交叉驗證

方法思想：

       CrossValidator將資料集劃分為若干子集分別地進行訓練和測試。如當k＝3時，CrossValidator產生3個訓練資料與測試資料對，每個資料對使用2/3的資料來訓練，1/3的資料來測試。對於一組特定的引數表，CrossValidator計算基於三組不同訓練資料與測試資料對訓練得到的模型的評估準則的平均值。確定最佳引數表後，CrossValidator最後使用最佳引數表基於全部資料來重新擬合估計器。

示例：

       注意對引數網格進行交叉驗證的成本是很高的。如下面例子中，引數網格hashingTF.numFeatures有3個值，lr.regParam

Scala:

import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.ml.linalg.Vector
import org.apache.spark.ml.tuning.{CrossValidator, ParamGridBuilder}
import org.apache.spark.sql.Row

// Prepare training data 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),
  (4L, "b spark who", 1.0),
  (5L, "g d a y", 0.0),
  (6L, "spark fly", 1.0),
  (7L, "was mapreduce", 0.0),
  (8L, "e spark program", 1.0),
  (9L, "a e c l", 0.0),
  (10L, "spark compile", 1.0),
  (11L, "hadoop software", 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()
  .setInputCol(tokenizer.getOutputCol)
  .setOutputCol("features")
val lr = new LogisticRegression()
  .setMaxIter(10)
val pipeline = new Pipeline()
  .setStages(Array(tokenizer, hashingTF, lr))

// We use a ParamGridBuilder to construct a grid of parameters to search over.
// With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
// this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
val paramGrid = new ParamGridBuilder()
  .addGrid(hashingTF.numFeatures, Array(10, 100, 1000))
  .addGrid(lr.regParam, Array(0.1, 0.01))
  .build()

// We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
// This will allow us to jointly choose parameters for all Pipeline stages.
// A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
// Note that the evaluator here is a BinaryClassificationEvaluator and its default metric
// is areaUnderROC.
val cv = new CrossValidator()
  .setEstimator(pipeline)
  .setEvaluator(new BinaryClassificationEvaluator)
  .setEstimatorParamMaps(paramGrid)
  .setNumFolds(2)  // Use 3+ in practice

// Run cross-validation, and choose the best set of parameters.
val cvModel = cv.fit(training)

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

// Make predictions on test documents. cvModel uses the best model found (lrModel).
cvModel.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.PipelineStage;
import org.apache.spark.ml.classification.LogisticRegression;
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator;
import org.apache.spark.ml.feature.HashingTF;
import org.apache.spark.ml.feature.Tokenizer;
import org.apache.spark.ml.param.ParamMap;
import org.apache.spark.ml.tuning.CrossValidator;
import org.apache.spark.ml.tuning.CrossValidatorModel;
import org.apache.spark.ml.tuning.ParamGridBuilder;
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),
  new JavaLabeledDocument(4L, "b spark who", 1.0),
  new JavaLabeledDocument(5L, "g d a y", 0.0),
  new JavaLabeledDocument(6L, "spark fly", 1.0),
  new JavaLabeledDocument(7L, "was mapreduce", 0.0),
  new JavaLabeledDocument(8L, "e spark program", 1.0),
  new JavaLabeledDocument(9L, "a e c l", 0.0),
  new JavaLabeledDocument(10L, "spark compile", 1.0),
  new JavaLabeledDocument(11L, "hadoop software", 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(0.01);
Pipeline pipeline = new Pipeline()
  .setStages(new PipelineStage[] {tokenizer, hashingTF, lr});

// We use a ParamGridBuilder to construct a grid of parameters to search over.
// With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
// this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
ParamMap[] paramGrid = new ParamGridBuilder()
  .addGrid(hashingTF.numFeatures(), new int[] {10, 100, 1000})
  .addGrid(lr.regParam(), new double[] {0.1, 0.01})
  .build();

// We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
// This will allow us to jointly choose parameters for all Pipeline stages.
// A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
// Note that the evaluator here is a BinaryClassificationEvaluator and its default metric
// is areaUnderROC.
CrossValidator cv = new CrossValidator()
  .setEstimator(pipeline)
  .setEvaluator(new BinaryClassificationEvaluator())
  .setEstimatorParamMaps(paramGrid).setNumFolds(2);  // Use 3+ in practice

// Run cross-validation, and choose the best set of parameters.
CrossValidatorModel cvModel = cv.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, "mapreduce spark"),
  new JavaDocument(7L, "apache hadoop")
), JavaDocument.class);

// Make predictions on test documents. cvModel uses the best model found (lrModel).
Dataset<Row> predictions = cvModel.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.evaluation import BinaryClassificationEvaluator
from pyspark.ml.feature import HashingTF, Tokenizer
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder

# Prepare training documents, which are labeled.
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),
    (4, "b spark who", 1.0),
    (5, "g d a y", 0.0),
    (6, "spark fly", 1.0),
    (7, "was mapreduce", 0.0),
    (8, "e spark program", 1.0),
    (9, "a e c l", 0.0),
    (10, "spark compile", 1.0),
    (11, "hadoop software", 0.0)
], ["id", "text", "label"])

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

# We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
# This will allow us to jointly choose parameters for all Pipeline stages.
# A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
# We use a ParamGridBuilder to construct a grid of parameters to search over.
# With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
# this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
paramGrid = ParamGridBuilder() \
    .addGrid(hashingTF.numFeatures, [10, 100, 1000]) \
    .addGrid(lr.regParam, [0.1, 0.01]) \
    .build()

crossval = CrossValidator(estimator=pipeline,
                          estimatorParamMaps=paramGrid,
                          evaluator=BinaryClassificationEvaluator(),
                          numFolds=2)  # use 3+ folds in practice

# Run cross-validation, and choose the best set of parameters.
cvModel = crossval.fit(training)

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

# Make predictions on test documents. cvModel uses the best model found (lrModel).
prediction = cvModel.transform(test)
selected = prediction.select("id", "text", "probability", "prediction")
for row in selected.collect():
    print(row)