{"payload":{"header_redesign_enabled":false,"results":[{"id":"654629005","archived":false,"color":"#3572A5","followers":49,"has_funding_file":false,"hl_name":"onesuper/HuggingFace-Datasets-Text-Quality-Analysis","hl_trunc_description":"Retrieves parquet files from Hugging Face, identifies and quantifies junky data, duplication, contamination, and biased content in datase…","language":"Python","mirror":false,"owned_by_organization":false,"public":true,"repo":{"repository":{"id":654629005,"name":"HuggingFace-Datasets-Text-Quality-Analysis","owner_id":977633,"owner_login":"onesuper","updated_at":"2023-07-06T14:07:05.209Z","has_issues":true}},"sponsorable":false,"topics":["nlp","machine-learning","dataset","text-processing","streamlit","huggingface-datasets","llm"],"type":"Public","help_wanted_issues_count":0,"good_first_issue_issues_count":0,"starred_by_current_user":false}],"type":"repositories","page":1,"page_count":1,"elapsed_millis":88,"errors":[],"result_count":1,"facets":[],"protected_org_logins":[],"topics":null,"query_id":"","logged_in":false,"sign_up_path":"/signup?source=code_search_results","sign_in_path":"/login?return_to=https%3A%2F%2Fgithub.com%2Fsearch%3Fq%3Drepo%253Aonesuper%252FHuggingFace-Datasets-Text-Quality-Analysis%2B%2Blanguage%253APython","metadata":null,"warn_limited_results":false,"csrf_tokens":{"/onesuper/HuggingFace-Datasets-Text-Quality-Analysis/star":{"post":"397wxrNgvyh-DARt8YDRYZE085bSzOXnimOt--mmAkHYtSFTFrYb1bk_VBh7LAflrWPJtotdpx7raedK7eeRBQ"},"/onesuper/HuggingFace-Datasets-Text-Quality-Analysis/unstar":{"post":"C9kr_Sxtl4eEEvxNDRKWUNVnhs4D_DXF_pl2-iwPI2WkxhDZSqpq77VuwLPDm5qDSqA51EZB2fe-8scYhy1_aQ"},"/sponsors/batch_deferred_sponsor_buttons":{"post":"fv3BjGir7wVhr2dYQ0FYO2C2ouuCHLAVvp2iVs8xAJK-wI934zOg0v9MqLf6QO189C0DYczmLUUwn59x1_2XOg"}}},"title":"Repository search results"}