Question

Python

Modify your recommendation program so that it reports the titles of the works rather than their file names. To do this, write a program that reads in the titles.txt file and creates a dictionary that looks up the title using the file name. This dictionary should then be used to report the works by their title instead of their file name.

Script to use:

import os
import math

def count_word(table, word):
'for the word entry in the table, increment its count or init to 1'
if word in table:
table[word] += 1
else:
# initialize count of word to 1
table[word] = 1

def analyze():
'''read all texts from the docs folder, report similarity comparisons
among all pairs'''
  
doc_table = dict()
word_set = set()
os.chdir('docs')
fileList = os.listdir()
for fname in fileList:
print("Opening " + fname)
fd = open(fname, "r", encoding="utf8")
doc_table[fname] = dict()
data = fd.read()
print("splitting")
dataList = data.split()
print("{} has {} words". format(fname, len(dataList)))
for word in dataList:
word_set.add(word)
count_word(doc_table[fname], word)
fd.close()
os.chdir('..') # return to parent directory

for fname in fileList:
for fname2 in fileList:
sim = similarity(doc_table[fname], doc_table[fname2], word_set)
print("{:.2f} : {} vs. {}".format(sim, fname, fname2))

def build_title_file():
"creates titles.txt based on works in the docs folder"
tfd = open("titles.txt", "w")
os.chdir('docs')
fileList = os.listdir()
for fname in fileList:
print("Opening " + fname)
fd = open(fname, "r", encoding="utf8")
for line in fd:
if "Title: " in line:
tfd.write(fname + "\n")
tfd.write(line[7:])
break
fd.close()
os.chdir("..") # return to parent directory
tfd.close()
  

def similarity(tableA, tableB, words):
'return cosine similarity between tableA and tableB over all words'
ab = 0
a2 = 0
b2 = 0
for w in words:
ab += tableA.get(w, 0) * tableB.get(w, 0)
a2 += tableA.get(w, 0) * tableA.get(w, 0)
b2 += tableB.get(w, 0) * tableB.get(w, 0)
return ab / (math.sqrt(a2) * math.sqrt(b2))

Titles.txt file

alice_in_wonderland.txt
Aliceís Adventures in Wonderland
dracula.txt
Dracula
frankenstein.txt
Frankenstein
jane_eyre.txt
Jane Eyre
moby_dick.txt
Moby Dick; or The Whale
pride_and_prejudice.txt
Pride and Prejudice
tale_of_two_cities.txt
A Tale of Two Cities
udolpho.txt
The Mysteries of Udolpho
wizard_of_oz.txt
The Wonderful Wizard of Oz

Answer 1

dictionary contents: ('alice_in_wonderland.txt': 'AliceAlxads Adventures in Wonderland', 'dracula.txt': 'Drac a', frankenstein.txt' 'Frankenstein', 'jane_eyre.txt' 'Jane Eyre', 'moby _dick.txt': Moby Dick: or The Whale', 'pride_and_prejudice.txt 'Pride and Prejudice', 'tale_of_two cities.txt' 'A Tale of Two cities', 'udolpho.txt' 'The Mysteries of Udolpho', 'wizard of_oz.txt' 'The Wonderful Wizard of oz') Keys in dictionary: dict_keys (['alice_in_wonderland.txt', 'dracula.txt', 'frankenstein.txt',"jane_eyre.txt , 'moby_dick.txt', 'pride_and_prejudice.txt','tale_of_two_cities.txt', 'udolpho.txt', 'w izard of oz.txt') Values in dictionary: dict_values (['AliceAlxads Adventures in Wonderland', 'Dracula', Frankenstein', 'Jane Ey re', 'Moby Dick: or The Whale', 'Pride and Prejudice', 'A Tale of Two cities', 'The Myste ries of Udolpho', 'The Wonderful Wizard of oz')

