我发现setdefault非常有用;它检查一个键是否存在，如果不存在就添加它:

d = {}
d.setdefault('new jersey', {}).setdefault('mercer county', {})['plumbers'] = 3

Setdefault总是返回相关的键，所以你实际上是在原地更新'd'的值。

说到迭代，我相信你可以很容易地编写一个生成器，如果Python中还没有这样的生成器:

def iterateStates(d):
    # Let's count up the total number of "plumbers" / "dentists" / etc.
    # across all counties and states
    job_totals = {}

    # I guess this is the annoying nested stuff you were talking about?
    for (state, counties) in d.iteritems():
        for (county, jobs) in counties.iteritems():
            for (job, num) in jobs.iteritems():
                # If job isn't already in job_totals, default it to zero
                job_totals[job] = job_totals.get(job, 0) + num

    # Now return an iterator of (job, number) tuples
    return job_totals.iteritems()

# Display all jobs
for (job, num) in iterateStates(d):
    print "There are %d %s in total" % (job, num)

Defaultdict()是你的朋友!

对于一个二维字典，你可以这样做:

d = defaultdict(defaultdict)
d[1][2] = 3

更多维度你可以:

d = defaultdict(lambda :defaultdict(defaultdict))
d[1][2][3] = 4

为了方便遍历嵌套的字典，为什么不写一个简单的生成器呢?

def each_job(my_dict):
    for state, a in my_dict.items():
        for county, b in a.items():
            for job, value in b.items():
                yield {
                    'state'  : state,
                    'county' : county,
                    'job'    : job,
                    'value'  : value
                }

因此，如果你有编译好的嵌套字典，遍历它就变得很简单:

for r in each_job(my_dict):
    print "There are %d %s in %s, %s" % (r['value'], r['job'], r['county'], r['state'])

显然，您的生成器可以生成对您有用的任何格式的数据。

为什么使用try catch块读取树?在试图检索字典之前，查询一个键是否存在于字典中是很容易的(而且可能更安全)。使用保护子句的函数可能是这样的:

if not my_dict.has_key('new jersey'):
    return False

nj_dict = my_dict['new jersey']
...

或者，一个可能有点啰嗦的方法是使用get方法:

value = my_dict.get('new jersey', {}).get('middlesex county', {}).get('salesmen', 0)

但是为了更简洁的方式，您可能想要使用collections.defaultdict，它是python 2.5以来标准库的一部分。

import collections

def state_struct(): return collections.defaultdict(county_struct)
def county_struct(): return collections.defaultdict(job_struct)
def job_struct(): return 0

my_dict = collections.defaultdict(state_struct)

print my_dict['new jersey']['middlesex county']['salesmen']

我在这里对数据结构的含义做了假设，但是根据实际需要进行调整应该很容易。

如果嵌套层的数量很少，我使用collections.defaultdict:

from collections import defaultdict

def nested_dict_factory(): 
  return defaultdict(int)
def nested_dict_factory2(): 
  return defaultdict(nested_dict_factory)
db = defaultdict(nested_dict_factory2)

db['new jersey']['mercer county']['plumbers'] = 3
db['new jersey']['mercer county']['programmers'] = 81

像这样使用defaultdict可以避免大量混乱的setdefault()、get()等。

我也有类似的事情。我有很多这样的案例:

thedict = {}
for item in ('foo', 'bar', 'baz'):
  mydict = thedict.get(item, {})
  mydict = get_value_for(item)
  thedict[item] = mydict

但要深入很多层次。这是“。”Get (item，{})"，这是一个键，因为如果已经没有字典，它将创建另一个字典。与此同时，我一直在想办法对付 这个更好。现在，有很多

value = mydict.get('foo', {}).get('bar', {}).get('baz', 0)

所以，我做了:

def dictgetter(thedict, default, *args):
  totalargs = len(args)
  for i,arg in enumerate(args):
    if i+1 == totalargs:
      thedict = thedict.get(arg, default)
    else:
      thedict = thedict.get(arg, {})
  return thedict

如果你这样做，效果是一样的:

value = dictgetter(mydict, 0, 'foo', 'bar', 'baz')

更好吗?我想是的。

class JobDb(object):
    def __init__(self):
        self.data = []
        self.all = set()
        self.free = []
        self.index1 = {}
        self.index2 = {}
        self.index3 = {}

    def _indices(self,(key1,key2,key3)):
        indices = self.all.copy()
        wild = False
        for index,key in ((self.index1,key1),(self.index2,key2),
                                             (self.index3,key3)):
            if key is not None:
                indices &= index.setdefault(key,set())
            else:
                wild = True
        return indices, wild

    def __getitem__(self,key):
        indices, wild = self._indices(key)
        if wild:
            return dict(self.data[i] for i in indices)
        else:
            values = [self.data[i][-1] for i in indices]
            if values:
                return values[0]

    def __setitem__(self,key,value):
        indices, wild = self._indices(key)
        if indices:
            for i in indices:
                self.data[i] = key,value
        elif wild:
            raise KeyError(k)
        else:
            if self.free:
                index = self.free.pop(0)
                self.data[index] = key,value
            else:
                index = len(self.data)
                self.data.append((key,value))
                self.all.add(index)
            self.index1.setdefault(key[0],set()).add(index)
            self.index2.setdefault(key[1],set()).add(index)
            self.index3.setdefault(key[2],set()).add(index)

    def __delitem__(self,key):
        indices,wild = self._indices(key)
        if not indices:
            raise KeyError
        self.index1[key[0]] -= indices
        self.index2[key[1]] -= indices
        self.index3[key[2]] -= indices
        self.all -= indices
        for i in indices:
            self.data[i] = None
        self.free.extend(indices)

    def __len__(self):
        return len(self.all)

    def __iter__(self):
        for key,value in self.data:
            yield key

例子:

>>> db = JobDb()
>>> db['new jersey', 'mercer county', 'plumbers'] = 3
>>> db['new jersey', 'mercer county', 'programmers'] = 81
>>> db['new jersey', 'middlesex county', 'programmers'] = 81
>>> db['new jersey', 'middlesex county', 'salesmen'] = 62
>>> db['new york', 'queens county', 'plumbers'] = 9
>>> db['new york', 'queens county', 'salesmen'] = 36

>>> db['new york', None, None]
{('new york', 'queens county', 'plumbers'): 9,
 ('new york', 'queens county', 'salesmen'): 36}

>>> db[None, None, 'plumbers']
{('new jersey', 'mercer county', 'plumbers'): 3,
 ('new york', 'queens county', 'plumbers'): 9}

>>> db['new jersey', 'mercer county', None]
{('new jersey', 'mercer county', 'plumbers'): 3,
 ('new jersey', 'mercer county', 'programmers'): 81}

>>> db['new jersey', 'middlesex county', 'programmers']
81

>>>

编辑:现在使用通配符(None)查询时返回字典，否则返回单值。