scdataloader 0.0.4__py3-none-any.whl → 1.0.1__py3-none-any.whl

scdataloader/preprocess.py

@@ -204,7 +204,9 @@ class Preprocessor:
             )
         )
 
-        if self.is_symbol:
+        if self.is_symbol or not adata.var.index.str.contains("ENSG").any():
+            if not adata.var.index.str.contains("ENSG").any():
+                print("No ENSG genes found, assuming gene symbols...")
             genesdf["ensembl_gene_id"] = genesdf.index
             var = (
                 adata.var.merge(
@@ -692,209 +694,3 @@ def additional_postprocess(adata):
     # to query N next time points we just get the N elements below and check they are in the group
     # to query the N nearest neighbors we just get the N elements above and N below and check they are in the group
     return adata
-
-
-"""
-sexr = {
-    "Male": "PATO:0000384",
-    "Female": "PATO:0000383",
-}
-tissuer = {
-    "Kidney": "UBERON:0002113",
-    "Lung": "UBERON:0002048",
-    "Heart": "UBERON:0000948",
-    "Liver": "UBERON:0002107",
-    "Brain": "UBERON:0000955",
-    "BAT": "UBERON:0001348",
-    "Jejunum": "UBERON:0002115",
-    "Colon": "UBERON:0001155",
-    "Ileum": "UBERON:0002116",
-    "Stomach": "UBERON:0000945",
-    "gWAT": "UBERON:0001347",
-    "Duodenum": "UBERON:0002114",
-    "iWAT": "UBERON:0001347",
-    "Muscle": "UBERON:0001630",
-}
-ager = {
-    "03_months": "MmusDv:0000063",
-    "16_months": "MmusDv:0000087",
-    "06_months": "MmusDv:0000077",
-    "23_months": "MmusDv:0000127",
-    "12_months": "MmusDv:0000083",
-    "21_months": "MmusDv:0000125",
-}
-
-celltyper = {
-    "Proximal tubule cells": "epithelial cell of proximal tubule",
-    "Vascular endothelial cells": "endothelial cell of vascular tree",
-    "Intestinal epithelial cells": "intestinal epithelial cell",
-    "Hepatocytes": "hepatocyte",
-    "Fibroblasts": "fibroblast",
-    "Lymphoid cells_T cells": "T cell",
-    "Myeloid cells": "myeloid cell",
-    "Brown adipocytes": "brown fat cell",
-    "Lymphoid cells_B cells": "B cell",
-    "Adipocytes": "fat cell",
-    "Type II alveolar epithelial cells": "type II pneumocyte",
-    "Colonic epithelial cells": "colon epithelial cell",
-    "Mural cells": "mural cell",
-    "Cerebellum granule neurons": "cerebellar neuron",
-    "Goblet cells": "goblet cell",
-    "Vascular endothelial cells_General capillary cells": "endothelial cell of vascular tree",
-    "Ventricular cardiomyocytes": "regular ventricular cardiac myocyte",
-    "Type II myonuclei": "type II muscle cell",
-    "Thick ascending limb of LOH cells": "vasa recta ascending limb cell",
-    "Gastric mucous cells": "mucous cell of stomach",
-    "Distal convoluted tubule cells": "kidney distal convoluted tubule epithelial cell",
-    "Adipoce stem and progenitor cells": "hepatic oval stem cell",
-    "Chief cells": "chief cell of parathyroid gland",
-    "Paneth cells": "paneth cell",
-    "Myeloid cells_Alveolar macrophages": "alveolar macrophage",
-    "Lymphoid cells_Plasma cells": "plasma cell",
-    "Secretory cells": "secretory cell",
-    "Lymphoid cells_Resting B cells": "B cell",
-    "Cortical projection neurons 1": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Endocardial endothelial cells": "endocardial cell",
-    "Type I alveolar epithelial cells": "type I pneumocyte",
-    "Interbrain and midbrain neurons 1": "midbrain dopaminergic neuron",
