Github user yanboliang commented on a diff in the pull request:
https://github.com/apache/spark/pull/12754#discussion_r62604290
--- Diff:
examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala
---
@@ -0,0 +1,69 @@
+/*
+ * 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.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.ml
+
+// $example on$
+import org.apache.spark.ml.regression.GeneralizedLinearRegression
+// $example off$
+import org.apache.spark.sql.SparkSession
+
+object GeneralizedLinearRegressionExample {
+
+ def main(args: Array[String]): Unit = {
+ val spark = SparkSession
+ .builder
+ .appName("GeneralizedLinearRegressionExample")
+ .getOrCreate()
+
+ // $example on$
+ // Load training data
+ val training = spark.read.format("libsvm")
+ .load("data/mllib/sample_linear_regression_data.txt")
+
+ val glr = new GeneralizedLinearRegression()
+ .setFamily("gaussian")
+ .setLink("identity")
+ .setMaxIter(10)
+ .setRegParam(0.3)
+
+ // Fit the model
+ val model = glr.fit(training)
+
+ // Print the coefficients and intercept for generalized linear
regression model
+ println(s"Coefficients: ${model.coefficients} Intercept:
${model.intercept}")
+
+ // Summarize the model over the training set and print out some metrics
+ val summary = model.summary
--- End diff --
We should keep the example succinct, so I think it does not necessary to
illustrate a complete ML pipeline in the algorithm example.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
