您好,登錄后才能下訂單哦!
這篇文章主要介紹了python如何實現決策樹分類,具有一定借鑒價值,感興趣的朋友可以參考下,希望大家閱讀完這篇文章之后大有收獲,下面讓小編帶著大家一起了解一下。
原始數據集:
變化后的數據集在程序代碼中體現,這就不截圖了
構建決策樹的代碼如下:
#coding :utf-8 ''' 2017.6.25 author :Erin function: "decesion tree" ID3 ''' import numpy as np import pandas as pd from math import log import operator def load_data(): #data=np.array(data) data=[['teenager' ,'high', 'no' ,'same', 'no'], ['teenager', 'high', 'no', 'good', 'no'], ['middle_aged' ,'high', 'no', 'same', 'yes'], ['old_aged', 'middle', 'no' ,'same', 'yes'], ['old_aged', 'low', 'yes', 'same' ,'yes'], ['old_aged', 'low', 'yes', 'good', 'no'], ['middle_aged', 'low' ,'yes' ,'good', 'yes'], ['teenager' ,'middle' ,'no', 'same', 'no'], ['teenager', 'low' ,'yes' ,'same', 'yes'], ['old_aged' ,'middle', 'yes', 'same', 'yes'], ['teenager' ,'middle', 'yes', 'good', 'yes'], ['middle_aged' ,'middle', 'no', 'good', 'yes'], ['middle_aged', 'high', 'yes', 'same', 'yes'], ['old_aged', 'middle', 'no' ,'good' ,'no']] features=['age','input','student','level'] return data,features def cal_entropy(dataSet): ''' 輸入data ,表示帶最后標簽列的數據集 計算給定數據集總的信息熵 {'是': 9, '否': 5} 0.9402859586706309 ''' numEntries = len(dataSet) labelCounts = {} for featVec in dataSet: label = featVec[-1] if label not in labelCounts.keys(): labelCounts[label] = 0 labelCounts[label] += 1 entropy = 0.0 for key in labelCounts.keys(): p_i = float(labelCounts[key]/numEntries) entropy -= p_i * log(p_i,2)#log(x,10)表示以10 為底的對數 return entropy def split_data(data,feature_index,value): ''' 劃分數據集 feature_index:用于劃分特征的列數,例如“年齡” value:劃分后的屬性值:例如“青少年” ''' data_split=[]#劃分后的數據集 for feature in data: if feature[feature_index]==value: reFeature=feature[:feature_index] reFeature.extend(feature[feature_index+1:]) data_split.append(reFeature) return data_split def choose_best_to_split(data): ''' 根據每個特征的信息增益,選擇最大的劃分數據集的索引特征 ''' count_feature=len(data[0])-1#特征個數4 #print(count_feature)#4 entropy=cal_entropy(data)#原數據總的信息熵 #print(entropy)#0.9402859586706309 max_info_gain=0.0#信息增益最大 split_fea_index = -1#信息增益最大,對應的索引號 for i in range(count_feature): feature_list=[fe_index[i] for fe_index in data]#獲取該列所有特征值 ####################################### ''' print('feature_list') ['青少年', '青少年', '中年', '老年', '老年', '老年', '中年', '青少年', '青少年', '老年', '青少年', '中年', '中年', '老年'] 0.3467680694480959 #對應上篇博客中的公式 =(1)*5/14 0.3467680694480959 0.6935361388961918 ''' # print(feature_list) unqval=set(feature_list)#去除重復 Pro_entropy=0.0#特征的熵 for value in unqval:#遍歷改特征下的所有屬性 sub_data=split_data(data,i,value) pro=len(sub_data)/float(len(data)) Pro_entropy+=pro*cal_entropy(sub_data) #print(Pro_entropy) info_gain=entropy-Pro_entropy if(info_gain>max_info_gain): max_info_gain=info_gain split_fea_index=i return split_fea_index ################################################## def most_occur_label(labels): #sorted_label_count[0][0] 次數最多的類標簽 label_count={} for label in labels: if label not in label_count.keys(): label_count[label]=0 else: label_count[label]+=1 sorted_label_count = sorted(label_count.items(),key = operator.itemgetter(1),reverse = True) return sorted_label_count[0][0] def build_decesion_tree(dataSet,featnames): ''' 字典的鍵存放節點信息,分支及葉子節點存放值 ''' featname = featnames[:] ################ classlist = [featvec[-1] for featvec in dataSet] #此節點的分類情況 if classlist.count(classlist[0]) == len(classlist): #全部屬于一類 return classlist[0] if len(dataSet[0]) == 1: #分完了,沒有屬性了 return Vote(classlist) #少數服從多數 # 選擇一個最優特征進行劃分 bestFeat = choose_best_to_split(dataSet) bestFeatname = featname[bestFeat] del(featname[bestFeat]) #防止下標不準 DecisionTree = {bestFeatname:{}} # 創建分支,先找出所有屬性值,即分支數 allvalue = [vec[bestFeat] for vec in dataSet] specvalue = sorted(list(set(allvalue))) #使有一定順序 for v in specvalue: copyfeatname = featname[:] DecisionTree[bestFeatname][v] = build_decesion_tree(split_data(dataSet,bestFeat,v),copyfeatname) return DecisionTree