-    "Interbrain and midbrain neurons 2": "midbrain dopaminergic neuron",
-    "Myeloid cells_Monocytes": "monocyte",
-    "Myeloid cells_Dendritic cells": "myeloid dendritic cell",
-    "Oligodendrocytes": "oligodendrocyte",
-    "Lymphatic endothelial cells": "endothelial cell of lymphatic vessel",
-    "Enteroendocrine cells": "enteroendocrine cell",
-    "Vascular endothelial cells_Aerocytes": "endothelial cell of vascular tree",
-    "Gastric epithelial cells": "epithelial cell of stomach",
-    "Fibro–adipogenic progenitors": "fibro/adipogenic progenitor cell",
-    "Parietal cells": "parietal cell",
-    "Astrocytes": "astrocyte",
-    "Connecting tubule cells": "kidney connecting tubule beta-intercalated cell",
-    "Hepatic stellate cells": "hepatic stellate cell",
-    "Striatal neurons 1": "striatum neuron",
-    "Mesothelial cells": "mesothelial cell",
-    "Lymphoid cells_Cycling B cells": "germinal center B cell",
-    "Type B intercalated cells": "renal beta-intercalated cell",
-    "Type A intercalated cells": "renal alpha-intercalated cell",
-    "Myeloid cells_Neutrophils": "neutrophil",
-    "Principal cells": "renal principal cell",
-    "Cortical projection neurons 2": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Muc2-producing goblet cells": "intestine goblet cell",
-    "OB neurons 1": "olfactory bulb interneuron",
-    "Atrial cardiomyocytes": "regular atrial cardiac myocyte",
-    "Lymphoid cells": "leukocyte",
-    "Skeletal muscle cells": "cell of skeletal muscle",
-    "Neural cells": "neural cell",
-    "Cerebellum interneurons": "cerebellar neuron",
-    "Interneurons 1": "interneuron",
-    "Descending thin limb of LOH cells": "vasa recta descending limb cell",
-    "Tuft cells": "intestinal tuft cell",
-    "Oligodendrocyte progenitor cells": "oligodendrocyte precursor cell",
-    "Enteric glia": "enteroglial cell",
-    "Endothelial cells": "endothelial cell",
-    "Dentate gyrus neurons": "dentate gyrus neuron",
-    "Myeloid cells_Interstitial macrophages": "tissue-resident macrophage",
-    "Ciliated cells": "ciliated cell",
-    "Microglia": "microglial cell",
-    "Interneurons 2": "interneuron",
-    "Ncam1 positive cells": "parafollicular cell",
-    "Rdh16 positive cells": "unknown",
-    "Circulating hepatoblasts": "hepatoblast",
-    "Enteric neurons": "enteric neuron",
-    "Ascending thin limb of LOH cells": "vasa recta ascending limb cell",
-    "Mfge8 positive cells": "unknown",
-    "Cholangiocytes": "cholangiocyte",
-    "Podocytes": "podocyte",
-    "Muscle satellite cells": "skeletal muscle satellite cell",
-    "Purkinje neurons": "Purkinje cell",
-    "Juxtaglomerular cells": "juxtaglomerular complex cell",
-    "Ngf positive cells": "neurogliaform cell",
-    "Bergmann glia": "Bergmann glial cell",
-    "Megf11 positive cells": "unknown",
-    "Myotendinous junction myonuclei": "unknown",
-    "Vascular leptomeningeal cells": "vascular leptomeningeal cell",
-    "Urothelial cells": "urothelial cell",
-    "Tenocytes": "tendon cell",
-    "Myelinating Schwann cells": "myelinating Schwann cell",
-    "Epididymal cells": "epididymis glandular cell",
-    "Muc6-producing goblet cells": "lung goblet cell",
-    "Type I myonuclei": "type I muscle cell",
-    "OB neurons 2": "olfactory bulb interneuron",
-    "Sis positive cells": "unknown",
-    "Lgr5 positive cells": "unknown",
-    "Macula densa cells": "macula densa epithelial cell",
