高斯混合模型 (GaussianMixture)

Java 类名：com.alibaba.alink.pipeline.clustering.GaussianMixture
Python 类名：GaussianMixture

功能介绍

高斯混合模型聚类

参数说明

代码示例

Python 代码

from pyalink.alink import *
import pandas as pd
useLocalEnv(1)
df = pd.DataFrame([
    ["-0.6264538 0.1836433"],
    ["-0.8356286 1.5952808"],
    ["0.3295078 -0.8204684"],
    ["0.4874291 0.7383247"],
    ["0.5757814 -0.3053884"],
    ["1.5117812 0.3898432"],
    ["-0.6212406 -2.2146999"],
    ["11.1249309 9.9550664"],
    ["9.9838097 10.9438362"],
    ["10.8212212 10.5939013"],
    ["10.9189774 10.7821363"],
    ["10.0745650 8.0106483"],
    ["10.6198257 9.9438713"],
    ["9.8442045 8.5292476"],
    ["9.5218499 10.4179416"],
])
data = BatchOperator.fromDataframe(df, schemaStr='features string')
gmm = GaussianMixture() \
    .setPredictionCol("cluster_id") \
    .setVectorCol("features") \
    .setPredictionDetailCol("cluster_detail") \
    .setEpsilon(0.)
gmm.fit(data).transform(data).print()

Java 代码

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import com.alibaba.alink.pipeline.clustering.GaussianMixture;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
public class GaussianMixtureTest {
    @Test
    public void testGaussianMixture() throws Exception {
        List <Row> df_data = Arrays.asList(
            Row.of("-0.6264538 0.1836433"),
            Row.of("-0.8356286 1.5952808"),
            Row.of("0.3295078 -0.8204684"),
            Row.of("0.4874291 0.7383247"),
            Row.of("0.5757814 -0.3053884"),
            Row.of("1.5117812 0.3898432"),
            Row.of("-0.6212406 -2.2146999"),
            Row.of("11.1249309 9.9550664"),
            Row.of("9.9838097 10.9438362"),
            Row.of("10.8212212 10.5939013"),
            Row.of("10.9189774 10.7821363"),
            Row.of("10.0745650 8.0106483"),
            Row.of("10.6198257 9.9438713"),
            Row.of("9.8442045 8.5292476"),
            Row.of("9.5218499 10.4179416")
        );
        BatchOperator <?> data = new MemSourceBatchOp(df_data, "features string");
        GaussianMixture gmm = new GaussianMixture()
            .setPredictionCol("cluster_id")
            .setVectorCol("features")
            .setPredictionDetailCol("cluster_detail")
            .setEpsilon(0.);
        gmm.fit(data).transform(data).print();
    }
}

运行结果