再谈随机森林---python实现

该代码是我从github上找了半天才找到非常适合初学者的，在此感谢原作者，从你的代码中我学到了很多。

from __future__ import divisionimport pandas as pdimport copyimport randomimport math# 最后一个属性还不能将样本完全分开，此时数量最多的label被选为最终类别def majorClass(classList):    classDict = {}    for cls in classList:        classDict[cls] = classDict.get(cls, 0) + 1    sortClass = sorted(classDict.items(), key=lambda item: item[1])    return sortClass[-1][0]# 计算基尼系数def calcGini(dataSet):    labelCounts = {}    # 给所有可能分类创建字典    for dt in dataSet:        currentLabel = dt[-1]        labelCounts[currentLabel] = labelCounts.get(currentLabel, 0) + 1    Gini = 1    for key in labelCounts:        prob = labelCounts[key] / len(dataSet)        Gini -= prob * prob    return Gini# 对连续变量划分数据集def splitDataSet(dataSet, featIndex, value):    leftData, rightData = [], []    for dt in dataSet:        if dt[featIndex] <= value:            leftData.append(dt)        else:            rightData.append(dt)    return leftData, rightData# 选择最好的数据集划分方式def chooseBestFeature(dataSet):    bestGini = 1    bestFeatureIndex = -1    bestSplitValue = None    # 第i个特征    for i in range(len(dataSet[0]) - 1):        featList = [dt[i] for dt in dataSet]        # 产生候选划分点        sortfeatList = sorted(list(set(featList)))        splitList = []        for j in range(len(sortfeatList) - 1):            splitList.append((sortfeatList[j] + sortfeatList[j + 1]) / 2)        # 第j个候选划分点，记录最佳划分点        for splitValue in splitList:            newGini = 0            subDataSet0, subDataSet1 = splitDataSet(dataSet, i, splitValue)            newGini += len(subDataSet0) / len(dataSet) * calcGini(subDataSet0)            newGini += len(subDataSet1) / len(dataSet) * calcGini(subDataSet1)            if newGini < bestGini:                bestGini = newGini                bestFeatureIndex = i                bestSplitValue = splitValue    return bestFeatureIndex, bestSplitValue# 去掉第i个属性，生成新的数据集def splitData(dataSet, featIndex, features, value):    newFeatures = copy.deepcopy(features)    newFeatures.remove(features[featIndex])    leftData, rightData = [], []    for dt in dataSet:        temp = []        temp.extend(dt[:featIndex])        temp.extend(dt[featIndex + 1:])        #实验时，有时会出现value=NONE的情况        #好像引起这个问题有两个原因        #1.chooseBestFeature有问题 （20%）        #2.你的数据集有问题（80%）        # 括号是出问题的可能性        if dt[featIndex] <= value:            leftData.append(temp)        else:            rightData.append(temp)    return newFeatures, leftData, rightData# 建立决策树def createTree(dataSet, features):    classList = [dt[-1] for dt in dataSet]    # label一样，全部分到一边    if classList.count(classList[0]) == len(classList):        return classList[0]    # 最后一个特征还不能把所有样本分到一边，则选数量最多的label    if len(features) == 1:        return majorClass(classList)    bestFeatureIndex, bestSplitValue = chooseBestFeature(dataSet)    bestFeature = features[bestFeatureIndex]    # 生成新的去掉bestFeature特征的数据集    newFeatures, leftData, rightData = splitData(dataSet, bestFeatureIndex, features, bestSplitValue)    # 左右两颗子树，左边小于等于最佳划分点，右边大于最佳划分点    myTree = {bestFeature: {'<' + str(bestSplitValue): {}, '>' + str(bestSplitValue): {}}}    myTree[bestFeature]['<' + str(bestSplitValue)] = createTree(leftData, newFeatures)    myTree[bestFeature]['>' + str(bestSplitValue)] = createTree(rightData, newFeatures)    return myTree# 用生成的决策树对测试样本进行分类def treeClassify(decisionTree, featureLabel, testDataSet):    firstFeature = decisionTree.keys()[0]    secondFeatDict = decisionTree[firstFeature]    splitValue = float(secondFeatDict.keys()[0][1:])    # secondFeatDict.keys()[0]是'<'+str(bestsplitValue)    #所以索引应该从1开始去掉之前的'<'或者‘>’    featureIndex = featureLabel.index(firstFeature)    if testDataSet[featureIndex] <= splitValue:        valueOfFeat = secondFeatDict['<' + str(splitValue)]    else:        valueOfFeat = secondFeatDict['>' + str(splitValue)]    if isinstance(valueOfFeat, dict):        pred_label = treeClassify(valueOfFeat, featureLabel, testDataSet)    else:        pred_label = valueOfFeat    return pred_label# 随机抽取样本，样本数量与原训练样本集一样，维度为sqrt(m-1)def baggingDataSet(dataSet):    n, m = dataSet.shape    features = random.sample(dataSet.columns.values[:-1], int(math.sqrt(m - 1)))    features.append(dataSet.columns.values[-1])    #不好疑惑这儿就是得添加最后一列，你可能想说不是应该抽取特征数的开方个特征不就行了吗？    #其实这个函数是为了构造一个新的数据集，所以必须加上最后一列（类别列）。    rows = [random.randint(0, n-1) for _ in range(n)]    trainData = dataSet.iloc[rows][features]    #利用pandas.DataFrame的iloc方法取值    return trainData.values.tolist(), featuresdef testWine():    df = pd.read_csv('wine.txt', header=None)    labels = df.columns.values.tolist()    df = df[df[labels[-1]] != 3]    # 生成多棵决策树，放到一个list里边    treeCounts = 10    treeList = []    for i in range(treeCounts):        baggingData, bagginglabels = baggingDataSet(df)        decisionTree = createTree(baggingData, bagginglabels)        treeList.append(decisionTree)    print treeList    # 对测试样本分类    labelPred = []    for tree in treeList:        testData = [12, 0.92, 2, 19, 86, 2.42, 2.26, 0.3, 1.43, 2.5, 1.38, 3.12, 278]        label = treeClassify(tree, labels[:-1], testData)        labelPred.append(label)    # 投票选择最终类别（其实也就是majorityclass（））    labelDict = {}    for label in labelPred:        labelDict[label] = labelDict.get(label, 0) + 1    sortClass = sorted(labelDict.items(), key=lambda item: item[1])    print "The predicted label is: {}".format(sortClass[-1][0])testWine()

