Spark Pipeline官方文档

import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.sql.Row

// Prepare training data from a list of (label, features) tuples.
val training = spark.createDataFrame(Seq(
  (1.0, Vectors.dense(0.0, 1.1, 0.1)),
  (0.0, Vectors.dense(2.0, 1.0, -1.0)),
  (0.0, Vectors.dense(2.0, 1.3, 1.0)),
  (1.0, Vectors.dense(0.0, 1.2, -0.5))
)).toDF("label", "features")

// Create a LogisticRegression instance. This instance is an Estimator.
val lr = new LogisticRegression()
// Print out the parameters, documentation, and any default values.
println(s"LogisticRegression parameters:\n ${lr.explainParams()}\n")

// We may set parameters using setter methods.
lr.setMaxIter(10)
  .setRegParam(0.01)

// Learn a LogisticRegression model. This uses the parameters stored in lr.
val model1 = lr.fit(training)
// Since model1 is a Model (i.e., a Transformer produced by an Estimator),
// we can view the parameters it used during fit().
// This prints the parameter (name: value) pairs, where names are unique IDs for this
// LogisticRegression instance.
println(s"Model 1 was fit using parameters: ${model1.parent.extractParamMap}")

// We may alternatively specify parameters using a ParamMap,
// which supports several methods for specifying parameters.
val paramMap = ParamMap(lr.maxIter -> 20)
  .put(lr.maxIter, 30)  // Specify 1 Param. This overwrites the original maxIter.
  .put(lr.regParam -> 0.1, lr.threshold -> 0.55)  // Specify multiple Params.

// One can also combine ParamMaps.
val paramMap2 = ParamMap(lr.probabilityCol -> "myProbability")  // Change output column name.
val paramMapCombined = paramMap ++ paramMap2

// Now learn a new model using the paramMapCombined parameters.
// paramMapCombined overrides all parameters set earlier via lr.set* methods.
val model2 = lr.fit(training, paramMapCombined)
println(s"Model 2 was fit using parameters: ${model2.parent.extractParamMap}")

// Prepare test data.
val test = spark.createDataFrame(Seq(
  (1.0, Vectors.dense(-1.0, 1.5, 1.3)),
  (0.0, Vectors.dense(3.0, 2.0, -0.1)),
  (1.0, Vectors.dense(0.0, 2.2, -1.5))
)).toDF("label", "features")

// Make predictions on test data using the Transformer.transform() method.
// LogisticRegression.transform will only use the 'features' column.
// Note that model2.transform() outputs a 'myProbability' column instead of the usual
// 'probability' column since we renamed the lr.probabilityCol parameter previously.
model2.transform(test)
  .select("features", "label", "myProbability", "prediction")
  .collect()
  .foreach { case Row(features: Vector, label: Double, prob: Vector, prediction: Double) =>
    println(s"($features, $label) -> prob=$prob, prediction=$prediction")
  }

import java.util.Arrays;
import java.util.List;

import org.apache.spark.ml.classification.LogisticRegression;
import org.apache.spark.ml.classification.LogisticRegressionModel;
import org.apache.spark.ml.linalg.VectorUDT;
import org.apache.spark.ml.linalg.Vectors;
import org.apache.spark.ml.param.ParamMap;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

// Prepare training data.
List<Row> dataTraining = Arrays.asList(
    RowFactory.create(1.0, Vectors.dense(0.0, 1.1, 0.1)),
    RowFactory.create(0.0, Vectors.dense(2.0, 1.0, -1.0)),
    RowFactory.create(0.0, Vectors.dense(2.0, 1.3, 1.0)),
    RowFactory.create(1.0, Vectors.dense(0.0, 1.2, -0.5))
);
StructType schema = new StructType(new StructField[]{
    new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
    new StructField("features", new VectorUDT(), false, Metadata.empty())
});
Dataset<Row> training = spark.createDataFrame(dataTraining, schema);

// Create a LogisticRegression instance. This instance is an Estimator.
LogisticRegression lr = new LogisticRegression();
// Print out the parameters, documentation, and any default values.
System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");

// We may set parameters using setter methods.
lr.setMaxIter(10).setRegParam(0.01);

// Learn a LogisticRegression model. This uses the parameters stored in lr.
LogisticRegressionModel model1 = lr.fit(training);
// Since model1 is a Model (i.e., a Transformer produced by an Estimator),
// we can view the parameters it used during fit().
// This prints the parameter (name: value) pairs, where names are unique IDs for this
// LogisticRegression instance.
System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());

// We may alternatively specify parameters using a ParamMap.
ParamMap paramMap = new ParamMap()
  .put(lr.maxIter().w(20))  // Specify 1 Param.
  .put(lr.maxIter(), 30)  // This overwrites the original maxIter.
  .put(lr.regParam().w(0.1), lr.threshold().w(0.55));  // Specify multiple Params.

