{"id":22202469,"url":"https://github.com/trim0500/fe-stats-classifier","last_synced_at":"2026-04-11T14:36:10.582Z","repository":{"id":264242953,"uuid":"892427575","full_name":"Trim0500/FE-Stats-Classifier","owner":"Trim0500","description":"An experiment to create a machine learning model via PyTorch to classify select Fire Emblem unit base stat distributions.","archived":false,"fork":false,"pushed_at":"2025-03-09T21:56:05.000Z","size":13970,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T08:45:19.490Z","etag":null,"topics":["creational-patterns","data-analysis","data-science","data-visualization","design-patterns","excel","jupyter","jupyter-notebook","matplotlib-pyplot","numpy","pandas","python","python-modules","python3","pytorch","singleton"],"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/Trim0500.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":"2024-11-22T04:58:26.000Z","updated_at":"2025-03-09T21:56:08.000Z","dependencies_parsed_at":"2025-02-02T09:36:50.346Z","dependency_job_id":null,"html_url":"https://github.com/Trim0500/FE-Stats-Classifier","commit_stats":null,"previous_names":["trim0500/fe-stats-classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trim0500%2FFE-Stats-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trim0500%2FFE-Stats-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trim0500%2FFE-Stats-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Trim0500%2FFE-Stats-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Trim0500","download_url":"https://codeload.github.com/Trim0500/FE-Stats-Classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245999322,"owners_count":20707554,"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":["creational-patterns","data-analysis","data-science","data-visualization","design-patterns","excel","jupyter","jupyter-notebook","matplotlib-pyplot","numpy","pandas","python","python-modules","python3","pytorch","singleton"],"created_at":"2024-12-02T16:25:56.822Z","updated_at":"2025-12-30T23:21:15.680Z","avatar_url":"https://github.com/Trim0500.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FE Stats Classifier\n---\n### Stats to Analyze\n- HP\n- Atk (If not Echoes or Binding Blade, take max between Str \u0026 Mag)\n- Skl/Dex\n- Spd\n- Lck\n- Def\n- Res\n---\n---\n### Metrics\n- Mean = sum of stat / count of stat\n  - ### $`\\mu={\\frac {1}{n}}\\sum _{i=1}^{n}x_{i}`$\n- Standard Deviation = sqrt(sum of diff of mean squared / count of stat)\n  - ### $`\\sigma = \\sqrt{\\frac{1}{n-1} \\sum_{i=1}^n (x_i - \\mu)^2}`$\n- Standardization = diff of mean / std\n  - ### $`z=\\frac{x - \\mu}{\\sigma}`$\n---\n---\n### Key Points\n- Analysis based on comparison with character with most amount of appearances (provided stats are comparable) and stat disribution (in %) after normalizing data and averaging\n- Use base stats from joining time\n- Include DLC and other means outside of strict base game availability\n- No spin-offs (except FEH)\n- Do not include seasonal FEH alts\n---\n---\n### Characters\n**Marth (13)**\n- Main line [1,3,11,12,13 as DLC 2x,14,15]\n- FEH [Base, Legend, Youth, Brave, Plot Ghost]\n\n**Linde (7)**\n- Main line [1,3,11,12,13 as DLC]\n- FEH [Base, Khadein]\n\n**Palla (10)**\n- Main line [1,2,3,11,12,13 as DLC,15]\n- FEH [Base, Youth, Falcon Knight]\n\n**Alm (6)**\n- Main line [2,13 as DLC,15]\n- FEH [Base, Legend, Brave]\n\n**Roy (6)**\n- Main line [6,13 as DLC,15]\n- FEH [Base, Legend, Brave]\n\n**Lilina (5)**\n- Main line [6,13 as DLC]\n- FEH [Base, Legend, Rearmed]\n\n**Claude (5)**\n- Main line [16 + DLC]\n- FEH [Base, Brave, Legend]\n\n**Lysithea (3)**\n- Main line [16]\n- FEH [Base, Brave]\n---\n---\n### Model Algorithms Used\n- Vanilla MLP (Multi-Layered Perceptron)\n- CNN (Convolutional Neural Network)\n- SVM (Support Vector Machine)\n- Random Forest\n---\n---\n### Model Algorithms Excluded\n- RNN (Recurrent Neural Network, not temporal data)\n- LSTM (Long Short-Term Memory, no need for memory)\n- Transformers (Not efficient)\n- Linear Regression (Not real number values)\n- Logistic Regression (Not binary classification)\n- Decision Tree (Not sophisticated enough)\n- Naive Bayes (Not sophisticated enough)\n---\n---\n### Data Sources\n- [Serenes Forest](https://serenesforest.net)\n  - [FE1 Stats](https://serenesforest.net/shadow-dragon-and-blade-of-light/characters/base-stats/)\n  - [FE2 Stats](https://serenesforest.net/gaiden/characters/base-stats/)\n  - [FE3 Stats](https://serenesforest.net/mystery-of-the-emblem/characters/base-stats/)\n  - [FE6 Stats](https://serenesforest.net/binding-blade/characters/base-stats/)\n  - [FE11 Stats](https://serenesforest.net/shadow-dragon/characters/base-stats/default/)\n  - [FE12 Stats](https://serenesforest.net/light-and-shadow/characters/base-stats/default/)\n  - [FE13 Stats (DLC)](https://serenesforest.net/awakening/characters/base-stats/dlc/)\n  - [FE13 Stats (Spot Pass)](https://serenesforest.net/awakening/characters/base-stats/spotpass/)\n  - [FE14 Stats](https://serenesforest.net/fire-emblem-fates/other-characters/base-stats/)\n  - [FE15 Stats](https://serenesforest.net/fire-emblem-echoes-shadows-valentia/characters/base-stats/)\n  - [FE15 Stats](https://serenesforest.net/fire-emblem-echoes-shadows-valentia/miscellaneous/amiibo/)\n  - [FE16 Stats](https://serenesforest.net/three-houses/characters/base-stats/)\n- [Fire Emblem Heroes Wiki (Fandom)](https://feheroes.fandom.com/wiki/List_of_Heroes) Hero List\n---\n---\n### Legal\n- This project is a non-profit, informational data analysis experiment. *Fire Emblem* and all its related material are copyrighted by Nintendo/Intelligent Systems. This project is in no way affiliated or related to either of the companies.\n---\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrim0500%2Ffe-stats-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrim0500%2Ffe-stats-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrim0500%2Ffe-stats-classifier/lists"}