繪制可視化圖的代碼如下:
def getNumLeafs(myTree): '計算決策樹的葉子數' # 葉子數 numLeafs = 0 # 節點信息 sides = list(myTree.keys()) firstStr =sides[0] # 分支信息 secondDict = myTree[firstStr] for key in secondDict.keys(): # 遍歷所有分支 # 子樹分支則遞歸計算 if type(secondDict[key]).__name__=='dict': numLeafs += getNumLeafs(secondDict[key]) # 葉子分支則葉子數+1 else: numLeafs +=1 return numLeafs def getTreeDepth(myTree): '計算決策樹的深度' # 最大深度 maxDepth = 0 # 節點信息 sides = list(myTree.keys()) firstStr =sides[0] # 分支信息 secondDict = myTree[firstStr] for key in secondDict.keys(): # 遍歷所有分支 # 子樹分支則遞歸計算 if type(secondDict[key]).__name__=='dict': thisDepth = 1 + getTreeDepth(secondDict[key]) # 葉子分支則葉子數+1 else: thisDepth = 1 # 更新最大深度 if thisDepth > maxDepth: maxDepth = thisDepth return maxDepth import matplotlib.pyplot as plt decisionNode = dict(box, fc="0.8") leafNode = dict(box, fc="0.8") arrow_args = dict(arrow) # ================================================== # 輸入: # nodeTxt: 終端節點顯示內容 # centerPt: 終端節點坐標 # parentPt: 起始節點坐標 # nodeType: 終端節點樣式 # 輸出: # 在圖形界面中顯示輸入參數指定樣式的線段(終端帶節點) # ================================================== def plotNode(nodeTxt, centerPt, parentPt, nodeType): '畫線(末端帶一個點)' createPlot.ax1.annotate(nodeTxt, xy=parentPt, xycoords='axes fraction', xytext=centerPt, textcoords='axes fraction', va="center", ha="center", bbox=nodeType, arrowprops=arrow_args ) # ================================================================= # 輸入: # cntrPt: 終端節點坐標 # parentPt: 起始節點坐標 # txtString: 待顯示文本內容 # 輸出: # 在圖形界面指定位置(cntrPt和parentPt中間)顯示文本內容(txtString) # ================================================================= def plotMidText(cntrPt, parentPt, txtString): '在指定位置添加文本' # 中間位置坐標 xMid = (parentPt[0]-cntrPt[0])/2.0 + cntrPt[0] yMid = (parentPt[1]-cntrPt[1])/2.0 + cntrPt[1] createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30) # =================================== # 輸入: # myTree: 決策樹 # parentPt: 根節點坐標 # nodeTxt: 根節點坐標信息 # 輸出: # 在圖形界面繪制決策樹 # =================================== def plotTree(myTree, parentPt, nodeTxt): '繪制決策樹' # 當前樹的葉子數 numLeafs = getNumLeafs(myTree) # 當前樹的節點信息 sides = list(myTree.keys()) firstStr =sides[0] # 定位第一棵子樹的位置(這是蛋疼的一部分) cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff) # 繪制當前節點到子樹節點(含子樹節點)的信息 plotMidText(cntrPt, parentPt, nodeTxt) plotNode(firstStr, cntrPt, parentPt, decisionNode) # 獲取子樹信息 secondDict = myTree[firstStr] # 開始繪制子樹,縱坐標-1。 plotTree.yOff = plotTree.yOff - 1.0/plotTree.totalD for key in secondDict.keys(): # 遍歷所有分支 # 子樹分支則遞歸 if type(secondDict[key]).__name__=='dict': plotTree(secondDict[key],cntrPt,str(key)) # 葉子分支則直接繪制 else: plotTree.xOff = plotTree.xOff + 1.0/plotTree.totalW plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt, leafNode) plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key)) # 子樹繪制完畢,縱坐標+1。 plotTree.yOff = plotTree.yOff + 1.0/plotTree.totalD # ============================== # 輸入: # myTree: 決策樹 # 輸出: # 在圖形界面顯示決策樹 # ============================== def createPlot(inTree): '顯示決策樹' # 創建新的圖像并清空 - 無橫縱坐標 fig = plt.figure(1, facecolor='white') fig.clf() axprops = dict(xticks=[], yticks=[]) createPlot.ax1 = plt.subplot(111, frameon=False, **axprops) # 樹的總寬度 高度 plotTree.totalW = float(getNumLeafs(inTree)) plotTree.totalD = float(getTreeDepth(inTree)) # 當前繪制節點的坐標 plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0; # 繪制決策樹 plotTree(inTree, (0.5,1.0), '') plt.show() if __name__ == '__main__': data,features=load_data() split_fea_index=choose_best_to_split(data) newtree=build_decesion_tree(data,features) print(newtree) createPlot(newtree) ''' {'age': {'old_aged': {'level': {'same': 'yes', 'good': 'no'}}, 'teenager': {'student': {'no': 'no', 'yes': 'yes'}}, 'middle_aged': 'yes'}} '''
結果如下:
感謝你能夠認真閱讀完這篇文章,希望小編分享的“python如何實現決策樹分類”這篇文章對大家有幫助,同時也希望大家多多支持億速云,關注億速云行業資訊頻道,更多相關知識等著你來學習!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。