Examples with RegexTokenizer com.alibaba.alink.pipeline.nlp.RegexTokenizer used on opensource projects

Example 1 with RegexTokenizer

use of com.alibaba.alink.pipeline.nlp.RegexTokenizer in project Alink by alibaba.

the class Chap23 method c_2.

static void c_2() throws Exception {
    if (!new File(DATA_DIR + TRAIN_FILE).exists()) {
        ArrayList<Row> trainRows = new ArrayList<>();
        ArrayList<Row> testRows = new ArrayList<>();
        for (String label : new String[] { "pos", "neg" }) {
            File subfolder = new File(ORIGIN_DATA_DIR + "train" + File.separator + label);
            for (File f : subfolder.listFiles()) {
                trainRows.add(Row.of(label, readFileContent(f)));
            }
        }
        for (String label : new String[] { "pos", "neg" }) {
            File subfolder = new File(ORIGIN_DATA_DIR + "test" + File.separator + label);
            for (File f : subfolder.listFiles()) {
                testRows.add(Row.of(label, readFileContent(f)));
            }
        }
        new MemSourceBatchOp(trainRows, COL_NAMES).link(new AkSinkBatchOp().setFilePath(DATA_DIR + TRAIN_FILE));
        new MemSourceBatchOp(testRows, COL_NAMES).link(new AkSinkBatchOp().setFilePath(DATA_DIR + TEST_FILE));
        BatchOperator.execute();
    }
    AkSourceBatchOp train_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TRAIN_FILE);
    AkSourceBatchOp test_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TEST_FILE);
    train_set.lazyPrint(2);
    new Pipeline().add(new RegexTokenizer().setPattern("\\W+").setSelectedCol(TXT_COL_NAME)).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol(TXT_COL_NAME).setOutputCol(VECTOR_COL_NAME).enableLazyPrintTransformData(1)).add(new LogisticRegression().setMaxIter(30).setVectorCol(VECTOR_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME)).fit(train_set).transform(test_set).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("pos").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics("DocCountVectorizer"));
    BatchOperator.execute();
    new Pipeline().add(new RegexTokenizer().setPattern("\\W+").setSelectedCol(TXT_COL_NAME)).add(new DocHashCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol(TXT_COL_NAME).setOutputCol(VECTOR_COL_NAME).enableLazyPrintTransformData(1)).add(new LogisticRegression().setMaxIter(30).setVectorCol(VECTOR_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME)).fit(train_set).transform(test_set).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("pos").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics("DocHashCountVectorizer"));
    BatchOperator.execute();
}

Example 2 with RegexTokenizer

use of com.alibaba.alink.pipeline.nlp.RegexTokenizer in project Alink by alibaba.

the class Chap23 method c_3.

static void c_3() throws Exception {
    AkSourceBatchOp train_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TRAIN_FILE);
    AkSourceBatchOp test_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TEST_FILE);
    new Pipeline().add(new RegexTokenizer().setPattern("\\W+").setSelectedCol(TXT_COL_NAME)).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol(TXT_COL_NAME).setOutputCol(VECTOR_COL_NAME)).add(new NGram().setN(2).setSelectedCol(TXT_COL_NAME).setOutputCol("v_2").enableLazyPrintTransformData(1, "2-gram")).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol("v_2").setOutputCol("v_2")).add(new VectorAssembler().setSelectedCols(VECTOR_COL_NAME, "v_2").setOutputCol(VECTOR_COL_NAME)).add(new LogisticRegression().setMaxIter(30).setVectorCol(VECTOR_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME)).fit(train_set).transform(test_set).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("pos").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics("NGram 2"));
    BatchOperator.execute();
    new Pipeline().add(new RegexTokenizer().setPattern("\\W+").setSelectedCol(TXT_COL_NAME)).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol(TXT_COL_NAME).setOutputCol(VECTOR_COL_NAME)).add(new NGram().setN(2).setSelectedCol(TXT_COL_NAME).setOutputCol("v_2")).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol("v_2").setOutputCol("v_2")).add(new NGram().setN(3).setSelectedCol(TXT_COL_NAME).setOutputCol("v_3")).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setVocabSize(10000).setSelectedCol("v_3").setOutputCol("v_3")).add(new VectorAssembler().setSelectedCols(VECTOR_COL_NAME, "v_2", "v_3").setOutputCol(VECTOR_COL_NAME)).add(new LogisticRegression().setMaxIter(30).setVectorCol(VECTOR_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME)).fit(train_set).transform(test_set).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("pos").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics("NGram 2 and 3"));
    BatchOperator.execute();
}

