A python script to print a histogram

histo.py

#!/usr/bin/env python

"""
Print a histogram of word distribution. Takes single word per line from stdin
and prints dtrace output like histogram:

$ echo "some text with some text fields as text" | tr -s '[:space:]' '\n' | ./histo.py 10
                    text |      3 | ##################################################
                    some |      2 | #################################
                    with |      1 | ################
                      as |      1 | ################
                  fields |      1 | ################
"""
import sys
import math

TERMINAL_SIZE = 50

# lambda used for extraxting second field of a pair
second_field = lambda x: x[1]

def histo(data, top=-1):

  # take all non empty records
  records = filter( lambda x : len(x) > 0, map(lambda x : x.strip(), data))

  values = {}

  # build a dictionary of { key : hit_count }
  for r in records:
    values[r] = values.get(r, 0) + 1

  # convert into list of pairs: (key:hit_count)
  values_as_pairs = values.items()

  # find the pair with highest hit_count and take the value
  max_value = max(values_as_pairs, key=second_field)[1]

  # sort in decending order ant take first top records
  for k,v in sorted(values_as_pairs, key=second_field, reverse=True)[0:top]:
    print("%24s | %6d | %s" % (k.strip(), v, '#'*int(math.floor((v*TERMINAL_SIZE)/max_value))))


if __name__ == '__main__':
  top = -1
  if len(sys.argv) > 1:
    top = int(sys.argv[1])

  histo(sys.stdin.readlines(), top)