RuntimeError: dictionary changed size during iteration

在运行《机器学习实战》第12章-构建FP树时遇到的小状况

def createtree(dataset, minsup=1):
    headertable = {}
    for trans in dataset:
        for item in trans:
            headertable[item] = headertable.get(item, 0) + dataset[trans]
    for k in headertable.keys():
        if headertable[k] < minsup:
            del(headertable[k]) #移除不满足最小支持度的元素项
    freqitemset = set(headertable.keys())
    if len(freqitemset) == 0:
        return None, None #如果没有元素项满足要求则退出
    for k in headertable:
        headertable[k] = [headertable[k], None]
    rettree = treenode('Null Set', 1, None)
    for transet, count in dataset.items():
        locald = {}
        for item in transet:
            if item in freqitemset:
                locald[item] = headertable[item][0] #根据全局频率对每个事务中的元素进行排序
        if len(locald) > 0:
            ordereditems = [v[0] for v in sorted(locald.items(), key=lambda p: p[1], reverse=True)]
            updatetree(ordereditems, rettree, headertable, count)  #使用排序后的频率项对树进行填充
    return rettree, headertable

运行结果如下：RuntimeError: dictionary changed size during iteration

得知遍历时不能修改字典元素

所以将for k in headertable.keys():改成 for k in list(headertable.keys()):即可

def createtree(dataset, minsup=1):
    headertable = {}
    for trans in dataset:
        for item in trans:
            headertable[item] = headertable.get(item, 0) + dataset[trans]
    for k in list(headertable.keys()):
        if headertable[k] < minsup:
            del(headertable[k]) #移除不满足最小支持度的元素项
    freqitemset = set(headertable.keys())
    if len(freqitemset) == 0:
        return None, None #如果没有元素项满足要求则退出
    for k in headertable:
        headertable[k] = [headertable[k], None]
    rettree = treenode('Null Set', 1, None)
    for transet, count in dataset.items():
        locald = {}
        for item in transet:
            if item in freqitemset:
                locald[item] = headertable[item][0] #根据全局频率对每个事务中的元素进行排序
        if len(locald) > 0:
            ordereditems = [v[0] for v in sorted(locald.items(), key=lambda p: p[1], reverse=True)]
            updatetree(ordereditems, rettree, headertable, count)  #使用排序后的频率项对树进行填充
    return rettree, headertable