add basic histogram stats filter

saucebrush/stats.py

@@ -7,7 +7,9 @@ def _average(values):
     
         :param values: an iterable of ints or floats to average
     """
-    return sum(values) / float(len(values))
+    value_count = len(values)
+    if len(values) > 0:
+        return sum(values) / float(value_count)
 
 def _median(values):
     """ Calculate the median of a list of values.
@@ -174,4 +176,28 @@ class StandardDeviation(StatsFilter):
             :param population: True if values represents entire population,
                 False if values is a sample. Default: False
         """
-        return _stddev(self._values, population)
+        return _stddev(self._values, population)
+
+class Histogram(StatsFilter):
+    
+    label_length = 6
+    
+    def __init__(self, field, **kwargs):
+        super(Histogram, self).__init__(field, **kwargs)
+        self._data = {}
+    
+    def process_field(self, item):
+        if item not in self._data:
+            self._data[item] = 0
+        self._data[item] += 1
+    
+    def value(self):
+        return self._data.copy()
+        
+    def __str__(self):
+        output = ""
+        for key in sorted(self._data.keys()):
+            key_str = str(key).ljust(self.label_length)[:self.label_length]
+            output += "%s %s\n" % (key_str, "*" * self._data[key])
+        return output
+        

saucebrush/tests/stats.py

@@ -1,5 +1,5 @@
 import unittest
-from saucebrush.stats import Sum, Average, Median, MinMax, StandardDeviation
+from saucebrush.stats import Sum, Average, Median, MinMax, StandardDeviation, Histogram
 
 class StatsTestCase(unittest.TestCase):
 
@@ -41,6 +41,12 @@ class StatsTestCase(unittest.TestCase):
         self.assertEqual(fltr.median(), 5)
         self.assertEqual(fltr.value(), (55.4346462061408, 3073.0))
         self.assertEqual(fltr.value(True), (45.2621990922521, 2048.6666666666665))
+    
+    def test_histogram(self):
+        fltr = Histogram('a')
+        fltr.label_length = 1
+        list(fltr.attach(self._simple_data()))
+        self.assertEqual(str(fltr), "1 **\n5 *\n")
 
 if __name__ == '__main__':
     unittest.main()