{"id":17841716,"url":"https://github.com/blackcipher101/newsclassifier","last_synced_at":"2025-04-02T14:11:18.348Z","repository":{"id":119133439,"uuid":"317833408","full_name":"Blackcipher101/Newsclassifier","owner":"Blackcipher101","description":"It classifies News into its genre using NLP","archived":false,"fork":false,"pushed_at":"2021-01-10T08:19:22.000Z","size":213,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-08T05:16:52.686Z","etag":null,"topics":["classification","news","nlp","tensowflow"],"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/Blackcipher101.png","metadata":{"files":{"readme":"README.md","changelog":"newsclassfier.ipynb","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":"2020-12-02T10:58:15.000Z","updated_at":"2021-04-21T21:13:28.000Z","dependencies_parsed_at":"2023-07-09T23:16:20.181Z","dependency_job_id":null,"html_url":"https://github.com/Blackcipher101/Newsclassifier","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/Blackcipher101%2FNewsclassifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Blackcipher101%2FNewsclassifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Blackcipher101%2FNewsclassifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Blackcipher101%2FNewsclassifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Blackcipher101","download_url":"https://codeload.github.com/Blackcipher101/Newsclassifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246828502,"owners_count":20840474,"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","news","nlp","tensowflow"],"created_at":"2024-10-27T21:06:05.330Z","updated_at":"2025-04-02T14:11:18.332Z","avatar_url":"https://github.com/Blackcipher101.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NewsClassfier\n\n## Thought process :thinking:\nI had to do something on my own to brush up what I had learned in the udacity course so I was searching for ideas I was by struck how news papers:newspaper:\nclassify its content into diffrent sections and if it could be automated \t:wrench: using NLP.\n\n## Hunt for the dataset\nI had now started the hunt for the dataset and after 2 days searching I had found nothing but I had eye on dataset provided on kaggle by BBC but it was for text\nsummary but I had a idea how to tweak it to get it my way. So decided not to waste more time on finding the dataset.\n\n## Preprocessing\nNow here comes the hard part :fearful: . I had the dataset already spilt into its section but now I had to load it into an array but not all of them had same number of files and some files were only readble in binary encoding.\n\nAfter this I had to go through the normal procedure of making them into a single line tokennize it , put paddings in place and split it into traning and valdataion set.\n\n## Model\nI actually started out with a embedding layer and two bidierctional LSTMs and it did what all my models do the first the first time they over fit :slightly_frowning_face:.\nThen I made it one Bidirectional LSTMs still over fit then I had to move to GlobalAveragePooling1D layer to fix it it gave me an accuracy of 82% which I was happy :smile: with.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackcipher101%2Fnewsclassifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblackcipher101%2Fnewsclassifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackcipher101%2Fnewsclassifier/lists"}