// One can also combine ParamMaps.
ParamMap paramMap2 = new ParamMap()
  .put(lr.probabilityCol().w("myProbability"));  // Change output column name
ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);

// Now learn a new model using the paramMapCombined parameters.
// paramMapCombined overrides all parameters set earlier via lr.set* methods.
LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());

// Prepare test documents.
List<Row> dataTest = Arrays.asList(
    RowFactory.create(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
    RowFactory.create(0.0, Vectors.dense(3.0, 2.0, -0.1)),
    RowFactory.create(1.0, Vectors.dense(0.0, 2.2, -1.5))
);
Dataset<Row> test = spark.createDataFrame(dataTest, schema);

// Make predictions on test documents using the Transformer.transform() method.
// LogisticRegression.transform will only use the 'features' column.
// Note that model2.transform() outputs a 'myProbability' column instead of the usual
// 'probability' column since we renamed the lr.probabilityCol parameter previously.
Dataset<Row> results = model2.transform(test);
Dataset<Row> rows = results.select("features", "label", "myProbability", "prediction");
for (Row r: rows.collectAsList()) {
  System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2)
    + ", prediction=" + r.get(3));
}

from pyspark.ml.linalg import Vectors
from pyspark.ml.classification import LogisticRegression

# Prepare training data from a list of (label, features) tuples.
training = spark.createDataFrame([
    (1.0, Vectors.dense([0.0, 1.1, 0.1])),
    (0.0, Vectors.dense([2.0, 1.0, -1.0])),
    (0.0, Vectors.dense([2.0, 1.3, 1.0])),
    (1.0, Vectors.dense([0.0, 1.2, -0.5]))], ["label", "features"])

# Create a LogisticRegression instance. This instance is an Estimator.
lr = LogisticRegression(maxIter=10, regParam=0.01)
# Print out the parameters, documentation, and any default values.
print("LogisticRegression parameters:\n" + lr.explainParams() + "\n")

# Learn a LogisticRegression model. This uses the parameters stored in lr.
model1 = lr.fit(training)

# Since model1 is a Model (i.e., a transformer produced by an Estimator),
# we can view the parameters it used during fit().
# This prints the parameter (name: value) pairs, where names are unique IDs for this
# LogisticRegression instance.
print("Model 1 was fit using parameters: ")
print(model1.extractParamMap())

# We may alternatively specify parameters using a Python dictionary as a paramMap
paramMap = {lr.maxIter: 20}
paramMap[lr.maxIter] = 30  # Specify 1 Param, overwriting the original maxIter.
paramMap.update({lr.regParam: 0.1, lr.threshold: 0.55})  # Specify multiple Params.

# You can combine paramMaps, which are python dictionaries.
paramMap2 = {lr.probabilityCol: "myProbability"}  # Change output column name
paramMapCombined = paramMap.copy()
paramMapCombined.update(paramMap2)

# Now learn a new model using the paramMapCombined parameters.
# paramMapCombined overrides all parameters set earlier via lr.set* methods.
model2 = lr.fit(training, paramMapCombined)
print("Model 2 was fit using parameters: ")
print(model2.extractParamMap())

# Prepare test data
test = spark.createDataFrame([
    (1.0, Vectors.dense([-1.0, 1.5, 1.3])),
    (0.0, Vectors.dense([3.0, 2.0, -0.1])),
    (1.0, Vectors.dense([0.0, 2.2, -1.5]))], ["label", "features"])

# Make predictions on test data using the Transformer.transform() method.
# LogisticRegression.transform will only use the 'features' column.
# Note that model2.transform() outputs a "myProbability" column instead of the usual
# 'probability' column since we renamed the lr.probabilityCol parameter previously.
prediction = model2.transform(test)
result = prediction.select("features", "label", "myProbability", "prediction") \
    .collect()

for row in result:
    print("features=%s, label=%s -> prob=%s, prediction=%s"
          % (row.features, row.label, row.myProbability, row.prediction))

import org.apache.spark.ml.{Pipeline, PipelineModel}
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.ml.linalg.Vector
import org.apache.spark.sql.Row

// Prepare training documents from a list of (id, text, label) tuples.
val training = spark.createDataFrame(Seq(
  (0L, "a b c d e spark", 1.0),
  (1L, "b d", 0.0),
  (2L, "spark f g h", 1.0),
  (3L, "hadoop mapreduce", 0.0)
)).toDF("id", "text", "label")

// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
val tokenizer = new Tokenizer()
  .setInputCol("text")
  .setOutputCol("words")
val hashingTF = new HashingTF()
  .setNumFeatures(1000)
  .setInputCol(tokenizer.getOutputCol)
  .setOutputCol("features")
val lr = new LogisticRegression()
  .setMaxIter(10)
  .setRegParam(0.001)
val pipeline = new Pipeline()
  .setStages(Array(tokenizer, hashingTF, lr))

// Fit the pipeline to training documents.
val model = pipeline.fit(training)

// Now we can optionally save the fitted pipeline to disk
model.write.overwrite().save("/tmp/spark-logistic-regression-model")

// We can also save this unfit pipeline to disk
pipeline.write.overwrite().save("/tmp/unfit-lr-model")

// And load it back in during production
val sameModel = PipelineModel.load("/tmp/spark-logistic-regression-model")

// Prepare test documents, which are unlabeled (id, text) tuples.
val test = spark.createDataFrame(Seq(
  (4L, "spark i j k"),
  (5L, "l m n"),
  (6L, "spark hadoop spark"),
  (7L, "apache hadoop")
)).toDF("id", "text")

// Make predictions on test documents.
model.transform(test)
  .select("id", "text", "probability", "prediction")
  .collect()
  .foreach { case Row(id: Long, text: String, prob: Vector, prediction: Double) =>
    println(s"($id, $text) --> prob=$prob, prediction=$prediction")
  }

import java.util.Arrays;

import org.apache.spark.ml.Pipeline;
import org.apache.spark.ml.PipelineModel;
import org.apache.spark.ml.PipelineStage;
import org.apache.spark.ml.classification.LogisticRegression;
import org.apache.spark.ml.feature.HashingTF;
import org.apache.spark.ml.feature.Tokenizer;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

// Prepare training documents, which are labeled.
Dataset<Row> training = spark.createDataFrame(Arrays.asList(
  new JavaLabeledDocument(0L, "a b c d e spark", 1.0),
  new JavaLabeledDocument(1L, "b d", 0.0),
  new JavaLabeledDocument(2L, "spark f g h", 1.0),
  new JavaLabeledDocument(3L, "hadoop mapreduce", 0.0)
), JavaLabeledDocument.class);

// Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
Tokenizer tokenizer = new Tokenizer()
  .setInputCol("text")
  .setOutputCol("words");
HashingTF hashingTF = new HashingTF()
  .setNumFeatures(1000)
  .setInputCol(tokenizer.getOutputCol())
  .setOutputCol("features");
LogisticRegression lr = new LogisticRegression()
  .setMaxIter(10)
  .setRegParam(0.001);
Pipeline pipeline = new Pipeline()
  .setStages(new PipelineStage[] {tokenizer, hashingTF, lr});

// Fit the pipeline to training documents.
PipelineModel model = pipeline.fit(training);

// Prepare test documents, which are unlabeled.
Dataset<Row> test = spark.createDataFrame(Arrays.asList(
  new JavaDocument(4L, "spark i j k"),
  new JavaDocument(5L, "l m n"),
  new JavaDocument(6L, "spark hadoop spark"),
  new JavaDocument(7L, "apache hadoop")
), JavaDocument.class);

// Make predictions on test documents.
Dataset<Row> predictions = model.transform(test);
for (Row r : predictions.select("id", "text", "probability", "prediction").collectAsList()) {
  System.out.println("(" + r.get(0) + ", " + r.get(1) + ") --> prob=" + r.get(2)
    + ", prediction=" + r.get(3));
}

from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer

# Prepare training documents from a list of (id, text, label) tuples.
training = spark.createDataFrame([
    (0, "a b c d e spark", 1.0),
    (1, "b d", 0.0),
    (2, "spark f g h", 1.0),
    (3, "hadoop mapreduce", 0.0)
], ["id", "text", "label"])

# Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10, regParam=0.001)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])

# Fit the pipeline to training documents.
model = pipeline.fit(training)

# Prepare test documents, which are unlabeled (id, text) tuples.
test = spark.createDataFrame([
    (4, "spark i j k"),
    (5, "l m n"),
    (6, "spark hadoop spark"),
    (7, "apache hadoop")
], ["id", "text"])

# Make predictions on test documents and print columns of interest.
prediction = model.transform(test)
selected = prediction.select("id", "text", "probability", "prediction")
for row in selected.collect():
    rid, text, prob, prediction = row
    print("(%d, %s) --> prob=%s, prediction=%f" % (rid, text, str(prob), prediction))