{"id":34260443,"url":"https://github.com/mdda/billion-placeholder","last_synced_at":"2026-03-12T11:06:02.561Z","repository":{"id":138389360,"uuid":"28610581","full_name":"mdda/billion-placeholder","owner":"mdda","description":"Placeholder while working on Kaggle HowTo","archived":false,"fork":false,"pushed_at":"2015-05-03T18:48:18.000Z","size":1344,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2023-03-11T07:58:06.069Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mdda.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2014-12-29T23:43:49.000Z","updated_at":"2023-03-12T21:25:39.530Z","dependencies_parsed_at":"2023-03-13T10:54:17.517Z","dependency_job_id":null,"html_url":"https://github.com/mdda/billion-placeholder","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"purl":"pkg:github/mdda/billion-placeholder","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdda%2Fbillion-placeholder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdda%2Fbillion-placeholder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdda%2Fbillion-placeholder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdda%2Fbillion-placeholder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mdda","download_url":"https://codeload.github.com/mdda/billion-placeholder/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdda%2Fbillion-placeholder/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27767501,"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","status":"online","status_checked_at":"2025-12-16T02:00:10.477Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2025-12-16T16:00:10.744Z","updated_at":"2025-12-16T16:00:13.601Z","avatar_url":"https://github.com/mdda.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"billion-placeholder\n===================\n\n*Placeholder while working on Kaggle HowTo* \n\nThe intention was to put a working solution \nto the [Billion Word Imputation challenge](http://www.kaggle.com/c/billion-word-imputation/) \ninto the pubic domain during Jan-2015 (i.e. well prior to the end of the competition).\nMy thinking was that many would-be competitors were holding back because\nthe task was so daunting, but would be encouraged to 'have a go' if there\nwas some known-decent starting point.\n\nHowever, the real world intervened, putting the Neural Network (Theano-based)\nimplementation on-hold - to such an extent that the clock started to run out.\n\nJust to put in some kind of showing, I created a wholely new approach, based\non bigrams only using the Go language, over a weekend, for fun.\n\nThis solution was (of course) much worse than would have been acheivable \nusing the NN method(s) originally targetted, but had the advantage of \nbeing ready to submit quickly.\n\nSo, somewhat resigned to not acheiving the original goals, I just submitted \na basic bigram approach-based submission, plus another couple that were\nbased on optimising a couple of hyperparameters too.  That was \ngood enough for 12th out of 87.\n\n\nAnd so it ends...\n-------------------\n\nThe only submittable results were produced by code in ```\u003cTHIS-REPO\u003e/go_src```, \nwhich took about a weekend to write.\n\nThere's probably enough 'juice' in the pure bigram approach (which is all\nthat is done in go_src) to get to #8 from current #12, \nbut no futher, since there is a step-wise change between #8 and #7.\n\nBut time would be better spent (i) sleeping; (ii) working on something \nthat can be submitted to a conference instead.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmdda%2Fbillion-placeholder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmdda%2Fbillion-placeholder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmdda%2Fbillion-placeholder/lists"}