\n",
2174 | "\n",
2187 | "\n",
2188 | " \n",
2189 | "
\n",
2229 | "
"
2230 | ],
2231 | "text/plain": [
2232 | " movie_id title \\\n",
2233 | "0 19995 Avatar \n",
2234 | "1 285 Pirates of the Caribbean: At World's End \n",
2235 | "2 206647 Spectre \n",
2236 | "3 49026 The Dark Knight Rises \n",
2237 | "4 49529 John Carter \n",
2238 | "\n",
2239 | " tags \n",
2240 | "0 In the 22nd century, a paraplegic Marine is di... \n",
2241 | "1 Captain Barbossa, long believed to be dead, ha... \n",
2242 | "2 A cryptic message from Bond’s past sends him o... \n",
2243 | "3 Following the death of District Attorney Harve... \n",
2244 | "4 John Carter is a war-weary, former military ca... "
2245 | ]
2246 | },
2247 | "execution_count": 191,
2248 | "metadata": {},
2249 | "output_type": "execute_result"
2250 | }
2251 | ],
2252 | "source": [
2253 | "# Converting list to str\n",
2254 | "new_df['tags'] = new_df['tags'].apply(lambda x: \" \".join(x))\n",
2255 | "new_df.head()"
2256 | ]
2257 | },
2258 | {
2259 | "cell_type": "code",
2260 | "execution_count": 192,
2261 | "metadata": {},
2262 | "outputs": [
2263 | {
2264 | "data": {
2265 | "text/plain": [
2266 | "'In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes torn between following orders and protecting an alien civilization. Action Adventure Fantasy ScienceFiction cultureclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi marine soldier battle loveaffair antiwar powerrelations mindandsoul 3d SamWorthington ZoeSaldana SigourneyWeaver JamesCameron'"
2267 | ]
2268 | },
2269 | "execution_count": 192,
2270 | "metadata": {},
2271 | "output_type": "execute_result"
2272 | }
2273 | ],
2274 | "source": [
2275 | "new_df.iloc[0]['tags']"
2276 | ]
2277 | },
2278 | {
2279 | "cell_type": "code",
2280 | "execution_count": 193,
2281 | "metadata": {},
2282 | "outputs": [
2283 | {
2284 | "name": "stderr",
2285 | "output_type": "stream",
2286 | "text": [
2287 | "| \n", 2191 | " | movie_id | \n", 2192 | "title | \n", 2193 | "tags | \n", 2194 | "
|---|---|---|---|
| 0 | \n", 2199 | "19995 | \n", 2200 | "Avatar | \n", 2201 | "In the 22nd century, a paraplegic Marine is di... | \n", 2202 | "
| 1 | \n", 2205 | "285 | \n", 2206 | "Pirates of the Caribbean: At World's End | \n", 2207 | "Captain Barbossa, long believed to be dead, ha... | \n", 2208 | "
| 2 | \n", 2211 | "206647 | \n", 2212 | "Spectre | \n", 2213 | "A cryptic message from Bond’s past sends him o... | \n", 2214 | "
| 3 | \n", 2217 | "49026 | \n", 2218 | "The Dark Knight Rises | \n", 2219 | "Following the death of District Attorney Harve... | \n", 2220 | "
| 4 | \n", 2223 | "49529 | \n", 2224 | "John Carter | \n", 2225 | "John Carter is a war-weary, former military ca... | \n", 2226 | "
\n",
2310 | "\n",
2323 | "\n",
2324 | " \n",
2325 | "
\n",
2365 | "
"
2366 | ],
2367 | "text/plain": [
2368 | " movie_id title \\\n",
2369 | "0 19995 Avatar \n",
2370 | "1 285 Pirates of the Caribbean: At World's End \n",
2371 | "2 206647 Spectre \n",
2372 | "3 49026 The Dark Knight Rises \n",
2373 | "4 49529 John Carter \n",
2374 | "\n",
2375 | " tags \n",
2376 | "0 in the 22nd century, a paraplegic marine is di... \n",
2377 | "1 captain barbossa, long believed to be dead, ha... \n",
2378 | "2 a cryptic message from bond’s past sends him o... \n",
2379 | "3 following the death of district attorney harve... \n",
2380 | "4 john carter is a war-weary, former military ca... "
2381 | ]
2382 | },
2383 | "execution_count": 194,
2384 | "metadata": {},
2385 | "output_type": "execute_result"
2386 | }
2387 | ],
2388 | "source": [
2389 | "new_df.head()"
2390 | ]
2391 | },
2392 | {
2393 | "cell_type": "code",
2394 | "execution_count": 195,
2395 | "metadata": {},
2396 | "outputs": [
2397 | {
2398 | "data": {
2399 | "text/plain": [
2400 | "'in the 22nd century, a paraplegic marine is dispatched to the moon pandora on a unique mission, but becomes torn between following orders and protecting an alien civilization. action adventure fantasy sciencefiction cultureclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi marine soldier battle loveaffair antiwar powerrelations mindandsoul 3d samworthington zoesaldana sigourneyweaver jamescameron'"
