友情提示：

本文档根据林大贵的《Python+Spark 2.0 + Hadoop机器学习与大数据实战》整理得到，代码均为书中提供的源码（python 2.X版本）。
本文的可以利用pandoc转换为docx文档，点击这里安装下载pandoc后，在终端输入以下命令：

pandoc youfilename.md -f markdown -t docx -s -o outputfilename.docx

Mllib

决策树二元分类

环境准备

这个阶段包括数据的下载和整理，去除缺失的数据，不符合规范的数据（比如乱码等），数据类型转换，将字符串类型映射为数字类型（建立字典），数据类型转患（将字符串类型的数字转换为浮点型的数字）。

导入这个模型我们需要的包

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
from pyspark.mllib.tree import DecisionTree
from pyspark.mllib.regression import LabeledPoint
import numpy as np
from pyspark.mllib.evaluation import BinaryClassificationMetrics

创建SparkContext，并设置日志级别

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)    
    
#如果要在cluster模式运行(hadoop yarn 或Spark Stand alone)，请按照书上的说明，先把文件上传到HDFS目录
def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/mnt/hdfs/Hadoop/"
    else:   
        Path="hdfs://master:9000/user/hduser/"

def CreateSparkContext():
    sparkConf = SparkConf().\
    					setAppName("RunDecisionTreeBinary").\
    					set("spark.ui.showConsoleProgress", "false")                           
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

def convert_float(x):
    return (0 if x=="?" else float(x))

def extract_label(record):
    label=(record[-1])
    return float(label)

def extract_features(field,categoriesMap,featureEnd):
    categoryIdx = categoriesMap[field[3]]
    categoryFeatures = np.zeros(len(categoriesMap))
    categoryFeatures[categoryIdx] = 1
    numericalFeatures=[convert_float(field)  for  field in field[4: featureEnd]]    
    return  np.concatenate(( categoryFeatures, numericalFeatures))

def extract_label(record):
    label=(record[-1])
    return float(label)

def extract_features(field,categoriesMap,featureEnd):
    categoryIdx = categoriesMap[field[3]]
    categoryFeatures = np.zeros(len(categoriesMap))
    categoryFeatures[categoryIdx] = 1
    numericalFeatures=[convert_float(field)  for  field in field[4: featureEnd]]    
    return  np.concatenate(( categoryFeatures, numericalFeatures))

def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"Data/train.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    categoriesMap = lines.map(lambda fields: fields[3]). \
                                        distinct().zipWithIndex().collectAsMap()
    # 提取特征字段和标签
    labelpointRDD = lines.map( lambda r:LabeledPoint(    \
                                  extract_label(r),      \
                                  extract_features(r,categoriesMap,len(r) - 1)))
    #print "labelpointRDD=",labelpointRDD.first(),"\n"
    
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count()) + 
              "   validationData:" + str(validationData.count()) +
              "   testData:" + str(testData.count()))
    return (trainData, validationData, testData, categoriesMap) #返回数据

模型训练

建立trainData，使用trainData执行DecisionTree训练并建立模型

from pyspark.mllib.tree import DecisionTree
model = DecisionTree.trainClassifier(trainData,numClasses=2,categoricalFeaturesInfo={},\
                                    impurity='entropy',maxDepth=5,maxBins=5)

使用 DecisionTree.trainClassifier(trainData,validationData,impurityParm, maxDepthParm, maxBinsParm)模型训练

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData.map(lambda p: p.label))
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return( AUC)

def trainEvaluateModel(trainData,validationData,
                                        impurityParm, maxDepthParm, maxBinsParm):
    startTime = time()
    model = DecisionTree.trainClassifier(trainData,
                numClasses=2, categoricalFeaturesInfo={},  #这里是二元分类所以numClasses设置为2
                impurity=impurityParm,
                maxDepth=maxDepthParm, 
                maxBins=maxBinsParm)
    
    AUC = evaluateModel(model, validationData)
    duration = time() - startTime
    print("训练评估：使用参数" + \
                " impurity="+str(impurityParm) +\
                " maxDepth="+str(maxDepthParm) + \
                " maxBins="+str(maxBinsParm) +\
                 " 所需时间="+str(duration) + \
                 " 结果AUC = " + str(AUC) )
    return (AUC,duration, impurityParm, maxDepthParm, maxBinsParm,model)

模型预测

PredictData(sc,model,categoriesMap)

def PredictData(sc,model,categoriesMap): 
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"Data/test.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    dataRDD = lines.map(lambda r:  ( r[0]  ,
                            extract_features(r,categoriesMap,len(r) )))
    DescDict = {
           0: "暂时性网页(ephemeral)",
           1: "长青网页(evergreen)"
     }
    for data in dataRDD.take(10):
        predictResult = model.predict(data[1])
        print( " 网址：  " +str(data[0])+"\n" +\
                  "             ==>预测:"+ str(predictResult)+ \
                  " 说明:"+DescDict[predictResult] +"\n")

模型评估

创建scoreAndLabels

score = model.predict(validationData.map(lambda p:p.features))
scoreAndLabels = score.zip(validationData.map(lambda p:p.label))
scoreAndLabels.take(5)

编写BinaryClassifierMetrix计算AUC

from pyspark.mllib.evaluation import BinaryClassificationMetrics
metrics = BinaryClassificationMetrics(scoreAndLabels)
print('AUC= ' + str(metrics.areaUnderROC))

使用BinaryClassificationMetrics(scoreAndLables).areaUnderROC进行评估分析，计算AUC。

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData.map(lambda p: p.label))
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return AUC

参数评估

评估impurity参数，决策树分裂结点的方法

impurityList = ['gini','entropy']
maxDepthList=[10]
maxBinList=[10]

metrics = [trainEvaluateModel(trainData,validationData,impurity,maxDepth,maxBins)    \  
           					    for impurity in impurityList \
          				        for maxDepth in maxDepthList \
          					    for maxBins in maxBinList]

