Fix a bug, add some testcases.

[python_utils.git] / math_utils.py

diff --git a/math_utils.py b/math_utils.py
index fa0bc0e7bdbbb7789ed56420f17d64b66375cd92..f77e0a1f2514f5a0201c81f57e9740d36d2ede47 100644 (file)
--- a/math_utils.py
+++ b/math_utils.py
@@ -1,12 +1,14 @@
 #!/usr/bin/env python3
 
+"""Mathematical helpers."""
+
 import functools
 import math
+from heapq import heappop, heappush
 from typing import List
-from heapq import heappush, heappop
 
 
-class RunningMedian:
+class RunningMedian(object):
     """A running median computer.
 
     >>> median = RunningMedian()
@@ -19,16 +21,22 @@ class RunningMedian:
     >>> median.add_number(5)
     >>> median.get_median()
     5
+    >>> median.get_mean()
+    5.2
+    >>> round(median.get_stdev(), 2)
+    6.99
     """
 
     def __init__(self):
         self.lowers, self.highers = [], []
+        self.aggregate = 0.0
 
-    def add_number(self, number):
+    def add_number(self, number: float):
         if not self.highers or number > self.highers[0]:
             heappush(self.highers, number)
         else:
             heappush(self.lowers, -number)  # for lowers we need a max heap
+        self.aggregate += number
         self.rebalance()
 
     def rebalance(self):
@@ -37,14 +45,28 @@ class RunningMedian:
         elif len(self.highers) - len(self.lowers) > 1:
             heappush(self.lowers, -heappop(self.highers))
 
-    def get_median(self):
+    def get_median(self) -> float:
         if len(self.lowers) == len(self.highers):
-            return (-self.lowers[0] + self.highers[0])/2
+            return (-self.lowers[0] + self.highers[0]) / 2
         elif len(self.lowers) > len(self.highers):
             return -self.lowers[0]
         else:
             return self.highers[0]
 
+    def get_mean(self) -> float:
+        count = len(self.lowers) + len(self.highers)
+        return self.aggregate / count
+
+    def get_stdev(self) -> float:
+        mean = self.get_mean()
+        variance = 0.0
+        for n in self.lowers:
+            n = -n
+            variance += (n - mean) ** 2
+        for n in self.highers:
+            variance += (n - mean) ** 2
+        return math.sqrt(variance)
+
 
 def gcd_floats(a: float, b: float) -> float:
     if a < b:
@@ -76,8 +98,8 @@ def truncate_float(n: float, decimals: int = 2):
     3.141
 
     """
-    assert decimals > 0 and decimals < 10
-    multiplier = 10 ** decimals
+    assert 0 < decimals < 10
+    multiplier = 10**decimals
     return int(n * multiplier) / multiplier
 
 
@@ -143,12 +165,12 @@ def is_prime(n: int) -> bool:
 
     # This is checked so that we can skip middle five numbers in below
     # loop
-    if (n % 2 == 0 or n % 3 == 0):
+    if n % 2 == 0 or n % 3 == 0:
         return False
 
     i = 5
     while i * i <= n:
-        if (n % i == 0 or n % (i + 2) == 0):
+        if n % i == 0 or n % (i + 2) == 0:
             return False
         i = i + 6
     return True
@@ -156,4 +178,5 @@ def is_prime(n: int) -> bool:
 
 if __name__ == '__main__':
     import doctest
+
     doctest.testmod()