Created
November 28, 2015 10:05
-
-
Save mitallast/2930494e09e44865e6d5 to your computer and use it in GitHub Desktop.
Apache spark text classifier
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark.mllib.regression import LabeledPoint | |
from pyspark.mllib.classification import NaiveBayes | |
from pyspark.mllib.feature import HashingTF | |
textFile = sc.textFile("sells.csv") | |
htf = HashingTF(100000) | |
data = textFile.map(lambda line: line.split(',', 1)).map(lambda parts: LabeledPoint(parts[0], htf.transform(parts[1].split(" ")))) | |
d_train, d_test = data.randomSplit([0.6, 0.4]) | |
model = NaiveBayes.train(d_train) | |
prediction_and_labels = d_test.map(lambda point: (model.predict(point.features), point.label)) | |
correct = prediction_and_labels.filter(lambda (predicted, actual): predicted == actual) | |
accuracy = correct.count() / float(testh.count()) | |
print "Classifier correctly predicted category " + str(accuracy * 100) + " percent of the time" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment