{"id":28376695,"url":"https://github.com/sarvamm/datars-ai","last_synced_at":"2025-06-26T14:31:09.686Z","repository":{"id":287150419,"uuid":"963671376","full_name":"Sarvamm/DATARS-AI","owner":"Sarvamm","description":"Automated data analysis powered by local LLMs","archived":false,"fork":false,"pushed_at":"2025-04-26T06:13:38.000Z","size":5192,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-30T00:07:35.740Z","etag":null,"topics":["chatbot","data-science","data-visualization","llms","streamlit"],"latest_commit_sha":null,"homepage":"","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/Sarvamm.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,"zenodo":null}},"created_at":"2025-04-10T03:22:31.000Z","updated_at":"2025-05-24T17:50:47.000Z","dependencies_parsed_at":"2025-04-14T06:32:18.789Z","dependency_job_id":null,"html_url":"https://github.com/Sarvamm/DATARS-AI","commit_stats":null,"previous_names":["sarvamm/datars","sarvamm/datars---automated-data-analysis","sarvamm/datars-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Sarvamm/DATARS-AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sarvamm%2FDATARS-AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sarvamm%2FDATARS-AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sarvamm%2FDATARS-AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sarvamm%2FDATARS-AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sarvamm","download_url":"https://codeload.github.com/Sarvamm/DATARS-AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sarvamm%2FDATARS-AI/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262084607,"owners_count":23256268,"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":["chatbot","data-science","data-visualization","llms","streamlit"],"created_at":"2025-05-30T00:07:35.665Z","updated_at":"2025-06-26T14:31:09.671Z","avatar_url":"https://github.com/Sarvamm.png","language":"Python","funding_links":["https://buymeacoffee.com/astrayn"],"categories":[],"sub_categories":[],"readme":"#  DATARS – Automated Data Analysis\n\nDATARS is a powerful and user-friendly Streamlit app that leverages local LLMs to understand, summarize, and visualize your dataset—all in a few clicks. Whether you're an analyst or a data science enthusiast, DATARS helps you interact with your data like never before.\n\n---\n\n## Features\n\n###  1. Data Overview Page\nHarness the power of AI to:\n- Summarize your dataset automatically\n- Detect outliers\n- Perform correlation analysis\n- Recommend and generate suitable graphs using LLMs\n![Data Overview](https://raw.githubusercontent.com/Sarvamm/DATARS---Automated-Data-Analysis/refs/heads/main/assets/overview.png)\n\n###  2. Data Profiling Page\nGet a comprehensive EDA report powered by ydata_profiling, including:\n- **Warnings**: Spot potential issues (missing values, skewness, etc.)\n- **Univariate Analysis**: Summary stats (mean, median, mode) and histograms\n- **Multivariate Analysis**: Correlation heatmaps, missing data patterns, duplicate detection, and pairwise relationships\n![Data Profiling](https://raw.githubusercontent.com/Sarvamm/DATARS---Automated-Data-Analysis/refs/heads/main/assets/profiling.png)\n\n###  3. Chatbot\nType in natural language commands like:\n\u003e “Plot the distribution of column A”  \n\u003e “Show mean values grouped by category”  \n\u003e “Detect missing values”\n\nLLM-backed chatbot will convert it into Python code, run it, and show you the result—instantly.\n![Talk to Tars](https://raw.githubusercontent.com/Sarvamm/DATARS---Automated-Data-Analysis/refs/heads/main/assets/chatbot.png)\n\n### 📈 4. Manual Graph Plotter\nIf you want to customize visualizations yourself, use the dedicated graph plotter to manually create a wide variety of plots.\n![Plot Graphs](https://raw.githubusercontent.com/Sarvamm/DATARS---Automated-Data-Analysis/refs/heads/main/assets/graphplotter.png)\n---\n\n## 🧰 Tech Stack \u0026 Libraries\n\n- [Streamlit](https://streamlit.io/) \n- [Ollama](https://ollama.com/) \n- [Pandas](https://pandas.pydata.org/) \n- [Matplotlib](https://matplotlib.org/)\n- [Seaborn](https://seaborn.pydata.org/) \n- [Plotly](https://plotly.com/python/) \n- [YData Profiling](https://github.com/ydataai/ydata-profiling) \n- [streamlit-extras](https://github.com/arnaudmiribel/streamlit-extras)\n- [streamlit-pandas-profiling](https://github.com/pandas-profiling/pandas-profiling)\n\n---\n\n##  Getting Started\n\n###  Installation\n```bash\ngit clone https://github.com/sarvamm/DATARS-AI.git\ncd DATARS-AI\npip install -r requirements.txt\n```\n\n###  Set Up Ollama\nEnsure Ollama and your preferred local LLM are installed and running.\nBy default gemma3 and qwen2.5-coder:7b are used so make sure you have them.\n\n### Install Ollama\n```bash\npip install ollama\n```\n\n### Install gemma3 and qwen2.5-coder:7b\n```bash\nollama pull gemma3\n```\n```bash\nollama pull qwen2.5-coder:7b\n```\n---\n\n## Run the App\n```bash\nstreamlit run App.py\n```\n\n---\n\n## Folder Structure\n```\nDATARS/\n│\n├── App.py                     # Main entry point\n├── Functions.py               # Helper functions\n├── .streamlit/                # Config and secrets\n├── pages/\n│   ├── About.py\n│   ├── Chatbot.py\n│   ├── Graph_Plots.py\n│   ├── Overview.py\n│   └── Statistics.py\n├── assets/                    # Logo and media\n├── outputs/                   # Generated reports\n├── requirements.txt\n├── LICENSE\n└── .gitignore\n```\n\n---\n\n## 📬 Contact\n \n🔗 [LinkedIn](https://www.linkedin.com/in/sarvamm) • [GitHub](https://github.com/sarvamm) • [Buy me a Coffee](https://buymeacoffee.com/astrayn) \n\n---\n\n##  License\n\nThis project is licensed under the terms of the Non-Profit Open Software License version 3.0.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsarvamm%2Fdatars-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsarvamm%2Fdatars-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsarvamm%2Fdatars-ai/lists"}