diff options
Diffstat (limited to 'examples/src/main/python')
-rw-r--r-- | examples/src/main/python/ml/isotonic_regression_example.py | 54 | ||||
-rw-r--r-- | examples/src/main/python/mllib/isotonic_regression_example.py | 11 |
2 files changed, 62 insertions, 3 deletions
diff --git a/examples/src/main/python/ml/isotonic_regression_example.py b/examples/src/main/python/ml/isotonic_regression_example.py new file mode 100644 index 0000000000..1e61bd8eff --- /dev/null +++ b/examples/src/main/python/ml/isotonic_regression_example.py @@ -0,0 +1,54 @@ +# +# 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. +# + +""" +Isotonic Regression Example. +""" +from __future__ import print_function + +# $example on$ +from pyspark.ml.regression import IsotonicRegression, IsotonicRegressionModel +# $example off$ +from pyspark.sql import SparkSession + +""" +An example demonstrating isotonic regression. +Run with: + bin/spark-submit examples/src/main/python/ml/isotonic_regression_example.py +""" +if __name__ == "__main__": + + spark = SparkSession\ + .builder\ + .appName("PythonIsotonicRegressionExample")\ + .getOrCreate() + + # $example on$ + # Loads data. + dataset = spark.read.format("libsvm")\ + .load("data/mllib/sample_isotonic_regression_libsvm_data.txt") + + # Trains an isotonic regression model. + model = IsotonicRegression().fit(dataset) + print("Boundaries in increasing order: " + str(model.boundaries)) + print("Predictions associated with the boundaries: " + str(model.predictions)) + + # Makes predictions. + model.transform(dataset).show() + # $example off$ + + spark.stop() diff --git a/examples/src/main/python/mllib/isotonic_regression_example.py b/examples/src/main/python/mllib/isotonic_regression_example.py index 89dc9f4b66..33d618ab48 100644 --- a/examples/src/main/python/mllib/isotonic_regression_example.py +++ b/examples/src/main/python/mllib/isotonic_regression_example.py @@ -23,7 +23,8 @@ from __future__ import print_function from pyspark import SparkContext # $example on$ import math -from pyspark.mllib.regression import IsotonicRegression, IsotonicRegressionModel +from pyspark.mllib.regression import LabeledPoint, IsotonicRegression, IsotonicRegressionModel +from pyspark.mllib.util import MLUtils # $example off$ if __name__ == "__main__": @@ -31,10 +32,14 @@ if __name__ == "__main__": sc = SparkContext(appName="PythonIsotonicRegressionExample") # $example on$ - data = sc.textFile("data/mllib/sample_isotonic_regression_data.txt") + # Load and parse the data + def parsePoint(labeledData): + return (labeledData.label, labeledData.features[0], 1.0) + + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_isotonic_regression_libsvm_data.txt") # Create label, feature, weight tuples from input data with weight set to default value 1.0. - parsedData = data.map(lambda line: tuple([float(x) for x in line.split(',')]) + (1.0,)) + parsedData = data.map(parsePoint) # Split data into training (60%) and test (40%) sets. training, test = parsedData.randomSplit([0.6, 0.4], 11) |