{"id":31579166,"url":"https://github.com/inesruizblach/data-science-project","last_synced_at":"2026-05-09T03:32:27.928Z","repository":{"id":317555796,"uuid":"1067904380","full_name":"inesruizblach/data-science-project","owner":"inesruizblach","description":"A data science project exploring Portuguese \"Vinho Verde\" wine quality prediction. Features EDA, feature engineering, ML models, and evaluation using Python, pandas, scikit-learn, and visualization tools.","archived":false,"fork":false,"pushed_at":"2025-10-02T11:03:16.000Z","size":4322,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-09T12:09:59.100Z","etag":null,"topics":["binary-classification","classification","data-science","exploratory-data-analysis","feature-engineering","imbalanced-learn","jupyter-notebook","machine-learning","model-evaluation","pandas","regression","scikit-learn","seaborn","uci-dataset","wine-quality"],"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/inesruizblach.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":"2025-10-01T14:58:08.000Z","updated_at":"2025-10-02T11:03:19.000Z","dependencies_parsed_at":"2025-10-01T17:36:27.312Z","dependency_job_id":null,"html_url":"https://github.com/inesruizblach/data-science-project","commit_stats":null,"previous_names":["inesruizblach/data-science-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/inesruizblach/data-science-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inesruizblach%2Fdata-science-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inesruizblach%2Fdata-science-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inesruizblach%2Fdata-science-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inesruizblach%2Fdata-science-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/inesruizblach","download_url":"https://codeload.github.com/inesruizblach/data-science-project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inesruizblach%2Fdata-science-project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32805909,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-08T08:22:46.396Z","status":"online","status_checked_at":"2026-05-09T02:00:06.633Z","response_time":123,"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":["binary-classification","classification","data-science","exploratory-data-analysis","feature-engineering","imbalanced-learn","jupyter-notebook","machine-learning","model-evaluation","pandas","regression","scikit-learn","seaborn","uci-dataset","wine-quality"],"created_at":"2025-10-05T20:47:39.950Z","updated_at":"2026-05-09T03:32:27.888Z","avatar_url":"https://github.com/inesruizblach.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Wine Quality Prediction Project\n\nThis repository contains a Jupyter Notebook for predicting the quality of Portuguese \"Vinho Verde\" wines using machine learning.\n\n\u003e **Note:** This project was completed as part of a university coursework.\n\n## Contents\n\n- Exploratory Data Analysis (EDA)\n- Feature engineering\n- Model training and evaluation (classification and regression)\n- Visualizations\n- Conclusions\n\n## Tech Stack\n\n- Python 3.8+\n- Jupyter Notebook\n- pandas\n- numpy\n- seaborn\n- scikit-learn\n- imbalanced-learn\n\n## Key Visualizations\n\n### Wine Quality Distribution\n\nRed and white wine quality scores are imbalanced, with most samples rated 5 or 6.\n\n![Red wine quality distribution](figures/red_quality_distribution.png)\n![White wine quality distribution](figures/white_quality_distribution.png)\n\n### Correlation Heatmaps\n\nChemical properties show strong correlations, e.g., free/total sulfur dioxide and residual sugar/density.\n\n![Red wine correlation heatmap](figures/red_correlation_heatmap.png)\n![White wine correlation heatmap](figures/white_correlation_heatmap.png)\n\n### Quality by Alcohol Category\n\nAlcohol content is discretized into low, mid, and high. Most wines with mid alcohol content are rated 5 or 6.\n\n![Red wine quality by alcohol](figures/red_quality_by_alcohol.png)\n![White wine quality by alcohol](figures/white_quality_by_alcohol.png)\n\n### Quality by Sweetness\n\nSweetness (dry/sweet) is associated with quality. Sweet wines tend to have higher quality scores.\n\n![Red wine quality by sweetness](figures/red_quality_by_sweetness.png)\n![White wine quality by sweetness](figures/white_quality_by_sweetness.png)\n\n### Model Performance\n\nConfusion matrices for classification models and regression error distributions show model accuracy and error spread.\n\n![Red wine confusion matrix](figures/red_confusion_matrix.png)\n![White wine confusion matrix](figures/white_confusion_matrix.png)\n![Red wine regression error](figures/red_regression_error.png)\n![White wine regression error](figures/white_regression_error.png)\n\n## Conclusions\n\n- Alcohol and sweetness are moderately correlated with wine quality.\n- Highly correlated features (e.g., free/total sulfur dioxide, residual sugar/density) can be dropped to improve model interpretability.\n- Logistic Regression and SVM models achieve good accuracy for binary classification of wine quality.\n- Linear Regression models provide reasonable predictions for continuous quality scores.\n- Hyperparameter tuning and cross-validation help prevent overfitting and improve model reliability.\n\n## Usage\n\n1. Clone the repository.\n2. Open the notebook in Jupyter.\n3. Run all cells to reproduce the analysis and results.\n\n## Dataset\n\nThe notebook uses the publicly available \"Vinho Verde\" wine quality datasets (red and white) from the UCI Machine Learning Repository.\n\n## License\n\nThis project is for educational purposes.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finesruizblach%2Fdata-science-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finesruizblach%2Fdata-science-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finesruizblach%2Fdata-science-project/lists"}