Hugging Face's logo

Spaces:
BonusLockSMith
/
csv-insights
Sleeping

App Files Community
csv-insights / README.md
BonusLockSMith's picture
BonusLockSMith
Upload folder using huggingface_hub
e2f9a1d verified
preview code
|
Raw History Blame Contribute Delete
2.22 kB
metadata 
title: CSV to Insights Analyst
emoji: 📊
colorFrom: gray
colorTo: red
sdk: docker
app_port: 7860
pinned: false

CSV → Insights Analyst 📊

Upload a CSV → get auto-generated charts + a plain-English briefing you can trust.

Project #12 of the "30 AI Projects in 15 Days" build-in-public challenge. Focus: code execution + a data agent (vs. #11's long-running service).

Honest by construction

The AI never invents a number. A deterministic pandas pass computes every statistic and chart; the model only turns that computed profile into prose. Units the model tries to guess (mm, °C, …) are stripped — they aren't in your file. Same grounded discipline as the #10 RAG app.

What it does

  • Profile — shape, dtypes, missing %, numeric summaries, top categories, correlations, outliers, date-range detection, and plain-language data-quality flags.
  • Charts — trend-over-time, correlation heatmap, distributions, and category bars (GritAI design system).
  • Findings — a short, plain-English briefing grounded only in the computed numbers, with follow-up questions the data could answer next.

How it works

  • profiler.py — computes the full structured profile (pandas). The source of every number.
  • charts.py — matplotlib charts from the profile, returned as inline base64 PNGs.
  • narrator.py — turns the profile into prose. Local Ollama by default (free/private); Claude optional. A deterministic post-pass strips any units the model added.
  • app.py — Flask UI: upload or try the sample, 12 MB cap, data handled in-memory (never persisted).

Two tiers

  • This hosted demo narrates via Claude-haiku (charts + stats are 100% local pandas).
  • GritAI Studio (paid) runs the whole thing — narrative included — on your own local GPU fleet: free per-analysis, fully private, nothing leaves your network.

Run locally 

pip install -r requirements.txt
python app.py            # http://127.0.0.1:7860
# Backend: set INSIGHTS_LLM_BACKEND=ollama (default, local) or =claude (set ANTHROPIC_API_KEY)

Built by Robert Lucyk · GritAI Solutions · part of the 30-in-15 challenge.