{"id":27736757,"url":"https://github.com/kakarotprince/fileclassification","last_synced_at":"2026-05-20T14:32:46.658Z","repository":{"id":290030512,"uuid":"973090162","full_name":"Kakarotprince/FileClassification","owner":"Kakarotprince","description":"Project - II","archived":false,"fork":false,"pushed_at":"2025-04-26T12:18:08.000Z","size":934,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-28T14:42:00.930Z","etag":null,"topics":["machine-learning","natural-language-processing","streamlit","webapp"],"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/Kakarotprince.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,"zenodo":null}},"created_at":"2025-04-26T08:29:44.000Z","updated_at":"2025-04-26T12:28:00.000Z","dependencies_parsed_at":"2025-04-28T14:42:36.471Z","dependency_job_id":null,"html_url":"https://github.com/Kakarotprince/FileClassification","commit_stats":null,"previous_names":["kakarotprince/fileclassification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Kakarotprince/FileClassification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kakarotprince%2FFileClassification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kakarotprince%2FFileClassification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kakarotprince%2FFileClassification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kakarotprince%2FFileClassification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kakarotprince","download_url":"https://codeload.github.com/Kakarotprince/FileClassification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kakarotprince%2FFileClassification/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265495381,"owners_count":23776621,"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":["machine-learning","natural-language-processing","streamlit","webapp"],"created_at":"2025-04-28T14:30:12.880Z","updated_at":"2026-05-20T14:32:46.587Z","avatar_url":"https://github.com/Kakarotprince.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 Document Classification using Machine Learning\n\nThis project is an intelligent document classification system that uses a range of machine learning models, traditional text vectorization techniques (TF-IDF), and modern embeddings (Word2Vec \u0026 Doc2Vec) to accurately classify text documents into predefined categories. Ensemble techniques like **hard voting** and **soft voting** are used to improve performance by combining multiple models.\n\n---\n\n## 📁 Datasets Used\n\nWe combined two existing datasets to build a richer and more diverse text classification corpus:\n\n1. **[News Article Category Dataset](https://www.kaggle.com/datasets/timilsinabimal/newsarticlecategories)**  \n2. **[Text Document Classification Dataset](https://www.kaggle.com/datasets/sunilthite/text-document-classification-dataset)**  \n\nThese datasets were mapped into unified categories such as:\n- News \u0026 Current Affairs\n- Business \u0026 Finance\n- Science \u0026 Technology\n- Arts \u0026 Entertainment\n- Education \u0026 Academia\n- Sports\n\n---\n\n## 🧩 Word Embedding\n\nWe used the **pre-trained Google News Word2Vec model** (`GoogleNews-vectors-negative300.bin`) for document vectorization:\n\n📥 Download it here: [Google News Word2Vec Embeddings](https://www.kaggle.com/datasets/leadbest/googlenewsvectorsnegative300)\n\n---\n\n## 🚀 Project Pipeline\n\n1. **Data Loading \u0026 Preprocessing**\n2. **Category Mapping \u0026 Merging Datasets**\n3. **Text Cleaning, Tokenization, and Lemmatization**\n4. **Vectorization:**\n   - TF-IDF\n   - Word2Vec\n   - Doc2Vec\n5. **Oversampling for Class Imbalance (SMOTE, ADASYN, Random Oversampling)**\n6. **Model Training:**\n   - Naive Bayes\n   - SVM\n   - Random Forest\n   - AdaBoost\n   - XGBoost\n   - Word2Vec + Logistic Regression\n   - Doc2Vec + Logistic Regression\n7. **Model Evaluation**\n8. **Ensemble Voting (Hard \u0026 Soft)**\n9. **Deployment via Streamlit Interface**\n\n---\n\n## 📦 First-Time Setup Instructions\n\n```bash\n# Clone the repository\ngit clone https://github.com/Kakarotprince/FileClassification.git\ncd FileClassification\n\n# Install dependencies\npip install -r Requirements.txt\n```\n\n### ⚠️ Important Note:\n\n- On **first run**, the Google News vectors need to be loaded and **vector cache saved**.\n- **Subsequent runs** will **reuse the saved vectors** to save time and memory.\n\n---\n\n## 📊 Models and Techniques\n\n- **Vectorizers:** TF-IDF, Word2Vec (Google News), Doc2Vec\n- **Classifiers:** SVM, RandomForest, AdaBoost, XGBoost, Naive Bayes, Logistic Regression\n- **Imbalanced Data Handling:** SMOTE, ADASYN, Random Oversampling\n- **Evaluation Metrics:** Accuracy, Precision, Recall, F1-Score\n- **Ensembling:** Hard Voting, Soft Voting (based on individual model accuracies)\n\n---\n\n## 🖼️ Streamlit Web Interface\n\nThe project includes a user-friendly Streamlit-based UI where users can upload text or files and receive classification results in real-time.\n\nTo launch the app:\n\n```bash\nstreamlit run app.py\n```\n\n---\n\n## 📚 References\n\n- [scikit-learn](https://scikit-learn.org/)\n- [Gensim](https://radimrehurek.com/gensim/)\n- [Streamlit](https://streamlit.io/)\n- [Kaggle: GoogleNews Word2Vec](https://www.kaggle.com/datasets/leadbest/googlenewsvectorsnegative300)\n- [Kaggle: News Article Categories](https://www.kaggle.com/datasets/timilsinabimal/newsarticlecategories)\n- [Kaggle: Text Document Dataset](https://www.kaggle.com/datasets/sunilthite/text-document-classification-dataset)\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkakarotprince%2Ffileclassification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkakarotprince%2Ffileclassification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkakarotprince%2Ffileclassification/lists"}