# Save a dictionary into a pickle file.
import pickle

favorite_color = {"lion": "yellow", "kitty": "red"}  # create a dictionary
pickle.dump(favorite_color, open("save.p", "wb"))  # save it into a file named save.p

# -------------------------------------------------------------
# Load the dictionary back from the pickle file.
import pickle

favorite_color = pickle.load(open("save.p", "rb"))
# favorite_color is now {"lion": "yellow", "kitty": "red"}

import pickle

your_data = {'foo': 'bar'}

# Store data (serialize)
with open('filename.pickle', 'wb') as handle:
    pickle.dump(your_data, handle, protocol=pickle.HIGHEST_PROTOCOL)

# Load data (deserialize)
with open('filename.pickle', 'rb') as handle:
    unserialized_data = pickle.load(handle)

print(your_data == unserialized_data)

HIGHEST_PROTOCOL的优点是文件变得更小。这使得解腌有时要快得多。

重要提示:pickle的最大文件大小约为2GB。

替代方法

import mpu
your_data = {'foo': 'bar'}
mpu.io.write('filename.pickle', data)
unserialized_data = mpu.io.read('filename.pickle')

选择格式

CSV:超简单格式(读写) JSON:适合编写人类可读的数据;非常常用(读和写) YAML: YAML是JSON的超集，但更容易阅读(读写，JSON和YAML的比较) pickle: Python序列化格式(读和写) MessagePack (Python包):更紧凑的表示(读和写) HDF5 (Python包):适合矩阵(读和写) XML:也存在*叹*(读和写)

对于您的应用程序，以下内容可能很重要:

其他编程语言的支持 读写能力 紧凑性(文件大小)

请参见:数据序列化格式的比较

如果您正在寻找一种创建配置文件的方法，您可能想要阅读我的简短文章Python中的配置文件

一般来说，除非字典中只有简单的对象，如字符串和整数，否则pickle字典将会失败。

Python 2.7.9 (default, Dec 11 2014, 01:21:43) 
[GCC 4.2.1 Compatible Apple Clang 4.1 ((tags/Apple/clang-421.11.66))] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from numpy import *
>>> type(globals())     
<type 'dict'>
>>> import pickle
>>> pik = pickle.dumps(globals())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 1374, in dumps
    Pickler(file, protocol).dump(obj)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 224, in dump
    self.save(obj)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 286, in save
    f(self, obj) # Call unbound method with explicit self
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 649, in save_dict
    self._batch_setitems(obj.iteritems())
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 663, in _batch_setitems
    save(v)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 306, in save
    rv = reduce(self.proto)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/copy_reg.py", line 70, in _reduce_ex
    raise TypeError, "can't pickle %s objects" % base.__name__
TypeError: can't pickle module objects
>>> 

即使是一个非常简单的字典也经常会失败。这取决于内容。

>>> d = {'x': lambda x:x}
>>> pik = pickle.dumps(d)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 1374, in dumps
    Pickler(file, protocol).dump(obj)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 224, in dump
    self.save(obj)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 286, in save
    f(self, obj) # Call unbound method with explicit self
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 649, in save_dict
    self._batch_setitems(obj.iteritems())
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 663, in _batch_setitems
    save(v)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 286, in save
    f(self, obj) # Call unbound method with explicit self
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.py", line 748, in save_global
    (obj, module, name))
pickle.PicklingError: Can't pickle <function <lambda> at 0x102178668>: it's not found as __main__.<lambda>

然而，如果你使用一个更好的序列化器，如dill或cloudpickle，那么大多数字典都可以被pickle:

>>> import dill
>>> pik = dill.dumps(d)

或者如果你想保存你的字典到一个文件…

>>> with open('save.pik', 'w') as f:
...   dill.dump(globals(), f)
... 

后一个例子与这里发布的任何其他好的答案是一样的(除了忽略了字典内容的可选择性之外，这些答案都是好的)。

供你参考，熊猫现在有办法拯救泡菜了。

我发现它更容易。

pd.to_pickle(object_to_save,'/temp/saved_pkl.pickle' )

# Save a dictionary into a pickle file.
import pickle

favorite_color = {"lion": "yellow", "kitty": "red"}  # create a dictionary
pickle.dump(favorite_color, open("save.p", "wb"))  # save it into a file named save.p

# -------------------------------------------------------------
# Load the dictionary back from the pickle file.
import pickle

favorite_color = pickle.load(open("save.p", "rb"))
# favorite_color is now {"lion": "yellow", "kitty": "red"}

如果你想在不打开文件的情况下在一行中处理写入或读取:

  import joblib

  my_dict = {'hello': 'world'}

  joblib.dump(my_dict, "my_dict.pickle") # write pickle file
  my_dict_loaded = joblib.load("my_dict.pickle") # read pickle file