0.1.2 (#29)

* Counting Bloom Filter
* Fix for pypi installation

Author: barrust

CHANGELOG.md

@@ -1,5 +1,13 @@
 # PyProbables Changelog
 
+### Version 0.1.2:
+* Counting Cuckoo Filter
+    * Basic functionality: add, remove, check
+    * Expand
+    * Import / Export
+* Fix and tests for utility functions
+* Fix package build
+
 ### Version 0.1.1:
 * CuckooFilter
     * Import / Export functionality

docs/source/code.rst

@@ -56,9 +56,17 @@ membership testing. Cuckoo filters support insertion, deletion, and lookup of
 elements with low overhead with few false positive results.
 `Further Reading <https://www.cs.cmu.edu/~dga/papers/cuckoo-conext2014.pdf>`__
 
+CuckooFilter
++++++++++++++++++++++++++++++++
 .. autoclass:: probables.CuckooFilter
     :members:
 
+CountingCuckooFilter
++++++++++++++++++++++++++++++++
+.. autoclass:: probables.CountingCuckooFilter
+    :members:
+    :inherited-members:
+
 
 Count-Min Sketches
 ------------------

probables/__init__.py

@@ -1,22 +1,22 @@
 ''' pyprobables module '''
 from __future__ import (unicode_literals, absolute_import, print_function)
-from .blooms import (BloomFilter, BloomFilterOnDisk, CountingBloomFilter)
-from .countminsketch import (CountMinSketch, HeavyHitters, StreamThreshold,
-                             CountMeanSketch, CountMeanMinSketch)
-from .cuckoo import (CuckooFilter)
-from .exceptions import (InitializationError, NotSupportedError,
-                         ProbablesBaseException, CuckooFilterFullError)
+from . blooms import (BloomFilter, BloomFilterOnDisk, CountingBloomFilter)
+from . countminsketch import (CountMinSketch, HeavyHitters, StreamThreshold,
+                              CountMeanSketch, CountMeanMinSketch)
+from . cuckoo import (CuckooFilter, CountingCuckooFilter)
+from . exceptions import (InitializationError, NotSupportedError,
+                          ProbablesBaseException, CuckooFilterFullError)
 
 __author__ = 'Tyler Barrus'
 __maintainer__ = 'Tyler Barrus'
 __email__ = '[email protected]'
 __license__ = 'MIT'
-__version__ = '0.1.1'
+__version__ = '0.1.2'
 __credits__ = []
 __url__ = 'https://github.com/barrust/pyprobables'
 __bugtrack_url__ = 'https://github.com/barrust/pyprobables/issues'
 
 __all__ = ['BloomFilter', 'BloomFilterOnDisk', 'CountMinSketch',
            'HeavyHitters', 'StreamThreshold', 'CountMeanSketch',
            'CountMeanMinSketch', 'CountingBloomFilter', 'CuckooFilter',
-           'CuckooFilterFullError']
+           'CuckooFilterFullError', 'CountingCuckooFilter']

probables/blooms/__init__.py

@@ -1,6 +1,6 @@
 ''' Bloom Filter based data structures '''
 from __future__ import (unicode_literals, absolute_import, print_function)
-from .bloom import (BloomFilter, BloomFilterOnDisk)
-from .countingbloom import (CountingBloomFilter)
+from . bloom import (BloomFilter, BloomFilterOnDisk)
+from . countingbloom import (CountingBloomFilter)
 
 __all__ = ['BloomFilter', 'BloomFilterOnDisk', 'CountingBloomFilter']

probables/blooms/countingbloom.py

@@ -115,11 +115,11 @@ def add_alt(self, hashes, num_els=1):
             j = self._get_element(k)
             tmp = j + num_els
             if tmp <= UINT32_T_MAX:
-                self._bloom[k] = self._get_set_element(j + num_els)
+                self.bloom[k] = self._get_set_element(j + num_els)
             else:
-                self._bloom[k] = UINT32_T_MAX
-            if self._bloom[k] < res:
-                res = self._bloom[k]
+                self.bloom[k] = UINT32_T_MAX
+            if self.bloom[k] < res:
+                res = self.bloom[k]
         self.elements_added += num_els
         if self.elements_added > UINT64_T_MAX:
             self.elements_added = UINT64_T_MAX
@@ -191,7 +191,7 @@ def remove_alt(self, hashes, num_els=1):
         for i in list(range(self.number_hashes)):
             k = int(hashes[i]) % self.number_bits
             j = self._get_element(k)
-            self._bloom[k] = self._get_set_element(j - t_num_els)
+            self.bloom[k] = self._get_set_element(j - t_num_els)
         self.elements_added -= t_num_els
         return tmp - t_num_els
 
@@ -223,7 +223,7 @@ def intersection(self, second):
         for i in list(range(self.bloom_length)):
             if self._get_element(i) > 0 and second._get_element(i) > 0:
                 tmp = self._get_element(i) + second._get_element(i)
-                res._bloom[i] = self._get_set_element(tmp)
+                res.bloom[i] = self._get_set_element(tmp)
         res.elements_added = res.estimate_elements()
         return res
 
@@ -287,7 +287,7 @@ def union(self, second):
                                   hash_function=self.hash_function)
         for i in list(range(self.bloom_length)):
             tmp = self._get_element(i) + second._get_element(i)
-            res._bloom[i] = self._get_set_element(tmp)
+            res.bloom[i] = self._get_set_element(tmp)
         res.elements_added = res.estimate_elements()
         return res
 

probables/countminsketch/__init__.py

@@ -1,7 +1,7 @@
 ''' count-min sketch submodule '''
 from __future__ import (unicode_literals, absolute_import, print_function)
-from .countminsketch import (CountMinSketch, HeavyHitters, StreamThreshold,
-                             CountMeanSketch, CountMeanMinSketch)
+from . countminsketch import (CountMinSketch, HeavyHitters, StreamThreshold,
+                              CountMeanSketch, CountMeanMinSketch)
 
 
 __all__ = ['CountMinSketch', 'HeavyHitters', 'StreamThreshold',

probables/cuckoo/__init__.py

@@ -1,3 +1,4 @@
 ''' Cuckoo Filter data structures '''
 from __future__ import (unicode_literals, absolute_import, print_function)
 from . cuckoo import (CuckooFilter)
+from . countingcuckoo import (CountingCuckooFilter)