-    "Choroid plexus epithelial cells": "choroid plexus epithelial cell",
-    "Cortical projection neurons 3": "corticothalamic-projecting glutamatergic cortical neuron",
-    "Interstitial cells of Cajal": "interstitial cell of Cajal",
-    "Cacna1b positive cells": "unknown",
-    "Hindbrain neurons 2": "neuron",
-    "Myeloid cells_Basophils": "basophil",
-    "Ependymal cells": "ependymal cell",
-    "Muc5ac-producing goblet cells": "lung goblet cell",
-    "Myeloid cells_Mast cells": "mast cell",
-    "Pulmonary neuroendocrine cells": "lung neuroendocrine cell",
-    "Basal cells": "basal cell",
-    "OB neurons 3": "olfactory bulb interneuron",
-    "Non-myelinating Schwann cells": "non-myelinating Schwann cell",
-    "Asic2 positive cells": "unknown",
-    "Striatal neurons 2": "striatum neuron",
-    "Erythroblasts": "erythroblast",
-    "Hindbrain neurons 1": "neuron",
-    "Neuromuscular junction myonuclei": "unknown",
-    "Habenula neurons": "unknown",
-    "Pituitary cells": "pituitary gland cell",
-    "Unipolar brush cells": "unipolar brush cell",
-    "Pde4c positive cells": "unknown",
-    "Pancreatic acinar cells": "pancreatic acinar cell",
-    "Inferior olivary nucleus neurons": "bushy cell",
-    "Colec10 positive cells": "unknown",
-    "Fcgbp positive cells": "unknown",
-    "Fut9 positive cells": "unknown",
-    "Mirg positive cells": "unknown",
-    "Alox15 positive cells": "unknown",
-    "Osteoblasts": "osteoblast",
-}
-genesdf = utils.load_genes("NCBITaxon:10090")
-{k: v if v =="unknown" else bt.CellType.filter(name=v).one().ontology_id for k, v in celltyper.items()}
-
-adata.obs["organism_ontology_term_id"] = "NCBITaxon:10090"
-adata.obs["tissue_ontology_term_id"] = adata.obs["Organ_name"].replace(tissuer)
-adata.obs["cell_type_ontology_term_id"] = adata.obs["Main_cell_type"].replace(
-    celltyper
-)
-adata.obs["disease_ontology_term_id"] = "PATO:0000461"
-adata.obs["assay_ontology_term_id"] = "unknown"
-adata.obs["self_reported_ethnicity_ontology_term_id"] = "unknown"
-adata.obs["development_stage_ontology_term_id"] = adata.obs["Age_group"].replace(
-    ager
-)
-adata.obs["sex_ontology_term_id"] = adata.obs["Gender"].replace(sexr)
-
-for i in range(num_blocks):
-    start_index = i * block_size
-    end_index = min((i + 1) * block_size, len(adata))
-    block = adata[start_index:end_index].to_memory()
-    # process block here
-
-    block = block[(block.obs["Gene_count"] > 400)]
-    
-    intersect_genes = set(block.var.index).intersection(set(genesdf.index))
-    print(f"Removed {len(block.var.index) - len(intersect_genes)} genes.")
-    block = block[:, list(intersect_genes)]
-    # marking unseen genes
-    unseen = set(genesdf.index) - set(block.var.index)
-    # adding them to adata
-    emptyda = ad.AnnData(
-        csr_matrix((block.shape[0], len(unseen)), dtype=np.float32),
-        var=pd.DataFrame(index=list(unseen)),
-        obs=pd.DataFrame(index=block.obs.index),
-    )
-    block = ad.concat([block, emptyda], axis=1, join="outer", merge="only")
-    # do a validation function
-    block.uns["unseen_genes"] = list(unseen)
-    block = block[:, block.var.sort_index().index]
-    block.var[genesdf.columns] = genesdf.loc[block.var.index]
-    for name in ["stable_id", "created_at", "updated_at"]:
-        if name in block.var.columns:
-            block.var = block.var.drop(columns=name)
-    block.write_h5ad('zhang2024_adata_'+str(i)+".h5ad")
-"""

