python多线程并行实现随机森林

程序针对特征值取值范围为[-1, 1]来实现，数据预处理后即可使用。

import math
import operator
import threading
import random

def loadDataSet(filename, boundry):
    num = len(open(filename).readline().split(','))-1
    dataMat = []; testMat = []
    fr = open(filename)
    ii = 0
    for line in fr.readlines():
        lineArr = []
        curLine = line.strip().split(',')
        for i in range(num):
            lineArr.append(float(curLine[i+1]))
        if ii >= boundry[0] and ii <= boundry[1]:
            testMat.append(lineArr)
        else:
            dataMat.append(lineArr)
        ii += 1
    return dataMat, testMat

def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0
        lab