From 9a0dfdf868187fb9a2e1656e4cf5f29d952ce5db Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Thu, 9 Jan 2014 23:55:06 -0800 Subject: Add Naive Bayes to Python MLlib, and some API fixes - Added a Python wrapper for Naive Bayes - Updated the Scala Naive Bayes to match the style of our other algorithms better and in particular make it easier to call from Java (added builder pattern, removed default value in train method) - Updated Python MLlib functions to not require a SparkContext; we can get that from the RDD the user gives - Added a toString method in LabeledPoint - Made the Python MLlib tests run as part of run-tests as well (before they could only be run individually through each file) --- python/run-tests | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'python/run-tests') diff --git a/python/run-tests b/python/run-tests index feba97cee0..a986ac9380 100755 --- a/python/run-tests +++ b/python/run-tests @@ -40,6 +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" if [[ $FAILED != 0 ]]; then echo -en "\033[31m" # Red -- cgit v1.2.3