scdataloader/utils.py

@@ -12,12 +12,48 @@ from scipy.sparse import csr_matrix
 from scipy.stats import median_abs_deviation
 from functools import lru_cache
 from collections import Counter
+from torch import Tensor
+import torch
 
 from typing import Union, List, Optional
 
 from anndata import AnnData
 
 
+def downsample_profile(mat: Tensor, dropout: float):
+    """
+    This function downsamples the expression profile of a given single cell RNA matrix.
+
+    The noise is applied based on the renoise parameter,
+    the total counts of the matrix, and the number of genes. The function first calculates the noise
+    threshold (scaler) based on the renoise parameter. It then generates an initial matrix count by
+    applying a Poisson distribution to a random tensor scaled by the total counts and the number of genes.
+    The function then models the sampling zeros by applying a Poisson distribution to a random tensor
+    scaled by the noise threshold, the total counts, and the number of genes. The function also models
+    the technical zeros by generating a random tensor and comparing it to the noise threshold. The final
+    matrix count is calculated by subtracting the sampling zeros from the initial matrix count and
+    multiplying by the technical zeros. The function ensures that the final matrix count is not less
+    than zero by taking the maximum of the final matrix count and a tensor of zeros. The function
+    returns the final matrix count.
+
+    Args:
+        mat (torch.Tensor): The input matrix.
+        dropout (float): The renoise parameter.
+
+    Returns:
+        torch.Tensor: The matrix count after applying noise.
+    """
+    batch = mat.shape[0]
+    ngenes = mat.shape[1]
+    dropout = dropout * 1.1
+    # we model the sampling zeros (dropping 30% of the reads)
+    res = torch.poisson((mat * (dropout / 2))).int()
+    # we model the technical zeros (dropping 50% of the genes)
+    notdrop = (torch.rand((batch, ngenes), device=mat.device) >= (dropout / 2)).int()
+    mat = (mat - res) * notdrop
+    return torch.maximum(mat, torch.zeros((1, 1), device=mat.device, dtype=torch.int))
+
+
 def createFoldersFor(filepath: str):
     """
     will recursively create folders if needed until having all the folders required to save the file in this filepath
@@ -38,6 +74,7 @@ def _fetchFromServer(
     Args:
         ensemble_server (str): The URL of the ensemble server to fetch data from.
         attributes (list): The list of attributes to fetch from the server.
+        database (str): The database to fetch data from.
 
     Returns:
         pd.DataFrame: A pandas DataFrame containing the fetched data.
@@ -68,6 +105,9 @@ def getBiomartTable(
         ensemble_server (str, optional): the biomart server. Defaults to "http://jul2023.archive.ensembl.org/biomart".
         useCache (bool, optional): whether to use the cache or not. Defaults to False.
         cache_folder (str, optional): the cache folder. Defaults to "/tmp/biomart/".
+        attributes (List[str], optional): the attributes to fetch. Defaults to [].
+        bypass_attributes (bool, optional): whether to bypass the attributes or not. Defaults to False.
+        database (str, optional): the database to fetch from. Defaults to "hsapiens_gene_ensembl".
 
