Repository: spark Updated Branches: refs/heads/master e5aaae6e1 -> 56a0aba0a
[SPARK-11952][ML] Remove duplicate ml examples Remove duplicate ml examples (only for ml). mengxr Author: Yanbo Liang <yblia...@gmail.com> Closes #9933 from yanboliang/SPARK-11685. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/56a0aba0 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/56a0aba0 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/56a0aba0 Branch: refs/heads/master Commit: 56a0aba0a60326ba026056c9a23f3f6ec7258c19 Parents: e5aaae6 Author: Yanbo Liang <yblia...@gmail.com> Authored: Tue Nov 24 09:52:53 2015 -0800 Committer: Xiangrui Meng <m...@databricks.com> Committed: Tue Nov 24 09:52:53 2015 -0800 ---------------------------------------------------------------------- .../main/python/ml/gradient_boosted_trees.py | 82 ------------------ .../src/main/python/ml/logistic_regression.py | 66 --------------- .../src/main/python/ml/random_forest_example.py | 87 -------------------- 3 files changed, 235 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/56a0aba0/examples/src/main/python/ml/gradient_boosted_trees.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/gradient_boosted_trees.py b/examples/src/main/python/ml/gradient_boosted_trees.py deleted file mode 100644 index c3bf8aa..0000000 --- a/examples/src/main/python/ml/gradient_boosted_trees.py +++ /dev/null @@ -1,82 +0,0 @@ -# -# 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. -# - -from __future__ import print_function - -import sys - -from pyspark import SparkContext -from pyspark.ml.classification import GBTClassifier -from pyspark.ml.feature import StringIndexer -from pyspark.ml.regression import GBTRegressor -from pyspark.mllib.evaluation import BinaryClassificationMetrics, RegressionMetrics -from pyspark.sql import Row, SQLContext - -""" -A simple example demonstrating a Gradient Boosted Trees Classification/Regression Pipeline. -Note: GBTClassifier only supports binary classification currently -Run with: - bin/spark-submit examples/src/main/python/ml/gradient_boosted_trees.py -""" - - -def testClassification(train, test): - # Train a GradientBoostedTrees model. - - rf = GBTClassifier(maxIter=30, maxDepth=4, labelCol="indexedLabel") - - model = rf.fit(train) - predictionAndLabels = model.transform(test).select("prediction", "indexedLabel") \ - .map(lambda x: (x.prediction, x.indexedLabel)) - - metrics = BinaryClassificationMetrics(predictionAndLabels) - print("AUC %.3f" % metrics.areaUnderROC) - - -def testRegression(train, test): - # Train a GradientBoostedTrees model. - - rf = GBTRegressor(maxIter=30, maxDepth=4, labelCol="indexedLabel") - - model = rf.fit(train) - predictionAndLabels = model.transform(test).select("prediction", "indexedLabel") \ - .map(lambda x: (x.prediction, x.indexedLabel)) - - metrics = RegressionMetrics(predictionAndLabels) - print("rmse %.3f" % metrics.rootMeanSquaredError) - print("r2 %.3f" % metrics.r2) - print("mae %.3f" % metrics.meanAbsoluteError) - - -if __name__ == "__main__": - if len(sys.argv) > 1: - print("Usage: gradient_boosted_trees", file=sys.stderr) - exit(1) - sc = SparkContext(appName="PythonGBTExample") - sqlContext = SQLContext(sc) - - # Load the data stored in LIBSVM format as a DataFrame. - df = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") - - # Map labels into an indexed column of labels in [0, numLabels) - stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel") - si_model = stringIndexer.fit(df) - td = si_model.transform(df) - [train, test] = td.randomSplit([0.7, 0.3]) - testClassification(train, test) - testRegression(train, test) - sc.stop() http://git-wip-us.apache.org/repos/asf/spark/blob/56a0aba0/examples/src/main/python/ml/logistic_regression.