scdataloader 1.2.2__tar.gz → 1.6.4__tar.gz

{scdataloader-1.2.2 → scdataloader-1.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scdataloader
-Version: 1.2.2
+Version: 1.6.4
 Summary: a dataloader for single cell data in lamindb
 Project-URL: repository, https://github.com/jkobject/scDataLoader
 Author-email: jkobject <jkobject@gmail.com>
@@ -11,6 +11,7 @@ Requires-Dist: anndata>=0.9.0
 Requires-Dist: biomart>=0.9.0
 Requires-Dist: cellxgene-census>=0.1.0
 Requires-Dist: django>=4.0.0
+Requires-Dist: harmonypy>=0.0.10
 Requires-Dist: ipykernel>=6.20.0
 Requires-Dist: lamindb[bionty]==0.76.12
 Requires-Dist: leidenalg>=0.8.0
@@ -49,6 +50,8 @@ Description-Content-Type: text/markdown
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![DOI](https://img.shields.io/badge/DOI-10.1101%2F2024.07.29.605556-blue)](https://doi.org/10.1101/2024.07.29.605556)
 
+<img src="scdataloader.png" width="600">
+
 This single cell pytorch dataloader / lighting datamodule is designed to be used with:
 
 - [lamindb](https://lamin.ai/)

{scdataloader-1.2.2 → scdataloader-1.6.4}/README.md

@@ -10,6 +10,8 @@
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![DOI](https://img.shields.io/badge/DOI-10.1101%2F2024.07.29.605556-blue)](https://doi.org/10.1101/2024.07.29.605556)
 
+<img src="scdataloader.png" width="600">
+
 This single cell pytorch dataloader / lighting datamodule is designed to be used with:
 
 - [lamindb](https://lamin.ai/)

{scdataloader-1.2.2 → scdataloader-1.6.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "scdataloader"
-version = "1.2.2"
+version = "1.6.4"
 description = "a dataloader for single cell data in lamindb"
 authors = [
     {name = "jkobject", email = "jkobject@gmail.com"}
@@ -26,6 +26,7 @@ dependencies = [
     "django>=4.0.0",
     "scikit-misc>=0.5.0",
     "palantir>=1.3.3",
+    "harmonypy>=0.0.10",
 ]
 
 [project.optional-dependencies]

scdataloader-1.6.4/scdataloader/VERSION

@@ -0,0 +1 @@
+1.6.4

{scdataloader-1.2.2 → scdataloader-1.6.4}/scdataloader/data.py

@@ -97,8 +97,8 @@ class Dataset(torchDataset):
             for clss in self.clss_to_pred:
                 if clss not in self.hierarchical_clss:
                     # otherwise it's already been done
-                    self.class_topred[clss] = self.mapped_dataset.get_merged_categories(
-                        clss
+                    self.class_topred[clss] = set(
+                        self.mapped_dataset.get_merged_categories(clss)
                     )
                     if (
                         self.mapped_dataset.unknown_label

{scdataloader-1.2.2 → scdataloader-1.6.4}/scdataloader/datamodule.py

@@ -290,7 +290,7 @@ class DataModule(L.LightningDataModule):
                     break
                 else:
                     self.test_datasets.append(
-                        self.dataset.mapped_dataset._path_list[i].path
+                        self.dataset.mapped_dataset.path_list[i].path
                     )
                     cs += c
             len_test = cs