     Raises:
         ValueError: should be a dataframe (when the result from the server is something else)
@@ -102,11 +142,12 @@ def getBiomartTable(
     res.columns = attr + attributes
     if type(res) is not type(pd.DataFrame()):
         raise ValueError("should be a dataframe")
-    res = res[~(res["ensembl_gene_id"].isna() & res["hgnc_symbol"].isna())]
-    res.loc[res[res.hgnc_symbol.isna()].index, "hgnc_symbol"] = res[
-        res.hgnc_symbol.isna()
-    ]["ensembl_gene_id"]
-
+    res = res[~(res["ensembl_gene_id"].isna())]
+    if "hgnc_symbol" in res.columns:
+        res = res[res["hgnc_symbol"].isna()]
+        res.loc[res[res.hgnc_symbol.isna()].index, "hgnc_symbol"] = res[
+            res.hgnc_symbol.isna()
+        ]["ensembl_gene_id"]
     return res
 
 
@@ -206,6 +247,16 @@ def get_all_ancestors(val: str, df: pd.DataFrame):
         return set.union(set(parents), *[get_all_ancestors(val, df) for val in parents])
 
 
+# setting a cache of 200 elements
+# @lru_cache(maxsize=200)
+def get_descendants(val, df):
+    ontos = set(df[df.parents__ontology_id.str.contains(val)].index.tolist())
+    r_onto = set()
+    for onto in ontos:
+        r_onto |= get_descendants(onto, df)
+    return r_onto | ontos
+
+
 def get_ancestry_mapping(all_elem: list, onto_df: pd.DataFrame):
     """
     This function generates a mapping of all elements to their ancestors in the ontology dataframe.
@@ -404,9 +455,7 @@ def populate_my_ontology(
     ln.save(records, parents=bool(tissues))
     bt.Tissue(name="unknown", ontology_id="unknown").save()
     # DevelopmentalStage
-    names = (
-        bt.DevelopmentalStage.public().df().index if not dev_stages else dev_stages
-    )
+    names = bt.DevelopmentalStage.public().df().index if not dev_stages else dev_stages
     records = bt.DevelopmentalStage.from_values(names, field="ontology_id")
     ln.save(records, parents=bool(dev_stages))
     bt.DevelopmentalStage(name="unknown", ontology_id="unknown").save()

{scdataloader-0.0.4.dist-info → scdataloader-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scdataloader
-Version: 0.0.4
+Version: 1.0.1
 Summary: a dataloader for single cell data in lamindb
 Home-page: https://github.com/jkobject/scDataLoader
 License: GPL3
@@ -34,14 +34,16 @@ Description-Content-Type: text/markdown
 
 [![codecov](https://codecov.io/gh/jkobject/scDataLoader/branch/main/graph/badge.svg?token=scDataLoader_token_here)](https://codecov.io/gh/jkobject/scDataLoader)
 [![CI](https://github.com/jkobject/scDataLoader/actions/workflows/main.yml/badge.svg)](https://github.com/jkobject/scDataLoader/actions/workflows/main.yml)
-[![DOI](https://zenodo.org/badge/731248665.svg)](https://zenodo.org/doi/10.5281/zenodo.10573143)
+[![PyPI version](https://badge.fury.io/py/scDataLoader.svg)](https://badge.fury.io/py/scDataLoader)
+[![Documentation Status](https://readthedocs.org/projects/scDataLoader/badge/?version=latest)](https://scDataLoader.readthedocs.io/en/latest/?badge=latest)
+[![Downloads](https://pepy.tech/badge/scDataLoader)](https://pepy.tech/project/scDataLoader)
+[![Downloads](https://pepy.tech/badge/scDataLoader/month)](https://pepy.tech/project/scDataLoader)
+[![Downloads](https://pepy.tech/badge/scDataLoader/week)](https://pepy.tech/project/scDataLoader)
+[![GitHub issues](https://img.shields.io/github/issues/jkobject/scDataLoader)](https://img.shields.io/github/issues/jkobject/scDataLoader)
+[![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)
 
-
-Awesome single cell dataloader created by @jkobject 
-
-built on top of `lamindb` and the `.mapped()` function by Sergey: https://github.com/Koncopd 
-
-This data loader is designed to be used with:
+This single cell pytorch dataloader / lighting datamodule is designed to be used with:
 
 - [lamindb](https://lamin.ai/)
 
