renamed download_by_prefix to download

PNNL-CompBio · Dec 10, 2024 · 8ab2d77 · 8ab2d77
1 parent 7c7342c
commit 8ab2d77
Show file tree

Hide file tree

Showing 10 changed files with 24 additions and 17 deletions.
diff --git a/coderdata/__init__.py b/coderdata/__init__.py
@@ -1,4 +1,4 @@
-from .download.downloader import download_data_by_prefix
+from .download.downloader import download
 from .load.loader import DatasetLoader, join_datasets
 from .split.splitter import train_test_validate
 from .dataset.dataset import (

diff --git a/coderdata/cli.py b/coderdata/cli.py
@@ -1,5 +1,5 @@
 import argparse
-from .download.downloader import download_data_by_prefix
+from .download.downloader import download
 
 def main():
     parser = argparse.ArgumentParser(prog='coderdata')
@@ -9,7 +9,7 @@ def main():
     parser_download = subparsers.add_parser('download', help='Download datasets')
     parser_download.add_argument('--prefix', type=str, default=None,
                                  help='Prefix of the dataset to download (e.g., "hcmi"), "all", or leave empty for all files.')
-    parser_download.set_defaults(func=download_data_by_prefix)
+    parser_download.set_defaults(func=download)
 
     args = parser.parse_args()
     if hasattr(args, 'func'):

diff --git a/coderdata/download/__init__.py b/coderdata/download/__init__.py
@@ -1,2 +1,2 @@
-from .downloader import download_data_by_prefix
+from .downloader import download
 
diff --git a/coderdata/download/downloader.py b/coderdata/download/downloader.py
@@ -1,8 +1,15 @@
 # coderdata/download/downloader.py
 
+from pathlib import Path
+from os import PathLike
+import os
 import requests
 
-def download_data_by_prefix(dataset_prefix=None):
+def download(
+        name: str=None,
+        local_path: PathLike=Path.cwd(),
+        exist_ok: bool=False
+        ):
     """
     Download the most recent version of files from a Figshare dataset, filtered by a specific prefix or all files.
 

diff --git a/tests/test_download_and_load_beataml.py b/tests/test_download_and_load_beataml.py
@@ -1,6 +1,6 @@
 # tests/test_download_beataml.py
 
-from coderdata.download.downloader import download_data_by_prefix
+from coderdata.download.downloader import download
 from coderdata.load.loader import DatasetLoader
 import os
 import glob
@@ -9,7 +9,7 @@
 def test_download_data_beataml():
 
     #BeatAML
-    download_data_by_prefix('beataml')
+    download('beataml')
 
     beataml_drugs = glob.glob('beataml_drugs*')
     assert len(beataml_drugs) > 0, "File beataml_drugs  does not exist."

diff --git a/tests/test_download_and_load_cell_line.py b/tests/test_download_and_load_cell_line.py
@@ -1,6 +1,6 @@
 # tests/test_download_depmap.py
 
-from coderdata.download.downloader import download_data_by_prefix
+from coderdata.download.downloader import download
 from coderdata.load.loader import DatasetLoader
 import os
 import glob
@@ -9,7 +9,7 @@
 def test_download_data_depmap():
 
     #depmap
-    download_data_by_prefix('depmap')
+    download('depmap')
 
     depmap_samples = glob.glob('depmap_samples*')
     assert len(depmap_samples) > 0, "File depmap_samples does not exist."

diff --git a/tests/test_download_and_load_cptac.py b/tests/test_download_and_load_cptac.py
@@ -1,7 +1,7 @@
 
 # tests/test_download_cptac.py
 
-from coderdata.download.downloader import download_data_by_prefix
+from coderdata.download.downloader import download
 from coderdata.load.loader import DatasetLoader
 import os
 import glob
@@ -10,7 +10,7 @@
 def test_download_data_cptac():
 
     #CPTAC
-    download_data_by_prefix('cptac')
+    download('cptac')
 
     cptac_copy_number = glob.glob('cptac_copy_number*')
     assert len(cptac_copy_number) > 0, "File cptac_copy_number does not exist."

diff --git a/tests/test_download_and_load_hcmi.py b/tests/test_download_and_load_hcmi.py
@@ -1,6 +1,6 @@
 # tests/test_download_hcmi.py
 
-from coderdata.download.downloader import download_data_by_prefix
+from coderdata.download.downloader import download
 from coderdata.load.loader import DatasetLoader
 import os
 import glob
@@ -9,7 +9,7 @@
 def test_download_data_hcmi():
 
     #HCMI
-    download_data_by_prefix('hcmi')
+    download('hcmi')
 
     hcmi_mutations = glob.glob('hcmi_mutations*')
     assert len(hcmi_mutations) > 0, "File hcmi_mutations does not exist."

diff --git a/tests/test_reload_all.py b/tests/test_reload_all.py
@@ -4,11 +4,11 @@
 import pandas as pd
 import os
 from coderdata.load.loader import DatasetLoader
-from coderdata.download import download_data_by_prefix
+from coderdata.download import download
 
 
 def test_reload_all_datasets():
-    download_data_by_prefix("hcmi")
+    download("hcmi")
     loader = DatasetLoader("hcmi")
 
     # Ensure the datasets are initially empty

diff --git a/tests/test_reload_one.py b/tests/test_reload_one.py
@@ -4,11 +4,11 @@
 import pandas as pd
 import os
 from coderdata.load.loader import DatasetLoader
-from coderdata.download import download_data_by_prefix
+from coderdata.download import download
 
 
 def test_reload_specific_dataset():
-    download_data_by_prefix("hcmi")
+    download("hcmi")
     loader = DatasetLoader("hcmi")
 
     # Ensure the dataset is initially empty
Original file line number	Diff line number	Diff line change
		@@ -1,2 +1,2 @@
		from .downloader import download_data_by_prefix
		from .downloader import download