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;genes&#39;</span><span class="p">]</span>        <span class="c1"># Shape: (32, 2000)</span>
    <span class="n">proteins</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;proteins&#39;</span><span class="p">]</span>  <span class="c1"># Shape: (32, 100)</span>
    <span class="n">meta</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;metadata&#39;</span><span class="p">]</span>      <span class="c1"># Shape: (32, 10)</span>

    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Genes: </span><span class="si">{</span><span class="n">genes</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">, Proteins: </span><span class="si">{</span><span class="n">proteins</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">, Meta: </span><span class="si">{</span><span class="n">meta</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
    <span class="c1"># All correspond to the same 32 cells</span>
    <span class="k">break</span>
</pre></div>
</div>
<p>Alternative approach with custom fetch function (for AnnData objects):</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span><span class="w"> </span><span class="nf">fetch_multimodal</span><span class="p">(</span><span class="n">adata</span><span class="p">,</span> <span class="n">indices</span><span class="p">):</span>
    <span class="c1"># Fetch both gene expression and protein data</span>
    <span class="n">gene_data</span> <span class="o">=</span> <span class="n">adata</span><span class="p">[</span><span class="n">indices</span><span class="p">]</span><span class="o">.</span><span class="n">X</span><span class="o">.</span><span class="n">toarray</span><span class="p">()</span>
    <span class="n">protein_data</span> <span class="o">=</span> <span class="n">adata</span><span class="p">[</span><span class="n">indices</span><span class="p">]</span><span class="o">.</span><span class="n">obsm</span><span class="p">[</span><span class="s1">&#39;protein&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">toarray</span><span class="p">()</span>

    <span class="k">return</span> <span class="n">MultiIndexable</span><span class="p">(</span>
        <span class="n">genes</span><span class="o">=</span><span class="n">gene_data</span><span class="p">,</span>
        <span class="n">proteins</span><span class="o">=</span><span class="n">protein_data</span>
    <span class="p">)</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">adata</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span>
    <span class="n">fetch_callback</span><span class="o">=</span><span class="n">fetch_multimodal</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="large-scale-training">
<h2>Large-Scale Training<a class="headerlink" href="#large-scale-training" title="Link to this heading">#</a></h2>
<section id="memory-efficient-data-loading">
<h3>Memory-Efficient Data Loading<a class="headerlink" href="#memory-efficient-data-loading" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">BlockWeightedSampling</span>

<span class="c1"># For very large datasets, use higher fetch factors</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">large_data_collection</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">4</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
    <span class="n">fetch_factor</span><span class="o">=</span><span class="mi">16</span><span class="p">,</span>  <span class="c1"># Fetch 16 batches worth of data at once</span>
<span class="p">)</span>

<span class="c1"># Configure DataLoader for optimal performance</span>
<span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span>
    <span class="n">dataset</span><span class="p">,</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
    <span class="n">num_workers</span><span class="o">=</span><span class="mi">12</span><span class="p">,</span>          <span class="c1"># Use multiple workers</span>
    <span class="n">prefetch_factor</span><span class="o">=</span><span class="mi">17</span><span class="p">,</span>      <span class="c1"># fetch_factor + 1</span>
    <span class="n">pin_memory</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>        <span class="c1"># For GPU training</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
<section id="subset-training-and-validation">
<h3>Subset Training and Validation<a class="headerlink" href="#subset-training-and-validation" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">sklearn.model_selection</span><span class="w"> </span><span class="kn">import</span> <span class="n">train_test_split</span>

<span class="c1"># Split indices for train/validation</span>
<span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">))</span>
<span class="n">train_idx</span><span class="p">,</span> <span class="n">val_idx</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">indices</span><span class="p">,</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.2</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">42</span><span class="p">)</span>

<span class="c1"># Training dataset</span>
<span class="n">train_dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">data</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">indices</span><span class="o">=</span><span class="n">train_idx</span><span class="p">,</span> <span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span>
<span class="p">)</span>

<span class="c1"># Validation dataset (streaming for deterministic evaluation)</span>
<span class="n">val_dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">data</span><span class="p">,</span>
    <span class="n">Streaming</span><span class="p">(</span><span class="n">indices</span><span class="o">=</span><span class="n">val_idx</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span>
<span class="p">)</span>

<span class="c1"># Training loader</span>
<span class="n">train_loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">train_dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>

