Spark Pyhon credit
LR-creditdata In [1]: from pyspark.mllib.regression import LabeledPoint from pyspark.mllib.classification import LogisticRegressionWithSGD In [2]: from pyspark import SparkContext sc = SparkContext ( 'local' , 'pyspark' ) In [3]: inputData = sc . textFile ( "./creditdata.csv" ) In [4]: inputData . count () Out[4]: 10000 In [5]: inputData . take ( 5 ) Out[5]: ['1,No,No,729.5264952073,44361.6250742669', '2,No,Yes,817.1804065555,12106.1347003149', '3,No,No,1073.5491640117,31767.1389473999', '4,No,No,529.2506047453,35704.4939350781', '5,No,No,785.6558829305,38463.4958787229'] In [6]: def parseData ( line ): """ Parse a line of text into an MLlib LabeledPoint object. ...