Search in sources :

Example 1 with LocalPredictor

use of com.alibaba.alink.pipeline.LocalPredictor in project Alink by alibaba.

the class BaseRecommender method collectLocalPredictor.

@Override
public LocalPredictor collectLocalPredictor(TableSchema inputSchema) {
    List<Row> modelRows = this.modelData.collect();
    ModelMapper mapper = new RecommMapper(this.recommKernelBuilder, this.recommType, modelData.getSchema(), inputSchema, this.getParams());
    mapper.loadModel(modelRows);
    return new LocalPredictor(mapper);
}
Also used : LocalPredictor(com.alibaba.alink.pipeline.LocalPredictor) Row(org.apache.flink.types.Row) RecommMapper(com.alibaba.alink.operator.common.recommendation.RecommMapper) ModelMapper(com.alibaba.alink.common.mapper.ModelMapper)

Example 2 with LocalPredictor

use of com.alibaba.alink.pipeline.LocalPredictor in project Alink by alibaba.

the class Chap24 method c_6.

static void c_6() throws Exception {
    MemSourceBatchOp test_data = new MemSourceBatchOp(new Long[] { 50L }, ITEM_COL);
    new ItemCfSimilarItemsRecommender().setItemCol(ITEM_COL).setRecommCol(RECOMM_COL).setModelData(new AkSourceBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE)).transform(test_data).print();
    LocalPredictor recomm_predictor = new ItemCfSimilarItemsRecommender().setItemCol(ITEM_COL).setRecommCol(RECOMM_COL).setK(10).setModelData(new AkSourceBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE)).collectLocalPredictor("item_id long");
    LocalPredictor kv_predictor = new Lookup().setSelectedCols(ITEM_COL).setOutputCols("item_name").setModelData(getSourceItems()).setMapKeyCols("item_id").setMapValueCols("title").collectLocalPredictor("item_id long");
    MTable recommResult = (MTable) recomm_predictor.map(Row.of(50L)).getField(1);
    System.out.println(recommResult);
}
Also used : MemSourceBatchOp(com.alibaba.alink.operator.batch.source.MemSourceBatchOp) AkSourceBatchOp(com.alibaba.alink.operator.batch.source.AkSourceBatchOp) MTable(com.alibaba.alink.common.MTable) LocalPredictor(com.alibaba.alink.pipeline.LocalPredictor) Lookup(com.alibaba.alink.pipeline.dataproc.Lookup)

Example 3 with LocalPredictor

use of com.alibaba.alink.pipeline.LocalPredictor 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));
}
Also used : LocalPredictor(com.alibaba.alink.pipeline.LocalPredictor) VectorAssembler(com.alibaba.alink.pipeline.dataproc.vector.VectorAssembler) NGram(com.alibaba.alink.pipeline.nlp.NGram) DocCountVectorizer(com.alibaba.alink.pipeline.nlp.DocCountVectorizer) Pipeline(com.alibaba.alink.pipeline.Pipeline) PipelineModel(com.alibaba.alink.pipeline.PipelineModel) EvalBinaryClassBatchOp(com.alibaba.alink.operator.batch.evaluation.EvalBinaryClassBatchOp) AkSourceBatchOp(com.alibaba.alink.operator.batch.source.AkSourceBatchOp) RegexTokenizer(com.alibaba.alink.pipeline.nlp.RegexTokenizer) AkSourceStreamOp(com.alibaba.alink.operator.stream.source.AkSourceStreamOp) Row(org.apache.flink.types.Row) LogisticRegression(com.alibaba.alink.pipeline.classification.LogisticRegression) File(java.io.File)

Example 4 with LocalPredictor

use of com.alibaba.alink.pipeline.LocalPredictor in project Alink by alibaba.

the class Chap24 method c_5.

