从Spark MLlib到美图机器学习框架实践

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")
 }

// 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
 .setParallelism(2)  // Evaluate up to 2 parameter settings in parallel

// 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 org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}

// Prepare training and test data.
val data = spark.read.format("libsvm").load("data/mllib/sample_linear_regression_data.txt")
val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345)

val lr = new LinearRegression()
   .setMaxIter(10)

// We use a ParamGridBuilder to construct a grid of parameters to search over.
// TrainValidationSplit will try all combinations of values and determine best model using
// the evaluator.
val paramGrid = new ParamGridBuilder()
 .addGrid(lr.regParam, Array(0.1, 0.01))
 .addGrid(lr.fitIntercept)
 .addGrid(lr.elasticNetParam, Array(0.0, 0.5, 1.0))
 .build()

// In this case the estimator is simply the linear regression.
// A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
val trainValidationSplit = new TrainValidationSplit()
 .setEstimator(lr)
 .setEvaluator(new RegressionEvaluator)
 .setEstimatorParamMaps(paramGrid)
 // 80% of the data will be used for training and the remaining 20% for validation.
 .setTrainRatio(0.8)
 // Evaluate up to 2 parameter settings in parallel
 .setParallelism(2)

// Run train validation split, and choose the best set of parameters.
val model = trainValidationSplit.fit(training)

// Make predictions on test data. model is the model with combination of parameters
// that performed best.
model.transform(test)
 .select("features", "label", "prediction")
 .show()