ENH: Add expiring cache.

Add a cache interface which supports expirable entries with a changeable
backend for the cache into which they are entered.

The default cache is a `dict` but could swapped for
`cachetools.LRUCache` or any other cache which supports `__get__`,
`__set__`, and `__del__`.

So that consumers can change the use of `CachedObjects` stored in a
cache from:

```
self._cache = {}

...

try:
    obj = self._cache[key]
    try:
        return obj.unwrap(dt)
    except Expired:
        pass
except KeyError:
    pass

...

self._cache[key] = CachedObject(value, new_expiration)
```

to:

```
self._cache = ExpiringCache(LRUCache(maxsize=6))

...

try:
    return self._cache.get(key, dt)
except KeyError:
    # Get fresh value
    ...

    self._cache.set(key, value, new_expiration)
```
This commit is contained in:
Eddie Hebert
2016-04-14 13:54:12 -04:00
parent 86667685d7
commit 76e14eda2f
2 changed files with 95 additions and 1 deletions
+40 -1
View File
@@ -2,7 +2,7 @@ from unittest import TestCase
from pandas import Timestamp, Timedelta
from zipline.utils.cache import CachedObject, Expired
from zipline.utils.cache import CachedObject, Expired, ExpiringCache
class CachedObjectTestCase(TestCase):
@@ -19,3 +19,42 @@ class CachedObjectTestCase(TestCase):
with self.assertRaises(Expired) as e:
obj.unwrap(after)
self.assertEqual(e.exception.args, (expiry,))
class ExpiringCacheTestCase(TestCase):
def test_expiring_cache(self):
expiry_1 = Timestamp('2014')
before_1 = expiry_1 - Timedelta('1 minute')
after_1 = expiry_1 + Timedelta('1 minute')
expiry_2 = Timestamp('2015')
after_2 = expiry_1 + Timedelta('1 minute')
expiry_3 = Timestamp('2016')
cache = ExpiringCache()
cache.set('foo', 1, expiry_1)
cache.set('bar', 2, expiry_2)
self.assertEqual(cache.get('foo', before_1), 1)
# Unwrap on expiry is allowed.
self.assertEqual(cache.get('foo', expiry_1), 1)
with self.assertRaises(KeyError) as e:
self.assertEqual(cache.get('foo', after_1))
self.assertEqual(e.exception.args, ('foo',))
# Should raise same KeyError after deletion.
with self.assertRaises(KeyError) as e:
self.assertEqual(cache.get('foo', before_1))
self.assertEqual(e.exception.args, ('foo',))
# Second value should still exist.
self.assertEqual(cache.get('bar', after_2), 2)
# Should raise similar KeyError on non-existent key.
with self.assertRaises(KeyError) as e:
self.assertEqual(cache.get('baz', expiry_3))
self.assertEqual(e.exception.args, ('baz',))
+55
View File
@@ -57,3 +57,58 @@ class CachedObject(namedtuple("_CachedObject", "value expires")):
if dt > self.expires:
raise Expired(self.expires)
return self.value
class ExpiringCache(object):
"""
A cache of multiple CachedObjects, which returns the wrapped the value
or raises and deletes the CachedObject if the value has expired.
Parameters
----------
cache : dict-like
An instance of a dict-like object which needs to support at least:
`__del__`, `__getitem__`, `__setitem__`
If `None`, than a dict is used as a default.
Methods
-------
get(self, key, dt)
Get the value of a cached object for the given `key` at `dt`, if the
CachedObject has expired then the object is removed from the cache,
and `KeyError` is raised.
set(self, key, value, expiration_dt)
Add a new `value` to the cache at `dt` wrapped in a CachedObject which
expires at `expiration_dt`.
Usage
-----
>>> from pandas import Timestamp, Timedelta
>>> expires = Timestamp('2014', tz='UTC')
>>> value = 1
>>> cache = ExpiringCache()
>>> cache.set('foo', value, expires)
>>> cache.get('foo', expires - Timedelta('1 minute'))
1
>>> cache.get('foo', expires + Timedelta('1 minute'))
Traceback (most recent call last):
...
KeyError: 'foo'
"""
def __init__(self, cache=None):
if cache is not None:
self._cache = cache
else:
self._cache = {}
def get(self, key, dt):
try:
return self._cache[key].unwrap(dt)
except Expired:
del self._cache[key]
raise KeyError(key)
def set(self, key, value, expiration_dt):
self._cache[key] = CachedObject(value, expiration_dt)