Run Ruff

river/sketch/hierarchical_heavy_hitters.py

@@ -1,10 +1,11 @@
 from __future__ import annotations
-import typing
 
 import math
+import typing
 
 from river import base
 
+
 class HierarchicalHeavyHitters(base.Base):
 
     """Full Ancestry Algorithm implementation for the Hierarchical Heavy Hitters problem.[^1]
@@ -140,7 +141,7 @@ def __init__(self):
             self.max_e = 0
             self.fe = 0
             self.m_fe = 0
-            self.children: typing.Dict[typing.Hashable, HierarchicalHeavyHitters.Node] = {}
+            self.children: typing.dict[typing.Hashable, HierarchicalHeavyHitters.Node] = {}
 
     def __init__(self, k: int, epsilon: float, parent_func: typing.Callable[[typing.Hashable, int], typing.Hashable] = None, root_value: typing.Hashable = None):
         self.k = k
@@ -219,7 +220,7 @@ def _compress_node(self, node: HierarchicalHeavyHitters.Node):
                     node.max_e = max (node.max_e, child_node.ge + child_node.delta_e)
                     del node.children[child_key]
 
-    def output(self, phi: float) -> list[typing.Tuple[typing.Hashable, int]]:
+    def output(self, phi: float) -> list[typing.tuple[typing.Hashable, int]]:
         """Generate a list of heavy hitters with frequency estimates above the given threshold."""
         result: list[tuple[typing.Hashable, int]] = []
         if self.root:

river/sketch/hyper_log_log.py

@@ -5,6 +5,7 @@
 
 from river import base
 
+
 class HyperLogLog(base.Base):
 
     """HyperLogLog algorithm for cardinality estimation.[^1][^2]
@@ -13,10 +14,10 @@ class HyperLogLog(base.Base):
     of m bytes of auxiliary memory, known as registers.
 
     Firstly, each element in the data set is hashed into a binary string, ensuring data is
-    uniformly distributed and simulating random distribution. The algorithm hashes each element 
-    into a binary string and then organizes these binary representations into registers. 
+    uniformly distributed and simulating random distribution. The algorithm hashes each element
+    into a binary string and then organizes these binary representations into registers.
 
-    HyperLogLog, represents an improvement over the original LogLog algorithm by utilizing a 
+    HyperLogLog, represents an improvement over the original LogLog algorithm by utilizing a
     technique called harmonic mean to estimate the cardinality.
 
     Parameters
@@ -59,14 +60,14 @@ class HyperLogLog(base.Base):
     ...     hyperloglog.update(i)
 
     >>> print(hyperloglog.count())
-    100 
+    100
 
     >>> hyperloglog = HyperLogLog(b=15)
 
     >>> for i in range(100):
     ...     hyperloglog.update(i%10)
 
-    >>> print(hyperloglog.count())  
+    >>> print(hyperloglog.count())
     10
 
     References

river/sketch/space_saving.py

@@ -2,14 +2,14 @@
 
 import typing
 
-
 from river import base
 
+
 class SpaceSaving(base.Base):
     """Space-Saving algorithm for finding heavy hitters.[^1]
 
     The Space-Saving algorithm is designed to find the heavy hitters in a data stream using a
-    hash map with a fixed amount of memory. It keeps track of the k most frequent items at any 
+    hash map with a fixed amount of memory. It keeps track of the k most frequent items at any
     given time, as well as their corresponding approximate frequency.
 
     Upon receiving a new item from the data stream, if it corresponds to a monitored element,
@@ -20,13 +20,13 @@ class SpaceSaving(base.Base):
     Parameters
     ----------
     k
-        The maximum number of heavy hitters to store. The higher the value of k, the higher the 
+        The maximum number of heavy hitters to store. The higher the value of k, the higher the
         accuracy of the algorithm.
 
     Attributes
     ----------
     counts : dict
-        A dictionary to store the counts of items. The keys correspond to the elements and the 
+        A dictionary to store the counts of items. The keys correspond to the elements and the
         values to their respective count.
 
     Methods
@@ -47,10 +47,10 @@ class SpaceSaving(base.Base):
     >>> from river import sketch
 
     >>> spacesaving = sketch.SpaceSaving(k=10)
-    
+
     >>> for i in range(100):
     ...     spacesaving.update(i % 10)
-    
+
     >>> print(len(spacesaving))
     10
     >>> print(spacesaving.total())
@@ -59,7 +59,7 @@ class SpaceSaving(base.Base):
     {0: 10, 1: 10, 2: 10, 3: 10, 4: 10, 5: 10, 6: 10, 7: 10, 8: 10, 9: 10}
     >>> print(spacesaving[10])
     10
-    
+
 
     References
     ----------