How mainakadak02/end-to-endsalesforecasting works
This is a Streamlit retail-sales analytics dashboard. Users select an overview, forecast, anomaly report, or product-segmentation view; the app loads and prepares the sales CSV, then computes and visualizes the selected analysis. The distinct analysis stages and data-loading layer are all implemented in app.py. The repository provides no README and has only one substantive source file, so the graph stays compact; all shown relationships are evidenced by that excerpt.
Main entry points: app.py Streamlit Dashboard · train.csv Training Data
Components 8
Dashboard
- Streamlit Dashboard
app.py
Sales Analytics
- Sales Overview
app.py - Sales Forecast
app.py - Anomaly Detection
app.py - Product Clustering
app.py
Data
- Data Loader
app.py - Training Data
train.csv
Other components
- Dashboard User
Connections 11
- Dashboard User → Streamlit Dashboard: selects view
app.py - Streamlit Dashboard → Data Loader: loads data
app.py - Data Loader → Training Data: reads CSV
app.py - Streamlit Dashboard → Sales Overview: renders selected
app.py - Streamlit Dashboard → Sales Forecast: renders selected
app.py - Streamlit Dashboard → Anomaly Detection: renders selected
app.py - Streamlit Dashboard → Product Clustering: renders selected
app.py - Sales Overview → Data Loader: uses loaded data
app.py - Sales Forecast → Data Loader: uses loaded data
app.py - Anomaly Detection → Data Loader: uses loaded data
app.py - Product Clustering → Data Loader: uses loaded data
app.py