2401 | ]
2402 | },
2403 | "execution_count": 195,
2404 | "metadata": {},
2405 | "output_type": "execute_result"
2406 | }
2407 | ],
2408 | "source": [
2409 | "new_df.iloc[0]['tags']"
2410 | ]
2411 | },
2412 | {
2413 | "cell_type": "code",
2414 | "execution_count": 196,
2415 | "metadata": {},
2416 | "outputs": [],
2417 | "source": [
2418 | "import nltk\n",
2419 | "from nltk.stem import PorterStemmer"
2420 | ]
2421 | },
2422 | {
2423 | "cell_type": "code",
2424 | "execution_count": 197,
2425 | "metadata": {},
2426 | "outputs": [],
2427 | "source": [
2428 | "ps = PorterStemmer()"
2429 | ]
2430 | },
2431 | {
2432 | "cell_type": "code",
2433 | "execution_count": 198,
2434 | "metadata": {},
2435 | "outputs": [],
2436 | "source": [
2437 | "def stems(text):\n",
2438 | " T = []\n",
2439 | " \n",
2440 | " for i in text.split():\n",
2441 | " T.append(ps.stem(i))\n",
2442 | " \n",
2443 | " return \" \".join(T)"
2444 | ]
2445 | },
2446 | {
2447 | "cell_type": "code",
2448 | "execution_count": 199,
2449 | "metadata": {},
2450 | "outputs": [
2451 | {
2452 | "name": "stderr",
2453 | "output_type": "stream",
2454 | "text": [
2455 | "| \n", 2327 | " | movie_id | \n", 2328 | "title | \n", 2329 | "tags | \n", 2330 | "
|---|---|---|---|
| 0 | \n", 2335 | "19995 | \n", 2336 | "Avatar | \n", 2337 | "in the 22nd century, a paraplegic marine is di... | \n", 2338 | "
| 1 | \n", 2341 | "285 | \n", 2342 | "Pirates of the Caribbean: At World's End | \n", 2343 | "captain barbossa, long believed to be dead, ha... | \n", 2344 | "
| 2 | \n", 2347 | "206647 | \n", 2348 | "Spectre | \n", 2349 | "a cryptic message from bond’s past sends him o... | \n", 2350 | "
| 3 | \n", 2353 | "49026 | \n", 2354 | "The Dark Knight Rises | \n", 2355 | "following the death of district attorney harve... | \n", 2356 | "
| 4 | \n", 2359 | "49529 | \n", 2360 | "John Carter | \n", 2361 | "john carter is a war-weary, former military ca... | \n", 2362 | "
4 |
5 | Recommendation systems are becoming increasingly important in today’s extremely busy world. People are always short on time with the myriad tasks they need to accomplish in the limited 24 hours. Therefore, the recommendation systems are important as they help them make the right choices, without having to expend their cognitive resources.
6 |
7 | The purpose of a recommendation system basically is to search for content that would be interesting to an individual. Moreover, it involves a number of factors to create personalised lists of useful and interesting content specific to each user/individual. Recommendation systems are Artificial Intelligence based algorithms that skim through all possible options and create a customized list of items that are interesting and relevant to an individual. These results are based on their profile, search/browsing history, what other people with similar traits/demographics are watching, and how likely are you to watch those movies. This is achieved through predictive modeling and heuristics with the data available.
8 |
9 | # Types of Recommendation System :
10 |
11 | ### 1 ) Content Based :
12 |
13 | - Content-based systems, which use characteristic information and takes item attriubutes into consideration .
14 |
15 | - Twitter , Youtube .
16 |
17 | - Which music you are listening , what singer are you watching . Form embeddings for the features .
18 |
19 | - User specific actions or similar items reccomendation .
20 |
21 | - It will create a vector of it .
22 |
23 | - These systems make recommendations using a user's item and profile features. They hypothesize that if a user was interested in an item in the past, they will once again be interested in it in the future
24 |
25 | - One issue that arises is making obvious recommendations because of excessive specialization (user A is only interested in categories B, C, and D, and the system is not able to recommend items outside those categories, even though they could be interesting to them).
