decision_tree_regression_example.py

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

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

# $example on$
from pyspark.ml import Pipeline
from pyspark.ml.regression import DecisionTreeRegressor
from pyspark.ml.feature import VectorIndexer
from pyspark.ml.evaluation import RegressionEvaluator
# $example off$
from pyspark.sql import SparkSession

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

    # 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 = DecisionTreeRegressor(featuresCol="indexedFeatures")

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

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

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

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

    # Select (prediction, true label) and compute test error
    evaluator = RegressionEvaluator(
        labelCol="label", predictionCol="prediction", metricName="rmse")
    rmse = evaluator.evaluate(predictions)
    print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)

    treeModel = model.stages[1]
    # summary only
    print(treeModel)
    # $example off$

    spark.stop()