Merge pull request #426 from mateiz/py-ml-tests

Re-enable Python MLlib tests (require Python 2.7 and NumPy 1.7+)

We disabled these earlier because Jenkins didn't have these versions.

python/pyspark/mllib/__init__.py

@@ -18,3 +18,13 @@
 """
 Python bindings for MLlib.
 """
+
+# MLlib currently needs Python 2.7+ and NumPy 1.7+, so complain if lower
+
+import sys
+if sys.version_info[0:2] < (2, 7):
+    raise Exception("MLlib requires Python 2.7+")
+
+import numpy
+if numpy.version.version < '1.7':
+    raise Exception("MLlib requires NumPy 1.7+")

python/run-tests

@@ -40,11 +40,11 @@ run_test "-m doctest pyspark/broadcast.py"
 run_test "-m doctest pyspark/accumulators.py"
 run_test "-m doctest pyspark/serializers.py"
 run_test "pyspark/tests.py"
-#run_test "pyspark/mllib/_common.py"
-#run_test "pyspark/mllib/classification.py"
-#run_test "pyspark/mllib/clustering.py"
-#run_test "pyspark/mllib/recommendation.py"
-#run_test "pyspark/mllib/regression.py"
+run_test "pyspark/mllib/_common.py"
+run_test "pyspark/mllib/classification.py"
+run_test "pyspark/mllib/clustering.py"
+run_test "pyspark/mllib/recommendation.py"
+run_test "pyspark/mllib/regression.py"
 
 if [[ $FAILED != 0 ]]; then
     echo -en "\033[31m"  # Red