26 |
27 | ### 2 ) Collaborative Based :
28 |
29 | - Collaborative filtering systems, which are based on user-item interactions.
30 |
31 | - Clusters of users with same ratings , similar users .
32 |
33 | - Book recommendation , so use cluster mechanism .
34 |
35 | - We take only one parameter , ratings or comments .
36 |
37 | - In short, collaborative filtering systems are based on the assumption that if a user likes item A and another user likes the same item A as well as another item, item B, the first user could also be interested in the second item .
38 |
39 | - Issues are :
40 |
41 | - User-Item nXn matrix , so computationally expensive .
42 |
43 | - Only famous items will get reccomended .
44 |
45 | - New items might not get reccomended at all .
46 |
47 | ### 3 ) Hybrid Based :
48 |
49 | - Hybrid systems, which combine both types of information with the aim of avoiding problems that are generated when working with just one kind.
50 |
51 | - Combination of both and used now a days .
52 |
53 | - Uses : word2vec , embedding .
54 |
55 | # About this project:
56 |
57 | This is a streamlit web application that can recommend various kinds of similar movies based on an user interest.
58 | here is a demo,
59 |
60 | * [Click here to run it live on server](https://movie-recommeder-system.herokuapp.com/)
61 |
62 |
63 | # Demo:
64 |
65 | 
66 |
67 | 
68 |
69 | 
70 |
71 |
72 | # Dataset has been used:
73 |
74 | * [Dataset link](https://www.kaggle.com/tmdb/tmdb-movie-metadata?select=tmdb_5000_movies.csv)
75 |
76 | # Concept used to build the model.pkl file : cosine_similarity
77 |
78 | 1 . Cosine Similarity is a metric that allows you to measure the similarity of the documents.
79 |
80 | 2 . In order to demonstrate cosine similarity function we need vectors. Here vectors are numpy array.
81 |
82 | 3 . Finally, Once we have vectors, We can call cosine_similarity() by passing both vectors. It will calculate the cosine similarity between these two.
83 |
84 | 4 . It will be a value between [0,1]. If it is 0 then both vectors are complete different. But in the place of that if it is 1, It will be completely similar.
85 |
86 | 5 . For more details , check URL : https://www.learndatasci.com/glossary/cosine-similarity/
87 |
88 | # How to run?
89 | ### STEPS:
90 |
91 | Clone the repository
92 |
93 | ```bash
94 | https://github.com/entbappy/Movie-Recommender-System-Using-Machine-Learning.git
95 | ```
96 | ### STEP 01- Create a conda environment after opening the repository
97 |
98 | ```bash
99 | conda create -n movie python=3.7.10 -y
100 | ```
101 |
102 | ```bash
103 | conda activate movie
104 | ```
105 |
106 |
107 | ### STEP 02- install the requirements
108 | ```bash
109 | pip install -r requirements.txt
110 | ```
111 |
112 |
113 | ```bash
114 | #run this file to generate the models
115 |
116 | Movie Recommender System Data Analysis.ipynb
117 | ```
118 |
119 | Now run,
120 | ```bash
121 | streamlit run app.py
122 | ```
123 |
124 |
125 | ```bash
126 | Author: Bappy Ahmed
127 | Data Scientist
128 | Email: entbappy73@gmail.com
129 |
130 | ```
131 |
--------------------------------------------------------------------------------
/app.py:
--------------------------------------------------------------------------------
1 | '''
2 | Author: Bappy Ahmed
3 | Email: entbappy73@gmail.com
4 | Date: 2021-Nov-15
5 | '''
6 |
7 | import pickle
8 | import streamlit as st
9 | import requests
10 |
11 | def fetch_poster(movie_id):
12 | url = "https://api.themoviedb.org/3/movie/{}?api_key=8265bd1679663a7ea12ac168da84d2e8&language=en-US".format(movie_id)
13 | data = requests.get(url)
14 | data = data.json()
15 | poster_path = data['poster_path']
16 | full_path = "https://image.tmdb.org/t/p/w500/" + poster_path
17 | return full_path
18 |
19 | def recommend(movie):
20 | index = movies[movies['title'] == movie].index[0]
21 | distances = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda x: x[1])
22 | recommended_movie_names = []
23 | recommended_movie_posters = []
24 | for i in distances[1:6]:
25 | # fetch the movie poster
26 | movie_id = movies.iloc[i[0]].movie_id
27 | recommended_movie_posters.append(fetch_poster(movie_id))
28 | recommended_movie_names.append(movies.iloc[i[0]].title)
29 |
30 | return recommended_movie_names,recommended_movie_posters
31 |
32 |