static void c_5() throws Exception {
    if (!new File(DATA_DIR + ITEMCF_MODEL_FILE).exists()) {
        getSourceRatings().link(new ItemCfTrainBatchOp().setUserCol(USER_COL).setItemCol(ITEM_COL).setRateCol(RATING_COL)).link(new AkSinkBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE));
        BatchOperator.execute();
    }
    MemSourceBatchOp test_data = new MemSourceBatchOp(new Long[] { 1L }, "user_id");
    new ItemCfItemsPerUserRecommender().setUserCol(USER_COL).setRecommCol(RECOMM_COL).setModelData(new AkSourceBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE)).transform(test_data).print();
    LocalPredictor recomm_predictor = new ItemCfItemsPerUserRecommender().setUserCol(USER_COL).setRecommCol(RECOMM_COL).setK(20).setModelData(new AkSourceBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE)).collectLocalPredictor("user_id long");
    System.out.println(recomm_predictor.getOutputSchema());
    LocalPredictor kv_predictor = new Lookup().setSelectedCols(ITEM_COL).setOutputCols("item_name").setModelData(getSourceItems()).setMapKeyCols("item_id").setMapValueCols("title").collectLocalPredictor("item_id long");
    System.out.println(kv_predictor.getOutputSchema());
    MTable recommResult = (MTable) recomm_predictor.map(Row.of(1L)).getField(1);
    System.out.println(recommResult);
    new Lookup().setSelectedCols(ITEM_COL).setOutputCols("item_name").setModelData(getSourceItems()).setMapKeyCols("item_id").setMapValueCols("title").transform(getSourceRatings().filter("user_id=1 AND rating>4")).select("item_name").orderBy("item_name", 1000).lazyPrint(-1);
    LocalPredictor recomm_predictor_2 = new ItemCfItemsPerUserRecommender().setUserCol(USER_COL).setRecommCol(RECOMM_COL).setK(20).setExcludeKnown(true).setModelData(new AkSourceBatchOp().setFilePath(DATA_DIR + ITEMCF_MODEL_FILE)).collectLocalPredictor("user_id long");
    recommResult = (MTable) recomm_predictor_2.map(Row.of(1L)).getField(1);
    System.out.println(recommResult);
}
Also used : MemSourceBatchOp(com.alibaba.alink.operator.batch.source.MemSourceBatchOp) AkSourceBatchOp(com.alibaba.alink.operator.batch.source.AkSourceBatchOp) MTable(com.alibaba.alink.common.MTable) LocalPredictor(com.alibaba.alink.pipeline.LocalPredictor) Lookup(com.alibaba.alink.pipeline.dataproc.Lookup) AkSinkBatchOp(com.alibaba.alink.operator.batch.sink.AkSinkBatchOp) File(java.io.File) ItemCfTrainBatchOp(com.alibaba.alink.operator.batch.recommendation.ItemCfTrainBatchOp)

Example 5 with LocalPredictor

use of com.alibaba.alink.pipeline.LocalPredictor in project Alink by alibaba.

the class Chap01 method c_5_5.

static void c_5_5() throws Exception {
    LocalPredictor predictor = new LocalPredictor(DATA_DIR + "gmv_pipeline.model", "x int");
    System.out.println(predictor.getOutputSchema());
    for (int x : new int[] { 2018, 2019 }) {
        System.out.println(predictor.map(Row.of(x)));
    }
}
Also used : LocalPredictor(com.alibaba.alink.pipeline.LocalPredictor)

Aggregations

LocalPredictor (com.alibaba.alink.pipeline.LocalPredictor)5 AkSourceBatchOp (com.alibaba.alink.operator.batch.source.AkSourceBatchOp)3 MTable (com.alibaba.alink.common.MTable)2 MemSourceBatchOp (com.alibaba.alink.operator.batch.source.MemSourceBatchOp)2 Lookup (com.alibaba.alink.pipeline.dataproc.Lookup)2 File (java.io.File)2 Row (org.apache.flink.types.Row)2 ModelMapper (com.alibaba.alink.common.mapper.ModelMapper)1 EvalBinaryClassBatchOp (com.alibaba.alink.operator.batch.evaluation.EvalBinaryClassBatchOp)1 ItemCfTrainBatchOp (com.alibaba.alink.operator.batch.recommendation.ItemCfTrainBatchOp)1 AkSinkBatchOp (com.alibaba.alink.operator.batch.sink.AkSinkBatchOp)1 RecommMapper (com.alibaba.alink.operator.common.recommendation.RecommMapper)1 AkSourceStreamOp (com.alibaba.alink.operator.stream.source.AkSourceStreamOp)1 Pipeline (com.alibaba.alink.pipeline.Pipeline)1 PipelineModel (com.alibaba.alink.pipeline.PipelineModel)1 LogisticRegression (com.alibaba.alink.pipeline.classification.LogisticRegression)1 VectorAssembler (com.alibaba.alink.pipeline.dataproc.vector.VectorAssembler)1 DocCountVectorizer (com.alibaba.alink.pipeline.nlp.DocCountVectorizer)1 NGram (com.alibaba.alink.pipeline.nlp.NGram)1 RegexTokenizer (com.alibaba.alink.pipeline.nlp.RegexTokenizer)1