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/logistic_regression.py b/examples/src/main/python/ml/logistic_regression.py deleted file mode 100644 index 4cd027f..0000000 --- a/examples/src/main/python/ml/logistic_regression.py +++ /dev/null @@ -1,66 +0,0 @@ -# -# 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. -# - -from __future__ import print_function - -import sys - -from pyspark import SparkContext -from pyspark.ml.classification import LogisticRegression -from pyspark.mllib.evaluation import MulticlassMetrics -from pyspark.ml.feature import StringIndexer -from pyspark.sql import SQLContext - -""" -A simple example demonstrating a logistic regression with elastic net regularization Pipeline. -Run with: - bin/spark-submit examples/src/main/python/ml/logistic_regression.py -""" - -if __name__ == "__main__": - - if len(sys.argv) > 1: - print("Usage: logistic_regression", file=sys.stderr) - exit(-1) - - sc = SparkContext(appName="PythonLogisticRegressionExample") - sqlContext = SQLContext(sc) - - # Load the data stored in LIBSVM format as a DataFrame. - df = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") - - # Map labels into an indexed column of labels in [0, numLabels) - stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel") - si_model = stringIndexer.fit(df) - td = si_model.transform(df) - [training, test] = td.randomSplit([0.7, 0.3]) - - lr = LogisticRegression(maxIter=100, regParam=0.3).setLabelCol("indexedLabel") - lr.setElasticNetParam(0.8) - - # Fit the model - lrModel = lr.fit(training) - - predictionAndLabels = lrModel.transform(test).select("prediction", "indexedLabel") \ - .map(lambda x: (x.prediction, x.indexedLabel)) - - metrics = MulticlassMetrics(predictionAndLabels) - print("weighted f-measure %.3f" % metrics.weightedFMeasure()) - print("precision %s" % metrics.precision()) - print("recall %s" % metrics.recall()) - - sc.stop() http://git-wip-us.apache.org/repos/asf/spark/blob/56a0aba0/examples/src/main/python/ml/random_forest_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/random_forest_example.py b/examples/src/main/python/ml/random_forest_example.py deleted file mode 100644 index dc6a778..0000000 --- a/examples/src/main/python/ml/random_forest_example.py +++ /dev/null @@ -1,87 +0,0 @@ -# -# 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. -# - -from __future__ import print_function - -import sys - -from pyspark import SparkContext -from pyspark.ml.classification import RandomForestClassifier -from pyspark.ml.feature import StringIndexer -from pyspark.ml.regression import RandomForestRegressor -from pyspark.mllib.evaluation import MulticlassMetrics, RegressionMetrics -from pyspark.mllib.util import MLUtils -from pyspark.sql import Row, SQLContext - -""" -A simple example demonstrating a RandomForest Classification/Regression Pipeline. -Run with: - bin/spark-submit examples/src/main/python/ml/random_forest_example.py -""" - - -def testClassification(train, test): - # Train a RandomForest model. - # Setting featureSubsetStrategy="auto" lets the algorithm choose. - # Note: Use larger numTrees in practice. - - rf = RandomForestClassifier(labelCol="indexedLabel", numTrees=3, maxDepth=4) - - model = rf.fit(train) - predictionAndLabels = model.transform(test).select("prediction", "indexedLabel") \ - .map(lambda x: (x.prediction, x.indexedLabel)) - - metrics = MulticlassMetrics(predictionAndLabels) - print("weighted f-measure %.3f" % metrics.weightedFMeasure()) - print("precision %s" % metrics.precision()) - print("recall %s" % metrics.recall()) - - -def testRegression(train, test): - # Train a RandomForest model. - # Note: Use larger numTrees in practice. - - rf = RandomForestRegressor(labelCol="indexedLabel", numTrees=3, maxDepth=4) - - model = rf.fit(train) - predictionAndLabels = model.transform(test).select("prediction", "indexedLabel") \ - .map(lambda x: (x.prediction, x.indexedLabel)) - - metrics = RegressionMetrics(predictionAndLabels) - print("rmse %.3f" % metrics.rootMeanSquaredError) - print("r2 %.3f" % metrics.r2) - print("mae %.3f" % metrics.meanAbsoluteError) - - -if __name__ == "__main__": - if len(sys.argv) > 1: - print("Usage: random_forest_example", file=sys.stderr) - exit(1) - sc = SparkContext(appName="PythonRandomForestExample") - sqlContext = SQLContext(sc) - - # Load the data stored in LIBSVM format as a DataFrame. - df = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") - - # Map labels into an indexed column of labels in [0, numLabels) - stringIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel") - si_model = stringIndexer.fit(df) - td = si_model.transform(df) - [train, test] = td.randomSplit([0.7, 0.3]) - testClassification(train, test) - testRegression(train, test) - sc.stop() --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