<span class="c1"># Validation loader</span>
<span class="n">val_loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">val_dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>

<span class="c1"># Training loop</span>
<span class="k">for</span> <span class="n">epoch</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_epochs</span><span class="p">):</span>
    <span class="c1"># Training</span>
    <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">train_loader</span><span class="p">:</span>
        <span class="n">train_step</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>

    <span class="c1"># Validation</span>
    <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">val_loader</span><span class="p">:</span>
        <span class="n">val_step</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="custom-data-transformations">
<h2>Custom Data Transformations<a class="headerlink" href="#custom-data-transformations" title="Link to this heading">#</a></h2>
<section id="on-the-fly-normalization">
<h3>On-the-Fly Normalization<a class="headerlink" href="#on-the-fly-normalization" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span><span class="w"> </span><span class="nf">log_normalize</span><span class="p">(</span><span class="n">batch</span><span class="p">):</span>
    <span class="c1"># Apply log1p normalization per batch</span>
    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">log1p</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>

<span class="k">def</span><span class="w"> </span><span class="nf">standardize_genes</span><span class="p">(</span><span class="n">batch</span><span class="p">):</span>
    <span class="c1"># Standardize genes (features) across batch</span>
    <span class="k">return</span> <span class="p">(</span><span class="n">batch</span> <span class="o">-</span> <span class="n">batch</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">))</span> <span class="o">/</span> <span class="p">(</span><span class="n">batch</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1e-8</span><span class="p">)</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">data</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
    <span class="n">batch_transform</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">standardize_genes</span><span class="p">(</span><span class="n">log_normalize</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
<section id="data-augmentation">
<h3>Data Augmentation<a class="headerlink" href="#data-augmentation" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span><span class="w"> </span><span class="nf">add_noise</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">noise_level</span><span class="o">=</span><span class="mf">0.1</span><span class="p">):</span>
    <span class="c1"># Add Gaussian noise for data augmentation</span>
    <span class="n">noise</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">normal</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">noise_level</span><span class="p">,</span> <span class="n">batch</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
    <span class="k">return</span> <span class="n">batch</span> <span class="o">+</span> <span class="n">noise</span>

<span class="k">def</span><span class="w"> </span><span class="nf">dropout_genes</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">dropout_rate</span><span class="o">=</span><span class="mf">0.1</span><span class="p">):</span>
    <span class="c1"># Randomly set some genes to zero</span>
    <span class="n">mask</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">(</span><span class="n">batch</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">&gt;</span> <span class="n">dropout_rate</span>
    <span class="k">return</span> <span class="n">batch</span> <span class="o">*</span> <span class="n">mask</span>

<span class="k">def</span><span class="w"> </span><span class="nf">augment_batch</span><span class="p">(</span><span class="n">batch</span><span class="p">):</span>
    <span class="n">batch</span> <span class="o">=</span> <span class="n">add_noise</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>
    <span class="n">batch</span> <span class="o">=</span> <span class="n">dropout_genes</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span>
    <span class="k">return</span> <span class="n">batch</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">data</span><span class="p">,</span>
    <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
    <span class="n">batch_transform</span><span class="o">=</span><span class="n">augment_batch</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="working-with-huggingface-datasets">
<h2>Working with HuggingFace Datasets<a class="headerlink" href="#working-with-huggingface-datasets" title="Link to this heading">#</a></h2>
<section id="basic-usage">
<h3>Basic Usage<a class="headerlink" href="#basic-usage" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datasets</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_dataset</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">torch.utils.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataLoader</span>

<span class="c1"># Load a HuggingFace dataset</span>
<span class="n">hf_dataset</span> <span class="o">=</span> <span class="n">load_dataset</span><span class="p">(</span><span class="s2">&quot;imdb&quot;</span><span class="p">,</span> <span class="n">split</span><span class="o">=</span><span class="s2">&quot;train[:1000]&quot;</span><span class="p">)</span>

<span class="c1"># Custom batch callback for HuggingFace datasets</span>
<span class="k">def</span><span class="w"> </span><span class="nf">extract_hf_batch</span><span class="p">(</span><span class="n">fetched_data</span><span class="p">,</span> <span class="n">batch_indices</span><span class="p">):</span>

<span class="c1"># Create dataset with custom batch callback</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
<span class="p">)</span>