编写 evalParameter 评估单个参数

def evalParameter(trainData, validationData, evalparm,
                  impurityList, maxDepthList, maxBinsList):
    
    metrics = [trainEvaluateModel(trainData, validationData,  
                                impurity,maxDepth,  maxBins  ) 
                       for impurity in impurityList
                       for maxDepth in maxDepthList  
                       for maxBins in maxBinsList ]
    
    if evalparm=="impurity":
        IndexList=impurityList[:]
    elif evalparm=="maxDepth":
        IndexList=maxDepthList[:]
    elif evalparm=="maxBins":
        IndexList=maxBinsList[:]
    
    df = pd.DataFrame(metrics,index=IndexList,
            columns=['AUC', 'duration','impurity', 'maxDepth', 'maxBins','model'])
    showchart(df,evalparm,'AUC','duration',0.5,0.7 )
    
evalParameter(trainData,validationData,'maxDepth',impurityList=['gini'],maxDepthList=[3,5,10,15,25,],maxBinList=[10])

可视化，编写showchart() 函数

def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', title =evalparm,figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[[lineData ]].values, linestyle='-', marker='o', linewidth=2.0,color='r')
    plt.show()

找出准确率最高的参数组合，编写evalAllParameter() 函数，包括impurity， maxDepth，maxBins

def evalAllParameter(trainData, validationData, 
                     impurityList, maxDepthList, maxBinsList):    
    metrics = [trainEvaluateModel(trainData, validationData,  
                            impurity,maxDepth,  maxBins  ) 
                      for impurity in impurityList 
                      for maxDepth in maxDepthList  
                      for  maxBins in maxBinsList ]
    
    Smetrics = sorted(metrics, key=lambda k: k[0], reverse=True)
    bestParameter=Smetrics[0]
    
    print("调校后最佳参数：impurity:" + str(bestParameter[2]) + 
                                      "  ,maxDepth:" + str(bestParameter[3]) + 
                                     "  ,maxBins:" + str(bestParameter[4])   + 
                                      "  ,结果AUC = " + str(bestParameter[0]))
    
    return bestParameter[5]  # 这里的bestParameter[5]指的是返回的带有最佳参数的最佳模型

检验AUC

检测模型是否过度训练，看一下testData的AUC是否过低。

AUC = evaluateModel(model,testData)
print("AUC = " + str(AUC))

驱动函数

if __name__ == "__main__":
    print("RunDecisionTreeBinary")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData, categoriesMap) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    (AUC,duration, impurityParm, maxDepthParm, maxBinsParm,model)= \
        trainEvaluateModel(trainData, validationData, "entropy", 10, 200)
        
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData,
                          ["gini", "entropy"],
                          [3, 5, 10, 15, 20, 25], 
                          [3, 5, 10, 50, 100, 200 ])
    print("==========测试阶段===============")
    auc = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 AUC:" + str(auc))
    print("==========预测数据===============")
    PredictData(sc, model, categoriesMap)
    print(model.toDebugString())

逻辑回归二元分类

环境准备

导入这个模型需要的包

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
from pyspark.mllib.classification import LogisticRegressionWithSGD
from pyspark.mllib.regression import LabeledPoint
import numpy as np
from pyspark.mllib.evaluation import BinaryClassificationMetrics
from pyspark.mllib.feature import StandardScaler

前期准备

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)    

def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/home/hduser/pythonsparkexample/PythonProject/"
    else:   
        Path="hdfs://master:9000/user/hduser/"
        
def CreateSparkContext():
    sparkConf = SparkConf()                                                       \
                         .setAppName("LogisticRegressionWithSGD")                         \
                         .set("spark.ui.showConsoleProgress", "false") 
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

标准化将数值特征字段具有共同的标准

def extract_label(record):
    label=(record[-1])
    return float(label)

def extract_features(field,categoriesMap,featureEnd):
    categoryIdx = categoriesMap[field[3]]
    categoryFeatures = np.zeros(len(categoriesMap))
    categoryFeatures[categoryIdx] = 1
    numericalFeatures=[convert_float(field)  for  field in field[4: featureEnd]]    
    return  np.concatenate(( categoryFeatures, numericalFeatures))

def convert_float(x):
    return (0 if x=="?" else float(x))

def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/train.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    print "标准化之前：",
    categoriesMap = lines.map(lambda fields: fields[3]). \
                                        distinct().zipWithIndex().collectAsMap()
    labelRDD = lines.map(lambda r:  extract_label(r))
    featureRDD = lines.map(lambda r:  extract_features(r,categoriesMap,len(r) - 1))
    for i in featureRDD.first():
        print (str(i)+","),
    print ("")       
    print ("标准化之后：")
    #这里的withMean参数为True，在朴素贝叶斯的模型立这个参数应当设置为False
    stdScaler = StandardScaler(withMean=True, withStd=True).fit(featureRDD)
    ScalerFeatureRDD=stdScaler.transform(featureRDD)
    for i in ScalerFeatureRDD.first():
        print (str(i)+","),
    labelpoint=labelRDD.zip(ScalerFeatureRDD)
    labelpointRDD=labelpoint.map(lambda r: LabeledPoint(r[0], r[1]))
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count()) + 
              "   validationData:" + str(validationData.count()) +
              "   testData:" + str(testData.count()))
    return (trainData, validationData, testData, categoriesMap) #返回数据

模型训练

使用LogisticRegressionWithSGD.train(trainData, numIterations, stepSize, miniBatchFraction)进行模型训练

numIterations：使用SGD迭代的次数

stepSize：每次执行SGD迭代步长大小，默认为1

minBatchFraction：每次迭代参与计算的样本比例，数值在0 - 1之间，默认为1

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData \
                                   .map(lambda p: p.label))  \
                                   .map(lambda (x,y): (float(x),float(y)) )
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return( AUC)

def trainEvaluateModel(trainData,validationData,
                                        numIterations, stepSize, miniBatchFraction):
    startTime = time()
    model = LogisticRegressionWithSGD.train(trainData, 
                                        numIterations, stepSize, miniBatchFraction)
    AUC = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " numIterations="+str(numIterations) +\
                " stepSize="+str(stepSize) + \
                " miniBatchFraction="+str(miniBatchFraction) +\
                 " 所需时间="+str(duration) + \
                 " 结果AUC = " + str(AUC) 
    return (AUC,duration, numIterations, stepSize, miniBatchFraction,model)

