{"id":23279938,"url":"https://github.com/siddhantborse/atmosviz","last_synced_at":"2026-05-05T00:37:59.003Z","repository":{"id":268785497,"uuid":"905463584","full_name":"siddhantborse/ATMOSVIZ","owner":"siddhantborse","description":"Atmos Viz is a Python-based project designed to analyze, visualize, and predict global temperature trends across various cities and countries using time-series analysis and advanced data science techniques. Leveraging historical climate data, this project integrates machine learning models, geospatial mapping, and interactive visualizations to unco","archived":false,"fork":false,"pushed_at":"2024-12-18T22:23:33.000Z","size":12698,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-06T13:19:04.336Z","etag":null,"topics":["geopandas","geospatial-analysis","gis","matplotlib","numpy","pandas","plotly","python","scikit-learn","seaborn","shapefiles","time","timeseries-analysis","timeseries-data"],"latest_commit_sha":null,"homepage":"","language":"HTML","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/siddhantborse.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":"2024-12-18T22:03:13.000Z","updated_at":"2024-12-18T22:34:11.000Z","dependencies_parsed_at":"2024-12-18T23:29:28.182Z","dependency_job_id":null,"html_url":"https://github.com/siddhantborse/ATMOSVIZ","commit_stats":null,"previous_names":["siddhantborse/atmosviz"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/siddhantborse%2FATMOSVIZ","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/siddhantborse%2FATMOSVIZ/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/siddhantborse%2FATMOSVIZ/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/siddhantborse%2FATMOSVIZ/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/siddhantborse","download_url":"https://codeload.github.com/siddhantborse/ATMOSVIZ/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247485295,"owners_count":20946399,"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":["geopandas","geospatial-analysis","gis","matplotlib","numpy","pandas","plotly","python","scikit-learn","seaborn","shapefiles","time","timeseries-analysis","timeseries-data"],"created_at":"2024-12-19T23:19:44.098Z","updated_at":"2026-05-05T00:37:58.965Z","avatar_url":"https://github.com/siddhantborse.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🌍 **Atmos Viz: Global Temperature Analysis and Prediction**\n### **Overview**\n**Atmos Viz** is a Python-based project designed to analyze, visualize, and predict global temperature trends across various cities and countries. Leveraging historical climate data, this project combines **machine learning models**, **geospatial mapping**, and **interactive visualizations** to uncover meaningful insights into temperature variations over time.\n\n---\n\n### **Project Features**\n- **Data Preprocessing**: Efficiently handles large-scale datasets, cleans missing values, and extracts features like **Year**, **Month**, and cyclic seasonal trends.\n- **Geospatial Mapping**: Visualizes temperature data geographically using **shapefiles** and tools like **GeoPandas** and **Plotly**.\n- **Machine Learning Prediction**: Forecasts future temperature trends using **Linear Regression** and **Random Forest** models.\n- **Interactive Visualizations**: Generates engaging charts, heatmaps, and world maps for better analysis and understanding.\n- **Performance Evaluation**: Measures model accuracy using metrics like **MAE**, **RMSE**, and **R²**.\n\n---\n\n### **Technologies Used**\n- **Programming Language**: Python\n- **Libraries**:\n  - Data Handling: `Pandas`, `NumPy`\n  - Visualization: `Matplotlib`, `Seaborn`, `Plotly`\n  - Geospatial Mapping: `GeoPandas`\n  - Machine Learning: `Scikit-learn`\n  - GIS Tools: **Shapefiles**\n\n---\n\n### **Project Workflow**\n1. **Data Preprocessing**\n   - Load the temperature dataset (sourced from Kaggle, originally from Berkeley Earth).\n   - Clean and normalize missing temperature values using **monthly means**.\n   - Extract cyclic seasonal trends using sine and cosine transformations.\n\n2. **Model Development**\n   - Use **Linear Regression** and **Random Forest** for predictive modeling.\n   - Train models using features like **Year**, **sin_month**, and **cos_month**.\n   - Evaluate performance using **MAE**, **RMSE**, and **R²** metrics.\n\n3. **Visualization**\n   - **Geospatial Maps**: Display temperature data using **GeoPandas** and **Plotly**.\n   - **Time-Series Trends**: Plot temperature trends with trendlines for specific cities.\n   - **Interactive Maps**: Visualize data with **hover information** for cities on the map.\n   - **Heatmaps \u0026 Boxplots**: Analyze monthly and regional temperature variations.\n   \n## Contributions\n### Contributions are welcome! If you'd like to improve this project, please fork the repository and create a pull request.\n\n## Contact\n### For any queries or suggestions, feel free to contact me:\n\n## Email: siddhantborse27@gmail.com\n## VPortfolio: Siddhant Borse\n## ⭐ If you like this project, star it on GitHub! ⭐\n\n---\n\n### **Project Directory Structure**\n```plaintext\nAtmos-Viz/\n│\n├── Package/\n│   ├── data_preprocessing.py      # Data loading, cleaning, and feature extraction\n│   ├── models.py                  # Machine learning model training\n│   ├── evaluation.py              # Model evaluation metrics\n│   ├── viz.py                     # Visualization functions (maps, charts, heatmaps)\n│\n├── shapefiles/                    # GIS shapefiles for mapping\n│\n├── data/                          # Raw and preprocessed temperature datasets\n│\n├── main.py                        # Main script for model execution and visualization\n│\n├── requirements.txt               # List of dependencies\n│\n└── README.md                      # Project documentation\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsiddhantborse%2Fatmosviz","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsiddhantborse%2Fatmosviz","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsiddhantborse%2Fatmosviz/lists"}