diff options
author | Vikas Nelamangala <vikasnelamangala@Vikass-MacBook-Pro.local> | 2015-11-20 15:18:41 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-11-20 15:18:41 -0800 |
commit | ed47b1e660b830e2d4fac8d6df93f634b260393c (patch) | |
tree | 0c3805370f6a088791d7d8767d7ce3e90238b501 /examples/src/main/python/mllib | |
parent | 4b84c72dfbb9ddb415fee35f69305b5d7b280891 (diff) | |
download | spark-ed47b1e660b830e2d4fac8d6df93f634b260393c.tar.gz spark-ed47b1e660b830e2d4fac8d6df93f634b260393c.tar.bz2 spark-ed47b1e660b830e2d4fac8d6df93f634b260393c.zip |
[SPARK-11549][DOCS] Replace example code in mllib-evaluation-metrics.md using include_example
Author: Vikas Nelamangala <vikasnelamangala@Vikass-MacBook-Pro.local>
Closes #9689 from vikasnp/master.
Diffstat (limited to 'examples/src/main/python/mllib')
5 files changed, 299 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/binary_classification_metrics_example.py b/examples/src/main/python/mllib/binary_classification_metrics_example.py new file mode 100644 index 0000000000..437acb998a --- /dev/null +++ b/examples/src/main/python/mllib/binary_classification_metrics_example.py @@ -0,0 +1,55 @@ +# +# 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. +# +""" +Binary Classification Metrics Example. +""" +from __future__ import print_function +import sys +from pyspark import SparkContext, SQLContext +# $example on$ +from pyspark.mllib.classification import LogisticRegressionWithLBFGS +from pyspark.mllib.evaluation import BinaryClassificationMetrics +from pyspark.mllib.util import MLUtils +# $example off$ + +if __name__ == "__main__": + sc = SparkContext(appName="BinaryClassificationMetricsExample") + sqlContext = SQLContext(sc) + # $example on$ + # Several of the methods available in scala are currently missing from pyspark + # Load training data in LIBSVM format + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt") + + # Split data into training (60%) and test (40%) + training, test = data.randomSplit([0.6, 0.4], seed=11L) + training.cache() + + # Run training algorithm to build the model + model = LogisticRegressionWithLBFGS.train(training) + + # Compute raw scores on the test set + predictionAndLabels = test.map(lambda lp: (float(model.predict(lp.features)), lp.label)) + + # Instantiate metrics object + metrics = BinaryClassificationMetrics(predictionAndLabels) + + # Area under precision-recall curve + print("Area under PR = %s" % metrics.areaUnderPR) + + # Area under ROC curve + print("Area under ROC = %s" % metrics.areaUnderROC) + # $example off$ diff --git a/examples/src/main/python/mllib/multi_class_metrics_example.py b/examples/src/main/python/mllib/multi_class_metrics_example.py new file mode 100644 index 0000000000..cd56b3c97c --- /dev/null +++ b/examples/src/main/python/mllib/multi_class_metrics_example.py @@ -0,0 +1,69 @@ +# +# 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. +# + +# $example on$ +from pyspark.mllib.classification import LogisticRegressionWithLBFGS +from pyspark.mllib.util import MLUtils +from pyspark.mllib.evaluation import MulticlassMetrics +# $example off$ + +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="MultiClassMetricsExample") + + # Several of the methods available in scala are currently missing from pyspark + # $example on$ + # Load training data in LIBSVM format + data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_multiclass_classification_data.txt") + + # Split data into training (60%) and test (40%) + training, test = data.randomSplit([0.6, 0.4], seed=11L) + training.cache() + + # Run training algorithm to build the model + model = LogisticRegressionWithLBFGS.train(training, numClasses=3) + + # Compute raw scores on the test set + predictionAndLabels = test.map(lambda lp: (float(model.predict(lp.features)), lp.label)) + + # Instantiate metrics object + metrics = MulticlassMetrics(predictionAndLabels) + + # Overall statistics + precision = metrics.precision() + recall = metrics.recall() + f1Score = metrics.fMeasure() + print("Summary Stats") + print("Precision = %s" % precision) + print("Recall = %s" % recall) + print("F1 Score = %s" % f1Score) + + # Statistics by class + labels = data.map(lambda lp: lp.label).distinct().collect() + for label in sorted(labels): + print("Class %s precision = %s" % (label, metrics.precision(label))) + print("Class %s recall = %s" % (label, metrics.recall(label))) + print("Class %s F1 Measure = %s" % (label, metrics.fMeasure(label, beta=1.0))) + + # Weighted stats + print("Weighted recall = %s" % metrics.weightedRecall) + print("Weighted precision = %s" % metrics.weightedPrecision) + print("Weighted F(1) Score = %s" % metrics.weightedFMeasure()) + print("Weighted F(0.5) Score = %s" % metrics.weightedFMeasure(beta=0.5)) + print("Weighted false positive rate = %s" % metrics.weightedFalsePositiveRate) + # $example off$ diff --git a/examples/src/main/python/mllib/multi_label_metrics_example.py