sklearn-porter

In [1]:

    

import sys
sys.path.append('../../../../..')


    

In [2]:

    

from sklearn.datasets import load_iris

iris_data = load_iris()

X = iris_data.data
y = iris_data.target

print(X.shape, y.shape)


    

    




((150, 4), (150,))

In [3]:

    

from sklearn.ensemble import RandomForestClassifier

clf = RandomForestClassifier(n_estimators=15, max_depth=None,
                             min_samples_split=2, random_state=0)
clf.fit(X, y)


    

    
Out[3]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=15, n_jobs=None,
            oob_score=False, random_state=0, verbose=0, warm_start=False)

In [4]:

    

from sklearn_porter import Porter

porter = Porter(clf, language='java')
output = porter.export(export_data=True)

print(output)


    

    




import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.lang.reflect.Type;
import java.util.List;
import java.util.Scanner;
import com.google.gson.Gson;
import com.google.gson.reflect.TypeToken;


class RandomForestClassifier {

    private class Tree {
        private int[] childrenLeft;
        private int[] childrenRight;
        private double[] thresholds;
        private int[] indices;
        private double[][] classes;

        private int predict (double[] features, int node) {
            if (this.thresholds[node] != -2) {
                if (features[this.indices[node]] <= this.thresholds[node]) {
                    return this.predict(features, this.childrenLeft[node]);
                } else {
                    return this.predict(features, this.childrenRight[node]);
                }
            }
            return RandomForestClassifier.findMax(this.classes[node]);
        }
        private int predict (double[] features) {
            return this.predict(features, 0);
        }
    }

    private List<Tree> forest;
    private int nClasses;
    private int nEstimators;

    public RandomForestClassifier (String file) throws FileNotFoundException {
        String jsonStr = new Scanner(new File(file)).useDelimiter("\\Z").next();
        Gson gson = new Gson();
        Type listType = new TypeToken<List<Tree>>(){}.getType();
        this.forest = gson.fromJson(jsonStr, listType);
        this.nEstimators = this.forest.size();
        this.nClasses = this.forest.get(0).classes[0].length;
    }

    private static int findMax(double[] nums) {
        int index = 0;
        for (int i = 0; i < nums.length; i++) {
            index = nums[i] > nums[index] ? i : index;
        }
        return index;
    }

    public int predict(double[] features) {
        double[] classes = new double[this.nClasses];
        for (int i = 0; i < this.nEstimators; i++) {
            classes[this.forest.get(i).predict(features, 0)]++;
        }
        return RandomForestClassifier.findMax(classes);
    }

    public static void main(String[] args) throws IOException {
        if (args.length > 0 && args[0].endsWith(".json")) {

            // Features:
            double[] features = new double[args.length-1];
            for (int i = 1, l = args.length; i < l; i++) {
                features[i-1] = Double.parseDouble(args[i]);
            }

            // Parameters:
            String modelData = args[0];

            // Estimator:
            RandomForestClassifier clf = new RandomForestClassifier(modelData);

            // Prediction:
            int prediction = clf.predict(features);
            System.out.println(prediction);

        }
    }
}

In [5]:

    

# Save classifier:
# with open('RandomForestClassifier.java', 'w') as f:
#     f.write(output)

# Check model data:
# $ cat data.json

# Download dependencies:
# $ wget -O gson.jar http://central.maven.org/maven2/com/google/code/gson/gson/2.8.5/gson-2.8.5.jar

# Compile model:
# $ javac -cp .:gson.jar RandomForestClassifier.java

# Run classification:
# $ java -cp .:gson.jar RandomForestClassifier data.json 1 2 3 4