{"id":17110805,"url":"https://github.com/eeddaann/data-mining-project","last_synced_at":"2025-07-24T17:31:48.685Z","repository":{"id":97229582,"uuid":"109301686","full_name":"eeddaann/data-mining-project","owner":"eeddaann","description":null,"archived":false,"fork":false,"pushed_at":"2018-01-27T22:43:43.000Z","size":7385,"stargazers_count":3,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-01T13:51:14.987Z","etag":null,"topics":["boosting","confusion-matrix","data-mining","feature-engineering","feature-selection","gaussian-naive-bayes-implementation","knn-classifier","machine-learning","mlp-classifier","pca-analysis","roc-curve"],"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/eeddaann.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":"2017-11-02T18:10:20.000Z","updated_at":"2022-01-16T11:37:47.000Z","dependencies_parsed_at":"2023-03-13T16:18:40.184Z","dependency_job_id":null,"html_url":"https://github.com/eeddaann/data-mining-project","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/eeddaann/data-mining-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eeddaann%2Fdata-mining-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eeddaann%2Fdata-mining-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eeddaann%2Fdata-mining-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eeddaann%2Fdata-mining-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eeddaann","download_url":"https://codeload.github.com/eeddaann/data-mining-project/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eeddaann%2Fdata-mining-project/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266878574,"owners_count":23999620,"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":"2025-07-24T02:00:09.469Z","response_time":99,"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":["boosting","confusion-matrix","data-mining","feature-engineering","feature-selection","gaussian-naive-bayes-implementation","knn-classifier","machine-learning","mlp-classifier","pca-analysis","roc-curve"],"created_at":"2024-10-14T16:46:27.040Z","updated_at":"2025-07-24T17:31:48.671Z","avatar_url":"https://github.com/eeddaann.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data Mining Project\nThis notebook is the final project for data-mining course.\nFor this project we applied data-mining techniques with python's scikit-learn library.\nThe project consist:\n1. **Data Exploration:**\n    - statistics about the features\n    - scatter plots for the features\n    - correlation matrix\n    - violinplot\n2. **Feature Engineering:**\n    - LDA\n    - PCA\n    - Modification for PCA\n    - Feature Generation\n3. **KNN**\n    - Hyperparameter optimization\n    - apply with different preprocessing\n4. **Gaussian Naive Bayes**\n    - apply with different preprocessing\n5. **Multilayer Perceptron:**\n    - apply with different preprocessing \n6. **Boosting:**\n    - Based on decision trees\n    - Based on Gaussian Naive Bayes\n7. **Evaluation**:\n    - Confusion matrix\n    - Receiver operating characteristic (ROC)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feeddaann%2Fdata-mining-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feeddaann%2Fdata-mining-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feeddaann%2Fdata-mining-project/lists"}