def classify(inputTree, features,
testVec): #这里的inputTree就是决策树的序列化表示方法,python中是字典类型,也可以看做是json类型
firstStr = inputTree.keys()[0] #获取决策树的当前分割属性
secondDict = inputTree[firstStr] #当前分割节点下面的一堆树枝+节点
featIndex = features.index(firstStr) #当前是第几个特征
key = testVec[featIndex] #根据划分属性的下标来获取测试数据的对应下标的属性的具体取值
#--------------获得子树--------------------------------
if isinstance(key, str): #如果是离散特征
# print"secondDict=",secondDict
valueOfFeat = secondDict[key] #根据这个值来顺着树枝key选择子树secondDict[key](离散特征)
else:
item_lists = []
for item in secondDict:
item_lists.append(item)
common_str = getNumofCommonSubstr(item_lists[0],
item_lists[1])[0] #common_str是
# print"item_lists=",item_lists
if key <= float(common_str):
key = "<=" + common_str
valueOfFeat = secondDict[key]
else:
key = ">" + common_str
valueOfFeat = secondDict[key]
#----------------获得子树------------------------------
if isinstance(valueOfFeat, dict): #如果是子树
classLabel = classify(valueOfFeat, features, testVec) #递归调用
else: #如果是叶子节点
classLabel = valueOfFeat
return classLabel #递归函数的结束条件
def chi_square_continuous(bestfeature,branch_names,sub_datas,feature_list):
data=copy.deepcopy(sub_datas)
# print"feature_list=",feature_list
feature_index=feature_list.index(bestfeature)
feature_list.append('class')
feature=bestfeature
#根据《概率论与数理统计》中的双因素检验可知，需要把连续特征转化为有限个“取值水平”
threshold=getNumofCommonSubstr(branch_names[0], branch_names[1])[0]
threshold=float(threshold)
# print "feature_index=",feature_index
for index,item in enumerate(data):
try:
if float(item[feature_index])<=threshold:
data[index][feature_index]="<="+str(threshold)#这里的用意是把连续特征改为因素的不同水平，便于计算自由度，由于C4.5对连续特征的处理是“二分处理”，所以这里改成两个水平，"≥"和“小于”
else:
data[index][feature_index]=">"+str(threshold)
except:
pass
# Contingency table.
feature=bestfeature
datas = pd.DataFrame(data, columns=feature_list)
contingency = pd.crosstab(datas[feature], datas["class"])
#这个应该是指定特征和最后一列类别列之间的卡方检验计算
# Chi-square test of independence.
chi2, p_value, Degree_Freedom, expected_Xij = chi2_contingency(contingency)
# print "Degree_Freedom=",Degree_Freedom
# print"当期数据的长度=",len(datas)
return chi2