该算法解决了上一篇关于随机森林中的两个问题。
如果拓展下加上重复做十次又该怎么做呢。
注意：这不是十折交叉验证，因为在十交叉验证中，块都是分好的。也就是说已经被分为测试集的样本将不会再分成测试集。我做的时候忘记了这点只想着循环十次就是十-交叉验证，做完才发现自己的错误。。。。

在这给大家一个参考的例子，我自己将这两篇关于随机森林的代码综合了下 ，能力有限，凑合着看吧。

import scipy.io as sioimport numpy as npimport pandas as pdimport copyimport randomimport mathfrom sklearn.cross_validation import train_test_splitdef load_data(filename):    load_data = sio.loadmat(filename)    PET = load_data['PET']    MRI = load_data['MRI']    #MRI = np.round(MRI, decimals=6)    GND4 = load_data['GND4']    GND3 = load_data['GND3']    CSF = load_data['CSF']    dataset = np.append(PET,MRI,axis=1)    dataset = np.append(dataset,CSF,axis = 1)    dataset = np.append(dataset,GND3,axis = 1)    df = pd.DataFrame(dataset)    labels = df.columns.values.tolist()    df = df[df[labels[-1]] != 2] # only    left 1 and 3    dataset = df.iloc[:,0:189]    label = df.iloc[:,189]       dataset = np.array(dataset)    label  = np.array(label)    label = label.tolist()    labels = []    for i in label:        g = [i]        labels.append(g)        labels = np.array(labels)    #print(GND3[0:150,])#retudata = []#for i in range(dataset.shape[0]):    #retudata.append(dataset[i].tolist())    return dataset,labelsdef majorClass(classList):    classDict = {}    for cls in classList:        classDict[cls] = classDict.get(cls, 0) + 1    sortClass = sorted(classDict.items(), key=lambda item: item[1])    return sortClass[-1][0]def calcGini(dataSet):    labelCounts = {}    for dt in dataSet:        currentLabel = dt[-1]        labelCounts[currentLabel] = labelCounts.get(currentLabel, 0) + 1    Gini = 1    for key in labelCounts:        prob = labelCounts[key] / len(dataSet)        Gini -= prob * prob    return Ginidef splitDataSet(dataSet, featIndex, value):    leftData, rightData = [], []    for dt in dataSet:        if dt[featIndex] <= value:            leftData.append(dt)        else:            rightData.append(dt)    return leftData, rightDatadef chooseBestFeature(dataSet):    bestGini = 999    bestFeatureIndex = -1    bestSplitValue = None        for i in range(len(dataSet[0]) - 1):        featList = [dt[i] for dt in dataSet]        sortfeatList = sorted(list(set(featList)))        splitList = []        for j in range(len(sortfeatList) - 1):            #splitList.append((sortfeatList[j] + sortfeatList[j + 1]) / 2)        for splitValue in sortfeatList:            newGini = 0            subDataSet0, subDataSet1 = splitDataSet(dataSet, i, splitValue)            newGini += len(subDataSet0) / len(dataSet) * calcGini(subDataSet0)            newGini += len(subDataSet1) / len(dataSet) * calcGini(subDataSet1)            if newGini < bestGini:                bestGini = newGini                bestFeatureIndex = i                bestSplitValue = splitValue    return bestFeatureIndex, bestSplitValuedef splitData(dataSet, featIndex, features, value):    newFeatures = copy.deepcopy(features)    newFeatures.remove(features[featIndex])    leftData, rightData = [], []    for dt in dataSet:        temp = []        temp.extend(dt[:featIndex])        temp.extend(dt[featIndex + 1:])        if value == None or dt[featIndex] <= value:            leftData.append(temp)        else:            rightData.append(temp)    return newFeatures, leftData, rightDatadef createTree(dataSet, features):    classList = [dt[-1] for dt in dataSet]    if classList.count(classList[0]) == len(classList):        return classList[0]    if len(features) == 1:        return majorClass(classList)    bestFeatureIndex, bestSplitValue = chooseBestFeature(dataSet)    bestFeature = features[bestFeatureIndex]    