模型预测

使用test.tsv进行预测

def PredictData(sc,model,categoriesMap): 
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/test.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    dataRDD = lines.map(lambda r:  ( r[0]  ,
                            extract_features(r,categoriesMap,len(r) )))
    DescDict = {
           0: "暂时性网页(ephemeral)",
           1: "长青网页(evergreen)"
     }
    for data in dataRDD.take(10):
        predictResult = model.predict(data[1])
        print " 网址：  " +str(data[0])+"\n" +\
                  "             ==>预测:"+ str(predictResult)+ \
                  " 说明:"+DescDict[predictResult] +"\n"

模型评估

使用BinaryClassificationMetrics(scoreAndLables)进行评估分析，计算AUC，标准化后的模型都需要浮点类型的转换。

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData.map(lambda p: p.label)).map(lambda (x,y):(float(x),float(y)) )
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return( AUC)

参数评估

可视化函数

def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', title =evalparm,figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[[lineData ]].values, linestyle='-', marker='o', linewidth=2.0,color='r')
    plt.show()

单个参数评估

def evalParameter(trainData, validationData, evalparm,
                  numIterationsList, stepSizeList, miniBatchFractionList):
    
    metrics = [trainEvaluateModel(trainData, validationData,  
                                numIterations,stepSize,  miniBatchFraction  ) 
                       for numIterations in numIterationsList
                       for stepSize in stepSizeList  
                       for miniBatchFraction in miniBatchFractionList ]
    
    if evalparm=="numIterations":
        IndexList=numIterationsList[:]
    elif evalparm=="stepSize":
        IndexList=stepSizeList[:]
    elif evalparm=="miniBatchFraction":
        IndexList=miniBatchFractionList[:]
    
    df = pd.DataFrame(metrics,index=IndexList,
            columns=['AUC', 'duration','numIterations', 'stepSize','miniBatchFraction','model'])
    
    showchart(df,evalparm,'AUC','duration',0.5,0.7 )

多个参数评估

def  parametersEval(trainData, validationData):
    print("----- 评估numIterations参数使用 ---------")
    evalParameter(trainData, validationData,"numIterations", 
                              numIterationsList=[5, 15, 20, 60, 100],   
                              stepSizeList=[10],  
                              miniBatchFractionList=[1 ])  
    print("----- 评估stepSize参数使用 ---------")
    evalParameter(trainData, validationData,"stepSize", 
                              numIterationsList=[100],                    
                              stepSizeList=[10, 50, 100, 200],    
                              miniBatchFractionList=[1])   
    print("----- 评估miniBatchFraction参数使用 ---------")
    evalParameter(trainData, validationData,"miniBatchFraction", 
                              numIterationsList=[100],      
                              stepSizeList =[100],        
                              miniBatchFractionList=[0.5, 0.8, 1 ])

多个参数同时评估，包括numIterations、stepSize 、minBatchFraction

numIterations：使用SGD迭代的次数

stepSize：每次执行SGD迭代步长大小，默认为1

minBatchFraction：每次迭代参与计算的样本比例，数值在0 - 1之间，默认为1

def evalAllParameter(trainData, validationData, 
                     numIterationsList, stepSizeList, miniBatchFractionList):    
    metrics = [trainEvaluateModel(trainData, validationData,  
                            numIterations,stepSize,  miniBatchFraction  ) 
                      for numIterations in numIterationsList 
                      for stepSize in stepSizeList  
                      for  miniBatchFraction in miniBatchFractionList ]
    
    Smetrics = sorted(metrics, key=lambda k: k[0], reverse=True)
    bestParameter=Smetrics[0]
    
    print("调校后最佳参数：numIterations:" + str(bestParameter[2]) + 
                                      "  ,stepSize:" + str(bestParameter[3]) + 
                                     "  ,miniBatchFraction:" + str(bestParameter[4])   + 
                                      "  ,结果AUC = " + str(bestParameter[0]))
    
    return bestParameter[5] # 这里的bestParameter[5]指的是返回的带有最佳参数的最佳模型

检验AUC

AUC = evaluateModel(model,testData)
print("AUC = " + str(AUC))

驱动函数

if __name__ == "__main__":
    print("RunLogisticRegressionWithSGDBinary")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData, categoriesMap) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    (AUC,duration, numIterationsParm, stepSizeParm, miniBatchFractionParm,model)= \
          trainEvaluateModel(trainData, validationData, 15, 10, 0.5)
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData,
                         [3, 5, 10,15], 
                         [10, 50, 100],
                          [0.5, 0.8, 1 ])
    print("==========测试阶段===============")
    auc = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 AUC:" + str(auc))
    print("==========预测数据===============")
    PredictData(sc, model, categoriesMap)

支持向量机SVM二元分类

环境准备

导入SVMWithSGD 和StandardScale模块

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
from pyspark.mllib.classification import SVMWithSGD
from pyspark.mllib.regression import LabeledPoint
import numpy as np
from pyspark.mllib.evaluation import BinaryClassificationMetrics
from pyspark.mllib.feature import StandardScale

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)    

def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/home/hduser/pythonsparkexample/PythonProject/"
    else:   
        Path="hdfs://master:9000/user/hduser/"
def CreateSparkContext():
    sparkConf = SparkConf()                                                       \
                         .setAppName("LogisticRegressionWithSGD")                         \
                         .set("spark.ui.showConsoleProgress", "false") 
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

def extract_label(record):
    label=(record[-1])
    return float(label)

def extract_features(field,categoriesMap,featureEnd):
    categoryIdx = categoriesMap[field[3]]
    categoryFeatures = np.zeros(len(categoriesMap))
    categoryFeatures[categoryIdx] = 1
    numericalFeatures=[convert_float(field)  for  field in field[4: featureEnd]]    
    return  np.concatenate(( categoryFeatures, numericalFeatures))

def convert_float(x):
    return (0 if x=="?" else float(x))

def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/train.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    print "标准化之前：",
    categoriesMap = lines.map(lambda fields: fields[3]). \
                                        distinct().zipWithIndex().collectAsMap()
    labelRDD = lines.map(lambda r:  extract_label(r))
    featureRDD = lines.map(lambda r:  extract_features(r,categoriesMap,len(r) - 1))

    for i in featureRDD.first():
        print (str(i)+","),
    print ""       
    
    stdScaler = StandardScaler(withMean=True, withStd=True).fit(featureRDD)
    ScalerFeatureRDD=stdScaler.transform(featureRDD)
    print "标准化之后：",
    for i in ScalerFeatureRDD.first():
        print (str(i)+","),        
    labelpoint=labelRDD.zip(ScalerFeatureRDD)
    labelpointRDD=labelpoint.map(lambda r: LabeledPoint(r[0], r[1]))

