aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python
diff options
context:
space:
mode:
authorXusen Yin <yinxusen@gmail.com>2015-11-10 10:05:53 -0800
committerXiangrui Meng <meng@databricks.com>2015-11-10 10:05:53 -0800
commita81f47ff7498e7063c855ccf75bba81ab101b43e (patch)
treeb5e07052ba1b895da31ce66553355ef171b21efc /examples/src/main/python
parent5507a9d0935aa42d65c3a4fa65da680b5af14faf (diff)
downloadspark-a81f47ff7498e7063c855ccf75bba81ab101b43e.tar.gz
spark-a81f47ff7498e7063c855ccf75bba81ab101b43e.tar.bz2
spark-a81f47ff7498e7063c855ccf75bba81ab101b43e.zip
[SPARK-11382] Replace example code in mllib-decision-tree.md using include_example
https://issues.apache.org/jira/browse/SPARK-11382 B.T.W. I fix an error in naive_bayes_example.py. Author: Xusen Yin <yinxusen@gmail.com> Closes #9596 from yinxusen/SPARK-11382.
Diffstat (limited to 'examples/src/main/python')
-rw-r--r--examples/src/main/python/mllib/decision_tree_classification_example.py55
-rw-r--r--examples/src/main/python/mllib/decision_tree_regression_example.py56
-rw-r--r--examples/src/main/python/mllib/naive_bayes_example.py1
3 files changed, 112 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/decision_tree_classification_example.py b/examples/src/main/python/mllib/decision_tree_classification_example.py
new file mode 100644
index 0000000000..1b529768b6
--- /dev/null
+++ b/examples/src/main/python/mllib/decision_tree_classification_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.
+#
+
+"""
+Decision Tree Classification Example.
+"""
+from __future__ import print_function
+
+from pyspark import SparkContext
+# $example on$
+from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
+from pyspark.mllib.util import MLUtils
+# $example off$
+
+if __name__ == "__main__":
+
+ sc = SparkContext(appName="PythonDecisionTreeClassificationExample")
+
+ # $example on$
+ # Load and parse the data file into an RDD of LabeledPoint.
+ data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
+ # 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.
+ # Empty categoricalFeaturesInfo indicates all features are continuous.
+ model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
+ impurity='gini', maxDepth=5, maxBins=32)
+
+ # Evaluate model on test instances and compute test error
+ predictions = model.predict(testData.map(lambda x: x.features))
+ labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
+ testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
+ print('Test Error = ' + str(testErr))
+ print('Learned classification tree model:')
+ print(model.toDebugString())
+
+ # Save and load model
+ model.save(sc, "target/tmp/myDecisionTreeClassificationModel")
+ sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeClassificationModel")
+ # $example off$
diff --git a/examples/src/main/python/mllib/decision_tree_regression_example.py b/examples/src/main/python/mllib/decision_tree_regression_example.py
new file mode 100644
index 0000000000..cf518eac67
--- /dev/null
+++ b/examples/src/main/python/mllib/decision_tree_regression_example.py
@@ -0,0 +1,56 @@
+#
+# 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
+
+from pyspark import SparkContext
+# $example on$
+from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
+from pyspark.mllib.util import MLUtils
+# $example off$
+
+if __name__ == "__main__":
+
+ sc = SparkContext(appName="PythonDecisionTreeRegressionExample")
+
+ # $example on$
+ # Load and parse the data file into an RDD of LabeledPoint.
+ data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
+ # 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.
+ # Empty categoricalFeaturesInfo indicates all features are continuous.
+ model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={},
+ impurity='variance', maxDepth=5, maxBins=32)
+
+ # Evaluate model on test instances and compute test error
+ predictions = model.predict(testData.map(lambda x: x.features))
+ labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
+ testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() /\
+ float(testData.count())
+ print('Test Mean Squared Error = ' + str(testMSE))
+ print('Learned regression tree model:')
+ print(model.toDebugString())
+
+ # Save and load model
+ model.save(sc, "target/tmp/myDecisionTreeRegressionModel")
+ sameModel = DecisionTreeModel.load(sc, "target/tmp/myDecisionTreeRegressionModel")
+ # $example off$
diff --git a/examples/src/main/python/mllib/naive_bayes_example.py b/examples/src/main/python/mllib/naive_bayes_example.py
index a2e7dacf25..f5e120c678 100644
--- a/examples/src/main/python/mllib/naive_bayes_example.py
+++ b/examples/src/main/python/mllib/naive_bayes_example.py
@@ -20,6 +20,7 @@ NaiveBayes Example.
"""
from __future__ import print_function
+from pyspark import SparkContext
# $example on$
from pyspark.mllib.classification import NaiveBayes, NaiveBayesModel
from pyspark.mllib.linalg import Vectors