{"id":22572826,"url":"https://github.com/gaurav-van/toxic-comment-web_app","last_synced_at":"2026-05-02T09:31:46.435Z","repository":{"id":186281330,"uuid":"526929283","full_name":"Gaurav-Van/Toxic-Comment-Web_App","owner":"Gaurav-Van","description":"Data Science Project to classify a comment into several toxicity categories. This Repository is used for deployment of the project. ","archived":false,"fork":false,"pushed_at":"2024-05-10T04:54:24.000Z","size":4244,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-02T15:14:08.969Z","etag":null,"topics":["classification","data-science","datacleaning","exploratory-data-analysis","machine-learning","nlp","nlp-machine-learning","python","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Gaurav-Van.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":"threat_model.pkl","audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-08-20T13:06:45.000Z","updated_at":"2024-06-18T13:16:16.000Z","dependencies_parsed_at":null,"dependency_job_id":"bb5fcc78-148a-435e-a082-0cd19a6a1602","html_url":"https://github.com/Gaurav-Van/Toxic-Comment-Web_App","commit_stats":null,"previous_names":["gaurav-van/toxic-comment-web_app"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gaurav-Van%2FToxic-Comment-Web_App","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gaurav-Van%2FToxic-Comment-Web_App/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gaurav-Van%2FToxic-Comment-Web_App/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gaurav-Van%2FToxic-Comment-Web_App/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Gaurav-Van","download_url":"https://codeload.github.com/Gaurav-Van/Toxic-Comment-Web_App/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246049632,"owners_count":20715511,"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":["classification","data-science","datacleaning","exploratory-data-analysis","machine-learning","nlp","nlp-machine-learning","python","streamlit"],"created_at":"2024-12-08T02:12:57.213Z","updated_at":"2026-05-02T09:31:46.396Z","avatar_url":"https://github.com/Gaurav-Van.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Toxic-Comment-App\n\u003chr\u003e\n\u003ch4\u003eNote: This Repository is required for deployment of this project on Streamlit Cloud.\u003c/h4\u003e\n\u003chr\u003e\nWeb App Link :- https://gaurav-van-toxic-comment-web-app-app-24y37c.streamlitapp.com/\n\u003chr\u003e\nProject Repo: https://github.com/Gaurav-Van/Data_Science__Machine_Learning-Projects\n\u003chr\u003e\n\nClassifying Comments in Six different Categories including their Neutral Cases Using Concepts of NLP and ML\n- Toxic \n- Severe Toxic\n- Threat \n- Obscene\n- Insult\n- Identity Hate\n\u003chr\u003e\n\n## Concept Used\u003c/br\u003e\u003c/br\u003e\nInstead of Multiclass classification, Binary Classification of Each Category is performed\u003c/br\u003e\u003c/br\u003e\n\u003cb\u003e1. Data Collection -\u003c/b\u003e From Kaggle: https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge\u003cbr\u003e\u003cbr\u003e\n\u003cb\u003e2. Data Pre-Procesing - Text Pre-Processing Using Regular Expressions\u003c/b\u003e\u003cbr\u003e\n* Removing \\n characters \n* Removing Aplha-Numeric Characters\n* Removing Punctuations  \n* Removing Non Ascii Characters\n\n\u003cb\u003e3. EDA - Performaing Data analysis to Discover some Issues and trend of the Data\u003c/b\u003e\u003cbr\u003e\n - Through Bar charts of Each Category :- \u003cb\u003eProb\u003c/b\u003e = Class Imbalance -\u003e \u003cb\u003eSolution\u003c/b\u003e = Making Frequency of 0s equal to Frequency of 1s by Making Different Dataset of each Category [ id, comment_text, category]. \n - Helps to solve the Issue of Class Imbalance and Helps in Binary Classification of Each Category\n\n\u003cb\u003e4. Model Building\u003c/b\u003e\u003cbr\u003e\n\n* \u003cb\u003eVECTORIZATION :-\u003c/b\u003e Using TF-IDF and Unigram Approach\n* \u003cb\u003eModel Used For Each Category :-\u003c/b\u003e KNN, Logistic Regression, SVM, CNB, BNB, DT and RF\n* \u003cb\u003eModel Selected/b\u003e - Logistic Regression\n* Exporting Trained ML Models as 6 pickle files [ one of each category ] \n* Exporting Trained Vectorized Models as 6 pickle files [ one for each category ] \n\u003c/br\u003e\u003c/br\u003e\n\n\u003cb\u003e5. Deployment - \u003c/b\u003e Building web app with the help of streamlit and deploying it on Streamlit cloud\n\u003chr\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaurav-van%2Ftoxic-comment-web_app","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgaurav-van%2Ftoxic-comment-web_app","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgaurav-van%2Ftoxic-comment-web_app/lists"}