{scdataloader-1.2.2 → scdataloader-1.6.4}/scdataloader/utils.py

@@ -378,6 +378,169 @@ def load_genes(organisms: Union[str, list] = "NCBITaxon:9606"):  # "NCBITaxon:10
     ]:
         if col in organismdf.columns:
             organismdf.drop(columns=[col], inplace=True)
+    # temp fix
+    drop = {
+        "ENSG00000112096",
+        "ENSG00000137808",
+        "ENSG00000161149",
+        "ENSG00000182230",
+        "ENSG00000203812",
+        "ENSG00000204092",
+        "ENSG00000205485",
+        "ENSG00000212951",
+        "ENSG00000215271",
+        "ENSG00000221995",
+        "ENSG00000224739",
+        "ENSG00000224745",
+        "ENSG00000225178",
+        "ENSG00000225932",
+        "ENSG00000226377",
+        "ENSG00000226380",
+        "ENSG00000226403",
+        "ENSG00000227021",
+        "ENSG00000227220",
+        "ENSG00000227902",
+        "ENSG00000228139",
+        "ENSG00000228206",
+        "ENSG00000228906",
+        "ENSG00000229352",
+        "ENSG00000231575",
+        "ENSG00000232196",
+        "ENSG00000232295",
+        "ENSG00000233776",
+        "ENSG00000236166",
+        "ENSG00000236673",
+        "ENSG00000236740",
+        "ENSG00000236886",
+        "ENSG00000236996",
+        "ENSG00000237133",
+        "ENSG00000237513",
+        "ENSG00000237548",
+        "ENSG00000237838",
+        "ENSG00000239446",
+        "ENSG00000239467",
+        "ENSG00000239665",
+        "ENSG00000244693",
+        "ENSG00000244952",
+        "ENSG00000249860",
+        "ENSG00000251044",
+        "ENSG00000253878",
+        "ENSG00000254561",
+        "ENSG00000254740",
+        "ENSG00000255633",
+        "ENSG00000255823",
+        "ENSG00000256045",
+        "ENSG00000256222",
+        "ENSG00000256374",
+        "ENSG00000256427",
+        "ENSG00000256618",
+        "ENSG00000256863",
+        "ENSG00000256892",
+        "ENSG00000258414",
+        "ENSG00000258808",
+        "ENSG00000258861",
+        "ENSG00000259444",
+        "ENSG00000259820",
+        "ENSG00000259834",
+        "ENSG00000259855",
+        "ENSG00000260461",
+        "ENSG00000261068",
+        "ENSG00000261438",
+        "ENSG00000261490",
+        "ENSG00000261534",
+        "ENSG00000261737",
+        "ENSG00000261773",
+        "ENSG00000261963",
+        "ENSG00000262668",
+        "ENSG00000263464",
+        "ENSG00000267637",
+        "ENSG00000268955",
+        "ENSG00000269028",
+        "ENSG00000269900",
+        "ENSG00000269933",
+        "ENSG00000269966",
+        "ENSG00000270188",
+        "ENSG00000270394",
+        "ENSG00000270672",
+        "ENSG00000271043",
+        "ENSG00000271409",
+        "ENSG00000271734",
+        "ENSG00000271870",
+        "ENSG00000272040",
+        "ENSG00000272196",
+        "ENSG00000272267",
+        "ENSG00000272354",
+        "ENSG00000272370",
+        "ENSG00000272551",
+        "ENSG00000272567",
+        "ENSG00000272880",
+        "ENSG00000272904",
+        "ENSG00000272934",
+        "ENSG00000273301",
+        "ENSG00000273370",
+        "ENSG00000273496",
+        "ENSG00000273576",
+        "ENSG00000273614",
+        "ENSG00000273837",
+        "ENSG00000273888",
+        "ENSG00000273923",
+        "ENSG00000276612",
+        "ENSG00000276814",
+        "ENSG00000277050",
+        "ENSG00000277077",
+        "ENSG00000277352",
+        "ENSG00000277666",
+        "ENSG00000277761",
+        "ENSG00000278198",
+        "ENSG00000278782",
+        "ENSG00000278927",
+        "ENSG00000278955",
+        "ENSG00000279226",
+        "ENSG00000279765",
+        "ENSG00000279769",
+        "ENSG00000279948",
+        "ENSG00000280058",
+        "ENSG00000280095",
+        "ENSG00000280250",
+        "ENSG00000280346",
+        "ENSG00000280374",
+        "ENSG00000280710",
+        "ENSG00000282080",
+        "ENSG00000282246",
+        "ENSG00000282965",
+        "ENSG00000283486",
+        "ENSG00000284299",
+        "ENSG00000284741",
+        "ENSG00000285106",
+        "ENSG00000285162",
+        "ENSG00000285476",
+        "ENSG00000285762",
+        "ENSG00000286065",
+        "ENSG00000286228",
+        "ENSG00000286601",
+        "ENSG00000286699",
+        "ENSG00000286949",
+        "ENSG00000286996",
+        "ENSG00000287116",
+        "ENSG00000287388",
+        "ENSG00000288541",
+        "ENSG00000288546",
+        "ENSG00000288630",
+        "ENSG00000288639",
+        "ENSMUSG00000069518",
+        "ENSMUSG00000073682",
+        "ENSMUSG00000075014",
+        "ENSMUSG00000075015",
+        "ENSMUSG00000078091",
+        "ENSMUSG00000094958",
+        "ENSMUSG00000095547",
+        "ENSMUSG00000095891",
+        "ENSMUSG00000096385",
+        "ENSMUSG00000096519",
+        "ENSMUSG00000096923",
+        "ENSMUSG00000097078",
+    }
+    organismdf = organismdf[~organismdf.index.isin(drop)]
     return organismdf
 
 

scdataloader-1.2.2/scdataloader/VERSION

@@ -1 +0,0 @@
-1.2.2