16-03-2011 Laura Amy Laurier

Simple Statistics

Legal terminology present the language used in terms and conditions policies often We want to highlight the ambiguity of legal terminology

Word frequency distribution

from nltk import FreqDist
from matplotlib import *
import urllib2

t = "** 20.1 ** SITE shall not be responsible for any failure to perform due to unforeseen circumstances or to causes beyond our reasonable control, including but not limited to: acts of God, such as fire, flood, earthquakes, hurricanes, tropical storms or other natural disasters; war, riot, arson, embargoes, acts of civil or military authority, or terrorism; fiber cuts; strikes, or shortages in transportation, facilities, fuel, energy, labor or materials; failure of the telecommunications or information services infrastructure; hacking, SPAM, or any failure of a computer, server or software, including Y2K errors or omissions, for so long as such event continues to delay the SITE's performance.   "

words = t.split()

fdist = FreqDist(words)

voc = fdist.keys() 

print voc[:10]

#fdist.plot(50, cumulative=True)

from nltk import FreqDist
from matplotlib import *
import urllib2
from nltk.corpus import stopwords
n
english_stops = set(stopwords.words("english"))

 
t = "** 20.1 ** SITE shall not be responsible for any failure to perform due to unforeseen circumstances or to causes beyond our reasonable control, including but not limited to: acts of God, such as fire, flood, earthquakes, hurricanes, tropical storms or other natural disasters; war, riot, arson, embargoes, acts of civil or military authority, or terrorism; fiber cuts; strikes, or shortages in transportation, facilities, fuel, energy, labor or materials; failure of the telecommunications or information services infrastructure; hacking, SPAM, or any failure of a computer, server or software, including Y2K errors or omissions, for so long as such event continues to delay the SITE's performance.   "
 
words = t.split()
words = [w for w in words if w not in english_stops]
fdist = FreqDist(words)
 
voc = fdist.keys() 
 
print voc[:10]