    
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count()) + 
              "   validationData:" + str(validationData.count()) +
              "   testData:" + str(testData.count()))
    return (trainData, validationData, testData, categoriesMap) #返回数据

模型训练

使用SVMWithSGD.train(trainData, numIterations, stepSize, regParam)进行模型训练

trainData：输入的训练数据LabeledPointRDD

numIterations：使用SGD迭代的次数，默认为100

stepSize：每次执行SGD迭代步长的大小，默认为1

regParam：正则化参数，数值为 0-1 之间

def trainEvaluateModel(trainData,validationData,
                                        numIterations, stepSize, regParam):
    startTime = time()
    model = SVMWithSGD.train(trainData, numIterations, stepSize, regParam)
    AUC = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " numIterations="+str(numIterations) +\
                " stepSize="+str(stepSize) + \
                " regParam="+str(regParam) +\
                 " 所需时间="+str(duration) + \
                 " 结果AUC = " + str(AUC) 
    return (AUC,duration, numIterations, stepSize, regParam,model)

模型预测

利用 model.predict() 进行预测

def PredictData(sc,model,categoriesMap): 
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/test.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    dataRDD = lines.map(lambda r:  ( r[0]  ,
                            extract_features(r,categoriesMap,len(r) )))
    DescDict = {
           0: "暂时性网页(ephemeral)",
           1: "长青网页(evergreen)"
     }
    for data in dataRDD.take(10):
        predictResult = model.predict(data[1])
        print " 网址：  " +str(data[0])+"\n" +\
                  "             ==>预测:"+ str(predictResult)+ \
                  " 说明:"+DescDict[predictResult] +"\n"

模型评估

利用BinaryClassificationMetrics(scoreAndLabels)计算AUC评估结果，标准化后的模型都需要浮点类型的转换。

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    # 这里的validationData实际上是一个元祖（label,features）,而最后的map(lambda (x,y): (float(x),float(y))就是将rdd中的预测结果和实际结果进行类型转换
    scoreAndLabels=score.zip(validationData \
                                   .map(lambda p: p.label))  \
                                   .map(lambda (x,y): (float(x),float(y)))
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return AUC

参数评估

利用parametersEval()进行单个参数评估

trainData：输入的训练数据LabeledPointRDD

numIterations：使用SGD迭代的次数，默认为100

stepSize：每次执行SGD迭代步长的大小，默认为1

regParam：正则化参数，数值为 0-1 之间

def  parametersEval(trainData, validationData):
    print("----- 评估numIterations参数使用 ---------")
    evalParameter(trainData, validationData,"numIterations", 
                              numIterationsList= [1, 3, 5, 15, 25],   
                              stepSizeList=[100],  
                              regParamList=[1 ])  
    print("----- 评估stepSize参数使用 ---------")
    evalParameter(trainData, validationData,"stepSize", 
                              numIterationsList=[25],                    
                              stepSizeList= [10, 50, 100, 200],    
                              regParamList=[1])   
    print("----- 评估regParam参数使用 ---------")
    evalParameter(trainData, validationData,"regParam", 
                              numIterationsList=[25],      
                              stepSizeList =[100],        
                              regParamList=[0.01, 0.1, 1 ])

利用trainEvaluateModel多个参数评估

def trainEvaluateModel(trainData,validationData,
                                        numIterations, stepSize, regParam):
    startTime = time()
    model = SVMWithSGD.train(trainData, numIterations, stepSize, regParam)
    AUC = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " numIterations="+str(numIterations) +\
                " stepSize="+str(stepSize) + \
                " regParam="+str(regParam) +\
                 " 所需时间="+str(duration) + \
                 " 结果AUC = " + str(AUC) 
    return (AUC,duration, numIterations, stepSize, regParam,model)

多个参数同时评估

def evalAllParameter(trainData, validationData, 
                     numIterationsList, stepSizeList, regParamList):    
    metrics = [trainEvaluateModel(trainData, validationData,  
                            numIterations,stepSize,  regParam  ) 
                      for numIterations in numIterationsList 
                      for stepSize in stepSizeList  
                      for  regParam in regParamList ]
    
    Smetrics = sorted(metrics, key=lambda k: k[0], reverse=True)
    bestParameter=Smetrics[0]
    
    print("调校后最佳参数：numIterations:" + str(bestParameter[2]) + 
                                      "  ,stepSize:" + str(bestParameter[3]) + 
                                     "  ,regParam:" + str(bestParameter[4])   + 
                                      "  ,结果AUC = " + str(bestParameter[0]))
    
    return bestParameter[5]

检验AUC

AUC = evaluateModel(model, testData)
print(AUC)

驱动函数

注意修改参数为SVMWithSGD训练评估所需要的参数

if __name__ == "__main__":
    print("RunSVMWithSGDBinary")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData, categoriesMap) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    (AUC,duration, numIterations, stepSize, regParam,model)= \
          trainEvaluateModel(trainData, validationData, 3, 50, 1)
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData,
                        [1, 3, 5, 15, 25], 
                        [10, 50, 100, 200],
                        [0.01, 0.1, 1 ])
    print("==========测试阶段===============")
    auc = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 AUC:" + str(auc))
    print("==========预测数据===============")
    PredictData(sc, model, categoriesMap)

朴素贝叶斯二元分类

环境准备

导入我们需要包

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
# 导入NavieBayes模块
from pyspark.mllib.classification import NaiveBayes
from pyspark.mllib.regression import LabeledPoint
import numpy as np
from pyspark.mllib.evaluation import BinaryClassificationMetrics
from pyspark.mllib.feature import StandardScaler

