for line in docs:
if re.search(term, line, flags=re.I):
list_fact.append(line)
return list_fact
def sent_to_words(sent):
# splits sentence to words, filtering out non-alphabetical terms
words = nltk.word_tokenize(sent)
words_filtered = filter(lambda x: x.isalpha(), words)
return words_filtered
movie_name = []
movie_dict = {}
for name, vote in zip(read_predata()['movie'], read_predata()['votes']):
movie_name.append(name)
movie_dict[name] = vote
index_orig_forms = build_inverted_index_orig_forms(movie_name)
vocabulary = Counter()
for name in movie_name:
for word in sent_to_words(name.lower()):
vocabulary[word] += 1
WORDS = vocabulary
# Norvig's spellchecker
def P(word, N=sum(WORDS.values())):
"""Probability of `word`."""
def title_handler(query):
data = query.data
movie_name = data.replace('*', '')
# print('up', movie_name)
result = recommendations(movie_name)
one = result.pop(0)
save_one.append(one)
# print(len(save_one))
# print(save_one)
if data.startswith('*'):
markups = telebot.types.InlineKeyboardMarkup()
for idx in result:
markups.add(
telebot.types.InlineKeyboardButton(
text='{} ({})'.format(read_predata()['movie'].values[idx],
read_predata()['year'].values[idx]),
callback_data=str(read_predata()['movie'].values[idx])))
reply = str("Top 5 recommended movies to *{}* are:".format(movie_name))
markups.add(
telebot.types.InlineKeyboardButton(text="<<Try Again>>",
callback_data="back"))
bot.edit_message_text(reply,
query.message.chat.id,
query.message.message_id,
parse_mode="Markdown",
reply_markup=markups)
else:
markups = telebot.types.InlineKeyboardMarkup()
stars = ', '.join(read_predata()['stars'].values[one])
reply = "*{} ({})*".format(movie_name, read_predata()['year'].values[one]) + "\n" \
"{} | {}".format(read_predata()['certificate'].values[one], read_predata()['duration'].values[one]) + "\n" \
"IMDB Rating: *{}*".format(read_predata()['imdb'].values[one]) + "\n\n" \
"*Director*: {}".format(read_predata()['director'].values[one].replace("'", "")) + "\n" \
"*Stars*: {}".format(stars.replace("'", "")) + "\n" \
"*Genre*: {}".format('[' + ', '.join(read_predata()['genre'].values[one]) + ']') + "\n\n" \
"*Description*: _{}_".format(read_predata()['description'].values[one]) + "\n" \
"[Movie Poster]({})".format(read_predata()['movie_img'].values[one])
# print('down', read_predata()['movie'].values[save_one[0]])
markups.add(
telebot.types.InlineKeyboardButton(
text="<<Back>>",
callback_data=str(
'*' + read_predata()['movie'].values[save_one[0]])))
bot.edit_message_text(reply,
query.message.chat.id,
query.message.message_id,
parse_mode="Markdown",
reply_markup=markups)
def get_title_from_index(index):
return read_predata()[read_predata()['Unnamed: 0'] ==
index]["movie"].values[0]
def get_index_from_title(title):
return read_predata()[read_predata()["movie"] ==
title]["Unnamed: 0"].values[0]
# Library
from preprocess_data import read_predata
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity, linear_kernel
# count = CountVectorizer(analyzer='word', stop_words='english')
score = TfidfVectorizer(analyzer='word', stop_words='english')
# movies_matrix = count.fit_transform(read_predata()['list_bag'])
movies_matrix = score.fit_transform(read_predata()['list_bag'])
# cosine_sim = cosine_similarity(movies_matrix)
cosine_sim = linear_kernel(movies_matrix, movies_matrix)
def get_title_from_index(index):
return read_predata()[read_predata()['Unnamed: 0'] ==
index]["movie"].values[0]
def get_index_from_title(title):
return read_predata()[read_predata()["movie"] ==
title]["Unnamed: 0"].values[0]
def recommendations(movie_user_likes):
movie_index = get_index_from_title(movie_user_likes)
similar_movies = list(enumerate(cosine_sim[movie_index]))
sorted_similar_movies = sorted(similar_movies,
key=lambda x: x[1],
reverse=True)[0:6]