{"id":19012666,"url":"https://github.com/e19166/predicta-1.0-competition","last_synced_at":"2025-07-25T02:04:02.879Z","repository":{"id":245775729,"uuid":"819086728","full_name":"e19166/Predicta-1.0-Competition","owner":"e19166","description":"Codes Used for predicta 1.0 competition","archived":false,"fork":false,"pushed_at":"2024-06-24T03:07:06.000Z","size":135,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-01T22:11:40.754Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/e19166.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":"2024-06-23T18:31:43.000Z","updated_at":"2024-06-24T03:07:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"87cc40be-481a-4ee7-884b-832e36c5c4f0","html_url":"https://github.com/e19166/Predicta-1.0-Competition","commit_stats":null,"previous_names":["e19166/preficta-1.0-competition"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/e19166%2FPredicta-1.0-Competition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/e19166%2FPredicta-1.0-Competition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/e19166%2FPredicta-1.0-Competition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/e19166%2FPredicta-1.0-Competition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/e19166","download_url":"https://codeload.github.com/e19166/Predicta-1.0-Competition/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240044677,"owners_count":19739183,"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":[],"created_at":"2024-11-08T19:19:07.161Z","updated_at":"2025-02-21T15:51:23.652Z","avatar_url":"https://github.com/e19166.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Preficta-1.0-Competition\nCodes Used for predicta 1.0 competition\n\n# Overview\nThe goal of the time series prediction task was to forecast future weather conditions using historical weather data. Accurate weather prediction is crucial for various applications, including agriculture, transportation, and disaster management. The NeuralProphet model demonstrated the ability to forecast weather conditions with reasonable accuracy, as indicated by the RMSE values. This approach highlighted the effectiveness of using advanced time series models for weather prediction.\nThe classification task aimed to predict the categorical weather conditions based on various numerical and categorical weather features. This is essential for providing specific weather-related advisories.\n\n# Problem 1\nFor time series forecasting, the NeuralProphet model was employed due to its robustness in handling complex temporal patterns. NeuralProphet is an advanced version of Facebook's Prophet model, integrating neural network capabilities to capture non-linear trends and seasonality more effectively. The model was chosen for its ability to handle missing data, incorporate external regressors, and provide interpretable forecasts. The model's architecture includes components for trend, seasonality, and holidays, making it well-suited for weather forecasting where such factors play a significant role. The NeuralProphet model's flexibility and ease of use made it an ideal choice for this project, allowing for accurate and reliable weather predictions.\n\n# Problem 2\nIn Problem 2, a diverse set of classification algorithms was employed to predict weather conditions based on the processed daily weather dataset. The chosen models included Random Forest, Gradient Boosting, AdaBoost, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, and Gaussian Naive Bayes. Each of these algorithms was selected for their unique strengths and ability to handle different aspects of the classification task. Random Forest and Gradient Boosting are ensemble methods that combine multiple decision trees to enhance predictive accuracy and robustness. AdaBoost is another ensemble technique that adjusts the weights of misclassified instances to improve model performance iteratively. SVM is known for its effectiveness in high-dimensional spaces, while KNN is a simple yet powerful instance-based learning method. Decision Trees provide clear and interpretable decision rules, and Gaussian Naive Bayes is efficient for probabilistic classification. By leveraging this diverse set of algorithms, the goal was to capture a broad spectrum of patterns and relationships within the data, ultimately leading to a more accurate and reliable weather condition classification.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fe19166%2Fpredicta-1.0-competition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fe19166%2Fpredicta-1.0-competition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fe19166%2Fpredicta-1.0-competition/lists"}