pep8 compliance

1 files changed, 76 insertions, 54 deletions

diff --git a/data_hacks/histogram.py b/data_hacks/histogram.py
index 738b8ac..605f54e 100755
--- a/data_hacks/histogram.py
+++ b/data_hacks/histogram.py
@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-# 
+#
 # Copyright 2010 Bitly
 #
 # Licensed under the Apache License, Version 2.0 (the "License"); you may
@@ -31,16 +31,17 @@ import math
 from optparse import OptionParser
 from collections import namedtuple
 
+
 class MVSD(object):
-    """ A class that calculates a running Mean / Variance / Standard Deviation"""
+    "A class that calculates a running Mean / Variance / Standard Deviation"
     def __init__(self):
         self.is_started = False
-        self.ss = Decimal(0) # (running) sum of square deviations from mean
-        self.m = Decimal(0) # (running) mean
-        self.total_w = Decimal(0) # weight of items seen
-        
+        self.ss = Decimal(0)  # (running) sum of square deviations from mean
+        self.m = Decimal(0)  # (running) mean
+        self.total_w = Decimal(0)  # weight of items seen
+
     def add(self, x, w=1):
-        """ add another datapoint to the Mean / Variance / Standard Deviation"""
+        "add another datapoint to the Mean / Variance / Standard Deviation"
         if not isinstance(x, Decimal):
             x = Decimal(x)
         if not self.is_started:
@@ -50,32 +51,33 @@ class MVSD(object):
             self.is_started = True
         else:
             temp_w = self.total_w + w
-            self.ss += (self.total_w * w * (x - self.m) * (x - self.m )) / temp_w
-            self.m += (x - self.m) / temp_w 
+            self.ss += (self.total_w * w * (x - self.m) *
+                        (x - self.m)) / temp_w
+            self.m += (x - self.m) / temp_w
             self.total_w = temp_w
-        
-        # print "added %-2d mean=%0.2f var=%0.2f std=%0.2f" % (x, self.mean(), self.var(), self.sd())
-        
+
     def var(self):
         return self.ss / self.total_w
-    
+
     def sd(self):
         return math.sqrt(self.var())
-    
+
     def mean(self):
         return self.m
 
 DataPoint = namedtuple('DataPoint', ['value', 'count'])
 
+
 def test_mvsd():
     mvsd = MVSD()
     for x in range(10):
         mvsd.add(x)
-    
+
     assert '%.2f' % mvsd.mean() == "4.50"
     assert '%.2f' % mvsd.var() == "8.25"
     assert '%.14f' % mvsd.sd() == "2.87228132326901"
 
+
 def load_stream(input_stream, agg_value_key, agg_key_value):
     for line in input_stream:
         clean_line = line.strip()
@@ -97,29 +99,34 @@ def load_stream(input_stream, agg_value_key, agg_key_value):
             logging.exception('failed %r', line)
             print >>sys.stderr, "invalid line %r" % line
 
+
 def median(values, key=None):
     if not key:
-        key= lambda x: x
+        key = None  # map and sort accept None as identity
     length = len(values)
-    if length%2:
+    if length % 2:
         median_indeces = [length/2]
     else:
         median_indeces = [length/2-1, length/2]
 
     values = sorted(values, key=key)
-    return sum(map(key, [values[i] for i in median_indeces])) / len(median_indeces)
+    return sum(map(key,
+                   [values[i] for i in median_indeces])) / len(median_indeces)
+
 
 def test_median():
-    assert 6 == median([8,7,9,1,2,6,3]) # odd-sized list
-    assert 4 == median([4,5,2,1,9,10]) # even-sized int list. (4+5)/2 = 4
-    assert "4.50" == "%.2f" % median([4.0,5,2,1,9,10]) #even-sized float list. (4.0+5)/2 = 4.5
+    assert 6 == median([8, 7, 9, 1, 2, 6, 3])  # odd-sized list
+    assert 4 == median([4, 5, 2, 1, 9, 10])  # even-sized int list. (4+5)/2 = 4
+    # even-sized float list. (4.0+5)/2 = 4.5
+    assert "4.50" == "%.2f" % median([4.0, 5, 2, 1, 9, 10])
 
 
 def histogram(stream, options):
     """
-    Loop over the stream and add each entry to the dataset, printing out at the end
-    
-    stream yields Decimal() 
+    Loop over the stream and add each entry to the dataset, printing out at the
+    end.
+
+    stream yields Decimal()
     """
     if not options.min or not options.max:
         # glob the iterator here so we can do min/max on it
@@ -127,7 +134,7 @@ def histogram(stream, options):
     else:
         data = stream
     bucket_scale = 1
-    
+
     if options.min:
         min_v = Decimal(options.min)
     else:
@@ -154,7 +161,7 @@ def histogram(stream, options):
         # if the last value is smaller than the maximum, replace it
         if bound_sort[-1] < max_v:
             bound_sort[-1] = max_v
-        
+
         # iterate through the sorted list and append to boundaries
         for x in bound_sort:
             if x >= min_v and x <= max_v:
@@ -163,14 +170,18 @@ def histogram(stream, options):
                 boundaries.append(max_v)
                 break
 
