Github user dorx commented on a diff in the pull request: https://github.com/apache/spark/pull/1733#discussion_r16015802 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/stat/test/TestResult.scala --- @@ -0,0 +1,88 @@ +/* + * 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. + */ + +package org.apache.spark.mllib.stat.test + +import org.apache.spark.annotation.Experimental + +/** + * :: Experimental :: + * Trait for hypothesis test results. + * @tparam DF Return type of `degreesOfFreedom` + */ +@Experimental +trait TestResult[DF] { + + /** + * + */ + def pValue: Double + + /** + * + * @return + */ + def degreesOfFreedom: DF + + /** + * + * @return + */ + def statistic: Double + + /** + * String explaining the hypothesis test result. + * Specific classes implementing this trait should override this method to output test-specific + * information. + */ + override def toString: String = { + + // String explaining what the p-value indicates. + val pValueExplain = if (pValue <= 0.01) { + "Very strong presumption against null hypothesis." + } else if (0.01 < pValue && pValue <= 0.05) { + "Strong presumption against null hypothesis." + } else if (0.05 < pValue && pValue <= 0.01) { + "Low presumption against null hypothesis." + } else { + "No presumption against null hypothesis." + } + + s"degrees of freedom = ${degreesOfFreedom.toString} \n" + + s"statistic = $statistic \n" + + s"pValue = $pValue \n" + pValueExplain + } +} + +/** + * :: Experimental :: + * Object containing the test results for the chi squared hypothesis test. + */ +@Experimental +case class ChiSquaredTestResult(override val pValue: Double, --- End diff -- Whether correction is used or not can actually be reflected in the method name (`pearson` v `yates`). I doubt there's a lot of use cases for parsing the result back from JSON so let's not worry about it for now. The way I see case classes is that they're like data structs that encapsulates immutable fields (the list of fields can be modified in later releases given that this is all experimental), but if there are compiler optimization complications, I can change it to a regular class.
--- 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