{"id":171,"date":"2025-10-28T02:29:49","date_gmt":"2025-10-28T02:29:49","guid":{"rendered":"https:\/\/codetypingpro.com\/?p=171"},"modified":"2025-12-17T07:45:46","modified_gmt":"2025-12-17T07:45:46","slug":"28-real-world-python-projects-movie-recommendation-system","status":"publish","type":"post","link":"https:\/\/codetypingpro.com\/?p=171","title":{"rendered":"28 – Real-World Python Projects – Movie Recommendation System"},"content":{"rendered":"\n
<\/h6>\n\n\n\n

\ud83c\udfaf Project<\/strong> Objective<\/strong><\/h3>\n\n\n\n

To build a Movie Recommendation System<\/strong> that suggests movies to users based on ratings, genres, or similarity<\/strong> using Python.<\/p>\n\n\n\n

You\u2019ll learn:<\/p>\n\n\n\n

    \n
  • Data analysis with pandas<\/strong><\/li>\n\n\n\n
  • Text similarity using cosine similarity<\/strong><\/li>\n\n\n\n
  • Building a content-based recommender<\/strong><\/li>\n\n\n\n
  • Optional: Collaborative filtering using user ratings<\/li>\n<\/ul>\n\n\n\n
    \n\n\n\n

    \ud83e\udde9 1. What Is a Recommendation System?<\/strong><\/h2>\n\n\n\n

    A recommendation system<\/strong> suggests items (like movies, books, or songs) to users based on patterns in their behavior or preferences.<\/p>\n\n\n\n

    \ud83e\udde0 Types:<\/h3>\n\n\n\n
    Type<\/th>Description<\/th>Example<\/th><\/tr><\/thead>
    Content-Based<\/strong><\/td>Recommends similar items to what the user liked<\/td>Similar movies to Inception<\/em><\/td><\/tr>
    Collaborative Filtering<\/strong><\/td>Recommends based on similar users\u2019 ratings<\/td>\u201cPeople who liked this also liked\u2026\u201d<\/td><\/tr>
    Hybrid<\/strong><\/td>Combination of both<\/td>Netflix or Spotify suggestions<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
    \n\n\n\n

    \u2699\ufe0f 2. Libraries Used<\/strong><\/h2>\n\n\n\n

    We\u2019ll include auto-installation<\/strong> for convenience \ud83d\udc47<\/p>\n\n\n\n

