scdataloader 1.2.1__py3-none-any.whl → 1.2.2__py3-none-any.whl

scdataloader/VERSION

@@ -1 +1 @@
-1.2.1
+1.2.2

scdataloader/__main__.py

@@ -53,14 +53,14 @@ def main():
     )
     parser.add_argument(
         "--filter_gene_by_counts",
-        type=Union[int, bool],
-        default=False,
+        type=int,
+        default=0,
         help="Determines whether to filter genes by counts.",
     )
     parser.add_argument(
         "--filter_cell_by_counts",
-        type=Union[int, bool],
-        default=False,
+        type=int,
+        default=0,
         help="Determines whether to filter cells by counts.",
     )
     parser.add_argument(
@@ -153,6 +153,12 @@ def main():
         default=False,
         help="Determines whether to do postprocessing.",
     )
+    parser.add_argument(
+        "--cache",
+        type=bool,
+        default=True,
+        help="Determines whether to cache the dataset.",
+    )
     args = parser.parse_args()
 
     # Load the collection
@@ -178,6 +184,7 @@ def main():
         normalize_sum=args.normalize_sum,
         subset_hvg=args.subset_hvg,
         hvg_flavor=args.hvg_flavor,
+        cache=args.cache,
         binning=args.binning,
         result_binned_key=args.result_binned_key,
         length_normalize=args.length_normalize,

scdataloader/utils.py

@@ -127,15 +127,15 @@ def getBiomartTable(
 
     cache_folder = os.path.expanduser(cache_folder)
     createFoldersFor(cache_folder)
-    cachefile = os.path.join(cache_folder, ".biomart.csv")
+    cachefile = os.path.join(cache_folder, ".biomart.parquet")
     if useCache & os.path.isfile(cachefile):
         print("fetching gene names from biomart cache")
-        res = pd.read_csv(cachefile)
+        res = pd.read_parquet(cachefile)
     else:
         print("downloading gene names from biomart")
 
         res = _fetchFromServer(ensemble_server, attr + attributes, database=database)
-        res.to_csv(cachefile, index=False)
+        res.to_parquet(cachefile, index=False)
     res.columns = attr + attributes
     if type(res) is not type(pd.DataFrame()):
         raise ValueError("should be a dataframe")
@@ -368,7 +368,14 @@ def load_genes(organisms: Union[str, list] = "NCBITaxon:9606"):  # "NCBITaxon:10
         genesdf["organism"] = organism
         organismdf.append(genesdf)
     organismdf = pd.concat(organismdf)
-    for col in ["source_id", "run_id", "created_by_id", "updated_at", "stable_id", "created_at"]:
+    for col in [
+        "source_id",
+        "run_id",
+        "created_by_id",
+        "updated_at",
+        "stable_id",
+        "created_at",
+    ]:
         if col in organismdf.columns:
             organismdf.drop(columns=[col], inplace=True)
     return organismdf
@@ -412,7 +419,7 @@ def populate_my_ontology(
     # cell type
     if celltypes is not None:
         if len(celltypes) == 0:
-            bt.CellType.import_from_source()
+            bt.CellType.import_from_source(update=True)
         else:
             names = bt.CellType.public().df().index if not celltypes else celltypes
             records = bt.CellType.from_values(names, field="ontology_id")
@@ -446,7 +453,7 @@ def populate_my_ontology(
     # ethnicity
     if ethnicities is not None:
         if len(ethnicities) == 0:
-            bt.Ethnicity.import_from_source()
+            bt.Ethnicity.import_from_source(update=True)
         else:
             names = bt.Ethnicity.public().df().index if not ethnicities else ethnicities
             records = bt.Ethnicity.from_values(names, field="ontology_id")
@@ -457,7 +464,7 @@ def populate_my_ontology(
     # ExperimentalFactor
     if assays is not None:
         if len(assays) == 0:
-            bt.ExperimentalFactor.import_from_source()
+            bt.ExperimentalFactor.import_from_source(update=True)
         else:
             names = bt.ExperimentalFactor.public().df().index if not assays else assays
             records = bt.ExperimentalFactor.from_values(names, field="ontology_id")
@@ -468,7 +475,7 @@ def populate_my_ontology(
     # Tissue
     if tissues is not None:
         if len(tissues) == 0:
-            bt.Tissue.import_from_source()
+            bt.Tissue.import_from_source(update=True)
         else:
             names = bt.Tissue.public().df().index if not tissues else tissues
             records = bt.Tissue.from_values(names, field="ontology_id")
@@ -477,7 +484,7 @@ def populate_my_ontology(
     # DevelopmentalStage
     if dev_stages is not None:
         if len(dev_stages) == 0:
-            bt.DevelopmentalStage.import_from_source()
+            bt.DevelopmentalStage.import_from_source(update=True)
             source = bt.PublicSource.filter(organism="mouse", name="mmusdv").last()
             bt.DevelopmentalStage.import_from_source(source=source)
         else:
@@ -493,7 +500,7 @@ def populate_my_ontology(
     # Disease
     if diseases is not None:
         if len(diseases) == 0:
-            bt.Disease.import_from_source()
+            bt.Disease.import_from_source(update=True)
         else:
             names = bt.Disease.public().df().index if not diseases else diseases
             records = bt.Disease.from_values(names, field="ontology_id")

