{"id":28764477,"url":"https://github.com/imprv-ai/date-a-scientist","last_synced_at":"2025-10-06T00:44:11.157Z","repository":{"id":246763363,"uuid":"822651895","full_name":"imprv-ai/date-a-scientist","owner":"imprv-ai","description":"Query dataframes, find issue with your notebook snippets as if a professional data scientist was pair coding with you.  Currently just a thin wrapper around an amazing library called pandas-ai by sinaptik-ai!","archived":false,"fork":false,"pushed_at":"2025-01-10T14:39:15.000Z","size":766,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-08-27T03:37:07.545Z","etag":null,"topics":["data-science","dataframes","notebook-jupyter","pandas","pandas-ai"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/imprv-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-07-01T14:47:53.000Z","updated_at":"2025-02-17T00:55:49.000Z","dependencies_parsed_at":"2025-01-10T15:37:11.561Z","dependency_job_id":"66a3591e-f821-4e93-9acd-0c953268d918","html_url":"https://github.com/imprv-ai/date-a-scientist","commit_stats":null,"previous_names":["imprv-ai/date-a-scientist"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/imprv-ai/date-a-scientist","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imprv-ai%2Fdate-a-scientist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imprv-ai%2Fdate-a-scientist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imprv-ai%2Fdate-a-scientist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imprv-ai%2Fdate-a-scientist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/imprv-ai","download_url":"https://codeload.github.com/imprv-ai/date-a-scientist/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imprv-ai%2Fdate-a-scientist/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278542680,"owners_count":26004060,"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":"2025-10-05T02:00:06.059Z","response_time":54,"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":["data-science","dataframes","notebook-jupyter","pandas","pandas-ai"],"created_at":"2025-06-17T10:01:13.514Z","updated_at":"2025-10-06T00:44:11.152Z","avatar_url":"https://github.com/imprv-ai.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\u003cpicture align=\"center\"\u003e\n  \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"assets/img/date_a_scientist_logo_white.svg\"\u003e\n  \u003cimg alt=\"date-a-scientist Logo\" src=\"assets/img/date_a_scientist_logo.svg\"\u003e\n\u003c/picture\u003e\n\n-----------------\n\n# date-a-scientist\n\nQuery dataframes, find issue with your notebook snippets as if a professional data scientist was pair coding with you.\n\nCurrently just a thin wrapper around an amazing library called `pandas-ai` by sinaptik-ai!\n\n## How to use it?\n\n```python\nfrom date_a_scientist import DateAScientist\nimport pandas as pd\n\ndf = pd.DataFrame(\n    [\n        {\"name\": \"Alice\", \"age\": 25, \"city\": \"New York\"},\n        {\"name\": \"Bob\", \"age\": 30, \"city\": \"Los Angeles\"},\n        {\"name\": \"Charlie\", \"age\": 35, \"city\": \"Chicago\"},\n    ]\n)\nds = DateAScientist(\n    df=df,\n    llm_openai_api_token=...,  # your OpenAI API token goes here\n    llm_model_name=\"gpt-3.5-turbo\",  # by default, it uses \"gpt-4o\"\n)\n\n# should return \"Alice\"\nds.chat(\"What is the name of the first person?\")\n```\n\nAdditionally we can pass a description of fields, so that more meaningful questions can be asked:\n\n```python\nds = DateAScientist(\n    df=df,\n    llm_openai_api_token=...,  # your OpenAI API token goes here\n    llm_model_name=\"gpt-3.5-turbo\",  # by default, it uses \"gpt-4o\"\n    column_descriptions={\n        \"name\": \"The name of the person\",\n        \"age\": \"The age of the person\",\n        \"city\": \"The city where the person lives\",\n    },\n)\n\nds = DateAScientist(\n    df=df,\n    llm_openai_api_token=...,  # your OpenAI API token goes here\n    llm_model_name=\"gpt-3.5-turbo\",  # by default, it uses \"gpt-4o\"\n)\n\n# should return DataFrame with Chicago rows\nds.chat(\"Who lives in Chicago?\")\n```\n\nFinally if you want to get the code that was generated, you can use `ds.code()`:\n\n```python\nds.code(\"Who lives in Chicago?\")\n```\n\nwhich will return monokai styled code. If you want to return plain code, you can use:\n```python\nds.code(\"Who lives in Chicago?\", return_as_string=True)\n```\n\n## Inspirations\n\n- https://github.com/sinaptik-ai/pandas-ai\n- https://levelup.gitconnected.com/create-copilot-inside-your-notebooks-that-can-chat-with-graphs-write-code-and-more-e9390e2b9ed8\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimprv-ai%2Fdate-a-scientist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimprv-ai%2Fdate-a-scientist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimprv-ai%2Fdate-a-scientist/lists"}