{"id":20419196,"url":"https://github.com/aaaastark/textclassification-nlp-project","last_synced_at":"2026-04-11T17:33:25.665Z","repository":{"id":179677717,"uuid":"486169815","full_name":"aaaastark/TextClassification-NLP-Project","owner":"aaaastark","description":"Dataset preparation, Feature Engineering, Model Building, Summary Statistics, Data Exploration by Visualizations, and Save File CSV","archived":false,"fork":false,"pushed_at":"2022-04-27T11:54:00.000Z","size":2017,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-04T04:16:03.618Z","etag":null,"topics":["matplotlib","nltk","numpy","pandas","python","seaborn","sklearn","textblob","wordcloud"],"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/aaaastark.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":"2022-04-27T11:47:07.000Z","updated_at":"2022-04-27T11:54:03.000Z","dependencies_parsed_at":null,"dependency_job_id":"518535e7-72e4-41bd-bfbf-0b6408e2c5b3","html_url":"https://github.com/aaaastark/TextClassification-NLP-Project","commit_stats":null,"previous_names":["aaaastark/textclassification-nlp-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/aaaastark/TextClassification-NLP-Project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaaastark%2FTextClassification-NLP-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaaastark%2FTextClassification-NLP-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaaastark%2FTextClassification-NLP-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaaastark%2FTextClassification-NLP-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aaaastark","download_url":"https://codeload.github.com/aaaastark/TextClassification-NLP-Project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaaastark%2FTextClassification-NLP-Project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31689758,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-11T13:07:20.380Z","status":"ssl_error","status_checked_at":"2026-04-11T13:06:47.903Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["matplotlib","nltk","numpy","pandas","python","seaborn","sklearn","textblob","wordcloud"],"created_at":"2024-11-15T06:36:15.002Z","updated_at":"2026-04-11T17:33:25.649Z","avatar_url":"https://github.com/aaaastark.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TextClassification-NLP-Project\nDataset preparation, Feature Engineering, Model Building, Summary Statistics, Data Exploration by Visualizations, and Save File CSV.\n\n## NOTE: Open the GPU (Google Colab)\n\n# 1. Dataset preparation\n*   Data Set Load (Movies - TV)\n*   Train, Test and Encoder (Train and Validation)\n\n# 2. Feature Engineering\n2.1 Count Vectors as features\n\n2.2 TF-IDF Vectors as features\n*   Word level\n*   N-Gram level\n*   Character level\n\n2.3 Text / NLP based features\n\n# 3. Model Building\n3.1   Naive Bayes Classifier (Accuray, Confusion Matrix, Precision, Recall Score, F1 Score)\n\n3.2   Linear Classifier (Accuray, Confusion Matrix, Precision, Recall Score, F1 Score)\n\n3.3   Support Vector Machine (Accuray, Confusion Matrix, Precision, Recall Score, F1 Score)\n\n# 4. Summary Statistics\n\n# 5. Data Exploration by Visualizations\n\n5.1 Word Density\n\n5.2 Rating Text\n\n5.3 Create Word Clouds\n\n*   5.3.1 Word Cloud for Rating (Label) Score is 5, 4, 3, 2, 1\n\n# 6. Save File CSV\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaaastark%2Ftextclassification-nlp-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faaaastark%2Ftextclassification-nlp-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaaastark%2Ftextclassification-nlp-project/lists"}