winnermarvi/business_analyst

How winnermarvi/business_analyst works

AI Business Analyst accepts CSV data for automated analysis, model selection, explanations, and reporting, with follow-up dataset chat and natural-language analytics. The evidenced backend entry points are FastAPI routes and the analysis orchestrator; README-documented capabilities whose implementation wiring was not sampled are shown as separate branches with documented or unverified links. The source index supports the ML subsystem relationships, but most individual feature implementations were not excerpted.

Main entry points: pipeline_service.py Analysis orchestrator · ml_pipeline.py ML workflow · app.py FastAPI endpoints · chat_service.py Dataset chat

Components 23

User interface and API

Streamlit frontend frontend
FastAPI endpoints src/api/app.py
API schemas src/api/schemas.py

Analysis workflow

Analysis orchestrator src/services/pipeline_service.py
Data preprocessing src/preprocessing
Exploratory analysis src/eda/eda.py
EDA insights src/insights

Machine learning

ML service src/services/ml_service.py
ML workflow src/ml/ml_pipeline.py
Target detection src/ml/target_detector.py
Best model selection src/ml/select_best_model.py
Classification models src/ml/classification
Regression models src/ml/regression
Feature insights and recommendations src/explainability

AI and exploration

Business narrative src/llm
Dataset chat src/services/chat_service.py
RAG retrieval src/rag
Natural-language analytics src/analytics

Reports and charts

Interactive charts src/visualization
PDF reporting src/reporting
PDF report
Plotly chart

Other components

Analyst

Connections 24

Analyst → Streamlit frontend: uses
Streamlit frontend → FastAPI endpoints: requests analysis
FastAPI endpoints → Analysis orchestrator: runs analysis src/api/app.py
FastAPI endpoints → Dataset chat: requests chat src/api/app.py
FastAPI endpoints → API schemas: uses response types src/api/app.py
Analysis orchestrator → Exploratory analysis: runs EDA src/services/pipeline_service.py
Analysis orchestrator → ML service: runs modeling src/services/pipeline_service.py
Analysis orchestrator → Business narrative: requests summary src/services/pipeline_service.py
Analysis orchestrator → PDF reporting: generates report src/services/pipeline_service.py
Analysis orchestrator → Interactive charts: generates charts src/services/pipeline_service.py
Analysis orchestrator → Data preprocessing: prepares dataset
Exploratory analysis → EDA insights: generates findings
ML service → ML workflow: runs ML workflow
ML workflow → Target detection: detects target type src/ml/ml_pipeline.py
ML workflow → Classification models: trains and evaluates src/ml/ml_pipeline.py
ML workflow → Regression models: trains and evaluates src/ml/ml_pipeline.py
ML workflow → Best model selection: selects best model src/ml/ml_pipeline.py
ML workflow → Feature insights and recommendations: generates explanations src/ml/ml_pipeline.py
Dataset chat → RAG retrieval: retrieves context
Dataset chat → Business narrative: generates response
FastAPI endpoints → Natural-language analytics: accepts query
Natural-language analytics → Interactive charts: requests chart
PDF reporting → PDF report: produces
Interactive charts → Plotly chart: renders

More Python diagrams: shopify/shopify_python_api · yi1108/printfilm · clats97/clatscope · gvcoder09/nodpi · m1guelpf/yt-whisper

Drawn by GitDiagram on October 16, 2026 from the repository's file tree, README and source files. Read as Markdown ·