设置SparkContext 环境

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)    

def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/home/hduser/pythonsparkexample/PythonProject/"
    else:   
        Path="hdfs://master:9000/user/hduser/"
def CreateSparkContext():
    sparkConf = SparkConf()                                                       \
                         .setAppName("LogisticRegressionWithSGD")                         \
                         .set("spark.ui.showConsoleProgress", "false") 
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

修改PrepareData()加入数据标准化，将withmean参数设置为False，在提取特征值时必须保证特征值大于0

def extract_label(record):
    label=(record[-1])
    return float(label)

def extract_features(field,categoriesMap,featureEnd):
    categoryIdx = categoriesMap[field[3]]
    categoryFeatures = np.zeros(len(categoriesMap))
    categoryFeatures[categoryIdx] = 1
    numericalFeatures=[convert_float(field)  for  field in field[4: featureEnd]]    
    return  np.concatenate(( categoryFeatures, numericalFeatures))

def convert_float(x):
    ret=(0 if x=="?" else float(x))
    return(0 if ret<0 else ret)  #NaiveBayes 特征字段一定大于0，所以负数也转换为0


def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/train.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    print ("标准化之前："),        
    categoriesMap = lines.map(lambda fields: fields[3]). \
                                        distinct().zipWithIndex().collectAsMap()
    labelRDD = lines.map(lambda r:  extract_label(r))
    featureRDD = lines.map(lambda r:  extract_features(r,categoriesMap,len(r) - 1))
    for i in featureRDD.first():
        print (str(i)+","),
    print ("")       
    
    print ("标准化之后："),
    # 这里有个withmean参数设置为False
    stdScaler = StandardScaler(withMean=False, withStd=True).fit(featureRDD)
    ScalerFeatureRDD=stdScaler.transform(featureRDD)
    for i in ScalerFeatureRDD.first():
        print (str(i)+","),        
                
    labelpoint=labelRDD.zip(ScalerFeatureRDD)
    labelpointRDD=labelpoint.map(lambda r: LabeledPoint(r[0], r[1]))
    
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count()) + 
              "   validationData:" + str(validationData.count()) +
              "   testData:" + str(testData.count()))
    return (trainData, validationData, testData, categoriesMap) #返回数据

模型训练

利用NaiveBayes.train(trainData, lambdaParam)训练模型
参数说明 NaiveBayes.train(input,lambda)
- input：输入的训练数据 LabelPointRDD
- lambda：设置lambda 参数，默认值为1.0

def trainEvaluateModel(trainData,validationData,lambdaParam):
    startTime = time()
    model = NaiveBayes.train(trainData,lambdaParam)
    AUC = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " lambda="+str( lambdaParam) +\
                 " 所需时间="+str(duration) + \
                 " 结果AUC = " + str(AUC) 
    return (AUC,duration,  lambdaParam,model)

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData \
                                   .map(lambda p: p.label))  \
                                   .map(lambda (x,y): (float(x),float(y)) )
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return( AUC)

模型评估

利用 BinaryClassificationMetrics(scoreAndLabels)评估

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData \
                                   .map(lambda p: p.label))  \
                                   .map(lambda (x,y): (float(x),float(y)) )
    metrics = BinaryClassificationMetrics(scoreAndLabels)
    AUC=metrics.areaUnderROC
    return( AUC)

参数评估

单个参数评估

def  parametersEval(trainData, validationData):
    print("----- 评估lambda参数使用 ---------")
    evalParameter(trainData, validationData,"lambdaParam", 
            lambdaParamList=[1.0, 3.0, 5.0, 15.0, 25.0,30.0,35.0,40.0,45.0,50.0,60.0])

参数评估

def evalParameter(trainData, validationData, evalparm,
                  lambdaParamList):
    
    metrics = [trainEvaluateModel(trainData, validationData,regParam ) 
                                  for regParam in  lambdaParamList]
    
    evalparm="lambdaParam"
    IndexList=lambdaParamList
    
    df = pd.DataFrame(metrics,index=IndexList,
            columns=['AUC', 'duration',' lambdaParam','model'])
    showchart(df,evalparm,'AUC','duration',0.5,0.7 )

可视化函数

def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', title =evalparm,figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[[lineData ]].values, linestyle='-', marker='o', linewidth=2.0,color='r')
    plt.show()

多个参数同时评估

def evalAllParameter(training_RDD, validation_RDD, lambdaParamList):    
    metrics = [trainEvaluateModel(trainData, validationData,  lambdaParam  ) 
                        for lambdaParam in lambdaParamList  ]
    Smetrics = sorted(metrics, key=lambda k: k[0], reverse=True)
    bestParameter=Smetrics[0]
    
    print("调校后最佳参数：lambdaParam:" + str(bestParameter[2]) +  
             "  ,结果AUC = " + str(bestParameter[0]))
    return bestParameter[3]

检验AUC

利用模型评估AUC大小

AUC = evaluateModel(model, testData)
print(AUC)

模型预测

def PredictData(sc,model,categoriesMap): 
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/test.tsv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    rData=rawData.map(lambda x: x.replace("\"", ""))    
    lines = rData.map(lambda x: x.split("\t"))
    print("共计：" + str(lines.count()) + "项")
    dataRDD = lines.map(lambda r:  ( r[0]  ,
                            extract_features(r,categoriesMap,len(r) )))
    DescDict = {
           0: "暂时性网页(ephemeral)",
           1: "长青网页(evergreen)"
     }
    for data in dataRDD.take(10):
        predictResult = model.predict(data[1])
        print " 网址：  " +str(data[0])+"\n" +\
                  "             ==>预测:"+ str(predictResult)+ \
                  " 说明:"+DescDict[predictResult] +"\n"

驱动函数

if __name__ == "__main__":
    print("RunNaiveBayesBinary")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData, categoriesMap) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    
    (AUC,duration,  lambdaParam,model)= \
            trainEvaluateModel(trainData, validationData, 60.0)
          
