{"id":26902502,"url":"https://github.com/dtg-lucifer/multiple-regression-with-neural-network","last_synced_at":"2026-05-19T10:35:03.345Z","repository":{"id":285413555,"uuid":"958059444","full_name":"dtg-lucifer/multiple-regression-with-neural-network","owner":"dtg-lucifer","description":"This is a repository containing code to imply multiple linear regression models and smash them into a single neural network with tensorflow to predict data on bike dataset","archived":false,"fork":false,"pushed_at":"2025-03-31T15:20:56.000Z","size":702,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-31T16:52:28.743Z","etag":null,"topics":["jupyter-notebook","linear-regression","neural-network","tensorflow"],"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/dtg-lucifer.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":"2025-03-31T15:20:04.000Z","updated_at":"2025-03-31T15:21:29.000Z","dependencies_parsed_at":"2025-03-31T17:02:41.549Z","dependency_job_id":null,"html_url":"https://github.com/dtg-lucifer/multiple-regression-with-neural-network","commit_stats":null,"previous_names":["dtg-lucifer/multiple-regression-with-neural-network"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dtg-lucifer/multiple-regression-with-neural-network","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dtg-lucifer%2Fmultiple-regression-with-neural-network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dtg-lucifer%2Fmultiple-regression-with-neural-network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dtg-lucifer%2Fmultiple-regression-with-neural-network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dtg-lucifer%2Fmultiple-regression-with-neural-network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dtg-lucifer","download_url":"https://codeload.github.com/dtg-lucifer/multiple-regression-with-neural-network/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dtg-lucifer%2Fmultiple-regression-with-neural-network/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266775366,"owners_count":23982273,"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","status":"online","status_checked_at":"2025-07-23T02:00:09.312Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"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":["jupyter-notebook","linear-regression","neural-network","tensorflow"],"created_at":"2025-04-01T09:43:41.143Z","updated_at":"2026-05-19T10:35:03.253Z","avatar_url":"https://github.com/dtg-lucifer.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Bike Sharing Demand Prediction with Linear Regression\n\n## Project Overview\n\nThis project demonstrates the application of regression techniques to predict bike sharing demand in Seoul, South Korea based on various environmental factors. The analysis explores both traditional linear regression and neural network approaches to compare their effectiveness in predicting the number of bikes rented based on weather conditions.\n\n## Dataset\n\nThe analysis uses the \"Seoul Bike Sharing Demand\" dataset from the UCI Machine Learning Repository. The dataset contains hourly records of:\n\n- Bike rental counts\n- Temperature (°C)\n- Humidity (%)\n- Wind speed (m/s)\n- Visibility (10m)\n- Dew point temperature (°C)\n- Solar radiation (MJ/m2)\n- Rainfall (mm)\n- Snowfall (cm)\n- Seasons\n- Holiday information\n- Functioning day status\n\n**Source**: Seoul Bike Sharing Demand [dataset]. 2020. UCI Machine Learning Repository.  \n**Available from**: https://doi.org/10.24432/C5F62R\n\n## Project Structure\n\n```\n├── data/\n│   └── bike_data.csv       # The Seoul bike sharing dataset\n├── linear_regression.ipynb # Main analysis notebook\n└── README.md               # Project documentation\n```\n\n## Installation and Setup\n\nTo run this project, you need Python with the following packages:\n\n```bash\npip install numpy pandas matplotlib seaborn scikit-learn tensorflow imblearn\n```\n\n## Analysis Approach\n\nThe analysis proceeds through several stages:\n\n1. **Data Preparation**:\n   - Loading and cleaning the dataset\n   - Focus on bike rentals at noon\n   - Feature selection based on exploratory analysis\n\n2. **Feature Selection**:\n   - Visualization of relationships between features and bike count\n   - Removal of less important features (wind, visibility, functioning day status)\n\n3. **Model Development**:\n   - Simple linear regression with temperature only\n   - Multiple linear regression with all relevant features\n   - Neural network regression models for comparison\n\n4. **Model Evaluation**:\n   - R-squared comparison\n   - Mean Squared Error (MSE) comparison\n   - Visual comparison of predictions against ground truth\n\n## Key Findings\n\n- Temperature shows a significant correlation with bike rental demand\n- Multiple regression with several features outperforms simple linear regression\n- Neural networks can capture more complex relationships in the data than linear models\n- The project demonstrates the practical differences between traditional statistical approaches and machine learning methods\n\n## Usage Examples\n\nOpen the Jupyter notebook to see the analysis:\n\n```bash\njupyter notebook linear_regression.ipynb\n```\n\nThe notebook contains all code with explanations of each step in the modeling process.\n\n## Visualizations\n\nThe project includes various visualizations:\n- Scatter plots showing the relationship between individual features and bike count\n- Fitted regression lines showing predicted relationships\n- Learning curves for neural network training\n- Comparison plots of predicted vs. actual values\n\n## License\n\nThis project uses publicly available data from the UCI Machine Learning Repository. Please cite the original dataset when using this code for academic or research purposes.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdtg-lucifer%2Fmultiple-regression-with-neural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdtg-lucifer%2Fmultiple-regression-with-neural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdtg-lucifer%2Fmultiple-regression-with-neural-network/lists"}