yunfengzhou-hub commented on code in PR #160: URL: https://github.com/apache/flink-ml/pull/160#discussion_r1012423267
########## flink-ml-python/pyflink/ml/lib/feature/randomsplitter.py: ########## @@ -0,0 +1,80 @@ +################################################################################ +# 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. +################################################################################ +import typing +from typing import Tuple +from pyflink.ml.core.param import Param, FloatArrayParam, ParamValidator +from pyflink.ml.core.wrapper import JavaWithParams +from pyflink.ml.lib.feature.common import JavaFeatureTransformer + + +class _SplitterParams( + JavaWithParams +): + """ + Checks the weights parameter. + """ + def weights_validator(self) -> ParamValidator[Tuple[float]]: + class WeightsValidator(ParamValidator[Tuple[float]]): + def validate(self, weights: Tuple[float]) -> bool: + for val in weights: + if val <= 0.0 or val >= 1.0: + return False + weights_set = set(weights) + if len(weights_set) != len(weights): + return False + return len(weights_set) != 0 + return WeightsValidator() + + """ + Params for :class:`RandomSplitter`. + """ + WEIGHTS: Param[Tuple[float]] = FloatArrayParam( + "weights", + "The weights of data splitting.", + [0.5], Review Comment: The default value should be [1.0, 1.0]. ########## flink-ml-python/pyflink/ml/lib/feature/randomsplitter.py: ########## @@ -0,0 +1,80 @@ +################################################################################ +# 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. +################################################################################ +import typing +from typing import Tuple +from pyflink.ml.core.param import Param, FloatArrayParam, ParamValidator +from pyflink.ml.core.wrapper import JavaWithParams +from pyflink.ml.lib.feature.common import JavaFeatureTransformer + + +class _SplitterParams( + JavaWithParams +): + """ + Checks the weights parameter. + """ + def weights_validator(self) -> ParamValidator[Tuple[float]]: + class WeightsValidator(ParamValidator[Tuple[float]]): + def validate(self, weights: Tuple[float]) -> bool: + for val in weights: + if val <= 0.0 or val >= 1.0: + return False + weights_set = set(weights) + if len(weights_set) != len(weights): + return False + return len(weights_set) != 0 + return WeightsValidator() Review Comment: Let's make the validator the same as that in Java. ########## flink-ml-lib/src/main/java/org/apache/flink/ml/feature/randomsplitter/RandomSplitter.java: ########## @@ -0,0 +1,134 @@ +/* + * 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.randomsplitter; + +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.ml.api.AlgoOperator; +import org.apache.flink.ml.common.datastream.TableUtils; +import org.apache.flink.ml.param.Param; +import org.apache.flink.ml.util.ParamUtils; +import org.apache.flink.ml.util.ReadWriteUtils; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator; +import org.apache.flink.streaming.api.operators.AbstractStreamOperator; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableImpl; +import org.apache.flink.types.Row; +import org.apache.flink.util.OutputTag; +import org.apache.flink.util.Preconditions; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; +import java.util.Random; + +/** An AlgoOperator which splits a datastream into N datastreams according to the given weights. */ Review Comment: I found that "datastream" might not be a suitable description, as Flink ML stages perform operations on Tables, not DataStreams. How do you think we can make this document more suitable? -- 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]
