本文整理汇总了Python中pyspark.mllib.regression.LinearRegressionWithSGD.predict方法的典型用法代码示例。如果您正苦于以下问题：Python LinearRegressionWithSGD.predict方法的具体用法？Python LinearRegressionWithSGD.predict怎么用？Python LinearRegressionWithSGD.predict使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pyspark.mllib.regression.LinearRegressionWithSGD的用法示例。
在下文中一共展示了LinearRegressionWithSGD.predict方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: do_all
# 需要导入模块: from pyspark.mllib.regression import LinearRegressionWithSGD [as 别名]
# 或者: from pyspark.mllib.regression.LinearRegressionWithSGD import predict [as 别名]
def do_all(f_path,out_name):
sc = SparkContext()
data = sc.textFile(f_path)
data = data.map(parseKeepD).filter(lambda p: p[0] != None)
# Scale Features
features = data.map(lambda x: x[0].features)
summary = Statistics.colStats(features)
global means
global varis
means = summary.mean()
varis = summary.variance()
#scale the points
data = data.map(lambda y: (conv_label_pt(y[0]),y[1]))
#train model
model = LinearRegressionWithSGD().train(data.map(lambda x: x[0]), intercept=True, regType='none')
#calculate disparity
disparity = data.map(lambda p: (p[0].label, model.predict(p[0].features), p[1]))
#calculate SSR for later
ssr = disparity.map(lambda x: (x[0] - x[1])**2).sum()
#keep N
N = disparity.count()
#shut down SC
MSE = ssr/float(N)
se = std_errors(data,MSE,N)
disparity.saveAsTextFile(out_loc + out_name)
sc.stop()
return model.intercept,model.weights,se,disparity, ssr, N