{"id":13335594,"url":"https://github.com/Vice777/SAFE-HEART","last_synced_at":"2025-03-11T04:31:11.022Z","repository":{"id":54378804,"uuid":"521303254","full_name":"Vice777/SAFE-HEART","owner":"Vice777","description":"Classify the chances of having a Heart Attack based on your Heart's Condition.","archived":false,"fork":false,"pushed_at":"2022-10-22T08:47:18.000Z","size":3799,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-10-23T16:05:54.330Z","etag":null,"topics":["kaggle","machine-learning","matplotlib","mlfromscratch","mlp-classifier","multilayer-perceptron-network","numpy","pandas","pickle","streamlit","streamlit-webapp"],"latest_commit_sha":null,"homepage":"https://vice777-safe-heart-classifier-multilayer-perceptron--app-idf5su.streamlitapp.com/","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/Vice777.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}},"created_at":"2022-08-04T14:41:08.000Z","updated_at":"2023-09-20T11:31:31.000Z","dependencies_parsed_at":"2023-01-20T10:03:42.643Z","dependency_job_id":null,"html_url":"https://github.com/Vice777/SAFE-HEART","commit_stats":null,"previous_names":["vice777/safe-heart"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vice777%2FSAFE-HEART","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vice777%2FSAFE-HEART/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vice777%2FSAFE-HEART/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vice777%2FSAFE-HEART/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vice777","download_url":"https://codeload.github.com/Vice777/SAFE-HEART/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242972173,"owners_count":20215145,"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":["kaggle","machine-learning","matplotlib","mlfromscratch","mlp-classifier","multilayer-perceptron-network","numpy","pandas","pickle","streamlit","streamlit-webapp"],"created_at":"2024-07-29T19:05:28.887Z","updated_at":"2025-03-11T04:31:10.262Z","avatar_url":"https://github.com/Vice777.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Safe-Heart-Classifier-Multi-Layer-Perceptron-from-Scratch\n\nLINK : https://vice777-safe-heart-classifier-multilayer-perceptron--app-idf5su.streamlitapp.com/\n___\n\u003ca href=\"url\"\u003e\u003cimg src=\"https://i.pinimg.com/originals/3d/e3/a6/3de3a6cae7d628ad1ae7b6d03a4cd649.gif\" align=\"right\" height=\"240\" width=\"240\" \u003e\u003c/a\u003e\n\n## Description:\u003cbr\u003e\nClassify the chances of having a Heart Attack based on your Heart's Condition.\u003cbr\u003e\nIn this end-to-end Machine Learning project-tutorial, I have created and trained Multi-Layer model from scratch, using NumPy.\u003cbr\u003e\nFurthermore, the model with the best accuracy is embedded in the web-app developed using streamlit module for the purpose of classification of your Heart's Condition.   \u003cbr\u003e\n___\n\n\u003ch2\u003eUnderstanding the Problem Statement\u003c/h2\u003e\n\nThis project uses the popular \u003ca href=\"https://www.kaggle.com/datasets/rashikrahmanpritom/heart-attack-analysis-prediction-dataset\" target=\"_blank\"\u003eHeart Attack Analysis \u0026 Prediction Dataset\u003c/a\u003e  for training the model and making predictions.\u003cbr\u003e\n\nFor the purpose of prediction and classification, the features given in the table below are used. \u003cbr\u003e\nDetailed description about the features is provided within the table.\u003cbr\u003e\u003cbr\u003e\n\n \u003ctable\u003e \n    \u003ctr\u003e \n        \u003cth align=\\centre\\\u003e\u003cb\u003eFeatures\u003c/b\u003e\u003c/th\u003e \n        \u003cth align=\\centre\\\u003e\u003cb\u003eDescription\u003c/b\u003e\u003c/th\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003eAge\u003c/td\u003e  \n        \u003ctd\u003eAge of the patient\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003eSex \u003c/td\u003e \n        \u003ctd\u003eSex of the patient\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003ecp \u003c/td\u003e \n        \u003ctd\u003eChest Pain type chest pain type: \n            \u003cul\u003e \n                \u003cli\u003eValue 1: Typical angina\u003c/li\u003e \n                \u003cli\u003eValue 2: Atypical angina\u003c/li\u003e \n                \u003cli\u003eValue 3: Non-anginal pain\u003c/li\u003e \n                \u003cli\u003eValue 4: Asymptomatic\u003c/li\u003e \n            \u003c/ul\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003etrtbps \u003c/td\u003e \n        \u003ctd\u003eResting Blood Pressure (in mm Hg)\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003echol \u003c/td\u003e \n        \u003ctd\u003eCholestoral in mg/dl fetched via BMI Sensor\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003efbs \u003c/td\u003e \n        \u003ctd\u003e \n            (Fasting blood sugar \u003e 120 mg/dl)  \n            \u003cli\u003e1 = true\u003c/li\u003e \n            \u003cli\u003e0 = false \u003c/li\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003erestecg\u003c/td\u003e \n        \u003ctd\u003e \n            \u003col\u003e \n                \u003cli\u003eValue 0: Normal\u003c/li\u003e \n                \u003cli\u003eValue 1: Having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of \u003e 0.05 mV)\u003c/li\u003e \n                \u003cli\u003eValue 2: Showing probable or definite left ventricular hypertrophy by Estes criteria\u003c/li\u003e \n            \u003c/ul\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003ethalach \u003c/td\u003e \n        \u003ctd\u003eMaximum Heart Rate achieved\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003eexang\u003c/td\u003e \n        \u003ctd\u003eExercise induced angina                         \n        \u003cli\u003e1 = yes\u003c/li\u003e \n            \u003cli\u003e0 = no\u003c/li\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003eOldpeak\u003c/td\u003e  \n        \u003ctd\u003eST depression induced by exercise relative to rest \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003eslp \u003c/td\u003e \n        \u003ctd\u003ePeak exercise ST segment Slop \n            \u003cli\u003e 0 = Downsloping\u003c/li\u003e \n            \u003cli\u003e 1 = Flat\u003c/li\u003e \n            \u003cli\u003e 2 = Upsloping\u003c/li\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003ecaa\u003c/td\u003e  \n        \u003ctd\u003eThe number of major vessels (0–3)\u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003ethall \u003c/td\u003e \n        \u003ctd\u003eA blood disorder called Thalassemia \n            \u003cli\u003e Value 1: fixed defect (no blood flow in some part of the heart)\u003c/li\u003e \n            \u003cli\u003e Value 2: normal blood flow\u003c/li\u003e \n            \u003cli\u003e Value 3: reversible defect (a blood flow is observed but it is not normal)\u003c/li\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n    \u003ctr\u003e \n        \u003ctd\u003etarget \u003c/td\u003e \n        \u003ctd\u003ePercentage of deliverable volume \n            \u003cli\u003e 0= less chance of heart attack\u003c/li\u003e \n            \u003cli\u003e 1= more chance of heart attack\u003c/li\u003e \n        \u003c/td\u003e \n    \u003c/tr\u003e \n\u003c/table\u003e\u003cbr\u003e \n\n \n\n___\n\u003ch2\u003eKey Project Takeaways\u003c/h2\u003e\nThis project provided hands-on experience in real-time data handling and working behind Neural Networks :\u003cbr\u003e\u003cbr\u003e\n  \u003cul\u003eData preprocessing and cleaning for training and testing the data\u003c/ul\u003e\n  \u003cul\u003eBuilding an efficient Neural Network \u003cb\u003e(Multi-Layer Perceptron)\u003c/b\u003e from scratch using NumPy\u003c/ul\u003e\n  \u003cul\u003eMathematics behind \u003cb\u003e Activation Functions\u003c/b\u003e and \u003cb\u003eGradient Losses\u003c/b\u003e\u003c/ul\u003e\n  \u003cul\u003eWeb-app development using Streamlit\u003c/ul\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVice777%2FSAFE-HEART","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FVice777%2FSAFE-HEART","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FVice777%2FSAFE-HEART/lists"}