b/examples/src/main/python/mllib/multi_label_metrics_example.py new file mode 100644 index 0000000000..960ade6597 --- /dev/null +++ b/examples/src/main/python/mllib/multi_label_metrics_example.py @@ -0,0 +1,61 @@ +# +# 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. +# + +# $example on$ +from pyspark.mllib.evaluation import MultilabelMetrics +# $example off$ +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="MultiLabelMetricsExample") + # $example on$ + scoreAndLabels = sc.parallelize([ + ([0.0, 1.0], [0.0, 2.0]), + ([0.0, 2.0], [0.0, 1.0]), + ([], [0.0]), + ([2.0], [2.0]), + ([2.0, 0.0], [2.0, 0.0]), + ([0.0, 1.0, 2.0], [0.0, 1.0]), + ([1.0], [1.0, 2.0])]) + + # Instantiate metrics object + metrics = MultilabelMetrics(scoreAndLabels) + + # Summary stats + print("Recall = %s" % metrics.recall()) + print("Precision = %s" % metrics.precision()) + print("F1 measure = %s" % metrics.f1Measure()) + print("Accuracy = %s" % metrics.accuracy) + + # Individual label stats + labels = scoreAndLabels.flatMap(lambda x: x[1]).distinct().collect() + for label in labels: + print("Class %s precision = %s" % (label, metrics.precision(label))) + print("Class %s recall = %s" % (label, metrics.recall(label))) + print("Class %s F1 Measure = %s" % (label, metrics.f1Measure(label))) + + # Micro stats + print("Micro precision = %s" % metrics.microPrecision) + print("Micro recall = %s" % metrics.microRecall) + print("Micro F1 measure = %s" % metrics.microF1Measure) + + # Hamming loss + print("Hamming loss = %s" % metrics.hammingLoss) + + # Subset accuracy + print("Subset accuracy = %s" % metrics.subsetAccuracy) + # $example off$ diff --git a/examples/src/main/python/mllib/ranking_metrics_example.py b/examples/src/main/python/mllib/ranking_metrics_example.py new file mode 100644 index 0000000000..327791966c --- /dev/null +++ b/examples/src/main/python/mllib/ranking_metrics_example.py @@ -0,0 +1,55 @@ +# +# 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. +# + +# $example on$ +from pyspark.mllib.recommendation import ALS, Rating +from pyspark.mllib.evaluation import RegressionMetrics, RankingMetrics +# $example off$ +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="Ranking Metrics Example") + + # Several of the methods available in scala are currently missing from pyspark + # $example on$ + # Read in the ratings data + lines = sc.textFile("data/mllib/sample_movielens_data.txt") + + def parseLine(line): + fields = line.split("::") + return Rating(int(fields[0]), int(fields[1]), float(fields[2]) - 2.5) + ratings = lines.map(lambda r: parseLine(r)) + + # Train a model on to predict user-product ratings + model = ALS.train(ratings, 10, 10, 0.01) + + # Get predicted ratings on all existing user-product pairs + testData = ratings.map(lambda p: (p.user, p.product)) + predictions = model.predictAll(testData).map(lambda r: ((r.user, r.product), r.rating)) + + ratingsTuple = ratings.map(lambda r: ((r.user, r.product), r.rating)) + scoreAndLabels = predictions.join(ratingsTuple).map(lambda tup: tup[1]) + + # Instantiate regression metrics to compare predicted and actual ratings + metrics = RegressionMetrics(scoreAndLabels) + + # Root mean sqaured error + print("RMSE = %s" % metrics.rootMeanSquaredError) + + # R-squared + print("R-squared = %s" % metrics.r2) + # $example off$ diff --git a/examples/src/main/python/mllib/regression_metrics_example.py b/examples/src/main/python/mllib/regression_metrics_example.py new file mode 100644 index 0000000000..a3a83aafd7 --- /dev/null +++ b/examples/src/main/python/mllib/regression_metrics_example.py @@ -0,0 +1,59 @@ +# +# 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. +# +# $example on$ +from pyspark.mllib.regression import LabeledPoint, LinearRegressionWithSGD +from pyspark.mllib.evaluation import RegressionMetrics +from pyspark.mllib.linalg import DenseVector +# $example off$ + +from pyspark import SparkContext + +if __name__ == "__main__": + sc = SparkContext(appName="Regression Metrics Example") + + # $example on$ + # Load and parse the data + def parsePoint(line): + values = line.split() + return LabeledPoint(float(values[0]), + DenseVector([float(x.split(':')[1]) for x in values[1:]])) + + data = sc.textFile("data/mllib/sample_linear_regression_data.txt") + parsedData = data.map(parsePoint) + + # Build the model + model = LinearRegressionWithSGD.train(parsedData) + + # Get predictions + valuesAndPreds = parsedData.map(lambda p: (float(model.predict(p.features)), p.label)) + + # Instantiate metrics object + metrics = RegressionMetrics(valuesAndPreds) + + # Squared Error + print("MSE = %s" % metrics.meanSquaredError) + print("RMSE = %s" % metrics.rootMeanSquaredError) + + # R-squared + print("R-squared = %s" % metrics.r2) + + # Mean absolute error + print("MAE = %s" % metrics.meanAbsoluteError) + + # Explained variance + print("Explained variance = %s" % metrics.explainedVariance) + # $example off$ |