spark pipeline 例子

"""
Pipeline Example.
"""

# $example on$
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
# $example off$
from pyspark.sql import SparkSession

if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("PipelineExample")\
        .getOrCreate()

    # $example on$
    # 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))
    # $example off$

    spark.stop()

"""
Decision Tree Classification Example.
"""
from __future__ import print_function

# $example on$
from pyspark.ml import Pipeline
from pyspark.ml.classification import DecisionTreeClassifier
from pyspark.ml.feature import StringIndexer, VectorIndexer
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
# $example off$
from pyspark.sql import SparkSession

if __name__ == "__main__":
    spark = SparkSession\
        .builder\
        .appName("DecisionTreeClassificationExample")\
        .getOrCreate()

    # $example on$
    # Load the data stored in LIBSVM format as a DataFrame.
    data = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")

    # Index labels, adding metadata to the label column.
    # Fit on whole dataset to include all labels in index.
    labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
    # Automatically identify categorical features, and index them.
    # We specify maxCategories so features with > 4 distinct values are treated as continuous.
    featureIndexer =\
        VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)

    # Split the data into training and test sets (30% held out for testing)
    (trainingData, testData) = data.randomSplit([0.7, 0.3])

    # Train a DecisionTree model.
    dt = DecisionTreeClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures")

    # Chain indexers and tree in a Pipeline
    pipeline = Pipeline(stages=[labelIndexer, featureIndexer, dt])

    # Train model.  This also runs the indexers.
    model = pipeline.fit(trainingData)

    # Make predictions.
    predictions = model.transform(testData)

    # Select example rows to display.
    predictions.select("prediction", "indexedLabel", "features").show(5)

    # Select (prediction, true label) and compute test error
    evaluator = MulticlassClassificationEvaluator(
        labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
    accuracy = evaluator.evaluate(predictions)
    print("Test Error = %g " % (1.0 - accuracy))

    treeModel = model.stages[2]
    # summary only
    print(treeModel)
    # $example off$

    spark.stop()