{"id":15398385,"url":"https://github.com/ototot/ytpoop","last_synced_at":"2025-10-29T04:40:10.062Z","repository":{"id":83335817,"uuid":"247342340","full_name":"oToToT/YTPoop","owner":"oToToT","description":"A lyric based recommendation system.","archived":false,"fork":false,"pushed_at":"2020-03-14T19:44:51.000Z","size":5,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-01T03:13:36.599Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://ytp.dve.tw/","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/oToToT.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":"2020-03-14T19:43:51.000Z","updated_at":"2020-03-20T19:30:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"39eaf390-f90a-409c-a622-f50bc5dd1adf","html_url":"https://github.com/oToToT/YTPoop","commit_stats":{"total_commits":1,"total_committers":1,"mean_commits":1.0,"dds":0.0,"last_synced_commit":"b192dd22a208bba6413316b39d05bda09f8031e3"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oToToT%2FYTPoop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oToToT%2FYTPoop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oToToT%2FYTPoop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oToToT%2FYTPoop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oToToT","download_url":"https://codeload.github.com/oToToT/YTPoop/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239952604,"owners_count":19723922,"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":"2024-10-01T15:42:59.986Z","updated_at":"2025-10-29T04:40:05.032Z","avatar_url":"https://github.com/oToToT.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# YTPoop #\n\n## Intro ##\n\nA song recommendation system with lyrics data.\n\n- Member\n  - [@minson123](https://github.com/minson123-github)\n  - [@harry900831](https://github.com/harry900831)\n  - [@oToToT](https://github.com/oToToT)\n- Instructor: Pu-Jen Cheng\n\nSlides: [https://dve.tw/V5B](https://dve.tw/V5B)\n\n## HowTo ##\n\n### Build up song database ###\n\nYou could use [@harry900831/mojim_lyrics_crawler](https://github.com/harry900831/mojim_lyrics_crawler) to crawl song data from [mojim.com](http://mojim.com/).\n\nAfter that, you should use `load_lyrics.py` to segment lyrics. Notice that we use [ckiptagger](https://github.com/ckiplab/ckiptagger) to segment lyrics, you should download it to `./ckiptagger/`.\n\nThen, we need to use [doc2vecC](https://github.com/mchen24/iclr2017) to perform doc2vec operation. However, we might want to add more corpus to train our data, so you could download [dump](https://dumps.wikimedia.org/zhwiki/latest/zhwiki-latest-pages-articles.xml.bz2) of wikipedia. To extract data from dumped data, you could use `wikiseg.py` to segment data.\n\nAlso, you might want to concat and shuffle wikicorpus and lyrics data.\n\nHere is some notes to use doc2vecC (assuming corpus in `corpus.txt` and lyrics data in `lyrics.txt`):\n1. `wget https://raw.githubusercontent.com/mchen24/iclr2017/master/doc2vecc.c`\n2. `gcc doc2vecc.c -o doc2vecc -lm -pthread -O3 -march=native -funroll-loops`\n3. `./doc2vecc -train corpus.txt -word wordvectors.txt -output docvectors.txt -cbow 1 -size 100 -window 10 -negative 5 -hs 0 -sample 0 -threads 4 -binary 0 -iter 20 -min-count 10 -test lyrics.txt -sentence-sample 0.1 -save-vocab alldata.vocab`\n\nWith docvectors generated, you might want to merge them back into the origin data, so you could run `parsevec.py` with log generated from `load_lyrics.py`. It will generate two `data/songs.json` without docvector inside it and `web/songs.json` with docvector inside it.\n\nThen, you need to add youtube link to every songs, you could use `youtubeid.py` to brute-forced crawl youtube data.\n\np.s [KKBOX](https://www.kkbox.com/) has provided a great [API](https://github.com/KKBOX/OpenAPI-Python) for songs data, but we doesn't know that before.\n\n### Launch Elasticsearch service ###\n\nYou could try to use Dockerfile inside `data` to launch a elsaticsearch sevice.\n\n### Launch Web Server ###\n\nYou could try to use Dockerfile inside `web` to launch a server from [@oToToT/YTPoop-Server](https://github.com/oToToT/YTPoop-Server). Notice that you may want to change the path to sqlite database or try other database, and also you could change `session_secret` inside it.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fototot%2Fytpoop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fototot%2Fytpoop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fototot%2Fytpoop/lists"}