datachain 0.36.2__tar.gz → 0.36.3__tar.gz

{datachain-0.36.2 → datachain-0.36.3}/.github/workflows/tests.yml

@@ -110,7 +110,7 @@ jobs:
 
       - name: Install FFmpeg on Windows
         if: runner.os == 'Windows'
-        run: choco install ffmpeg
+        run: choco install ffmpeg --version 7.0
 
       - name: Install FFmpeg on macOS
         if: runner.os == 'macOS'

{datachain-0.36.2 → datachain-0.36.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.36.2
+Version: 0.36.3
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -76,6 +76,7 @@ Requires-Dist: datasets[vision]>=4.0.0; extra == "hf"
 Requires-Dist: datasets[audio]>=4.0.0; (sys_platform == "linux" or sys_platform == "darwin") and extra == "hf"
 Requires-Dist: fsspec>=2024.12.0; extra == "hf"
 Requires-Dist: torch<2.9.0; extra == "hf"
+Requires-Dist: torchcodec<0.8.0; (sys_platform == "linux" or sys_platform == "darwin") and extra == "hf"
 Provides-Extra: video
 Requires-Dist: ffmpeg-python; extra == "video"
 Requires-Dist: imageio[ffmpeg,pyav]>=2.37.0; extra == "video"

{datachain-0.36.2 → datachain-0.36.3}/pyproject.toml

@@ -91,7 +91,8 @@ hf = [
   # Until datasets solve the issue, run test_hf_audio test to see if this can be removed
   # https://github.com/meta-pytorch/torchcodec/issues/912
   # https://github.com/huggingface/transformers/pull/41610
-  "torch<2.9.0"
+  "torch<2.9.0",
+  "torchcodec<0.8.0 ; (sys_platform == 'linux' or sys_platform == 'darwin')"
 ]
 video = [
   "ffmpeg-python",
@@ -139,6 +140,8 @@ examples = [
   "open_clip_torch",
   "openai",
   # Transformers still require it
+  # Remove this after HF tests and example work w/o these restrictions,
+  # make them >= probably
   "torchaudio<2.9.0"
 ]
 

{datachain-0.36.2 → datachain-0.36.3}/src/datachain.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.36.2
+Version: 0.36.3
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -76,6 +76,7 @@ Requires-Dist: datasets[vision]>=4.0.0; extra == "hf"
 Requires-Dist: datasets[audio]>=4.0.0; (sys_platform == "linux" or sys_platform == "darwin") and extra == "hf"
 Requires-Dist: fsspec>=2024.12.0; extra == "hf"
 Requires-Dist: torch<2.9.0; extra == "hf"
+Requires-Dist: torchcodec<0.8.0; (sys_platform == "linux" or sys_platform == "darwin") and extra == "hf"
 Provides-Extra: video
 Requires-Dist: ffmpeg-python; extra == "video"
 Requires-Dist: imageio[ffmpeg,pyav]>=2.37.0; extra == "video"

{datachain-0.36.2 → datachain-0.36.3}/src/datachain.egg-info/requires.txt

@@ -76,6 +76,7 @@ torch<2.9.0
 
 [hf:sys_platform == "linux" or sys_platform == "darwin"]
 datasets[audio]>=4.0.0
+torchcodec<0.8.0
 
 [postgres]
 psycopg2-binary>=2.9.0

{datachain-0.36.2 → datachain-0.36.3}/tests/func/test_hf.py

@@ -27,7 +27,7 @@ def require_torchcodec(test_case):
     """
     if not importlib.util.find_spec("torchcodec"):
         test_case = pytest.mark.skip(
-            "test requires torchcoded, not available on Windows yet"
+            "test requires torchcodec, not available on Windows yet"
         )(test_case)
     return test_case
 

{datachain-0.36.2 → datachain-0.36.3}/tests/unit/lib/test_datachain.py

@@ -1072,6 +1072,19 @@ def test_select_except(test_session):
     assert n == len(features_nested)
 
 
+def test_select_except_after_gen(test_session):
+    # https://github.com/iterative/datachain/issues/1359
+    # fixed by https://github.com/iterative/datachain/pull/1400
+    chain = dc.read_values(id=range(10), session=test_session)
+
+    chain = chain.gen(lambda id: [(id, 0)], output={"id": int, "x": int})
+    chain = chain.select_except("x")
+    chain = chain.merge(chain, on="id")
+    chain = chain.select_except("right_id")
+
+    assert set(chain.to_values("id")) == set(range(10))
+
+
 def test_select_wrong_type(test_session):
     chain = dc.read_values(fr1=features_nested, fr2=features, session=test_session)