{"id":13689319,"url":"https://github.com/benhamner/Metrics","last_synced_at":"2025-05-01T23:33:47.435Z","repository":{"id":3576751,"uuid":"4639444","full_name":"benhamner/Metrics","owner":"benhamner","description":"Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave","archived":false,"fork":false,"pushed_at":"2023-01-11T06:01:24.000Z","size":803,"stargazers_count":1628,"open_issues_count":36,"forks_count":454,"subscribers_count":87,"default_branch":"master","last_synced_at":"2024-10-29T15:39:57.451Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/benhamner.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2012-06-12T15:52:50.000Z","updated_at":"2024-10-24T18:38:52.000Z","dependencies_parsed_at":"2023-01-13T12:37:42.925Z","dependency_job_id":null,"html_url":"https://github.com/benhamner/Metrics","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benhamner%2FMetrics","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benhamner%2FMetrics/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benhamner%2FMetrics/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/benhamner%2FMetrics/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/benhamner","download_url":"https://codeload.github.com/benhamner/Metrics/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224155591,"owners_count":17265355,"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":"2024-08-02T15:01:43.035Z","updated_at":"2024-11-12T13:31:27.063Z","avatar_url":"https://github.com/benhamner.png","language":"Python","readme":"**Note: the current releases of this toolbox are a beta release, to test working with Haskell's, Python's, and R's code repositories.**\n\n![Build Status](https://travis-ci.org/benhamner/Metrics.png)\n\n**Metrics** provides implementations of various supervised machine learning evaluation metrics in the following languages:\n \n - [**Python**](https://github.com/benhamner/Metrics/tree/master/Python) ```easy_install ml_metrics```\n - [**R**](https://github.com/benhamner/Metrics/tree/master/R) ```install.packages(\"Metrics\")``` from the R prompt\n - [**Haskell**](https://github.com/benhamner/Metrics/tree/master/Haskell) ```cabal install Metrics```\n - [**MATLAB / Octave**](https://github.com/benhamner/Metrics/tree/master/MATLAB) (clone the repo \u0026 run setup from the MATLAB command line)\n\nFor more detailed installation instructions, see the README for each implementation.\n\nEVALUATION METRICS\n------------------\n\n\u003ctable\u003e\n\u003ctr\u003e\u003ctd\u003eEvaluation Metric\u003c/td\u003e\u003ctd\u003ePython\u003c/td\u003e\u003ctd\u003eR\u003c/td\u003e\u003ctd\u003eHaskell\u003c/td\u003e\u003ctd\u003eMATLAB / Octave\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eAbsolute Error (AE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eAverage Precision at K (APK, AP@K)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eArea Under the ROC (AUC)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eClassification Error (CE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eF1 Score (F1)\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eGini\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLevenshtein\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eLog Loss (LL)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Log Loss (LogLoss)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Absolute Error (MAE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Average Precision at K (MAPK, MAP@K)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Quadratic Weighted Kappa\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Squared Error (MSE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eMean Squared Log Error (MSLE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eNormalized Gini\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eQuadratic Weighted Kappa\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eRelative Absolute Error (RAE)\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eRoot Mean Squared Error (RMSE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eRelative Squared Error (RSE)\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eRoot Relative Squared Error (RRSE)\u003c/td\u003e\u003ctd\u003e \u003ctd\u003e\u0026#10003;\u003c/td\u003e \u003c/td\u003e\u003ctd\u003e \u003c/td\u003e\u003ctd\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eRoot Mean Squared Log Error (RMSLE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eSquared Error (SE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eSquared Log Error (SLE)\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003ctd\u003e\u0026#10003;\u003c/td\u003e\u003c/tr\u003e\n\u003c/table\u003e\n\nTO IMPLEMENT\n------------\n\n - F1 score\n - Multiclass log loss\n - Lift\n - Average Precision for binary classification\n - precision / recall break-even point\n - cross-entropy\n - True Pos / False Pos / True Neg / False Neg rates\n - precision / recall / sensitivity / specificity\n - mutual information\n\nHIGHER LEVEL TRANSFORMATIONS TO HANDLE\n--------------------------------------\n\n - GroupBy / Reduce\n - Weight individual samples or groups\n\nPROPERTIES METRICS CAN HAVE\n---------------------------\n\n(Nonexhaustive and to be added in the future)\n\n - Min or Max (optimize through minimization or maximization)\n - Binary Classification\n   - Scores predicted class labels\n   - Scores predicted ranking (most likely to least likely for being in one class)\n   - Scores predicted probabilities\n - Multiclass Classification\n   - Scores predicted class labels\n   - Scores predicted probabilities\n - Regression\n - Discrete Rater Comparison (confusion matrix)\n\n  ","funding_links":[],"categories":["Machine Learning","资源列表","Evaluation","Python","机器学习","Machine Learning [🔝](#readme)","Awesome Python"],"sub_categories":["机器学习","Synthetic Data","Automatic Plotting","NLP","Machine Learning","Drone Frames"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbenhamner%2FMetrics","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbenhamner%2FMetrics","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbenhamner%2FMetrics/lists"}