Example 3 with RegexTokenizer

use of com.alibaba.alink.pipeline.nlp.RegexTokenizer in project Alink by alibaba.

the class Chap23 method c_4.

static void c_4() throws Exception {
    AkSourceBatchOp train_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TRAIN_FILE);
    if (!new File(DATA_DIR + PIPELINE_MODEL).exists()) {
        new Pipeline().add(new RegexTokenizer().setPattern("\\W+").setSelectedCol(TXT_COL_NAME)).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setSelectedCol(TXT_COL_NAME).setOutputCol(VECTOR_COL_NAME)).add(new NGram().setN(2).setSelectedCol(TXT_COL_NAME).setOutputCol("v_2")).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setVocabSize(50000).setSelectedCol("v_2").setOutputCol("v_2")).add(new NGram().setN(3).setSelectedCol(TXT_COL_NAME).setOutputCol("v_3")).add(new DocCountVectorizer().setFeatureType("WORD_COUNT").setVocabSize(10000).setSelectedCol("v_3").setOutputCol("v_3")).add(new VectorAssembler().setSelectedCols(VECTOR_COL_NAME, "v_2", "v_3").setOutputCol(VECTOR_COL_NAME)).add(new LogisticRegression().setMaxIter(30).setVectorCol(VECTOR_COL_NAME).setLabelCol(LABEL_COL_NAME).setPredictionCol(PREDICTION_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME)).fit(train_set).save(DATA_DIR + PIPELINE_MODEL);
        BatchOperator.execute();
    }
    PipelineModel pipeline_model = PipelineModel.load(DATA_DIR + PIPELINE_MODEL);
    AkSourceBatchOp test_set = new AkSourceBatchOp().setFilePath(DATA_DIR + TEST_FILE);
    pipeline_model.transform(test_set).link(new EvalBinaryClassBatchOp().setPositiveLabelValueString("pos").setLabelCol(LABEL_COL_NAME).setPredictionDetailCol(PRED_DETAIL_COL_NAME).lazyPrintMetrics("NGram 2 and 3"));
    BatchOperator.execute();
    AkSourceStreamOp test_stream = new AkSourceStreamOp().setFilePath(DATA_DIR + TEST_FILE);
    pipeline_model.transform(test_stream).sample(0.001).select(PREDICTION_COL_NAME + ", " + LABEL_COL_NAME + ", " + TXT_COL_NAME).print();
    StreamOperator.execute();
    String str = "Oh dear. good cast, but to write and direct is an art and to write wit and direct wit is a bit of a " + "task. Even doing good comedy you have to get the timing and moment right. Im not putting it all down " + "there were parts where i laughed loud but that was at very few times. The main focus to me was on the " + "fast free flowing dialogue, that made some people in the film annoying. It may sound great while " + "reading the script in your head but getting that out and to the camera is a different task. And the " + "hand held camera work does give energy to few parts of the film. Overall direction was good but the " + "script was not all that to me, but I'm sure you was reading the script in your head it would sound good" + ". Sorry.";
    Row pred_row;
    LocalPredictor local_predictor = pipeline_model.collectLocalPredictor("review string");
    System.out.println(local_predictor.getOutputSchema());
    pred_row = local_predictor.map(Row.of(str));
    System.out.println(pred_row.getField(4));
    LocalPredictor local_predictor_2 = new LocalPredictor(DATA_DIR + PIPELINE_MODEL, "review string");
    System.out.println(local_predictor_2.getOutputSchema());
    pred_row = local_predictor_2.map(Row.of(str));
    System.out.println(pred_row.getField(4));
}