Examples with FeatureHasher com.alibaba.alink.pipeline.feature.FeatureHasher used on opensource projects

Example 1 with FeatureHasher

use of com.alibaba.alink.pipeline.feature.FeatureHasher in project Alink by alibaba.

the class Chap14 method c_3.

static void c_3() throws Exception {
    CsvSourceBatchOp trainBatchData = new CsvSourceBatchOp().setFilePath("http://alink-release.oss-cn-beijing.aliyuncs.com/data-files/avazu-small.csv").setSchemaStr(SCHEMA_STRING);
    // setup feature enginerring pipeline
    Pipeline feature_pipeline = new Pipeline().add(new StandardScaler().setSelectedCols(NUMERICAL_COL_NAMES)).add(new FeatureHasher().setSelectedCols(ArrayUtils.addAll(CATEGORY_COL_NAMES, NUMERICAL_COL_NAMES)).setCategoricalCols(CATEGORY_COL_NAMES).setOutputCol(VEC_COL_NAME).setNumFeatures(NUM_HASH_FEATURES));
    if (!new File(DATA_DIR + FEATURE_MODEL_FILE).exists()) {
        // fit and save feature pipeline model
        feature_pipeline.fit(trainBatchData).save(DATA_DIR + FEATURE_MODEL_FILE);
        BatchOperator.execute();
    }
}

Example 2 with FeatureHasher

use of com.alibaba.alink.pipeline.feature.FeatureHasher in project Alink by alibaba.

the class FTRLExample method main.

public static void main(String[] args) throws Exception {
    String schemaStr = "id string, click string, dt string, C1 string, banner_pos int, site_id string, site_domain string, " + "site_category string, app_id string, app_domain string, app_category string, device_id string, " + "device_ip string, device_model string, device_type string, device_conn_type string, C14 int, C15 int, " + "C16 int, C17 int, C18 int, C19 int, C20 int, C21 int";
    CsvSourceBatchOp trainBatchData = new CsvSourceBatchOp().setFilePath("http://alink-release.oss-cn-beijing.aliyuncs.com/data-files/avazu-small.csv").setSchemaStr(schemaStr);
    trainBatchData.firstN(10).print();
    String labelColName = "click";
    String[] selectedColNames = new String[] { "C1", "banner_pos", "site_category", "app_domain", "app_category", "device_type", "device_conn_type", "C14", "C15", "C16", "C17", "C18", "C19", "C20", "C21", "site_id", "site_domain", "device_id", "device_model" };
    String[] categoryColNames = new String[] { "C1", "banner_pos", "site_category", "app_domain", "app_category", "device_type", "device_conn_type", "site_id", "site_domain", "device_id", "device_model" };
    String[] numericalColNames = new String[] { "C14", "C15", "C16", "C17", "C18", "C19", "C20", "C21" };
    // result column name of feature engineering
    String vecColName = "vec";
    int numHashFeatures = 30000;
    // setup feature engineering pipeline
    Pipeline featurePipeline = new Pipeline().add(new StandardScaler().setSelectedCols(numericalColNames)).add(new FeatureHasher().setSelectedCols(selectedColNames).setCategoricalCols(categoryColNames).setOutputCol(vecColName).setNumFeatures(numHashFeatures));
    // fit feature pipeline model
    PipelineModel featurePipelineModel = featurePipeline.fit(trainBatchData);
    // prepare stream train data
    CsvSourceStreamOp data = new CsvSourceStreamOp().setFilePath("http://alink-release.oss-cn-beijing.aliyuncs.com/data-files/avazu-ctr-train-8M.csv").setSchemaStr(schemaStr).setIgnoreFirstLine(true);
    // split stream to train and eval data
    SplitStreamOp splitter = new SplitStreamOp().setFraction(0.5).linkFrom(data);
    // train initial batch model
    LogisticRegressionTrainBatchOp lr = new LogisticRegressionTrainBatchOp().setVectorCol(vecColName).setLabelCol(labelColName).setWithIntercept(true).setMaxIter(10);
    BatchOperator<?> initModel = featurePipelineModel.transform(trainBatchData).link(lr);
    // ftrl train
    FtrlTrainStreamOp model = new FtrlTrainStreamOp(initModel).setVectorCol(vecColName).setLabelCol(labelColName).setWithIntercept(true).setAlpha(0.1).setBeta(0.1).setL1(0.01).setL2(0.01).setTimeInterval(10).setVectorSize(numHashFeatures).linkFrom(featurePipelineModel.transform(splitter));
    // ftrl predict
    FtrlPredictStreamOp predictResult = new FtrlPredictStreamOp(initModel).setVectorCol(vecColName).setPredictionCol("pred").setReservedCols(new String[] { labelColName }).setPredictionDetailCol("details").linkFrom(model, featurePipelineModel.transform(splitter.getSideOutput(0)));
    // ftrl eval
    predictResult.link(new EvalBinaryClassStreamOp().setLabelCol(labelColName).setPredictionCol("pred").setPredictionDetailCol("details").setTimeInterval(10)).link(new JsonValueStreamOp().setSelectedCol("Data").setReservedCols(new String[] { "Statistics" }).setOutputCols(new String[] { "Accuracy", "AUC", "ConfusionMatrix" }).setJsonPath(new String[] { "$.Accuracy", "$.AUC", "$.ConfusionMatrix" })).print();
}

Example 3 with FeatureHasher

use of com.alibaba.alink.pipeline.feature.FeatureHasher in project Alink by alibaba.

the class Chap10 method c_3_2.

static void c_3_2() 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 FeatureHasher().setSelectedCols(FEATURE_COL_NAMES).setCategoricalCols(CATEGORY_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();
}