Use shutil.rmtree() to temporary directories for saving model testings, instead of os.removedirs()

Author: yu-iskw

python/pyspark/mllib/classification.py

@@ -135,8 +135,9 @@ class LogisticRegressionModel(LinearClassificationModel):
     1
     >>> sameModel.predict(SparseVector(2, {0: 1.0}))
     0
+    >>> from shutil import rmtree
     >>> try:
-    ...    os.removedirs(path)
+    ...    rmtree(path)
     ... except:
     ...    pass
     >>> multi_class_data = [
@@ -387,8 +388,9 @@ class SVMModel(LinearClassificationModel):
     1
     >>> sameModel.predict(SparseVector(2, {0: -1.0}))
     0
+    >>> from shutil import rmtree
     >>> try:
-    ...    os.removedirs(path)
+    ...    rmtree(path)
     ... except:
     ...    pass
     """
@@ -515,8 +517,9 @@ class NaiveBayesModel(Saveable, Loader):
     >>> sameModel = NaiveBayesModel.load(sc, path)
     >>> sameModel.predict(SparseVector(2, {0: 1.0})) == model.predict(SparseVector(2, {0: 1.0}))
     True
+    >>> from shutil import rmtree
     >>> try:
-    ...     os.removedirs(path)
+    ...     rmtree(path)
     ... except OSError:
     ...     pass
     """

python/pyspark/mllib/clustering.py

@@ -79,8 +79,9 @@ class KMeansModel(Saveable, Loader):
     >>> sameModel = KMeansModel.load(sc, path)
     >>> sameModel.predict(sparse_data[0]) == model.predict(sparse_data[0])
     True
+    >>> from shutil import rmtree
     >>> try:
-    ...     os.removedirs(path)
+    ...     rmtree(path)
     ... except OSError:
     ...     pass
     """

python/pyspark/mllib/recommendation.py

@@ -106,8 +106,9 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader):
     0.4...
     >>> sameModel.predictAll(testset).collect()
     [Rating(...
+    >>> from shutil import rmtree
     >>> try:
-    ...     os.removedirs(path)
+    ...     rmtree(path)
     ... except OSError:
     ...     pass
     """

python/pyspark/mllib/regression.py

@@ -135,9 +135,9 @@ class LinearRegressionModel(LinearRegressionModelBase):
     True
     >>> from shutil import rmtree
     >>> try:
-    ...    rmtree(path)
+    ...     rmtree(path)
     ... except:
-    ...    pass
+    ...     pass
     >>> data = [
     ...     LabeledPoint(0.0, SparseVector(1, {0: 0.0})),
     ...     LabeledPoint(1.0, SparseVector(1, {0: 1.0})),
@@ -503,8 +503,9 @@ class IsotonicRegressionModel(Saveable, Loader):
     2.0
     >>> sameModel.predict(5)
     16.5
+    >>> from shutil import rmtree
     >>> try:
-    ...     os.removedirs(path)
+    ...     rmtree(path)
     ... except OSError:
     ...     pass
     """

python/pyspark/mllib/tests.py

@@ -24,6 +24,7 @@
 import tempfile
 import array as pyarray
 from time import time, sleep
+from shutil import rmtree
 
 from numpy import array, array_equal, zeros, inf, all, random
 from numpy import sum as array_sum
@@ -398,7 +399,7 @@ def test_classification(self):
         self.assertEqual(same_gbt_model.toDebugString(), gbt_model.toDebugString())
 
         try:
-            os.removedirs(temp_dir)
+            rmtree(temp_dir)
         except OSError:
             pass