zhipeng93 commented on code in PR #139: URL: https://github.com/apache/flink-ml/pull/139#discussion_r947397118
########## flink-ml-lib/src/main/java/org/apache/flink/ml/feature/kbinsdiscretizer/KBinsDiscretizerParams.java: ########## @@ -0,0 +1,85 @@ +/* + * 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.flink.ml.feature.kbinsdiscretizer; + +import org.apache.flink.ml.param.IntParam; +import org.apache.flink.ml.param.Param; +import org.apache.flink.ml.param.ParamValidators; +import org.apache.flink.ml.param.StringParam; + +/** + * Params for {@link KBinsDiscretizer}. + * + * @param <T> The class type of this instance. + */ +public interface KBinsDiscretizerParams<T> extends KBinsDiscretizerModelParams<T> { + String UNIFORM = "uniform"; + String QUANTILE = "quantile"; + String KMEANS = "kmeans"; + + /** + * Supported options to define the widths of the bins are listed as follows. + * + * <ul> + * <li>uniform: all bins in each feature have identical widths. + * <li>quantile: all bins in each feature have the same number of points. + * <li>kmeans: values in each bin have the same nearest center of a 1D kmeans cluster. + * </ul> + */ + Param<String> STRATEGY = + new StringParam( + "strategy", + "Strategy used to define the width of the bin.", + QUANTILE, + ParamValidators.inArray(UNIFORM, QUANTILE, KMEANS)); + + Param<Integer> NUM_BINS = + new IntParam("numBins", "Number of bins to produce.", 5, ParamValidators.gtEq(2)); + + Param<Integer> SUB_SAMPLES = + new IntParam( + "subSamples", + "Maximum number of samples used to fit the model.", + 200000, + ParamValidators.gt(0)); Review Comment: I agree that `subSamples < 2` is not a valid use case and I have udpated the code. If `subSamples < numBins`, it should still work in `quantile` and `kmeans` case. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
