diff options
Diffstat (limited to 'examples/src/main/scala')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala | 78 |
1 files changed, 78 insertions, 0 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala new file mode 100644 index 0000000000..1b86d7cad0 --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/GeneralizedLinearRegressionExample.scala @@ -0,0 +1,78 @@ +/* + * 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 + +/** + * An example demonstrating generalized linear regression. + * Run with + * {{{ + * bin/run-example ml.GeneralizedLinearRegressionExample + * }}} + */ + +object GeneralizedLinearRegressionExample { + + def main(args: Array[String]): Unit = { + val spark = SparkSession + .builder + .appName("GeneralizedLinearRegressionExample") + .getOrCreate() + + // $example on$ + // Load training data + val dataset = 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(dataset) + + // Print the coefficients and intercept for generalized linear regression model + println(s"Coefficients: ${model.coefficients}") + println(s"Intercept: ${model.intercept}") + + // Summarize the model over the training set and print out some metrics + val summary = model.summary + println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}") + println(s"T Values: ${summary.tValues.mkString(",")}") + println(s"P Values: ${summary.pValues.mkString(",")}") + println(s"Dispersion: ${summary.dispersion}") + println(s"Null Deviance: ${summary.nullDeviance}") + println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}") + println(s"Deviance: ${summary.deviance}") + println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}") + println(s"AIC: ${summary.aic}") + println("Deviance Residuals: ") + summary.residuals().show() + // $example off$ + + spark.stop() + } +} +// scalastyle:on println |