-        # beware: the min_v is not included in the boundaries, so no need to do a -1!
+        # beware: the min_v is not included in the boundaries,
+        # so no need to do a -1!
         bucket_counts = [0 for x in range(len(boundaries))]
         buckets = len(boundaries)
     elif options.logscale:
         buckets = options.buckets and int(options.buckets) or 10
         if buckets <= 0:
             raise ValueError('# of buckets must be > 0')
-        fx = lambda k, n: n/(2**(k+1)-1)
+
+        def fx(k, n):
+            return n/(2**(k+1)-1)
+
         def log_steps(k, n):
             "k logarithmic steps whose sum is n"
             x = fx(k-1, n)
@@ -195,7 +206,7 @@ def histogram(stream, options):
     mvsd = MVSD()
     accepted_data = []
     for record in data:
-        samples +=  record.count
+        samples += record.count
         if options.mvsd:
             mvsd.add(record.value, record.count)
             accepted_data.append(record)
@@ -207,16 +218,20 @@ def histogram(stream, options):
             if record.value <= boundary:
                 bucket_counts[bucket_postion] += record.count
                 break
-    
+
     # auto-pick the hash scale
     if max(bucket_counts) > 75:
         bucket_scale = int(max(bucket_counts) / 75)
-    
-    print "# NumSamples = %d; Min = %0.2f; Max = %0.2f" % (samples, min_v, max_v)
+
+    print("# NumSamples = %d; Min = %0.2f; Max = %0.2f" %
+          (samples, min_v, max_v))
     if skipped:
-        print "# %d value%s outside of min/max" % (skipped, skipped > 1 and 's' or '')
+        print("# %d value%s outside of min/max" %
+              (skipped, skipped > 1 and 's' or ''))
     if options.mvsd:
-        print "# Mean = %f; Variance = %f; SD = %f; Median %f" % (mvsd.mean(), mvsd.var(), mvsd.sd(), median(accepted_data, key=lambda x: x.value))
+        print("# Mean = %f; Variance = %f; SD = %f; Median %f" %
+              (mvsd.mean(), mvsd.var(), mvsd.sd(),
+               median(accepted_data, key=lambda x: x.value)))
     print "# each ∎ represents a count of %d" % bucket_scale
     bucket_min = min_v
     bucket_max = min_v
@@ -230,33 +245,40 @@ def histogram(stream, options):
         if bucket_count:
             star_count = bucket_count / bucket_scale
         if options.percentage:
-            percentage = " (%0.2f%%)" % (100 * Decimal(bucket_count) / Decimal(samples))
-        print format_string % (bucket_min, bucket_max, bucket_count, '∎' * star_count, percentage)
-        
+            percentage = " (%0.2f%%)" % (100 * Decimal(bucket_count) /
+                                         Decimal(samples))
+        print format_string % (bucket_min, bucket_max, bucket_count, '∎' *
+                               star_count, percentage)
+
 
 if __name__ == "__main__":
     parser = OptionParser()
     parser.usage = "cat data | %prog [options]"
-    parser.add_option("-a", "--agg", dest="agg_value_key", default=False, action="store_true",
-                        help="Two column input format, space seperated with value<space>key")
-    parser.add_option("-A", "--agg-key-value", dest="agg_key_value", default=False, action="store_true",
-                        help="Two column input format, space seperated with key<space>value")
+    parser.add_option("-a", "--agg", dest="agg_value_key", default=False,
+                      action="store_true", help="Two column input format, " +
+                      "space seperated with value<space>key")
+    parser.add_option("-A", "--agg-key-value", dest="agg_key_value",
+                      default=False, action="store_true", help="Two column " +
+                      "input format, space seperated with key<space>value")
     parser.add_option("-m", "--min", dest="min",
-                        help="minimum value for graph")
+                      help="minimum value for graph")
     parser.add_option("-x", "--max", dest="max",
-                        help="maximum value for graph")
+                      help="maximum value for graph")
     parser.add_option("-b", "--buckets", dest="buckets",
-                        help="Number of buckets to use for the histogram")
-    parser.add_option("-l", "--logscale", dest="logscale", default=False, action="store_true",
-                        help="Buckets grow in logarithmic scale")
+                      help="Number of buckets to use for the histogram")
+    parser.add_option("-l", "--logscale", dest="logscale", default=False,
+                      action="store_true",
+                      help="Buckets grow in logarithmic scale")
     parser.add_option("-B", "--custom-buckets", dest="custbuckets",
-                        help="Comma seperated list of bucket edges for the histogram")
-    parser.add_option("--no-mvsd", dest="mvsd", action="store_false", default=True,
-                        help="Disable the calculation of Mean, Variance and SD (improves performance)")
+                      help="Comma seperated list of bucket " +
+                      "edges for the histogram")
+    parser.add_option("--no-mvsd", dest="mvsd", action="store_false",
+                      default=True, help="Disable the calculation of Mean, " +
+                      "Variance and SD (improves performance)")
     parser.add_option("-f", "--bucket-format", dest="format", default="%10.4f",
-                        help="format for bucket numbers")
-    parser.add_option("-p", "--percentage", dest="percentage", default=False, action="store_true",
-                        help="List percentage for each bar")
+                      help="format for bucket numbers")
+    parser.add_option("-p", "--percentage", dest="percentage", default=False,
+                      action="store_true", help="List percentage for each bar")
 
     (options, args) = parser.parse_args()
     if sys.stdin.isatty():
@@ -264,5 +286,5 @@ if __name__ == "__main__":
         parser.print_usage()
         print "for more help use --help"
         sys.exit(1)
-    histogram(load_stream(sys.stdin, options.agg_value_key, options.agg_key_value), options)
-
+    histogram(load_stream(sys.stdin, options.agg_value_key,
+                          options.agg_key_value), options)