Don't use pyarrow 4.0.0 since it segfaults when casting a sliced List…

…Array of integers (#2268)

* don't use pyarrow 4.0.0 since it segfaults on windows

* pin to 3.0.0 in CI tests

.circleci/config.yml

@@ -15,7 +15,7 @@ jobs:
             - run: source venv/bin/activate
             - run: pip install .[tests]
             - run: pip install -r additional-tests-requirements.txt --no-deps
-            - run: pip install pyarrow --upgrade
+            - run: pip install pyarrow==3.0.0
             - run: HF_SCRIPTS_VERSION=master python -m pytest -sv ./tests/
 
     run_dataset_script_tests_pyarrow_1:
@@ -47,7 +47,7 @@ jobs:
             - run: "& venv/Scripts/activate.ps1"
             - run: pip install .[tests]
             - run: pip install -r additional-tests-requirements.txt --no-deps
-            - run: pip install pyarrow --upgrade
+            - run: pip install pyarrow==3.0.0
             - run: $env:HF_SCRIPTS_VERSION="master"
             - run: python -m pytest -sv ./tests/
 

setup.py

@@ -74,7 +74,7 @@
     "numpy>=1.17",
     # Backend and serialization.
     # Minimum 1.0.0 to avoid permission errors on windows when using the compute layer on memory mapped data
-    "pyarrow>=1.0.0",
+    "pyarrow>=1.0.0<4.0.0",
     # For smart caching dataset processing
     "dill",
     # For performance gains with apache arrow