{"id":15033944,"url":"https://github.com/chenglongchen/kaggle-crowdflower","last_synced_at":"2025-05-15T19:05:10.525Z","repository":{"id":46798818,"uuid":"38952715","full_name":"ChenglongChen/kaggle-CrowdFlower","owner":"ChenglongChen","description":"1st Place Solution for CrowdFlower Product Search Results Relevance Competition on Kaggle.","archived":false,"fork":false,"pushed_at":"2021-09-25T02:32:49.000Z","size":6749,"stargazers_count":1767,"open_issues_count":1,"forks_count":658,"subscribers_count":101,"default_branch":"master","last_synced_at":"2025-05-15T19:04:23.044Z","etag":null,"topics":["crowdflower","kaggle","kaggle-competetion","kaggle-crowdflower","natural-language-processing","nlp","product-search","relevance-competition","search-engine","search-relevance","semantic-matching","semantic-similarity"],"latest_commit_sha":null,"homepage":"https://www.kaggle.com/c/crowdflower-search-relevance","language":"C++","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/ChenglongChen.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}},"created_at":"2015-07-12T06:41:27.000Z","updated_at":"2025-04-30T00:19:38.000Z","dependencies_parsed_at":"2022-08-22T23:20:32.167Z","dependency_job_id":null,"html_url":"https://github.com/ChenglongChen/kaggle-CrowdFlower","commit_stats":null,"previous_names":["chenglongchen/kaggle_crowdflower"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenglongChen%2Fkaggle-CrowdFlower","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenglongChen%2Fkaggle-CrowdFlower/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenglongChen%2Fkaggle-CrowdFlower/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenglongChen%2Fkaggle-CrowdFlower/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenglongChen","download_url":"https://codeload.github.com/ChenglongChen/kaggle-CrowdFlower/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254404357,"owners_count":22065641,"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":["crowdflower","kaggle","kaggle-competetion","kaggle-crowdflower","natural-language-processing","nlp","product-search","relevance-competition","search-engine","search-relevance","semantic-matching","semantic-similarity"],"created_at":"2024-09-24T20:23:20.163Z","updated_at":"2025-05-15T19:05:10.481Z","avatar_url":"https://github.com/ChenglongChen.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Kaggle_CrowdFlower\n\n1st Place Solution for [Search Results Relevance Competition on Kaggle](https://www.kaggle.com/c/crowdflower-search-relevance)\n\nThe best single model we have obtained during the competition was an [XGBoost](https://github.com/dmlc/xgboost) model with linear booster of Public LB score **0.69322** and Private LB score **0.70768**. Our final winning submission was a median ensemble of 35 best Public LB submissions. This submission scored **0.70807** on Public LB and **0.72189** on Private LB.\n\n## What's New\n* 2016/05/14: For a more clean and modularized version of this code and framework, you may want to check [Kaggle_HomeDepot](https://github.com/ChenglongChen/Kaggle_HomeDepot), which holds the code of Turing Test's solution for the recently [Home Depot Product Search Relevance Competition on Kaggle](https://www.kaggle.com/c/home-depot-product-search-relevance).\n\n## FlowChart\n\n\u003cimg src=\"./Doc/FlowChart.jpg\" alt=\"FlowChart\" align=\"center\" width=\"700px\"/\u003e\n\n\n## Documentation\n\nSee `./Doc/Kaggle_CrowdFlower_ChenglongChen.pdf` for documentation.\n\n## Instruction\n\n* download data from the [competition website](https://www.kaggle.com/c/crowdflower-search-relevance/data) and put all the data into folder `./Data`.\n* run `python ./Code/Feat/run_all.py` to generate features. This will take a few hours.\n* run `python ./Code/Model/generate_best_single_model.py` to generate best single model submission. In our experience, it only takes a few trials to generate model of best performance or similar performance. See the training log in `./Output/Log/[Pre@solution]_[Feat@svd100_and_bow_Jun27]_[Model@reg_xgb_linear]_hyperopt.log` for example.\n* run `python ./Code/Model/generate_model_library.py` to generate model library. This is quite time consuming. **But you don't have to wait for this script to finish: you can run the next step once you have some models trained.**\n* run `python ./Code/Model/generate_ensemble_submission.py` to generate submission via ensemble selection.\n* if you don't want to run the code, just submit the file in `./Output/Subm`.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchenglongchen%2Fkaggle-crowdflower","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchenglongchen%2Fkaggle-crowdflower","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchenglongchen%2Fkaggle-crowdflower/lists"}