01.py-C/Users/MANI KANTA/Desktop/test/Ol.py (3.7.2) File Edit Format Run Options Window Help if "Title: " in line: tfd.write (fname+ "\n") tfd.write (line[7:1) break fd.close () os.chdir("..") # return to parent directory tfd.close () def similarity (tableA, tableB, words): return cosine similarity between tableA and tableB over all words" a20 b2 = 0 for w in words: ab += tableA . get (w, 0) * tableB . get(w, 0) a2 += tableA . get (w, 0) * tableA . get(w, 0) 62 += tableB . get (w, 0) * tableB . get(w, 0) return ab (math.sqrt (a2) * math.sqrt (b2)) def CreateAndFillDictionary): titlesFile- open ("docs/titles.txt", "r") dict={ } cnt-0; for line in titlesFile.read).splitlines): key-line else: value-line dict [key]-value cnt-cnt+1 print ("dictionary contents: n",dict) print(" nKeys in dictionary:\n",dict.keys ) print("nValues in dictionary: In",dict.values )) #execution starts here CreateAndFillDictionary()

titles.tt X 1 alice in wonderland.txt 2 Aliceis Adventures in Wonderland 3 dracula.txt 4 Dracula 5 frankenstein.txt 6 Frankenstein 7 jane eyre.txt 8 Jane Eyre 9 moby dick.txt 10 Moby Dick; or The Whale 11 pride and prejudice.txt 12 Pride and Prejudice 13 tale of two cities.txt 14 A Tale of Two Cities IS udolpho. txt 16 The Mysteries of Udolpho 18 The Wonderful Wizard of Oz

#save the following in filename.py

import os
import math

def count_word(table, word):
'for the word entry in the table, increment its count or init to 1'
if word in table:
table[word] += 1
else:
# initialize count of word to 1
table[word] = 1

def analyze():
'''read all texts from the docs folder, report similarity comparisons
among all pairs'''
  
doc_table = dict()
word_set = set()
os.chdir('docs')
fileList = os.listdir()
for fname in fileList:
print("Opening " + fname)
fd = open(fname, "r", encoding="utf8")
doc_table[fname] = dict()
data = fd.read()
print("splitting")
dataList = data.split()
print("{} has {} words". format(fname, len(dataList)))
for word in dataList:
word_set.add(word)
count_word(doc_table[fname], word)
fd.close()
os.chdir('..') # return to parent directory
  
for fname in fileList:
for fname2 in fileList:
sim = similarity(doc_table[fname], doc_table[fname2], word_set)
print("{:.2f} : {} vs. {}".format(sim, fname, fname2))
  
def build_title_file():
"creates titles.txt based on works in the docs folder"
tfd = open("titles.txt", "w")
os.chdir('docs')
fileList = os.listdir()
for fname in fileList:
print("Opening " + fname)
fd = open(fname, "r", encoding="utf8")
for line in fd:
if "Title: " in line:
tfd.write(fname + "\n")
tfd.write(line[7:])
break
fd.close()
os.chdir("..") # return to parent directory
tfd.close()
  

def similarity(tableA, tableB, words):
'return cosine similarity between tableA and tableB over all words'
ab = 0
a2 = 0
b2 = 0
for w in words:
ab += tableA.get(w, 0) * tableB.get(w, 0)
a2 += tableA.get(w, 0) * tableA.get(w, 0)
b2 += tableB.get(w, 0) * tableB.get(w, 0)
return ab / (math.sqrt(a2) * math.sqrt(b2))

def CreateAndFillDictionary():
titlesFile = open("docs/titles.txt","r")
dict={}
cnt=0;
for line in titlesFile.read().splitlines():
if cnt%2==0:
key=line
else:
value=line
dict[key]=value
cnt=cnt+1
print("dictionary contents: \n",dict)
print("\nKeys in dictionary:\n",dict.keys())
print("\nValues in dictionary:\n",dict.values())

#execution starts here
CreateAndFillDictionary()