use of com.alibaba.alink.pipeline.dataproc.vector.VectorAssembler in project Alink by alibaba.
the class Chap10 method c_3_1.
static void c_3_1() throws Exception {
BatchOperator<?> train_data = new AkSourceBatchOp().setFilePath(DATA_DIR + TRAIN_FILE);
BatchOperator<?> test_data = new AkSourceBatchOp().setFilePath(DATA_DIR + TEST_FILE);
Pipeline pipeline = new Pipeline().add(new OneHotEncoder().setSelectedCols(CATEGORY_FEATURE_COL_NAMES).setEncode(Encode.VECTOR)).add(new VectorAssembler().setSelectedCols(FEATURE_COL_NAMES).setOutputCol(VEC_COL_NAME)).add(new LogisticRegression().setVectorCol(VEC_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME));
pipeline.fit(train_data).transform(test_data).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("2").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics());
BatchOperator.execute();
}
Aggregations