@@ -57,18 +59,13 @@ It allows you to:
 3. create a more complex single cell dataset
 4. extend it to your need
 
-## About
-
-the idea is to use it to train models like scGPT / GeneFormer (and soon, scPrint ;)). It is: 
+built on top of `lamindb` and the `.mapped()` function by Sergey: https://github.com/Koncopd 
 
-1. loading from lamin 
-2. doing some dataset specific preprocessing if needed 
-3. creating a dataset object on top of .mapped() (that is needed for mapping genes, cell labels etc..)
-4. passing it to a dataloader object that can work with it correctly
+## More
 
-Currently one would have to use the preprocess function to make the dataset fit for different tools like scGPT / Geneformer. But I would want to enable it through different Collators. This is still missing and a WIP... (please do contribute!)
+I needed to create this Data Loader for my PhD project. I am using it to load & preprocess thousands of datasets containing millions of cells in a few seconds. I believed that individuals employing AI for single-cell RNA sequencing and other sequencing datasets would eagerly utilize and desire such a tool, which presently does not exist.
 
-![docs/scdataloader.drawio.png](docs/scdataloader.drawio.png)
+![scdataloader.drawio.png](docs/scdataloader.drawio.png)
 
 ## Install it from PyPI
 
@@ -87,6 +84,8 @@ then run the notebooks with the poetry installed environment
 
 ## Usage
 
+### Direct Usage
+
 ```python
 # initialize a local lamin database
 # !lamin init --storage ~/scdataloader --schema bionty
@@ -129,15 +128,41 @@ for i in tqdm.tqdm(datamodule.train_dataloader()):
 
 ```
 
-see the notebooks in [docs](https://jkobject.github.io/scDataLoader/):
+see the notebooks in [docs](https://www.jkobject.com/scDataLoader/):
+
+1. [load a dataset](https://www.jkobject.com/scDataLoader/notebooks/1_download_and_preprocess/)
+2. [create a dataset](https://www.jkobject.com/scDataLoader/notebooks/2_create_dataloader/)
+
+### command line preprocessing
 
-1. [load a dataset](https://jkobject.github.io/scDataLoader/notebooks/01_load_dataset.html)
-2. [create a dataset](https://jkobject.github.io/scDataLoader/notebooks/02_create_dataset.html)
+You can use the command line to preprocess a large database of datasets like here for cellxgene. this allows parallelizing and easier usage.
+
+```bash
+scdataloader --instance "laminlabs/cellxgene" --name "cellxgene-census" --version "2023-12-15" --description "preprocessed for scprint" --new_name "scprint main" --start_at 10 >> scdataloader.out
+```
+
+### command line usage
+
+The main way to use
+
+> please refer to the [scPRINT documentation](https://www.jkobject.com/scPRINT/) and [lightning documentation](https://lightning.ai/docs/pytorch/stable/cli/lightning_cli_intermediate.html) for more information on command line usage
 
 ## Development
 
 Read the [CONTRIBUTING.md](CONTRIBUTING.md) file.
 
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- [lamin.ai](https://lamin.ai/)
+- [scanpy](https://scanpy.readthedocs.io/en/stable/)
+- [anndata](https://anndata.readthedocs.io/en/latest/)
+- [scprint](https://www.jkobject.com/scPRINT/)
+
+Awesome single cell dataloader created by @jkobject
                     GNU GENERAL PUBLIC LICENSE
                        Version 3, 29 June 2007
 