newFeatures, leftData, rightData = splitData(dataSet, bestFeatureIndex, features, bestSplitValue)    myTree = {bestFeature: {'<' + str(bestSplitValue): {}, '>' + str(bestSplitValue): {}}}    myTree[bestFeature]['<' + str(bestSplitValue)] = createTree(leftData, newFeatures)    myTree[bestFeature]['>' + str(bestSplitValue)] = createTree(rightData, newFeatures)    return myTreedef treeClassify(decisionTree, featureLabel, testDataSet):    firstFeature = list(decisionTree.keys())[0]    secondFeatDict = decisionTree[firstFeature]    splitValue = float(list(secondFeatDict.keys())[0][1:])    featureIndex = featureLabel.index(firstFeature)    if testDataSet[featureIndex] <= splitValue:        valueOfFeat = secondFeatDict['<' + str(splitValue)]    else:        valueOfFeat = secondFeatDict['>' + str(splitValue)]    if isinstance(valueOfFeat, dict):        pred_label = treeClassify(valueOfFeat, featureLabel, testDataSet)    else:        pred_label = valueOfFeat    return pred_labeldef baggingDataSet(dataSet):    n, m = dataSet.shape    features = random.sample(list(dataSet.columns.values[:-1]), int(math.sqrt(m - 1)) + 1)    features.append(dataSet.columns.values[-1])    rows = [random.randint(0, n-1) for _ in range(n)]    trainData = dataSet.iloc[rows][features]    return trainData.values.tolist(), features#def majorityCnt(classList):    #classCount = {}    #for vote in classList:        #if vote not in classCount.keys():            #classCount[vote] = 0        #classCount[vote] += 1    #sortClass = sorted(labelDict.items(), key=lambda item: item[1])    #return sortClass[-1][0]def ad_vs_nc(train_set,test_set,n_trees):    df = pd.DataFrame(train_set) # this is train dataset    labels = df.columns.values.tolist()    df = df[df[labels[-1]] != 2]    treeCounts = n_trees    treeList = []    for i in range(treeCounts): #get forest        baggingData, bagginglabels = baggingDataSet(df)        decisionTree = createTree(baggingData, bagginglabels)        treeList.append(decisionTree)    print( treeList,'treelist')    predictions = []    for row in test_set:        labelPred = []        for tree in treeList:            testData = row            label = treeClassify(tree, labels[:-1], testData)            labelPred.append(label)        predictions.append(majorClass(labelPred))    return predictionsdef change_y_test(y_test):    actualList = []    for i in range(len(y_test)):        #if y_test[i][0] != 2:            actualList.extend(y_test[i])    return actualListdef accuracy_cal(actual, predicted):      print(actual,'actual')    print(predicted,'predicted')    correct = 0    for i in range(len(actual)):        if actual[i] == predicted[i]:            correct += 1    return correct / float(len(actual)) * 100.0def evaluate_algorithm():    filename = 'f:\\ADNI202.mat'    data,labels = load_data(filename)    scores = []    n_trees = 100    for i in range(10):        x_train,x_test,y_train,y_test = train_test_split(data,labels,test_size = 0.1,random_state = 0)        #这是sklearn的方法，自动分测试集和训练集 x_train是测试样本的特征值        #y_train是测试样本的类别值        #train_set = np.append(x_train,y_train,axis = 1)        train_set = np.append(x_train,y_train,axis = 1)        train_set = pd.DataFrame(train_set)        test_set = x_test.tolist()        actual = change_y_test(y_test)        predicted = ad_vs_nc(train_set,test_set,n_trees)        accuracy = accuracy_cal(actual,predicted)        scores.append(accuracy)    print("trees {0}".format(n_trees))    print('scores{0}'.format(scores))    print('mean accuracy{0}'.format(sum(scores)/float(len(scores))))      evaluate_algorithm()