<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
</pre></div>
</div>
</section>
<section id="custom-processing-for-huggingface-data">
<h3>Custom Processing for HuggingFace Data<a class="headerlink" href="#custom-processing-for-huggingface-data" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span><span class="w"> </span><span class="nf">extract_hf_batch</span><span class="p">(</span><span class="n">fetched_data</span><span class="p">,</span> <span class="n">batch_indices</span><span class="p">):</span>

<span class="k">def</span><span class="w"> </span><span class="nf">process_hf_batch</span><span class="p">(</span><span class="n">batch_dict</span><span class="p">):</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="working-with-multiindexable">
<h2>Working with MultiIndexable<a class="headerlink" href="#working-with-multiindexable" title="Link to this heading">#</a></h2>
<p>The <code class="xref py py-class docutils literal notranslate"><span class="pre">MultiIndexable</span></code> class provides a convenient way to group multiple
indexable objects that should be indexed together. This is particularly useful
for multi-modal data or features and labels.</p>
<section id="basic-multiindexable-usage">
<h3>Basic MultiIndexable Usage<a class="headerlink" href="#basic-multiindexable-usage" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">MultiIndexable</span><span class="p">,</span> <span class="n">scDataset</span><span class="p">,</span> <span class="n">Streaming</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">torch.utils.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataLoader</span>

<span class="c1"># Create sample data</span>
<span class="n">features</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1000</span><span class="p">,</span> <span class="mi">50</span><span class="p">)</span>  <span class="c1"># Features</span>
<span class="n">labels</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1000</span><span class="p">)</span>  <span class="c1"># Labels</span>

<span class="c1"># Group them together</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">labels</span><span class="p">,</span> <span class="n">names</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;X&#39;</span><span class="p">,</span> <span class="s1">&#39;y&#39;</span><span class="p">])</span>

<span class="c1"># Or using dictionary syntax</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span><span class="n">X</span><span class="o">=</span><span class="n">features</span><span class="p">,</span> <span class="n">y</span><span class="o">=</span><span class="n">labels</span><span class="p">)</span>

<span class="c1"># Create dataset</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">Streaming</span><span class="p">(),</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">)</span>
<span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>

<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">loader</span><span class="p">:</span>
    <span class="n">X_batch</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;X&#39;</span><span class="p">]</span>  <span class="c1"># or batch[0]</span>
    <span class="n">y_batch</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;y&#39;</span><span class="p">]</span>  <span class="c1"># or batch[1]</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Features: </span><span class="si">{</span><span class="n">X_batch</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">, Labels: </span><span class="si">{</span><span class="n">y_batch</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
    <span class="k">break</span>
</pre></div>
</div>
</section>
<section id="multi-modal-single-cell-data">
<h3>Multi-Modal Single-Cell Data<a class="headerlink" href="#multi-modal-single-cell-data" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Simulate CITE-seq data (RNA + protein)</span>
<span class="n">n_cells</span> <span class="o">=</span> <span class="mi">5000</span>
<span class="n">rna_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">n_cells</span><span class="p">,</span> <span class="mi">2000</span><span class="p">)</span>      <span class="c1"># Gene expression</span>
<span class="n">protein_data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">n_cells</span><span class="p">,</span> <span class="mi">50</span><span class="p">)</span>    <span class="c1"># Surface proteins</span>
<span class="n">cell_types</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">([</span><span class="s1">&#39;T&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;NK&#39;</span><span class="p">],</span> <span class="n">n_cells</span><span class="p">)</span>  <span class="c1"># Labels</span>

<span class="c1"># Group all modalities</span>
<span class="n">cite_seq_data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span>
    <span class="n">rna</span><span class="o">=</span><span class="n">rna_data</span><span class="p">,</span>
    <span class="n">proteins</span><span class="o">=</span><span class="n">protein_data</span><span class="p">,</span>
    <span class="n">cell_types</span><span class="o">=</span><span class="n">cell_types</span>
<span class="p">)</span>

<span class="c1"># Use with class-balanced sampling</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">scdataset</span><span class="w"> </span><span class="kn">import</span> <span class="n">ClassBalancedSampling</span>
<span class="n">strategy</span> <span class="o">=</span> <span class="n">ClassBalancedSampling</span><span class="p">(</span><span class="n">cell_types</span><span class="p">,</span> <span class="n">total_size</span><span class="o">=</span><span class="mi">2000</span><span class="p">,</span> <span class="n">block_size</span><span class="o">=</span><span class="mi">16</span><span class="p">)</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span><span class="n">cite_seq_data</span><span class="p">,</span> <span class="n">strategy</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span><span class="p">)</span>

