Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/6358#discussion_r31385303
--- Diff: examples/src/main/python/ml/cross_validator.py ---
@@ -0,0 +1,87 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from __future__ import print_function
+
+from pyspark import SparkContext
+from pyspark.ml import Pipeline
+from pyspark.ml.classification import LogisticRegression
+from pyspark.ml.evaluation import BinaryClassificationEvaluator
+from pyspark.ml.feature import HashingTF, Tokenizer
+from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
+from pyspark.sql import Row, SQLContext
+
+"""
+A simple example demonstrating model selection using CrossValidator.
+This example also demonstrates how Pipelines are Estimators.
+Run with:
+
+ bin/spark-submit examples/src/main/python/ml/cross_validator.py
+"""
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="CrossValidatorExample")
+ sqlContext = SQLContext(sc)
+
+ # Prepare training documents, which are labeled.
+ LabeledDocument = Row("id", "text", "label")
+ training = sc.parallelize([(0, "a b c d e spark", 1.0),
+ (1, "b d", 0.0),
+ (2, "spark f g h", 1.0),
+ (3, "hadoop mapreduce", 0.0)]) \
+ .map(lambda x: LabeledDocument(*x)).toDF()
+
+ # Configure an ML pipeline, which consists of tree stages: tokenizer,
hashingTF, and lr.
+ tokenizer = Tokenizer(inputCol="text", outputCol="words")
+ hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(),
outputCol="features")
+ lr = LogisticRegression(maxIter=10, regParam=0.001)
--- End diff --
No need to set regParam since it's being estimated.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
