# -*-coding=utf-8 -*-  
from pyspark import SparkConf, SparkContext
sc = SparkContext(‘local‘)

from pyspark.mllib.classification import LogisticRegressionWithLBFGS, LogisticRegressionModel
from pyspark.mllib.regression import LabeledPoint

# Load and parse the data 加载和解析数据，将每一个数转化为浮点数。每一行第一个数作为标记，后面的作为特征
def parsePoint(line):
    values = [float(x) for x in line.split(‘ ‘)]
    return LabeledPoint(values[0], values[1:])

data = sc.textFile("data/mllib/sample_svm_data.txt")
print data.collect()[0] #1 0 2.52078447201548 0 0 0 2.004684436494304 2.00034729926846.....
parsedData = data.map(parsePoint)
print parsedData.collect()[0] #(1.0,[0.0,2.52078447202,0.0,0.0,0.0,2.00468....

# Build the model 建立模型
model = LogisticRegressionWithLBFGS.train(parsedData)

# Evaluating the model on training data 评估模型在训练集上的误差
labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda lp: lp[0] != lp[1]).count() / float(parsedData.count())
print("Training Error = " + str(trainErr)) #Training Error = 0.366459627329

# Save and load model 保存模型和加载模型
model.save(sc, "pythonLogisticRegressionWithLBFGSModel")
sameModel = LogisticRegressionModel.load(sc,"pythonLogisticRegressionWithLBFGSModel")

print sameModel.predict(parsedData.collect()[0].features) #1