    import os, sys, subprocess\ndef install(pkg):\n    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", pkg])\n\nfor pkg in [\"pandas\", \"scikit-learn\"]:\n    try:\n        __import__(pkg)\n    except ImportError:\n        install(pkg)\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83c\udfac 3. Sample Dataset<\/strong><\/h2>\n\n\n\n
    You can use any open dataset like TMDB<\/strong>, IMDB<\/strong>, or MovieLens<\/strong>, but let\u2019s use a small example dataset<\/strong> for demonstration:<\/p>\n\n\n\n
    import pandas as pd\n\n# Sample movie data\ndata = {\n    \"movie_id\": [1, 2, 3, 4, 5],\n    \"title\": [\"Inception\", \"Interstellar\", \"The Dark Knight\", \"The Matrix\", \"Tenet\"],\n    \"genre\": [\"Sci-Fi Action\", \"Sci-Fi Drama\", \"Action Crime\", \"Sci-Fi Action\", \"Sci-Fi Thriller\"],\n    \"description\": [\n        \"A thief who steals secrets through dreams.\",\n        \"Explorers travel through a wormhole in space.\",\n        \"Batman battles the Joker in Gotham.\",\n        \"A hacker learns about the nature of reality.\",\n        \"A secret agent manipulates time to prevent war.\"\n    ]\n}\n\nmovies = pd.DataFrame(data)\nprint(movies)\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83e\uddee 4. Building a Content-Based Recommender<\/strong><\/h2>\n\n\n\n
    We\u2019ll use TF-IDF (Term Frequency – Inverse Document Frequency)<\/strong> and Cosine Similarity<\/strong> to find similar movies.<\/p>\n\n\n\n
    from sklearn.feature_extraction.text import TfidfVectorizer\nfrom sklearn.metrics.pairwise import cosine_similarity\n\n# Combine genre and description into a single text column\nmovies[\"features\"] = movies[\"genre\"] + \" \" + movies[\"description\"]\n\n# Convert text data into TF-IDF matrix\ntfidf = TfidfVectorizer(stop_words=\"english\")\ntfidf_matrix = tfidf.fit_transform(movies[\"features\"])\n\n# Compute cosine similarity between movies\nsimilarity = cosine_similarity(tfidf_matrix, tfidf_matrix)\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83c\udfaf 5. Recommendation Function<\/strong><\/h2>\n\n\n\n
    def recommend_movie(title):\n    if title not in movies[\"title\"].values:\n        print(\"Movie not found.\")\n        return\n\n    index = movies[movies[\"title\"] == title].index[0]\n    scores = list(enumerate(similarity[index]))\n    sorted_scores = sorted(scores, key=lambda x: x[1], reverse=True)\n\n    print(f\"\\n\ud83c\udfac Movies similar to '{title}':\")\n    for i, score in sorted_scores[1:6]:  # Skip itself\n        print(f\"\u2022 {movies.iloc[i]['title']} ({round(score*100,2)}% match)\")\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83e\udde9 6. Example Output<\/strong><\/h2>\n\n\n\n
    recommend_movie(\"Inception\")\n<\/code><\/pre>\n\n\n\n
    \u2705 Output:<\/strong><\/p>\n\n\n\n
    \ud83c\udfac Movies similar to 'Inception':\n\u2022 The Matrix (87.45% match)\n\u2022 Tenet (81.12% match)\n\u2022 Interstellar (73.90% match)\n\u2022 The Dark Knight (42.55% match)\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83d\udca1 7. Optional: User-Based Collaborative Filtering<\/strong><\/h2>\n\n\n\n
    For large datasets (like MovieLens), you can recommend movies using user ratings<\/strong>:<\/p>\n\n\n\n
    # Example structure\nratings = pd.DataFrame({\n    \"user_id\": [1, 1, 2, 2, 3],\n    \"movie_id\": [1, 2, 2, 3, 4],\n    \"rating\": [5, 4, 5, 4, 5]\n})\n\n# Pivot to create a user-movie matrix\npivot_table = ratings.pivot_table(index=\"user_id\", columns=\"movie_id\", values=\"rating\").fillna(0)\n\n# Compute similarity between movies\nmovie_similarity = cosine_similarity(pivot_table.T)\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \ud83d\udcc8 8. Improving the System<\/strong><\/h2>\n\n\n\n
    Improvement<\/th>Description<\/th><\/tr><\/thead>
    \ud83d\udd0d Use full TMDB or MovieLens dataset<\/td>Thousands of real movie records<\/td><\/tr>
    \ud83d\udcac Add user input interface<\/td>Let users search dynamically<\/td><\/tr>
    \ud83e\udde0 Include actors, directors, or keywords<\/td>Improve similarity accuracy<\/td><\/tr>
    \ud83c\udf10 Create Flask web app<\/td>Build an online recommender<\/td><\/tr>
    \ud83e\uddee Hybrid filtering<\/td>Mix content + collaborative models<\/td><\/tr>
    \ud83d\udcca Visualization<\/td>Show recommended movie posters using matplotlib<\/code><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
    \n\n\n\n
    \ud83d\udce6 9. Exporting Model<\/strong><\/h2>\n\n\n\n
    You can save your trained TF-IDF matrix and use it in other scripts or web apps:<\/p>\n\n\n\n
    import pickle\nwith open(\"movie_recommender.pkl\", \"wb\") as f:\n    pickle.dump((movies, similarity), f)\n<\/code><\/pre>\n\n\n\n
    Later, load and use:<\/p>\n\n\n\n
    movies, similarity = pickle.load(open(\"movie_recommender.pkl\", \"rb\"))\nrecommend_movie(\"Tenet\")\n<\/code><\/pre>\n\n\n\n
    \n\n\n\n
    \u2705 Summary<\/strong><\/h2>\n\n\n\n
    Feature<\/th>Description<\/th><\/tr><\/thead>
    \ud83c\udfa5 Recommends similar movies<\/td>Based on genres + descriptions<\/td><\/tr>
    \u2699\ufe0f Uses Machine Learning<\/td>TF-IDF + Cosine Similarity<\/td><\/tr>
    \ud83e\udde0 Easy to expand<\/td>Add user data, genres, or ratings<\/td><\/tr>
    \ud83d\udcbe Data persistence<\/td>Save trained model with pickle<\/td><\/tr>
    \ud83d\udda5\ufe0f Extendable<\/td>Convert to Flask web app or dashboard<\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"
    \ud83c\udfaf Project Objective To build a Movie Recommendation System that suggests movies to users based on ratings, genres, or similarity using Python. You\u2019ll learn: \ud83e\udde9 1. What Is a Recommendation System? A recommendation system suggests items (like movies, books, or songs) to users based on patterns in their behavior or preferences. \ud83e\udde0 Types: Type Description […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-171","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/posts\/171","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=171"}],"version-history":[{"count":2,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/posts\/171\/revisions"}],"predecessor-version":[{"id":307,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=\/wp\/v2\/posts\/171\/revisions\/307"}],"wp:attachment":[{"href":"https:\/\/codetypingpro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=171"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=171"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/codetypingpro.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=171"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}