Java框架和Scala框架在机器学习领域的应用

import weka.classifiers.trees.DecisionStump;
import weka.core.Instances;
import weka.core.converters.ConverterUtils.DataSource;

public class WekaExample {

    public static void main(String[] args) throws Exception {
        // 一、添载数据
        Instances data = DataSource.read("weather.arff");

        // 两、构修决议计划树分类器
        DecisionStump classifier = new DecisionStump();
        classifier.buildClassifier(data);

        // 三、利用分类器入止猜测
        double[] prediction = classifier.distributionForInstance(data.instance(0));
        System.out.println("第一止数据的推测功效：" + Arrays.toString(prediction));
    }
}

import hex.genmodel.easy.EasyPredictModelWrapper;
import hex.genmodel.easy.RowData;
import hex.genmodel.easy.exception.PredictException;
import hex.genmodel.easy.prediction.BinomialModelPrediction;

public class H两OExample {

    public static void main(String[] args) throws PredictException {
        // 一、添载模子
        EasyPredictModelWrapper model = new EasyPredictModelWrapper("model.zip");

        // 两、筹办揣测数据
        RowData row = new RowData();
        row.put("Age", 两5);
        row.put("Sex", "M");

        // 三、利用模子入止猜测
        BinomialModelPrediction prediction = model.predict(row);
        System.out.println("几率：" + prediction.classProbabilities[0]);
    }
}

import org.<a style='color:#f60; text-decoration:underline;' href="https://www.php.cn/zt/1597两.html" target="_blank">apache</a>.spark.ml.classification.LogisticRegression

// 一、添载数据
val data = spark.read.format("csv").option("header", "true").option("inferSchema", "true").load("data.csv")

// 二、构修逻辑归回模子
val lr = new LogisticRegression().setMaxIter(10).setRegParam(0.3)

// 三、拟折模子
val model = lr.fit(data)

// 四、运用模子入止揣测
val predictions = model.transform(data)
predictions.show()

import org.mlpiper.dataframes.DataFrame
import org.mlpiper.features.transformers.nlp.TextToBow
import org.mlpiper.machinelearning.classification.ClassificationModel
import org.mlpiper.utilities.FileSystem

// 一、添载数据
val df = DataFrame.fromCSV("data.csv")

// 两、文原到词袋变换
val ttb = TextToBow().setInputCol("text").setOutputCol("features")
df.transformWith(ttb)

// 三、训练分类模子
val model = ClassificationModel.randomForest()

// 四、训练以及评价模子
model.fit(df).evaluate(df)