scdataloader-1.0.1.dist-info/RECORD

@@ -0,0 +1,16 @@
+scdataloader/VERSION,sha256=WYVJhIUxBN9cNT4vaBoV_HkkdC-aLkaMKa8kjc5FzgM,6
+scdataloader/__init__.py,sha256=NIlE4oTUPRZ3uSW_maozoEHp470I7PV1vMOJ4XpSmL4,122
+scdataloader/__main__.py,sha256=db_upDq3tNEtcDH17mPIczToAqGkSKfLy0Qbj6B4YmE,6385
+scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
+scdataloader/collator.py,sha256=zkFdxirTDub1dJ1OJXO0p48kvd2r2ncKMdevAKIdTTc,13447
+scdataloader/config.py,sha256=rrW2DZxG4J2_pmpDbXXsaKJkpNC57w5dIlItiFbANYw,2905
+scdataloader/data.py,sha256=VugtHo9T9PqoJSv3lkJJAB89KD-fRwdVw1D76gnCc9c,12584
+scdataloader/datamodule.py,sha256=WLEWcDMcC1G3VD5tORfhfqRRHcTscpI0EzPikg3udbI,16881
+scdataloader/mapped.py,sha256=yF9l3obuRWbQjW8QZGRSKhc50fizXTWf3Pe1m542fW8,19481
+scdataloader/preprocess.py,sha256=noynYWuy9clhFu9UnN-vSvAHJHwakDttkI5aj1e_T98,29055
+scdataloader/utils.py,sha256=xyDsWaqkjhzlVBP8FiYdBUWHsel3twcVWmI53PhKqTM,21888
+scdataloader-1.0.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+scdataloader-1.0.1.dist-info/METADATA,sha256=2Xd8M1dq_JmvmFjmrrzn-1U4eOtwU6L51Y_7MCkGxvY,41327
+scdataloader-1.0.1.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+scdataloader-1.0.1.dist-info/entry_points.txt,sha256=nLqucZaa5wiF7-1FCgMXO916WDQ9Qm0TcxQp0f1DwE4,59
+scdataloader-1.0.1.dist-info/RECORD,,

scdataloader-0.0.4.dist-info/RECORD

@@ -1,16 +0,0 @@
-scdataloader/VERSION,sha256=ln2a-xATRmZxZvLnboGRC8GQSI19QdUMoAcunZLwDjI,6
-scdataloader/__init__.py,sha256=NIlE4oTUPRZ3uSW_maozoEHp470I7PV1vMOJ4XpSmL4,122
-scdataloader/__main__.py,sha256=UyXtFHgWxE-ecJmM_oEDLlzBDBbH-uEKAVj1A7BkwmM,6297
-scdataloader/base.py,sha256=M1gD59OffRdLOgS1vHKygOomUoAMuzjpRtAfM3SBKF8,338
-scdataloader/collator.py,sha256=Ykjdw24GUvHdbowWUDtp28YTkaF3w65SiWTU2PKBzy4,11714
-scdataloader/config.py,sha256=0_LoIblgdZZ19yM2qvPE-padMGQzdhuaxX20zYrhWq0,2780
-scdataloader/data.py,sha256=faJWN--06N7irWBKcjeU6fcX5NbzyEPXs2_EVGxfBpw,12292
-scdataloader/datamodule.py,sha256=OhHPb3jhGG5HbvahzTGxgzJ_lxbVJ4PfZspVW9h7SZk,14789
-scdataloader/mapped.py,sha256=rhE11Xl3x_wIKu3m_wu8Is6mYsXdblu3nQpT5lNqr60,13301
-scdataloader/preprocess.py,sha256=67ewe6b4HIjz_vTDjlOAJ4lMe4K2oCw2HHHUS-7S77M,38205
-scdataloader/utils.py,sha256=6eKU3_cotEaQcxONMrCWzMx7U8DybabteNhk-vNqfUQ,19365
-scdataloader-0.0.4.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-scdataloader-0.0.4.dist-info/METADATA,sha256=Bf8UjMwRcqSbWW8VbWrLhSb7qKQYdjZtJ7d6Oz4-rn8,39733
-scdataloader-0.0.4.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-scdataloader-0.0.4.dist-info/entry_points.txt,sha256=nLqucZaa5wiF7-1FCgMXO916WDQ9Qm0TcxQp0f1DwE4,59
-scdataloader-0.0.4.dist-info/RECORD,,