[ci] run Dask examples on CI (#4064)

* Update Parallel-Learning-Guide.rst

* Update test.sh

* fix path

* address review comments

.ci/test.sh

@@ -224,7 +224,7 @@ import matplotlib\
 matplotlib.use\(\"Agg\"\)\
 ' plot_example.py  # prevent interactive window mode
     sed -i'.bak' 's/graph.render(view=True)/graph.render(view=False)/' plot_example.py
-    for f in *.py; do python $f || exit -1; done  # run all examples
+    for f in *.py **/*.py; do python $f || exit -1; done  # run all examples
     cd $BUILD_DIRECTORY/examples/python-guide/notebooks
     conda install -q -y -n $CONDA_ENV ipywidgets notebook
     jupyter nbconvert --ExecutePreprocessor.timeout=180 --to notebook --execute --inplace *.ipynb || exit -1  # run all notebooks

docs/Parallel-Learning-Guide.rst

@@ -62,10 +62,14 @@ Dask
 
 LightGBM's Python package supports distributed learning via `Dask`_. This integration is maintained by LightGBM's maintainers.
 
+.. warning::
+
+    Dask integration is only tested on Linux.
+
 Dask Examples
 '''''''''''''
 
-For sample code using ``lightgbm.dask``, see `these Dask examples`_ .
+For sample code using ``lightgbm.dask``, see `these Dask examples`_.
 
 Training with Dask
 ''''''''''''''''''

examples/python-guide/dask/binary-classification.py

@@ -5,7 +5,6 @@ from sklearn.datasets import make_blobs
 import lightgbm as lgb
 
 if __name__ == "__main__":
-
     print("loading data")
 
     X, y = make_blobs(n_samples=1000, n_features=50, centers=2)

examples/python-guide/dask/multiclass-classification.py

@@ -5,7 +5,6 @@ from sklearn.datasets import make_blobs
 import lightgbm as lgb
 
 if __name__ == "__main__":
-
     print("loading data")
 
     X, y = make_blobs(n_samples=1000, n_features=50, centers=3)

examples/python-guide/dask/prediction.py

@@ -6,7 +6,6 @@ from sklearn.metrics import mean_squared_error
 import lightgbm as lgb
 
 if __name__ == "__main__":
-
     print("loading data")
 
     X, y = make_regression(n_samples=1000, n_features=50)

examples/python-guide/dask/ranking.py

+import os
+
 import dask.array as da
 import numpy as np
 from distributed import Client, LocalCluster
@@ -6,11 +8,12 @@ from sklearn.datasets import load_svmlight_file
 import lightgbm as lgb
 
 if __name__ == "__main__":
-
     print("loading data")
 
-    X, y = load_svmlight_file("../lambdarank/rank.train")
-    group = np.loadtxt("../lambdarank/rank.train.query")
+    X, y = load_svmlight_file(os.path.join(os.path.dirname(os.path.realpath(__file__)),
+                                           '../../lambdarank/rank.train'))
+    group = np.loadtxt(os.path.join(os.path.dirname(os.path.realpath(__file__)),
+                                    '../../lambdarank/rank.train.query'))
 
     print("initializing a Dask cluster")
 

examples/python-guide/dask/regression.py

@@ -5,7 +5,6 @@ from sklearn.datasets import make_regression
 import lightgbm as lgb
 
 if __name__ == "__main__":
-
     print("loading data")
 
     X, y = make_regression(n_samples=1000, n_features=50)

python-package/README.rst

@@ -204,6 +204,10 @@ You can use ``python setup.py bdist_wheel`` instead of ``python setup.py install
 Install Dask-package
 ''''''''''''''''''''
 
+.. warning::
+
+    Dask-package is only tested on Linux.
+
 To install all additional dependencies required for Dask-package, you can append ``[dask]`` to LightGBM package name:
 
 .. code:: sh