<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">dataset</span><span class="p">:</span>
    <span class="n">rna</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;rna&#39;</span><span class="p">]</span>           <span class="c1"># RNA expression for 32 cells</span>
    <span class="n">proteins</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;proteins&#39;</span><span class="p">]</span> <span class="c1"># Protein expression for same 32 cells</span>
    <span class="n">types</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="s1">&#39;cell_types&#39;</span><span class="p">]</span>  <span class="c1"># Cell type labels for same 32 cells</span>
    <span class="c1"># All data is synchronized - same cells across modalities</span>
    <span class="k">break</span>
</pre></div>
</div>
</section>
<section id="subsetting-and-indexing">
<h3>Subsetting and Indexing<a class="headerlink" href="#subsetting-and-indexing" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Create MultiIndexable</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">MultiIndexable</span><span class="p">(</span>
    <span class="n">features</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1000</span><span class="p">,</span> <span class="mi">100</span><span class="p">),</span>
    <span class="n">labels</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">1000</span><span class="p">),</span>
    <span class="n">metadata</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1000</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
<span class="p">)</span>

<span class="c1"># Access individual indexables</span>
<span class="n">features</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">]</span>  <span class="c1"># or data[0]</span>
<span class="n">labels</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="s1">&#39;labels&#39;</span><span class="p">]</span>      <span class="c1"># or data[1]</span>

<span class="c1"># Subset by sample indices - returns new MultiIndexable</span>
<span class="n">subset</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="mi">100</span><span class="p">:</span><span class="mi">200</span><span class="p">]</span>       <span class="c1"># Samples 100-199 from all modalities</span>
<span class="n">train_data</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="n">train_indices</span><span class="p">]</span>  <span class="c1"># Training subset</span>

<span class="c1"># Check properties</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Original length: </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>      <span class="c1"># 1000 samples</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Subset length: </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">subset</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>      <span class="c1"># 100 samples</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Number of modalities: </span><span class="si">{</span><span class="n">data</span><span class="o">.</span><span class="n">count</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span> <span class="c1"># 3 modalities</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Modality names: </span><span class="si">{</span><span class="n">data</span><span class="o">.</span><span class="n">names</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>      <span class="c1"># [&#39;features&#39;, &#39;labels&#39;, &#39;metadata&#39;]</span>
</pre></div>
</div>
</section>
</section>
<section id="integration-with-pytorch-lightning">
<h2>Integration with PyTorch Lightning<a class="headerlink" href="#integration-with-pytorch-lightning" title="Link to this heading">#</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pytorch_lightning</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pl</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">torch.utils.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">DataLoader</span>

<span class="k">class</span><span class="w"> </span><span class="nc">SingleCellDataModule</span><span class="p">(</span><span class="n">pl</span><span class="o">.</span><span class="n">LightningDataModule</span><span class="p">):</span>
    <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data_path</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">):</span>
        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">data_path</span> <span class="o">=</span> <span class="n">data_path</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">=</span> <span class="n">batch_size</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">num_workers</span> <span class="o">=</span> <span class="n">num_workers</span>

    <span class="k">def</span><span class="w"> </span><span class="nf">setup</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">stage</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
        <span class="c1"># Load your data</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">load_data</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_path</span><span class="p">)</span>

        <span class="c1"># Split indices</span>
        <span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">))</span>
        <span class="n">train_idx</span><span class="p">,</span> <span class="n">val_idx</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">indices</span><span class="p">,</span> <span class="n">test_size</span><span class="o">=</span><span class="mf">0.2</span><span class="p">)</span>

        <span class="c1"># Create datasets</span>
        <span class="bp">self</span><span class="o">.</span><span class="n">train_dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">,</span>
            <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">),</span>
            <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span>
        <span class="p">)</span>

        <span class="bp">self</span><span class="o">.</span><span class="n">val_dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">,</span>
            <span class="n">Streaming</span><span class="p">(</span><span class="n">indices</span><span class="o">=</span><span class="n">val_idx</span><span class="p">),</span>
            <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span>
        <span class="p">)</span>

