Simple Text Summarizer

Comments:

• About 50 lines of code
• Gives reasonable results (try it out)
• tokenize need to be improved much more (better detection, stop words ...)
• split_to_sentences need to be improved much more (handle 3.2, Mr. Smith ...)
• In real life you'll need to "clean" the text (Ads, credits, ...)
  

attrgetter is fast

#!/usr/bin/env python

from operator import attrgetter
from random import shuffle

class Point:
    def __init__(self, x, y):
        self.x, self.y = x, y

def sort1(points):
    points.sort(key = lambda p: p.x)

def sort2(points):
    points.sort(key = attrgetter("x"))

if __name__ == "__main__":
    from timeit import Timer

    points1 = [Point(x, 2 * x) for x in range(100)]
    points2 = points1[:]

    num_times = 10000

    t1 = Timer("sort1(points1)", "from __main__ import sort1, points1")
    print t1.timeit(num_times)

    t2 = Timer("sort2(points2)", "from __main__ import sort2, points2")
    print t2.timeit(num_times)

$ ./attr.py
0.492087125778
0.29891705513
$

Faster and Shorter "dot" using itertools

Let's calculate the dot product of two vectors:

from itertools import starmap, izip
from operator import mul

def dot1(v1, v2):
  result = 0
  for i, value in enumerate(v1):
      result += value * v2[i]
  return result

def dot2(v1, v2):
  return sum(starmap(mul, izip(v1, v2)))

if __name__ == "__main__":
  from timeit import Timer

  num_times = 1000
  v1 = range(100)
  v2 = range(100)

  t1 = Timer("dot1(%s, %s)" % (v1, v2), "from __main__ import dot1")
  print t1.timeit(num_times) # 0.038722038269

  t2 = Timer("dot2(%s, %s)" % (v1, v2), "from __main__ import dot2")
  print t2.timeit(num_times) # 0.0260770320892

dot2 is faster and shorter, however dot1 is more readable - my vote goes to dot2.