'''
''

import math

'''
Method to return the norm of a vector stored as a dictionary,
as described in the handout for Project 2.
'''
def norm(vec):
sum_of_squares = 0.0 # floating point to handle large numbers
for x in vec:
   sum_of_squares += vec[x] * vec[x]

return math.sqrt(sum_of_squares)

'''
Method to return the cosine similarity of sparse vectors vec1 and vec2,
stored as dictionaries as described in the handout for Project 2.
'''
def cosine_similarity(vec1, vec2):
dot_product = 0.0 # floating point to handle large numbers
for x in vec1:
   if x in vec2:
         dot_product += vec1[x] * vec2[x]

return dot_product / (norm(vec1) * norm(vec2))

'''
Method to take a string of text and obtain list of lists of words.
Preprocess the string to remove punctuation, to split the text
into sentences, and to split the sentences into words.
'''
def get_sentence_lists(text):
keep = 'abcdefghijklmnopqrstuvwxyz1234567890.'
text = text.strip().lower()
text = text.replace('\n',' ')
text = text.replace('!','.').replace('?','.')
for c in set(text):
   if c not in keep:
         text = text.replace(c, ' ')
while '..' in text:
   text = text.replace('..', '.')
while ' ' in text:
   text = text.replace(' ', ' ')
text = text.split('.')
sentence_lists = []
for sentence in text:
   sentence = sentence.strip().split()
   if len(sentence) > 0:
         sentence_lists.append(sentence)
return sentence_lists

'''
Method to get sentence lists from a series of files whose
names are provided in list filenames
'''
def get_sentence_lists_from_files(filenames):
sentence_lists = []
for filename in filenames:
   text = ""
   f = open(filename, "r", encoding="latin-1")
   for line in f:
         text += line
   sentence_lists += get_sentence_lists(text)
   f.close()
return sentence_lists

'''
Method to build semantic descriptors as a dictionary of dictionaries
from a structure of sentence lists

x &gt; length of y and First letter of y is 'A' or 'a' or x is e...

x > length of y and First letter of y is 'A' or 'a' or x is e...