    <span class="k">def</span><span class="w"> </span><span class="nf">train_dataloader</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
        <span class="k">return</span> <span class="n">DataLoader</span><span class="p">(</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">train_dataset</span><span class="p">,</span>
            <span class="n">num_workers</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span>
            <span class="n">prefetch_factor</span><span class="o">=</span><span class="mi">2</span>
        <span class="p">)</span>

    <span class="k">def</span><span class="w"> </span><span class="nf">val_dataloader</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
        <span class="k">return</span> <span class="n">DataLoader</span><span class="p">(</span>
            <span class="bp">self</span><span class="o">.</span><span class="n">val_dataset</span><span class="p">,</span>
            <span class="n">num_workers</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_workers</span><span class="p">,</span>
            <span class="n">prefetch_factor</span><span class="o">=</span><span class="mi">2</span>
        <span class="p">)</span>
</pre></div>
</div>
</section>
<section id="advanced-sampling-strategies">
<h2>Advanced Sampling Strategies<a class="headerlink" href="#advanced-sampling-strategies" title="Link to this heading">#</a></h2>
<section id="custom-weighted-sampling">
<h3>Custom Weighted Sampling<a class="headerlink" href="#custom-weighted-sampling" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Create weights based on cell type frequency (inverse frequency weighting)</span>
<span class="n">cell_types</span> <span class="o">=</span> <span class="n">adata</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="s1">&#39;cell_type&#39;</span><span class="p">]</span>
<span class="n">type_counts</span> <span class="o">=</span> <span class="n">cell_types</span><span class="o">.</span><span class="n">value_counts</span><span class="p">()</span>
<span class="n">weights</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="n">type_counts</span><span class="p">[</span><span class="n">cell_types</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">weights</span> <span class="o">/</span> <span class="n">weights</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>  <span class="c1"># Normalize</span>

<span class="n">strategy</span> <span class="o">=</span> <span class="n">BlockWeightedSampling</span><span class="p">(</span>
    <span class="n">weights</span><span class="o">=</span><span class="n">weights</span><span class="p">,</span>
    <span class="n">total_size</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span>
    <span class="n">block_size</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
    <span class="n">replace</span><span class="o">=</span><span class="kc">True</span>
<span class="p">)</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span><span class="n">adata</span><span class="p">,</span> <span class="n">strategy</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="temporal-sampling-for-time-series-data">
<h3>Temporal Sampling for Time-Series Data<a class="headerlink" href="#temporal-sampling-for-time-series-data" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Custom strategy for time-series single-cell data</span>
<span class="k">def</span><span class="w"> </span><span class="nf">create_temporal_indices</span><span class="p">(</span><span class="n">timepoints</span><span class="p">,</span> <span class="n">window_size</span><span class="o">=</span><span class="mi">5</span><span class="p">):</span>
    <span class="n">indices</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">timepoints</span><span class="p">)</span> <span class="o">-</span> <span class="n">window_size</span> <span class="o">+</span> <span class="mi">1</span><span class="p">):</span>
        <span class="n">indices</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">i</span> <span class="o">+</span> <span class="n">window_size</span><span class="p">))</span>
    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">indices</span><span class="p">)</span>

<span class="n">temporal_indices</span> <span class="o">=</span> <span class="n">create_temporal_indices</span><span class="p">(</span><span class="n">adata</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="s1">&#39;timepoint&#39;</span><span class="p">])</span>

<span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
    <span class="n">adata</span><span class="p">,</span>
    <span class="n">Streaming</span><span class="p">(</span><span class="n">indices</span><span class="o">=</span><span class="n">temporal_indices</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="mi">32</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="performance-benchmarking">
<h2>Performance Benchmarking<a class="headerlink" href="#performance-benchmarking" title="Link to this heading">#</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">time</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">contextlib</span><span class="w"> </span><span class="kn">import</span> <span class="n">contextmanager</span>

<span class="nd">@contextmanager</span>
<span class="k">def</span><span class="w"> </span><span class="nf">timer</span><span class="p">():</span>
    <span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
    <span class="k">yield</span>
    <span class="n">end</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Time taken: </span><span class="si">{</span><span class="n">end</span><span class="w"> </span><span class="o">-</span><span class="w"> </span><span class="n">start</span><span class="si">:</span><span class="s2">.2f</span><span class="si">}</span><span class="s2"> seconds&quot;</span><span class="p">)</span>

