{"id":50801192,"url":"https://github.com/neelimabonangi/defect-detection-hot-rolling","last_synced_at":"2026-06-12T20:03:36.781Z","repository":{"id":361199983,"uuid":"1253510371","full_name":"neelimabonangi/defect-detection-hot-rolling","owner":"neelimabonangi","description":"Defect Detection in Hot Rolling Using Machine Learning","archived":false,"fork":false,"pushed_at":"2026-05-29T14:51:19.000Z","size":651,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-29T16:21:45.661Z","etag":null,"topics":["classification","data-analysis","data-science","defect-detection","jupyter-notebook","machine-learning","manufacturing","numpy","pandas","predictive-analytics","python","random-forest","scikit-learn"],"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/neelimabonangi.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-29T14:37:27.000Z","updated_at":"2026-05-29T14:58:52.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/neelimabonangi/defect-detection-hot-rolling","commit_stats":null,"previous_names":["neelimabonangi/defect-detection-hot-rolling"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/neelimabonangi/defect-detection-hot-rolling","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neelimabonangi%2Fdefect-detection-hot-rolling","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neelimabonangi%2Fdefect-detection-hot-rolling/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neelimabonangi%2Fdefect-detection-hot-rolling/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neelimabonangi%2Fdefect-detection-hot-rolling/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/neelimabonangi","download_url":"https://codeload.github.com/neelimabonangi/defect-detection-hot-rolling/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neelimabonangi%2Fdefect-detection-hot-rolling/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34260310,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["classification","data-analysis","data-science","defect-detection","jupyter-notebook","machine-learning","manufacturing","numpy","pandas","predictive-analytics","python","random-forest","scikit-learn"],"created_at":"2026-06-12T20:03:35.866Z","updated_at":"2026-06-12T20:03:36.764Z","avatar_url":"https://github.com/neelimabonangi.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Defect Detection in Hot Rolling Using Machine Learning - Hackathon Assessment\n\n## Assessment Information\n\nThis project was developed as part of a Machine Learning Hackathon Assessment.\n  \n## Project Overview\n\nThis project focuses on predicting Alpha defects in hot rolling mills using machine learning techniques. The objective is to identify defective coils based on process parameters collected during steel manufacturing.\n\nThe solution uses classification algorithms to predict whether a coil contains a defect or not, helping improve quality control and reduce production losses.\n\n---\n\n## Dataset Description\n\nThe dataset contains:\n\n### Training Data\n- 1352 records\n- 49 process parameter features (X1 – X49)\n- Target variable: Y\n  - 0 = No Defect\n  - 1 = Defect\n\n### Test Data\n- 339 records\n- 49 process parameter features\n\n### Additional Column\n- CoilID: Unique identifier for each coil\n\n---\n\n## Problem Statement\n\nBuild a machine learning model capable of predicting Alpha defects in steel coils while maximizing defect detection performance.\n\n---\n\n## Feature Engineering\n\nThe following preprocessing steps were performed:\n\n- Removed CoilID from model features\n- Used X1–X49 as predictive variables\n- Selected Y as target variable\n- Handled class imbalance using class weighting\n- Checked for missing values and data consistency\n- Prepared data for machine learning model training\n\n---\n\n## Machine Learning Model\n\n### Random Forest Classifier\n\nReasons for selection:\n\n- Handles classification tasks effectively\n- Works well with tabular data\n- Reduces overfitting through ensemble learning\n- Provides feature importance insights\n\n---\n\n## Technologies Used\n\n- Python\n- Pandas\n- NumPy\n- Scikit-learn\n- Jupyter Notebook\n\n---\n\n## Project Structure\n\n```\nDefect-Detection-Hot-Rolling/\n│\n├── train.csv\n├── test.csv\n├── expected_submission.csv\n├── defect_detection_code.py\n├── README.md\n└── requirements.txt\n```\n\n---\n\n## Installation\n\nClone the repository:\n\n```bash\ngit clone https://github.com/yourusername/defect-detection-hot-rolling.git\n```\n\nInstall dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n---\n\n## Running the Project\n\nExecute:\n\n```bash\npython defect_detection_code.py\n```\n\nThe script will:\n\n1. Load training and test datasets\n2. Train the machine learning model\n3. Generate predictions\n4. Create the submission file\n\nOutput:\n\n```text\nexpected_submission.csv\n```\n\n---\n\n## Results\n\nThe model predicts defect occurrence for unseen coils and generates a submission file containing:\n\n| CoilID | Y |\n|---------|---|\n| 1 | 0 |\n| 2 | 1 |\n\n---\n\n## Future Improvements\n\n- XGBoost implementation\n- CatBoost implementation\n- Hyperparameter tuning\n- Ensemble learning\n- Advanced feature engineering\n- Model explainability using SHAP\n\n---\n\n## Author\n\nNeelima Bonangi\n\nB.Tech Graduate | Java Full Stack Developer | Data Science Enthusiast\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneelimabonangi%2Fdefect-detection-hot-rolling","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fneelimabonangi%2Fdefect-detection-hot-rolling","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneelimabonangi%2Fdefect-detection-hot-rolling/lists"}