ALINK(三十五)：特征工程（十四）类别特征编码（二）独热编码

from pyalink.alink import *
import pandas as pd
useLocalEnv(1)
df = pd.DataFrame([
    ["a", 1],
    ["b", 1],
    ["c", 1],
    ["e", 2],
    ["a", 2],
    ["b", 1],
    ["c", 2],
    ["d", 2],
    [None, 1]
])
inOp = BatchOperator.fromDataframe(df, schemaStr='query string, weight long')
# one hot train
one_hot = OneHotTrainBatchOp().setSelectedCols(["query"])
model = inOp.link(one_hot)
model.lazyPrint(10)
# batch predict
predictor = OneHotPredictBatchOp().setOutputCols(["output"])
predictor.linkFrom(model, inOp).print()

import org.apache.flink.types.Row;
import com.alibaba.alink.operator.batch.BatchOperator;
import com.alibaba.alink.operator.batch.feature.OneHotPredictBatchOp;
import com.alibaba.alink.operator.batch.feature.OneHotTrainBatchOp;
import com.alibaba.alink.operator.batch.source.MemSourceBatchOp;
import org.junit.Test;
import java.util.Arrays;
import java.util.List;
public class OneHotTrainBatchOpTest {
    @Test
    public void testOneHotTrainBatchOp() throws Exception {
        List <Row> df = Arrays.asList(
            Row.of("a", 1),
            Row.of("b", 1),
            Row.of("c", 1),
            Row.of("e", 2),
            Row.of("a", 2),
            Row.of("b", 1),
            Row.of("c", 2),
            Row.of("d", 2),
            Row.of(null, 1)
        );
        BatchOperator <?> inOp = new MemSourceBatchOp(df, "query string, weight int");
        BatchOperator <?> one_hot = new OneHotTrainBatchOp().setSelectedCols("query");
        BatchOperator <?> model = inOp.link(one_hot);
        model.lazyPrint(10);
        BatchOperator <?> predictor = new OneHotPredictBatchOp().setOutputCols("output");
        predictor.linkFrom(model, inOp).print();
    }
}