spark 决策树分类算法demo

分类（Classification）

下面的例子说明了怎样导入LIBSVM 数据文件，解析成RDD[LabeledPoint]，然后使用决策树进行分类。GINI不纯度作为不纯度衡量标准并且树的最大深度设置为5。最后计算了测试错误率从而评估算法的准确性。

from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
from pyspark.mllib.util import MLUtils

# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLibSVMFile(sc, 'data/mllib/sample_libsvm_data.txt')
# Split the data into training and test sets (30% held out for testing)
(trainingData, testData) = data.randomSplit([0.7, 0.3])

# Train a DecisionTree model.
#  Empty categoricalFeaturesInfo indicates all features are continuous.
model = DecisionTree.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
                                     impurity='gini', maxDepth=5, maxBins=32)

# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
print('Test Error = ' + str(testErr))
print('Learned classification tree model:')
print(model.toDebugString())

# Save and load model
model.save(sc, "myModelPath")
sameModel = DecisionTreeModel.load(sc, "myModelPath")

 

以下代码展示了如何载入一个LIBSVM数据文件，解析成一个LabeledPointRDD，然后使用决策树，使用Gini不纯度作为不纯度衡量指标，最大树深度是5.测试误差用来计算算法准确率。

# -*- coding:utf-8 -*-
"""
测试决策树
"""

import os
import sys
import logging
from.mllib.tree importDecisionTree,DecisionTreeModel
from.mllib.util importMLUtils

# Path for spark source folder
os.environ['SPARK_HOME']="D:\javaPackages\spark-1.6.0-bin-hadoop2.6"
# Append pyspark to Python Path
sys.path.append("D:\javaPackages\spark-1.6.0-bin-hadoop2.6\python")
sys.path.append("D:\javaPackages\spark-1.6.0-bin-hadoop2.6\python\lib\py4j-0.9-src.zip")

fromimportSparkContext
fromimportSparkConf

conf =SparkConf()
conf.set("YARN_CONF_DIR ","D:\javaPackages\hadoop_conf_dir\yarn-conf")
conf.set("spark.driver.memory","2g")

#conf.set("spark.executor.memory", "1g")
#conf.set("spark.python.worker.memory", "1g")
conf.setMaster("yarn-client")
conf.setAppName("TestDecisionTree")
logger =.getLogger('pyspark')
sc =SparkContext(conf=conf)

mylog =[]
#载入和解析数据文件为 LabeledPoint RDDdata = MLUtils.loadLibSVMFile(sc,"/home/xiatao/machine_learing/")
#将数据拆分成训练集合测试集
(trainingData,testData)=.randomSplit([0.7,0.3])

##训练决策树模型
#空的 categoricalFeauresInfo 代表了所有的特征都是连续的
model =DecisionTree.trainClassifier(trainingData,=2,categoricalFeaturesInfo={},impurity='gini',maxDepth=5,maxBins=32)

# 在测试实例上评估模型并计算测试误差

predictions =.predict(testData.map(lambda:x.features))
labelsAndPoint =.map(lambda:lp.label).zip(predictions)
testMSE =.map(lambda(v,p):(v-p)**2).sum()/float(testData.count())
mylog.append("测试误差是")
mylog.append(testMSE)

#存储模型

model.save(sc,"/home/xiatao/machine_learing/")
sc.parallelize(mylog).saveAsTextFile("/home/xiatao/machine_learing/log")
sameModel =DecisionTreeModel.load(sc,"/home/xiatao/machine_learing/")