v0.5.5 (#97)

* remove unnecessary int casts
* remove unnecessary float casts
* more pylint requests
* version bump

Author: barrust

.pylintrc

@@ -349,7 +349,7 @@ max-attributes=20
 min-public-methods=2
 
 # Maximum number of public methods for a class (see R0904).
-max-public-methods=20
+max-public-methods=25
 
 # Maximum number of boolean expressions in a if statement
 max-bool-expr=5

CHANGELOG.md

@@ -1,5 +1,15 @@
 # PyProbables Changelog
 
+### Version 0.5.5
+* Bloom Filters:
+    * Re-implemented the entire Bloom Filter data structure to reduce complexity and code duplication
+* Removed un-unsed imports
+* Removed unnecessary casts
+* Pylint Requested Style Changes:
+    * Use python 3 `super()`
+    * Use python 3 classes
+* Remove use of temporary variables if possible and still clear
+
 ### Version 0.5.4
 * All Probablistic Data Structures:
     * Added ability to load each `frombytes()`

probables/__init__.py

@@ -27,7 +27,7 @@
 __maintainer__ = "Tyler Barrus"
 __email__ = "[email protected]"
 __license__ = "MIT"
-__version__ = "0.5.4"
+__version__ = "0.5.5"
 __credits__ = []  # type: ignore
 __url__ = "https://github.com/barrust/pyprobables"
 __bugtrack_url__ = "https://github.com/barrust/pyprobables/issues"

probables/blooms/bloom.py

@@ -1,4 +1,4 @@
-""" BloomFilter, python implementation
+""" BloomFilter and BloomFiter on Disk, python implementation
     License: MIT
     Author: Tyler Barrus ([email protected])
     URL: https://github.com/barrust/bloom
@@ -243,9 +243,9 @@ def add_alt(self, hashes: HashResultsT) -> None:
         Args:
             hashes (list): A list of integers representing the key to insert"""
         for i in range(0, self._number_hashes):
-            k = int(hashes[i]) % self._num_bits
+            k = hashes[i] % self._num_bits
             idx = k // 8
-            self._bloom[idx] = int(self._bloom[idx]) | int((1 << (k % 8)))
+            self._bloom[idx] = self._bloom[idx] | (1 << (k % 8))
         self._els_added += 1
 
     def check(self, key: KeyT) -> bool:
@@ -364,7 +364,7 @@ def current_false_positive_rate(self) -> float:
         Return:
             float: The current false positive rate"""
         num = self.number_hashes * -1 * self.elements_added
-        dbl = num / float(self.number_bits)
+        dbl = num / self.number_bits
         exp = math.exp(dbl)
         return math.pow((1 - exp), self.number_hashes)
 
@@ -483,21 +483,21 @@ def _get_optimized_params(cls, estimated_elements: int, false_positive_rate: flo
         if number_hashes == 0:
             raise InitializationError("Bloom: Number hashes is zero; unusable parameters provided")
 
-        return t_fpr, number_hashes, int(m_bt)
+        return t_fpr, number_hashes, m_bt
 
     def _set_values(
         self, est_els: int, fpr: float, n_hashes: int, n_bits: int, hash_func: Union[HashFuncT, None]
     ) -> None:
-        self._est_elements = int(est_els)
-        self._fpr = float(fpr)
-        self._bloom_length = int(math.ceil(n_bits / self._bits_per_elm))
+        self._est_elements = est_els
+        self._fpr = fpr
+        self._bloom_length = math.ceil(n_bits / self._bits_per_elm)
         if hash_func is not None:
             self._hash_func = hash_func
         else:
             self._hash_func = default_fnv_1a
         self._els_added = 0
-        self._number_hashes = int(n_hashes)
-        self._num_bits = int(n_bits)
+        self._number_hashes = n_hashes
+        self._num_bits = n_bits
 
     def _load_hex(self, hex_string: str, hash_function: Union[HashFuncT, None] = None) -> None:
         """placeholder for loading from hex string"""

probables/blooms/countingbloom.py

@@ -57,6 +57,7 @@ def __init__(
         self._on_disk = False
         self._type = "counting"
         self._typecode = "I"
+        self._els_added = 0
         if is_valid_file(filepath):
             self._load(filepath, hash_function)
         elif is_hex_string(hex_string):
@@ -205,7 +206,7 @@ def remove_alt(self, hashes: HashResultsT, num_els: int = 1) -> int:
         min_val = min(vals)
         if min_val == UINT32_T_MAX:  # cannot remove if we have hit the max
             return UINT32_T_MAX
-        elif min_val == 0:
+        if min_val == 0:
             return 0
 
         to_remove = num_els if min_val > num_els else min_val

probables/blooms/expandingbloom.py

@@ -1,4 +1,4 @@
-""" BloomFilter, python implementation
+""" Expanding and Rotating BloomFilter, python implementations
     License: MIT
     Author: Tyler Barrus ([email protected])
     URL: https://github.com/barrust/pyprobables
@@ -17,7 +17,7 @@
 from .bloom import BloomFilter
 
 
-class ExpandingBloomFilter(object):
+class ExpandingBloomFilter:
     """Simple expanding Bloom Filter implementation for use in python; the
     Bloom Fiter will automatically expand, or grow, if the false
     positive rate is about to become greater than the desired false
@@ -55,7 +55,7 @@ def __init__(
         self.__fpr = false_positive_rate
         self.__est_elements = est_elements
         self.__hash_func = hash_function
-        self._added_elements = int(0)  # total added...
+        self._added_elements = 0  # total added...
 
         if is_valid_file(filepath):
             self.__load(filepath)

probables/countminsketch/countminsketch.py

@@ -1,4 +1,4 @@
-""" Count-Min Sketch python implementation
+""" Count-Min Sketch, Heavy Hitters, and Stream Threshold, python implementations
     License: MIT
     Author: Tyler Barrus ([email protected])
     URL: https://github.com/barrust/count-min-sketch

probables/cuckoo/countingcuckoo.py

@@ -351,7 +351,7 @@ def __bucket_decomposition(buckets, bucket_size: int):
         return arr
 
 
-class CountingCuckooBin(object):
+class CountingCuckooBin:
     """A container class for the counting cuckoo filter"""
 
     # keep it lightweight

probables/cuckoo/cuckoo.py

@@ -243,7 +243,7 @@ def expansion_rate(self) -> int:
     @expansion_rate.setter
     def expansion_rate(self, val: int):
         """set the self expand value"""
-        self.__expansion_rate = int(val)
+        self.__expansion_rate = val
 
     @property
     def error_rate(self) -> float:
@@ -278,7 +278,7 @@ def fingerprint_size(self) -> int:
     @fingerprint_size.setter
     def fingerprint_size(self, val: int):
         """set the fingerprint size"""
-        tmp = int(val)
+        tmp = val
         if not 1 <= tmp <= 4:
             msg = ("{}: fingerprint size must be between 1 and 4").format(self.__class__.__name__)
             raise ValueError(msg)

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pyprobables"
-version = "0.5.4"
+version = "0.5.5"
 description = "Probabilistic data structures in Python"
 authors = ["Tyler Barrus <[email protected]>"]
 license = "MIT"