{"id":22429872,"url":"https://github.com/jerinpious/movie-recommendation-system","last_synced_at":"2026-04-20T09:05:10.157Z","repository":{"id":265390508,"uuid":"895331686","full_name":"jerinpious/Movie-Recommendation-System","owner":"jerinpious","description":"A content-based movie recommendation system built using Python. The system processes movie data, extracts relevant features, and provides recommendations based on user preferences","archived":false,"fork":false,"pushed_at":"2024-11-29T06:45:37.000Z","size":10608,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-27T07:13:50.328Z","etag":null,"topics":["content-based-recommendation","data-analysis","jupyter-notebook","machine-learning","pandas","python","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jerinpious.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-28T02:20:59.000Z","updated_at":"2024-11-29T06:45:40.000Z","dependencies_parsed_at":"2024-11-29T10:03:32.576Z","dependency_job_id":null,"html_url":"https://github.com/jerinpious/Movie-Recommendation-System","commit_stats":null,"previous_names":["jerinpious/movie-recommendation-system"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jerinpious%2FMovie-Recommendation-System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jerinpious%2FMovie-Recommendation-System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jerinpious%2FMovie-Recommendation-System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jerinpious%2FMovie-Recommendation-System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jerinpious","download_url":"https://codeload.github.com/jerinpious/Movie-Recommendation-System/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245798358,"owners_count":20673902,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["content-based-recommendation","data-analysis","jupyter-notebook","machine-learning","pandas","python","streamlit"],"created_at":"2024-12-05T21:06:00.295Z","updated_at":"2026-04-20T09:05:10.094Z","avatar_url":"https://github.com/jerinpious.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Movie Recommendation System\n\nThis project is a **content-based movie recommendation system** built using Python. The system processes movie data, extracts relevant features, and provides recommendations based on user preferences. It leverages **TMDb 5000 Movies** and **Credits datasets** for analysis and prediction.\n\n- Data Source: [Kaggle TMDb 5000 Dataset](https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata)\n---\n\n## Screenshots\n![Project_image](img/ss_1.png)\n\n![Project_image](img/ss_2.png)\n\n## Features\n\n- **Data Merging**: Combines information from two datasets (`tmdb_5000_movies.csv` and `tmdb_5000_credits.csv`) to create a unified database.\n- **Feature Engineering**: Extracts relevant features like genres, keywords, cast, and crew.\n- **Content-Based Recommendations**: Recommends movies based on shared features, such as:\n  - Genre similarity\n  - Common keywords\n  - Top cast members\n  - Shared directors\n- **Optimized Data Preprocessing**:\n  - Handles null values and removes duplicates.\n  - Converts JSON-like data (genres, keywords, cast) into readable and usable formats.\n- **Customized Casting**: Limits the cast feature to the top 3 main actors.\n\n---\n\n## Dataset Details\n\n### 1. TMDb 5000 Movies Dataset\n- **Source**: Kaggle\n- **Features**:\n  - Title, Budget, Revenue\n  - Genres, Keywords\n  - Popularity, Vote Count, Vote Average\n  - Overview, Homepage, Release Date\n\n### 2. TMDb 5000 Credits Dataset\n- **Source**: Kaggle\n- **Features**:\n  - Title\n  - Cast (detailed information about actors)\n  - Crew (including directors, writers, etc.)\n\n---\n\n## Data Preprocessing Steps\n\n1. **Merging Datasets**: Unified the `movies` and `credits` datasets on the `title` column.\n2. **Selected Features**: Filtered for the most relevant columns:\n   - `movie_id`, `title`, `overview`, `genres`, `keywords`, `cast`, `crew`\n3. **Null Handling**:\n   - Dropped rows with missing values in critical columns.\n4. **Duplicate Removal**:\n   - Ensured no repeated entries in the data.\n5. **Data Transformation**:\n   - Extracted and converted JSON-like data in `genres`, `keywords`, `cast`, and `crew` columns into usable lists.\n6. **Feature Customization**:\n   - Limited the cast feature to the top 3 actors using the `top3()` function.\n   - Extracted directors using the `fetch_director()` function.\n\n---\n\n## Project Workflow\n\n1. **Exploratory Data Analysis (EDA)**:\n   - Analyzed data distribution and cleaned missing values.\n2. **Feature Engineering**:\n   - Processed `genres` and `keywords` into lists for similarity computation.\n3. **Modeling**:\n   - Used cosine similarity to compute pairwise movie similarities.\n   - Built a recommendation engine based on the computed similarity matrix.\n4. **Integration**:\n   - Created functions to fetch recommendations for a given movie title.\n\n---\n\n## Installation and Setup\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/your-username/movie-recommendation-system.git\n   cd movie-recommendation-system\n   ```\n2. Install the required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n3. Add the datasets:\n   - Place `tmdb_5000_movies.csv` and `tmdb_5000_credits.csv` inside the `data/` directory.\n\n4. Run the project:\n   ```bash\n   python main.py\n   ```\n\n---\n\n## Usage\n\n- **Input**: Provide a movie title.\n- **Output**: A list of recommended movies with high similarity based on:\n  - Shared genres\n  - Common keywords\n  - Similar cast or crew\n\nExample:\n```python\nrecommendations = get_recommendations(\"Avatar\")\nprint(recommendations)\n```\n\n---\n\n## Future Enhancements\n\n- Implement **hybrid recommendations** by integrating collaborative filtering.\n- Develop a **web interface** using Flask or Streamlit for user interaction.\n\n\n---\n\n## Acknowledgments\n\n- Data Source: [Kaggle TMDb 5000 Dataset](https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata)\n- Inspiration: Building a robust content-based recommendation system.\n\n---\n\nLet me know if you'd like to add anything else! 😊","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjerinpious%2Fmovie-recommendation-system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjerinpious%2Fmovie-recommendation-system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjerinpious%2Fmovie-recommendation-system/lists"}