{"id":23707520,"url":"https://github.com/vertti/crypto-tweet-spam-ml","last_synced_at":"2025-07-04T17:04:39.130Z","repository":{"id":40845111,"uuid":"237961223","full_name":"vertti/crypto-tweet-spam-ml","owner":"vertti","description":null,"archived":false,"fork":false,"pushed_at":"2023-01-05T10:26:34.000Z","size":63523,"stargazers_count":1,"open_issues_count":28,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2024-12-30T16:57:08.771Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vertti.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":"2020-02-03T12:35:59.000Z","updated_at":"2023-10-31T00:10:33.000Z","dependencies_parsed_at":"2023-02-04T01:15:39.173Z","dependency_job_id":null,"html_url":"https://github.com/vertti/crypto-tweet-spam-ml","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/vertti%2Fcrypto-tweet-spam-ml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertti%2Fcrypto-tweet-spam-ml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertti%2Fcrypto-tweet-spam-ml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertti%2Fcrypto-tweet-spam-ml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vertti","download_url":"https://codeload.github.com/vertti/crypto-tweet-spam-ml/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239787795,"owners_count":19697083,"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":"2024-12-30T16:57:23.062Z","updated_at":"2025-02-20T06:24:36.622Z","avatar_url":"https://github.com/vertti.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# crypto-tweet-spam-ml\n\n## Fetching data\n\nInstall `twurl` and `jq`. Authenticate with Twitter using:\n\n```\ntwurl authorize --bearer --consumer-key your-consumer-key --consumer-secret your-consumer-secret\n```\n\nthen fetch tweets about different crypto currencies ($ETH, $NEO, $VET etc.) by running:\n\n```\n./load-tweet-set.sh\n```\n\nThis will do multiple Twitter search queries and convert the results to JSONL files where each line contains one tweet and it's metadata (like the retweet count of that tweet).\n\n## Training with Prodigy\n\nInstall Prodigy.\n\nInstall SpaCy language model with:\n\n```\npython -m spacy download en_core_web_sm\n```\n\nand start training with seed words defined in `spam-seeds.jsonl` with:\n\n```\nprodigy textcat.teach twitter_spam en_core_web_sm ./alltweets.jsonl --label SPAM --patterns ./spam-seeds.jsonl\n```\n\nWhen you've done enough teaching, quit Prodigy and run training:\n\n```\nprodigy textcat.batch-train twitter_spam en_core_web_sm --output twitter-spam-model --eval-split 0.2\n```\n\nThis will create training and evaluation sets and SpaCy model in `twitter-spam-model` folder.\n\n## Training with CatBoost\n\nInstall dependencies with `pipenv`.\n\nRun `catboost_train.py` to train CatBoost with training set from Prodigy:\n\n```\npipenv run python catboost_train.py\n```\n\n\n## Deploying to Kubernetes\n\n# Create configmap\n\n`.env` file needs to contain following values:\n\n\n\nThose can then be deployed to Kubernetes with:\n\n```\nkubectl create configmap shared-env --from-env-file=.env\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvertti%2Fcrypto-tweet-spam-ml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvertti%2Fcrypto-tweet-spam-ml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvertti%2Fcrypto-tweet-spam-ml/lists"}