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData, 
                           [1.0, 3.0, 5.0, 15.0, 25.0,30.0,35.0,40.0,45.0,50.0,60.0])

              
    print("==========测试阶段===============")
    auc = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 AUC:" + str(auc))
    print("==========预测数据===============")
    PredictData(sc, model, categoriesMap)

决策树多元分类

环境准备

导入需要的包

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
from pyspark.mllib.tree import DecisionTree
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.evaluation import MulticlassMetrics

设置SParkContext环境

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)    

def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/home/hduser/pythonsparkexample/PythonProject/"
    else:   
        Path="hdfs://master:9000/user/hduser/"
def CreateSparkContext():
    sparkConf = SparkConf()                                                       \
                         .setAppName("LogisticRegressionWithSGD")                         \
                         .set("spark.ui.showConsoleProgress", "false") 
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

执行 DecisionTree.trainClassifier 训练，规定label一定时从0开始的，所以在提取label时减去了1

def extract_label(record):
    label=(record[-1])
    return float(label)-1

def convert_float(x):
    return (0 if x=="?" else float(x))

def extract_features(record,featureEnd):
    # 这里的featureEnd就是 len(r) - 1
    numericalFeatures=[convert_float(field)  for  field in record[0: featureEnd]]
    return  numericalFeatures

def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawData = sc.textFile(Path+"data/covtype.data")
    print("共计：" + str(rawData.count()) + "项")
    lines = rawData.map(lambda x: x.split(","))
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    labelpointRDD = lines.map(lambda r: LabeledPoint(
                                                     extract_label(r), 
                                                     extract_features(r,len(r) - 1)))
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count())+\
             "   validationData:" + str(validationData.count()) +\
             "   testData:" + str(testData.count()))
    print labelpointRDD.first()
    return (trainData, validationData, testData)

模型训练

利用DecisionTree.trainClassifier(trainData,numClasses=7,categoricalFeatruesInfo={},impurity,maxDepth,maxBins)，因为这里的分类数目为7，所以我们将numClasses设置为7。

def trainEvaluateModel(trainData,validationData,impurityParm, maxDepthParm, maxBinsParm):
    startTime = time()
    model = DecisionTree.trainClassifier(trainData,\
                                    numClasses=7, categoricalFeaturesInfo={}, \
                                    impurity=impurityParm, 
                                    maxDepth=maxDepthParm, 
                                    maxBins=maxBinsParm)
    accuracy = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " impurityParm= %s"%impurityParm+ \
                " maxDepthParm= %s"%maxDepthParm+ \
                " maxBinsParm = %d."%maxBinsParm + \
                 " 所需时间=%d"%duration + \
                 " 结果accuracy = %f " % accuracy 
    return (accuracy,duration, impurityParm, maxDepthParm, maxBinsParm,model)

模型评估

利用MulticlassMetrics(scoreAndLabels).accuracy计算准确率

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData.map(lambda p: p.label))
    metrics = MulticlassMetrics(scoreAndLabels)
    accuracy = metrics.accuracy
    return( accuracy)

参数评估

评估单个参数

def evalParameter(trainData, validationData, evaparm,impurityList, maxDepthList, maxBinsList):
    metrics = [trainEvaluateModel(trainData, validationData,  impurity,numIter,  maxBins  ) 
               for impurity in impurityList for numIter in maxDepthList  for maxBins in maxBinsList ]
    if evaparm=="impurity":
        IndexList=impurityList[:]
    elif evaparm=="maxDepth":
        IndexList=maxDepthList[:]
    elif evaparm=="maxBins":
        IndexList=maxBinsList[:]
    df = pd.DataFrame(metrics,index=IndexList,
               columns=['accuracy', 'duration','impurity', 'maxDepth', 'maxBins','model'])
    
    showchart(df,evaparm,'accuracy','duration',0.6,1.0 )

评估多个参数

def  parametersEval(training_RDD, validation_RDD):
    print("----- 评估impurity参数使用 ---------")
    evalParameter(trainData, validationData,"impurity", 
                              impurityList=["gini", "entropy"],   
                              maxDepthList=[10],  
                              maxBinsList=[10 ])  

    print("----- 评估maxDepth参数使用 ---------")
    evalParameter(trainData, validationData,"maxDepth", 
                              impurityList=["gini"],                    
                              maxDepthList=[3, 5, 10, 15, 20, 25],    
                              maxBinsList=[10])   

    print("----- 评估maxBins参数使用 ---------")
    evalParameter(trainData, validationData,"maxBins", 
                              impurityList=["gini"],      
                              maxDepthList =[10],        
                              maxBinsList=[3, 5, 10, 50, 100, 200 ])

利用pandas自带的绘图工具绘图

def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', titl =evalparm,figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[[lineData ]].values, linestyle='-', marker='o', linewidth=2.0,color='r')
    plt.show()

同时评估多个参数

def evalAllParameter(training_RDD, validation_RDD, impurityList, maxDepthList, maxBinsList):    
    metrics = [trainEvaluateModel(trainData, validationData,  impurity,numIter,  maxBins  ) 
                        for impurity in impurityList for numIter in maxDepthList  for maxBins in maxBinsList ]
    Smetrics = sorted(metrics, key=lambda k: k[0], reverse=True)
    bestParameter=Smetrics[0]
    print("调校后最佳参数：impurity:" + str(bestParameter[2]) + 
             "  ,maxDepth:" + str(bestParameter[3]) + 
            "  ,maxBins:" + str(bestParameter[4])   + 
            "  ,结果accuracy = " + str(bestParameter[0]))
    return bestParameter[5]