33 | st.header('Movie Recommender System Using Machine Learning')
34 | movies = pickle.load(open('artifacts/movie_list.pkl','rb'))
35 | similarity = pickle.load(open('artifacts/similarity.pkl','rb'))
36 |
37 | movie_list = movies['title'].values
38 | selected_movie = st.selectbox(
39 | "Type or select a movie from the dropdown",
40 | movie_list
41 | )
42 |
43 | if st.button('Show Recommendation'):
44 | recommended_movie_names,recommended_movie_posters = recommend(selected_movie)
45 | col1, col2, col3, col4, col5 = st.columns(5)
46 | with col1:
47 | st.text(recommended_movie_names[0])
48 | st.image(recommended_movie_posters[0])
49 | with col2:
50 | st.text(recommended_movie_names[1])
51 | st.image(recommended_movie_posters[1])
52 |
53 | with col3:
54 | st.text(recommended_movie_names[2])
55 | st.image(recommended_movie_posters[2])
56 | with col4:
57 | st.text(recommended_movie_names[3])
58 | st.image(recommended_movie_posters[3])
59 | with col5:
60 | st.text(recommended_movie_names[4])
61 | st.image(recommended_movie_posters[4])
62 |
63 |
--------------------------------------------------------------------------------
/artifacts/.gitignore:
--------------------------------------------------------------------------------
1 | movie_list.pkl
2 | similarity.pkl
3 |
--------------------------------------------------------------------------------
/data/.gitignore:
--------------------------------------------------------------------------------
1 | tmdb_5000_credits.csv
2 | tmdb_5000_movies.csv
--------------------------------------------------------------------------------
/demo/1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/entbappy/Movie-Recommender-System-Using-Machine-Learning/ae06ef2abddf9daacdaf587f335228a494fddffb/demo/1.png
--------------------------------------------------------------------------------
/demo/2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/entbappy/Movie-Recommender-System-Using-Machine-Learning/ae06ef2abddf9daacdaf587f335228a494fddffb/demo/2.png
--------------------------------------------------------------------------------
/demo/3.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/entbappy/Movie-Recommender-System-Using-Machine-Learning/ae06ef2abddf9daacdaf587f335228a494fddffb/demo/3.png
--------------------------------------------------------------------------------
/demo/6.jpeg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/entbappy/Movie-Recommender-System-Using-Machine-Learning/ae06ef2abddf9daacdaf587f335228a494fddffb/demo/6.jpeg
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | ### dependency
2 | streamlit
3 |
4 | ### local packages -
5 | -e .
6 |
--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
1 | from setuptools import setup
2 |
3 | with open("README.md", "r", encoding="utf-8") as f:
4 | long_description = f.read()
5 |
6 | ## edit below variables as per your requirements -
7 | REPO_NAME = "Movie-Recommender-System-Using-Machine-Learning"
8 | AUTHOR_USER_NAME = "entbappy"
9 | SRC_REPO = "src"
10 | LIST_OF_REQUIREMENTS = ['streamlit']
11 |
12 |
13 | setup(
14 | name=SRC_REPO,
15 | version="0.0.1",
16 | author=AUTHOR_USER_NAME,
17 | description="A small package for Movie Recommender System",
18 | long_description=long_description,
19 | long_description_content_type="text/markdown",
20 | url=f"https://github.com/{AUTHOR_USER_NAME}/{REPO_NAME}",
21 | author_email="entbappy73@gmail.com",
22 | packages=[SRC_REPO],
23 | license="MIT",
24 | python_requires=">=3.7",
25 | install_requires=LIST_OF_REQUIREMENTS
26 | )
27 |
--------------------------------------------------------------------------------
/setup.sh:
--------------------------------------------------------------------------------
1 | mkdir -p ~/.streamlit/
2 |
3 | echo "\
4 | [server]\n\
5 | port = $PORT\n\
6 | enableCORS = false\n\
7 | headless = true\n\
8 | \n\
9 | " > ~/.streamlit/config.toml
--------------------------------------------------------------------------------
/src/__init__.py:
--------------------------------------------------------------------------------
1 |
2 |
--------------------------------------------------------------------------------
/src/utils/__init__.py:
--------------------------------------------------------------------------------
1 |
2 |
--------------------------------------------------------------------------------