Examples with LinearRegression com.alibaba.alink.pipeline.regression.LinearRegression used on opensource projects

Example 1 with LinearRegression

use of com.alibaba.alink.pipeline.regression.LinearRegression in project Alink by alibaba.

the class Chap16 method c_3.

static void c_3() throws Exception {
    AkSourceBatchOp train_data = new AkSourceBatchOp().setFilePath(DATA_DIR + TRAIN_FILE);
    AkSourceBatchOp test_data = new AkSourceBatchOp().setFilePath(DATA_DIR + TEST_FILE);
    new LinearRegression().setFeatureCols(FEATURE_COL_NAMES).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).enableLazyPrintTrainInfo().enableLazyPrintModelInfo().fit(train_data).transform(test_data).link(new EvalRegressionBatchOp().setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).lazyPrintMetrics("LinearRegression"));
    new LassoRegression().setLambda(0.05).setFeatureCols(FEATURE_COL_NAMES).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).enableLazyPrintTrainInfo().enableLazyPrintModelInfo("< LASSO model >").fit(train_data).transform(test_data).link(new EvalRegressionBatchOp().setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).lazyPrintMetrics("LassoRegression"));
    BatchOperator.execute();
}

Example 2 with LinearRegression

use of com.alibaba.alink.pipeline.regression.LinearRegression in project Alink by alibaba.

the class Chap01 method c_5_4.

static void c_5_4() throws Exception {
    MemSourceBatchOp train_set = new MemSourceBatchOp(new Row[] { Row.of(2009, 0.5), Row.of(2010, 9.36), Row.of(2011, 52.0), Row.of(2012, 191.0), Row.of(2013, 350.0), Row.of(2014, 571.0), Row.of(2015, 912.0), Row.of(2016, 1207.0), Row.of(2017, 1682.0) }, new String[] { "x", "gmv" });
    Pipeline pipeline = new Pipeline().add(new Select().setClause("*, x*x AS x2")).add(new LinearRegression().setFeatureCols("x", "x2").setLabelCol("gmv").setPredictionCol("pred"));
    File file = new File(DATA_DIR + "gmv_pipeline.model");
    if (file.exists()) {
        file.delete();
    }
    pipeline.fit(train_set).save(DATA_DIR + "gmv_pipeline.model");
    BatchOperator.execute();
    PipelineModel pipelineModel = PipelineModel.load(DATA_DIR + "gmv_pipeline.model");
    BatchOperator<?> pred_batch = new MemSourceBatchOp(new Integer[] { 2018, 2019 }, "x");
    pipelineModel.transform(pred_batch).print();
    MemSourceStreamOp pred_stream = new MemSourceStreamOp(new Integer[] { 2018, 2019 }, "x");
    pipelineModel.transform(pred_stream).print();
    StreamOperator.execute();
}

Example 3 with LinearRegression

use of com.alibaba.alink.pipeline.regression.LinearRegression in project Alink by alibaba.

the class Chap02 method c_6.

static void c_6() throws Exception {
    MemSourceBatchOp source = new MemSourceBatchOp(new Row[] { Row.of("sunny", 85.0, 85.0, false, "no"), Row.of("sunny", 80.0, 90.0, true, "no"), Row.of("overcast", 83.0, 78.0, false, "yes"), Row.of("rainy", 70.0, 96.0, false, "yes"), Row.of("rainy", 68.0, 80.0, false, "yes"), Row.of("rainy", 65.0, 70.0, true, "no"), Row.of("overcast", 64.0, 65.0, true, "yes"), Row.of("sunny", 72.0, 95.0, false, "no"), Row.of("sunny", 69.0, 70.0, false, "yes"), Row.of("rainy", 75.0, 80.0, false, "yes"), Row.of("sunny", 75.0, 70.0, true, "yes"), Row.of("overcast", 72.0, 90.0, true, "yes"), Row.of("overcast", 81.0, 75.0, false, "yes"), Row.of("rainy", 71.0, 80.0, true, "no") }, new String[] { "outlook", "Temperature", "Humidity", "Windy", "play" });
    source.link(new C45TrainBatchOp().setFeatureCols("outlook", "Temperature", "Humidity", "Windy").setCategoricalCols("outlook", "Windy").setLabelCol("play")).link(new AkSinkBatchOp().setFilePath(DATA_DIR + TREE_MODEL_FILE).setOverwriteSink(true));
    BatchOperator.execute();
    new AkSourceBatchOp().setFilePath(DATA_DIR + TREE_MODEL_FILE).link(new DecisionTreeModelInfoBatchOp().lazyPrintModelInfo().lazyCollectModelInfo(new Consumer<DecisionTreeModelInfo>() {

        @Override
        public void accept(DecisionTreeModelInfo decisionTreeModelInfo) {
            try {
                decisionTreeModelInfo.saveTreeAsImage(DATA_DIR + "tree_model.png", true);
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }));
    BatchOperator.execute();
    MemSourceBatchOp train_set = new MemSourceBatchOp(new Row[] { Row.of(2009, 0.5), Row.of(2010, 9.36), Row.of(2011, 52.0), Row.of(2012, 191.0), Row.of(2013, 350.0), Row.of(2014, 571.0), Row.of(2015, 912.0), Row.of(2016, 1207.0), Row.of(2017, 1682.0) }, new String[] { "x", "gmv" });
    Pipeline pipeline = new Pipeline().add(new Select().setClause("*, x*x AS x2")).add(new LinearRegression().setFeatureCols("x", "x2").setLabelCol("gmv").setPredictionCol("pred"));
    pipeline.fit(train_set).save(DATA_DIR + PIPELINE_MODEL_FILE, true);
    BatchOperator.execute();
    PipelineModel pipelineModel = PipelineModel.load(DATA_DIR + PIPELINE_MODEL_FILE);
    TransformerBase<?>[] stages = pipelineModel.getTransformers();
    for (int i = 0; i < stages.length; i++) {
        System.out.println(String.valueOf(i) + "\t" + stages[i]);
    }
    ((LinearRegressionModel) stages[1]).getModelData().link(new LinearRegModelInfoBatchOp().lazyPrintModelInfo());
    BatchOperator.execute();
}