检验AUC

auc = evaluateModel(model, testData)
return AUC

模型预测

def PredictData(sc,model): 
    #----------------------1.导入并转换数据-------------
    rawData = sc.textFile(Path+"data/covtype.data")
    print("共计：" + str(rawData.count()) + "项")
    print("建立训练评估所需数据 RDD...")
    lines = rawData.map(lambda x: x.split(","))
    #----------------------2.建立预测所需数据 RDD[LabeledPoint]-------------
    labelpointRDD = lines.map(lambda r: LabeledPoint(
                              extract_label(r), extract_features(r,len(r) - 1)))
    #----------------------3.进行预测并显示结果-------------
    for lp in labelpointRDD.take(100):
        predict = model.predict(lp.features)
        label=lp.label
        features=lp.features
        result = ("正确" if  (label == predict) else "错误")
        print("土地条件：海拔:" + str(features[0]) + 
                 " 方位:" + str(features[1]) + 
                 " 斜率:" + str(features[2]) + 
                 " 水源垂直距离:" + str(features[3]) + 
                 " 水源水平距离:" + str(features[4]) + 
                 " 9点时阴影:" + str(features[5]) + 
                 "....==>预测:" + str(predict) +
                 " 实际:" + str(label) + "结果:" + result)

驱动函数

if __name__ == "__main__":
    print("RunDecisionTreeMulti")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    (AUC,duration, impurityParm, maxDepthParm, maxBinsParm,model)= \
        trainEvaluateModel(trainData, validationData, "entropy", 15,50)
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData,
                          ["gini", "entropy"],
                          [3, 5, 10, 15],
                          [3, 5, 10, 50 ])
                
    print("==========测试阶段===============")
    accuracy = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 accuracy:" + str(accuracy))
    print("==========预测数据===============")
    PredictData(sc, model)
    #print   model.toDebugString()

决策树回归分析

环境准备

导入我们需要的包

# -*- coding: UTF-8 -*-
import sys
from time import time
import pandas as pd
import matplotlib.pyplot as plt
from pyspark import SparkConf, SparkContext
from pyspark.mllib.tree import DecisionTree
from pyspark.mllib.regression import LabeledPoint
import numpy as np
from pyspark.mllib.evaluation import RegressionMetrics
import math

搭建SparkContext环境

def SetLogger( sc ):
    logger = sc._jvm.org.apache.log4j
    logger.LogManager.getLogger("org"). setLevel( logger.Level.ERROR )
    logger.LogManager.getLogger("akka").setLevel( logger.Level.ERROR )
    logger.LogManager.getRootLogger().setLevel(logger.Level.ERROR)

def SetPath(sc):
    global Path
    if sc.master[0:5]=="local" :
        Path="file:/home/hduser/pythonsparkexample/PythonProject/"
    else:   
        Path="hdfs://master:9000/user/hduser/"
#如果要在cluster模式运行(hadoop yarn 或Spark Stand alone)，请按照书上的说明，先把文件上传到HDFS目录

def CreateSparkContext():
    sparkConf = SparkConf()                                            \
                         .setAppName("RunDecisionTreeRegression")           \
                         .set("spark.ui.showConsoleProgress", "false") 
    sc = SparkContext(conf = sparkConf)
    print ("master="+sc.master)    
    SetLogger(sc)
    SetPath(sc)
    return (sc)

数据准备

def extract_label(record):
    label=(record[-1])
    return float(label)

def convert_float(x):
    return (0 if x=="?" else float(x))

def extract_features(record,featureEnd):
    featureSeason=[convert_float(field)  for  field in record[2]] 
    features=[convert_float(field)  for  field in record[4: featureEnd-2]]
    return  np.concatenate( (featureSeason, features))

def PrepareData(sc): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/hour.csv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    lines = rawData.map(lambda x: x.split(","))
    print (lines.first())
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 RDD[LabeledPoint]-------------
    labelpointRDD = lines.map(lambda r:LabeledPoint(
                                                    extract_label(r), 
                                                    extract_features(r,len(r) - 1)))

    print labelpointRDD.first()
    #----------------------3.以随机方式将数据分为3个部分并且返回-------------
    (trainData, validationData, testData) = labelpointRDD.randomSplit([8, 1, 1])
    print("将数据分trainData:" + str(trainData.count()) + 
             "   validationData:" + str(validationData.count()) +
             "   testData:" + str(testData.count()))
    #print labelpointRDD.first()
    return (trainData, validationData, testData) #返回数据

训练模型

在做决策树回归分析时，我们必须使用DecisionTree.trainRegressor模型，且无numClasses参数，而且impurity固定为variance

def trainEvaluateModel(trainData,validationData,
                                           impurityParm, maxDepthParm, maxBinsParm):
    startTime = time()
    model = DecisionTree.trainRegressor(trainData, 
                                  categoricalFeaturesInfo={}, \
                                  impurity=impurityParm, 
                                  maxDepth=maxDepthParm, 
                                  maxBins=maxBinsParm)
    RMSE = evaluateModel(model, validationData)
    duration = time() - startTime
    print    "训练评估：使用参数" + \
                " impurityParm= %s"%impurityParm+ \
                "  maxDepthParm= %s"%maxDepthParm+ \
                "  maxBinsParm = %d."%maxBinsParm + \
                 "  所需时间=%d"%duration + \
                 "  结果RMSE = %f " % RMSE 
    return (RMSE,duration, impurityParm, maxDepthParm, maxBinsParm,model)

模型评估

以RSME评估模型准确率，Root Mean Square Error，通常RSME越小，代表的误差就越小，即代表了“计算预测结果” 与 “标签字段” 的误差平均值。
使用RegressionMetrics(scoreAndLabels).rootMeanSquaredError计算RMSE。

def evaluateModel(model, validationData):
    score = model.predict(validationData.map(lambda p: p.features))
    scoreAndLabels=score.zip(validationData.map(lambda p: p.label))
    metrics = RegressionMetrics(scoreAndLabels)
    RMSE=metrics.rootMeanSquaredError
    return( RMSE)

参数评估

单个参数评估

def  parametersEval(training_RDD, validation_RDD):
    
    print("----- 评估maxDepth参数使用 ---------")
    evalParameter(training_RDD, validation_RDD,"maxDepth", 
                              impurityList=["variance"],       
                              maxDepthList =[3, 5, 10, 15, 20, 25]  ,
                              maxBinsList=[10])
    print("----- 评估maxBins参数使用 ---------")
    evalParameter(training_RDD, validation_RDD,"maxBins", 
                              impurityList=["variance"],        
                              maxDepthList=[10],                   
                              maxBinsList=[3, 5, 10, 50, 100, 200 ])

