From 3f00bb3ef1384fabf86a68180d40a1a515f6f5e3 Mon Sep 17 00:00:00 2001 From: MechCoder Date: Sun, 1 Mar 2015 16:28:15 -0800 Subject: [SPARK-6083] [MLLib] [DOC] Make Python API example consistent in NaiveBayes Author: MechCoder Closes #4834 from MechCoder/spark-6083 and squashes the following commits: 1cdd7b5 [MechCoder] Add parse function 65bbbe9 [MechCoder] [SPARK-6083] Make Python API example consistent in NaiveBayes --- docs/mllib-naive-bayes.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/mllib-naive-bayes.md b/docs/mllib-naive-bayes.md index 5224a0b49a..55b8f2ce6c 100644 --- a/docs/mllib-naive-bayes.md +++ b/docs/mllib-naive-bayes.md @@ -115,22 +115,28 @@ used for evaluation and prediction. Note that the Python API does not yet support model save/load but will in the future. - {% highlight python %} -from pyspark.mllib.regression import LabeledPoint from pyspark.mllib.classification import NaiveBayes +from pyspark.mllib.linalg import Vectors +from pyspark.mllib.regression import LabeledPoint + +def parseLine(line): + parts = line.split(',') + label = float(parts[0]) + features = Vectors.dense([float(x) for x in parts[1].split(' ')]) + return LabeledPoint(label, features) + +data = sc.textFile('data/mllib/sample_naive_bayes_data.txt').map(parseLine) -# an RDD of LabeledPoint -data = sc.parallelize([ - LabeledPoint(0.0, [0.0, 0.0]) - ... # more labeled points -]) +# Split data aproximately into training (60%) and test (40%) +training, test = data.randomSplit([0.6, 0.4], seed = 0) # Train a naive Bayes model. -model = NaiveBayes.train(data, 1.0) +model = NaiveBayes.train(training, 1.0) -# Make prediction. -prediction = model.predict([0.0, 0.0]) +# Make prediction and test accuracy. +predictionAndLabel = test.map(lambda p : (model.predict(p.features), p.label)) +accuracy = 1.0 * predictionAndLabel.filter(lambda (x, v): x == v).count() / test.count() {% endhighlight %} -- cgit v1.2.3