<span class="c1"># Compare different configurations</span>
<span class="n">configs</span> <span class="o">=</span> <span class="p">[</span>
    <span class="p">{</span><span class="s1">&#39;block_size&#39;</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span> <span class="s1">&#39;fetch_factor&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">},</span>
    <span class="p">{</span><span class="s1">&#39;block_size&#39;</span><span class="p">:</span> <span class="mi">64</span><span class="p">,</span> <span class="s1">&#39;fetch_factor&#39;</span><span class="p">:</span> <span class="mi">2</span><span class="p">},</span>
    <span class="p">{</span><span class="s1">&#39;block_size&#39;</span><span class="p">:</span> <span class="mi">128</span><span class="p">,</span> <span class="s1">&#39;fetch_factor&#39;</span><span class="p">:</span> <span class="mi">4</span><span class="p">},</span>
<span class="p">]</span>

<span class="k">for</span> <span class="n">config</span> <span class="ow">in</span> <span class="n">configs</span><span class="p">:</span>
    <span class="n">dataset</span> <span class="o">=</span> <span class="n">scDataset</span><span class="p">(</span>
        <span class="n">large_data</span><span class="p">,</span>
        <span class="n">BlockShuffling</span><span class="p">(</span><span class="n">block_size</span><span class="o">=</span><span class="n">config</span><span class="p">[</span><span class="s1">&#39;block_size&#39;</span><span class="p">]),</span>
        <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
        <span class="n">fetch_factor</span><span class="o">=</span><span class="n">config</span><span class="p">[</span><span class="s1">&#39;fetch_factor&#39;</span><span class="p">]</span>
    <span class="p">)</span>

    <span class="n">loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>

    <span class="k">with</span> <span class="n">timer</span><span class="p">():</span>
        <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">batch</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">loader</span><span class="p">):</span>
            <span class="k">if</span> <span class="n">i</span> <span class="o">&gt;=</span> <span class="mi">100</span><span class="p">:</span>  <span class="c1"># Test first 100 batches</span>
                <span class="k">break</span>

    <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Config </span><span class="si">{</span><span class="n">config</span><span class="si">}</span><span class="s2">: done&quot;</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="tips-and-best-practices">
<h2>Tips and Best Practices<a class="headerlink" href="#tips-and-best-practices" title="Link to this heading">#</a></h2>
<ol class="arabic simple">
<li><p><strong>Choose appropriate block sizes</strong>: Larger blocks (128-512) work better for sequential data access, smaller blocks (16-64) for more randomness.</p></li>
<li><p><strong>Use fetch_factor &gt; 1</strong> for better I/O efficiency, especially with slow storage.</p></li>
<li><p><strong>Set prefetch_factor = fetch_factor + 1</strong> in DataLoader for optimal performance.</p></li>
<li><p><strong>For validation</strong>, use <code class="docutils literal notranslate"><span class="pre">Streaming</span></code> strategy for deterministic results.</p></li>
<li><p><strong>For large datasets</strong>, consider using fewer workers but higher fetch_factor to reduce memory overhead.</p></li>
<li><p><strong>Profile your pipeline</strong> to find the optimal configuration for your specific data and hardware setup.</p></li>
</ol>
</section>
</section>


                </article>


                <footer class="prev-next-footer d-print-none">

<div class="prev-next-area">
    <a class="left-prev"
       href="quickstart.html"
       title="previous page">
      <i class="fa-solid fa-angle-left"></i>
      <div class="prev-next-info">
        <p class="prev-next-subtitle">previous</p>
        <p class="prev-next-title">Quick Start Guide</p>
      </div>
    </a>
    <a class="right-next"
       href="scdataset.html"
       title="next page">
      <div class="prev-next-info">
        <p class="prev-next-subtitle">next</p>
        <p class="prev-next-title">API Reference</p>
      </div>
      <i class="fa-solid fa-angle-right"></i>
    </a>
</div>
                </footer>

            </div>


                <div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">


  <div class="sidebar-secondary-item">
  <div class="page-toc tocsection onthispage">
    <i class="fa-solid fa-list"></i> Contents
  </div>
  <nav class="bd-toc-nav page-toc">
    <ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#single-cell-data-analysis">Single-Cell Data Analysis</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#working-with-anndata">Working with AnnData</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#class-balanced-training">Class-Balanced Training</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#multi-modal-data">Multi-Modal Data</a></li>