多个参数评估

def evalParameter(trainData, validationData, evaparm,impurityList, maxDepthList, maxBinsList):
    metrics = [trainEvaluateModel(trainData, validationData,  impurity,maxdepth,  maxBins  ) 
                            for impurity in impurityList 
                            for maxdepth in maxDepthList  
                            for maxBins in maxBinsList ]
    if evaparm=="impurity":
        IndexList=impurityList[:]
    elif evaparm=="maxDepth":
        IndexList=maxDepthList[:]
    elif evaparm=="maxBins":
        IndexList=maxBinsList[:]

    df = pd.DataFrame(metrics,index=IndexList,
                      columns=['RMSE', 'duration','impurityParm', 'maxDepthParm', 'maxBinsParm','model'])
    
    showchart(df,evaparm,'RMSE','duration',0,200 )

可视化

def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', title =evalparm,figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[[lineData ]].values, linestyle='-', marker='o', linewidth=2.0,color='r')
    plt.show()

多个参数同时评估

def evalAllParameter(training_RDD, validation_RDD, impurityList, maxDepthList, maxBinsList):    
    metrics = [trainEvaluateModel(trainData, validationData,  impurity,maxdepth,  maxBins  ) 
                        for impurity in impurityList 
                        for maxdepth in maxDepthList  
                        for maxBins in maxBinsList ]
    Smetrics = sorted(metrics, key=lambda k: k[0])
    bestParameter=Smetrics[0]
    
    print("调校后最佳参数：impurity:" + str(bestParameter[2]) + 
            "  ,maxDepth:" + str(bestParameter[3]) + 
            "  ,maxBins:" + str(bestParameter[4])   + 
            "  ,结果RMSE = " + str(bestParameter[0]))
    
    return bestParameter[5]

检验AUC

RMSE = evaluateModel(model, testData)
return RMSE

模型预测

def PredictData(sc,model): 
    #----------------------1.导入并转换数据-------------
    print("开始导入数据...")
    rawDataWithHeader = sc.textFile(Path+"data/hour.csv")
    header = rawDataWithHeader.first() 
    rawData = rawDataWithHeader.filter(lambda x:x !=header)    
    lines = rawData.map(lambda x: x.split(","))
    #print (lines.first())
    print("共计：" + str(lines.count()) + "项")
    #----------------------2.建立训练评估所需数据 LabeledPoint RDD-------------
    labelpointRDD = lines.map(lambda r: LabeledPoint(
                                                     extract_label(r), 
                                                     extract_features(r,len(r) - 1)))
    #----------------------3.定义字典----------------
    SeasonDict = { 1 : "春",  2 : "夏",  3 :"秋",  4 : "冬"   }
    HoildayDict={  0 : "非假日", 1 : "假日"  }  
    WeekDict = {0:"一",1:"二",2:"三",3:"四",4 :"五",5:"六",6:"日"}
    WorkDayDict={ 1 : "工作日",  0 : "非工作日"  }
    WeatherDict={ 1 : "晴",  2 : "阴",  3 : "小雨", 4 : "大雨" }
    #----------------------4.进行预测并显示结果--------------
    for lp in labelpointRDD.take(100):
        predict = int(model.predict(lp.features))
        label=lp.label
        features=lp.features
        result = ("正确" if  (label == predict) else "错误")
        error = math.fabs(label - predict)
        dataDesc="  特征: "+SeasonDict[features[0]] +"季,"+\
                            str(features[1]) + "月," +\
                            str(features[2]) +  "时,"+ \
                            HoildayDict[features[3]] +","+\
                            "星期"+WeekDict[features[4]]+","+ \
                            WorkDayDict[features[5]]+","+\
                            WeatherDict[features[6]]+","+\
                            str(features[7] * 41)+ "度,"+\
                            "体感" + str(features[8] * 50) + "度," +\
                            "湿度" + str(features[9] * 100) + ","+\
                            "风速" + str(features[10] * 67) +\
                            " ==> 预测结果:" + str(predict )+\
                            "  , 实际:" + str(label) + result +",  误差:" + str(error)
        print dataDesc

驱动函数

if __name__ == "__main__":
    print("RunDecisionTreeRegression")
    sc=CreateSparkContext()
    print("==========数据准备阶段===============")
    (trainData, validationData, testData) =PrepareData(sc)
    trainData.persist(); validationData.persist(); testData.persist()
    print("==========训练评估阶段===============")
    (AUC,duration, impurityParm, maxDepthParm, maxBinsParm,model)= \
             trainEvaluateModel(trainData, validationData, "variance", 10, 100)
    if (len(sys.argv) == 2) and (sys.argv[1]=="-e"):
        parametersEval(trainData, validationData)
    elif   (len(sys.argv) == 2) and (sys.argv[1]=="-a"): 
        print("-----所有参数训练评估找出最好的参数组合---------")  
        model=evalAllParameter(trainData, validationData,
                          ["variance"],
                          [3, 5, 10, 15, 20, 25], 
                          [3, 5, 10, 50, 100, 200 ])
    print("==========测试阶段===============")
    RMSE = evaluateModel(model, testData)
    print("使用test Data测试最佳模型,结果 RMSE:" + str(RMSE))
    print("==========预测数据===============")
    PredictData(sc, model)
    #print   model.toDebugString()

来源：https://www.cnblogs.com/Toxin/p/9685489.html

标签

mllib

spark

HDFS

Spark机器学习之MLlib整理分析

Mllib

决策树二元分类

环境准备

数据准备

模型训练

模型预测

模型评估

参数评估

检验AUC

驱动函数

逻辑回归二元分类

环境准备

数据准备

模型训练

模型预测

模型评估

参数评估

检验AUC

驱动函数

支持向量机SVM二元分类

环境准备

数据准备

模型训练

模型预测

模型评估

参数评估

检验AUC

驱动函数

朴素贝叶斯二元分类

环境准备

数据准备

模型训练

模型评估

参数评估

检验AUC

模型预测

驱动函数

决策树多元分类

环境准备

数据准备

模型训练

模型评估

参数评估

检验AUC

模型预测

驱动函数

决策树回归分析

环境准备

数据准备

训练模型

模型评估

参数评估

检验AUC

模型预测

驱动函数