{scdataloader-1.2.1.dist-info → scdataloader-1.2.2.dist-info}/METADATA

@@ -1,11 +1,10 @@
 Metadata-Version: 2.3
 Name: scdataloader
-Version: 1.2.1
+Version: 1.2.2
 Summary: a dataloader for single cell data in lamindb
 Project-URL: repository, https://github.com/jkobject/scDataLoader
 Author-email: jkobject <jkobject@gmail.com>
-License-Expression: MIT
-License-File: LICENSE
+License: MIT
 Keywords: dataloader,lamindb,pytorch,scPRINT,scRNAseq
 Requires-Python: <3.11,>=3.10
 Requires-Dist: anndata>=0.9.0
@@ -18,6 +17,7 @@ Requires-Dist: leidenalg>=0.8.0
 Requires-Dist: lightning>=2.0.0
 Requires-Dist: matplotlib>=3.5.0
 Requires-Dist: numpy>=1.26.0
+Requires-Dist: palantir>=1.3.3
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: scikit-misc>=0.5.0
 Requires-Dist: seaborn>=0.11.0

{scdataloader-1.2.1.dist-info → scdataloader-1.2.2.dist-info}/RECORD

@@ -1,14 +1,14 @@
-scdataloader/VERSION,sha256=bPTghLR_M8mwLveSedFXgzho-PcFFBaadovjU-4yj-o,6
+scdataloader/VERSION,sha256=xipcxhrEUlk1dT9ewoTAoFKksdpLOjWA3OK313ohVK4,6
 scdataloader/__init__.py,sha256=5y9VzRhOAUWeYMn2MrRRRlzgdiMjRFytr7gcn-I6IkE,147
-scdataloader/__main__.py,sha256=Hu7Bnc7P4UfOzNWyDAVoNZsItgy27hldaw3y8OS3gPM,6387
+scdataloader/__main__.py,sha256=VXrt2IykBypnIXWydwA7NfF7LtRGc-0Khjtm5OIBNpI,6527
 scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
 scdataloader/collator.py,sha256=gzHiuixUwK8JClhAbG12kgWMU_VTKkowibA-tDFpbwo,11341
 scdataloader/config.py,sha256=rrW2DZxG4J2_pmpDbXXsaKJkpNC57w5dIlItiFbANYw,2905
 scdataloader/data.py,sha256=3dCp-lIAfOkCi76SH5W3iSqFmAWZslwARkN9v5mylz8,14907
 scdataloader/datamodule.py,sha256=B-udBevPSPF__hfy0pOz1dGovgE95K2pxPupjB7RblI,16936
 scdataloader/preprocess.py,sha256=pH4EPrcRqH34o3t5X3A4kETiYdCZngih5SdP_PPfgOo,29178
-scdataloader/utils.py,sha256=5-6CnI3Utn5XFpqgZiJa0MT6gfvkFNg078SgrE6P4s8,22365
-scdataloader-1.2.1.dist-info/METADATA,sha256=JeE7j8HkByp_MMGVXp4GOvpdkjIjoyEoByXA-FWISuk,9802
-scdataloader-1.2.1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-scdataloader-1.2.1.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-scdataloader-1.2.1.dist-info/RECORD,,
+scdataloader/utils.py,sha256=7tgt3sPj_XTKb-UlJDAZWvQr0_DG9VTC6ioiLdBWFFE,22498
+scdataloader-1.2.2.dist-info/METADATA,sha256=XMtKO9ImiyY--F92njvMUe69OaJgDx8C3xQtBAXqo8g,9800
+scdataloader-1.2.2.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
+scdataloader-1.2.2.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+scdataloader-1.2.2.dist-info/RECORD,,

{scdataloader-1.2.1.dist-info → scdataloader-1.2.2.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.26.3
 Root-Is-Purelib: true
 Tag: py3-none-any