Merge pull request #722 from sarthakpati/721-move-unit-testing-data-t…

…o-the-mlcommons-storage

Move unit testing data to the mlcommons storage

setup.py

@@ -92,7 +92,7 @@ def run(self):
     "pyyaml",
     "tiffslide",
     "matplotlib",
-    "requests>=2.25.0",
+    "gdown",
     "pytest",
     "coverage",
     "pytest-cov",

testing/test_full.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-import requests, zipfile, io, os, csv, random, copy, shutil, yaml, torch, pytest
+import gdown, zipfile, os, csv, random, copy, shutil, yaml, torch, pytest
 import SimpleITK as sitk
 import numpy as np
 import pandas as pd
@@ -109,9 +109,7 @@
 
 def test_generic_download_data():
     print("00: Downloading the sample data")
-    urlToDownload = (
-        "https://upenn.box.com/shared/static/y8162xkq1zz5555ye3pwadry2m2e39bs.zip"
-    )
+    urlToDownload = "https://drive.google.com/uc?id=1c4Yrv-jnK6Tk7Ne1HmMTChv-4nYk43NT"
 
     files_check = [
         os.path.join(inputDir, "2d_histo_segmentation", "1", "image.tiff"),
@@ -122,9 +120,11 @@ def test_generic_download_data():
     for file in files_check:
         if not os.path.isfile(file):
             print("Downloading and extracting sample data")
-            r = requests.get(urlToDownload)
-            z = zipfile.ZipFile(io.BytesIO(r.content))
-            z.extractall(testingDir)
+            output = os.path.join(testingDir, "gandlf_unit_test_data.tgz")
+            gdown.download(urlToDownload, output, quiet=False)
+            with zipfile.ZipFile(output, "r") as zip_ref:
+                zip_ref.extractall(testingDir)
+            os.remove(output)
             break
 
     sanitize_outputDir()