Support modin 0.10.0 (#121)

Co-authored-by: Kai Fricke <kai@anyscale.com>

Author: amogkam

xgboost_ray/data_sources/modin.py

@@ -14,7 +14,8 @@
 
 try:
     import modin  # noqa: F401
-    MODIN_INSTALLED = modin.__version__ >= "0.9.0"
+    from distutils.version import LooseVersion
+    MODIN_INSTALLED = LooseVersion(modin.__version__) >= LooseVersion("0.9.0")
 except (ImportError, AttributeError):
     MODIN_INSTALLED = False
 

xgboost_ray/matrix.py

@@ -282,7 +282,9 @@ def get_data_source(self) -> Type[DataSource]:
                 "np.ndarray, and CSV/Parquet file paths. If you specify a "
                 "file, path, consider passing the `filetype` argument to "
                 "specify the type of the source. Use the `RayFileType` "
-                "enum for that.".format(type(self.data), self.filetype))
+                "enum for that. If using Modin, Dask, or Petastorm, "
+                "make sure the library is installed.".format(
+                    type(self.data), self.filetype))
 
         if self.label is not None and not isinstance(self.label, str) and \
                 not type(self.data) != type(self.label):  # noqa: E721:
@@ -419,7 +421,9 @@ def get_data_source(self) -> Type[DataSource]:
                 f"with FileType: {self.filetype} for a distributed dataset."
                 "\nFIX THIS by passing a supported data type. Supported "
                 "data types for distributed datasets are a list of "
-                "CSV or Parquet sources as well as Ray MLDatasets.")
+                "CSV or Parquet sources as well as Ray MLDatasets. If using "
+                "Modin, Dask, or Petastorm, make sure the library is "
+                "installed.")
 
         self.data_source = data_source
         self._cached_n = data_source.get_n(self.data)

xgboost_ray/tests/test_client.py

@@ -15,7 +15,7 @@ def start_client_server_4_cpus():
 
 @pytest.fixture
 def start_client_server_5_cpus():
-    ray.init(num_cpus=4)
+    ray.init(num_cpus=5)
     with ray_start_client_server() as client:
         yield client
 
@@ -40,6 +40,12 @@ def test_simple_dask(start_client_server_5_cpus):
     main(cpus_per_actor=1, num_actors=4)
 
 
+def test_simple_modin(start_client_server_5_cpus):
+    assert ray.util.client.ray.is_connected()
+    from xgboost_ray.examples.simple_modin import main
+    main(cpus_per_actor=1, num_actors=4)
+
+
 if __name__ == "__main__":
     import pytest  # noqa: F811
     import sys