How keertan06/sales-forcasting-ml works
This Flask application serves retail sales predictions and an interactive analytics dashboard. The main path loads the trained model, feature schema, and retail dataset; dashboard routes derive KPIs and Plotly views, while POST /predict aligns submitted customer and product fields to the saved schema before returning a prediction. The separate model script documents dataset feature engineering, training, evaluation, and artifact creation. Dashboard and prediction details are grounded in app.py and the README; unsampled templates and artifact internals limit evidence about browser-side wiring.
Main entry points: app.py Flask App · retail_sales_dataset.csv Retail Dataset · style.css Dashboard Styling · model.py Model Training
Components 16
Sales Data
- Retail Dataset
data/retail_sales_dataset.csv
Model Lifecycle
- Feature Preparation
model.py - Model Training
model.py - Trained Regressor
sales_model.pkl - Feature Schema
model_features.pkl - Standalone Visualizations
visualize.py
Flask Application
- Flask App
app.py - Sales Prediction
app.py - Business KPIs
app.py - Analytics Plotting
app.py
Dashboard Views
- Overview Page
templates/index.html - Trends Page
templates/trends.html - Categories Page
templates/categories.html - Performance Page
templates/performance.html - Dashboard Styling
static/style.css
Other components
- Dashboard User
Connections 32
- Retail Dataset → Feature Preparation: provides rows
README.md - Retail Dataset → Flask App: loads
app.py - Retail Dataset → Standalone Visualizations: loads
visualize.py - Retail Dataset → Model Training: loads
model.py - Feature Preparation → Model Training: prepares features
model.py - Model Training → Trained Regressor: saves model
model.py - Model Training → Feature Schema: saves schema
model.py - Dashboard User → Flask App: requests pages
README.md - Flask App → Trained Regressor: loads model
app.py - Flask App → Feature Schema: loads schema
app.py - Flask App → Sales Prediction: routes request
app.py - Sales Prediction → Trained Regressor: predicts with
app.py - Sales Prediction → Feature Schema: aligns features
app.py - Sales Prediction → Dashboard User: returns prediction
app.py - Flask App → Business KPIs: computes
app.py - Flask App → Analytics Plotting: builds charts
app.py - Flask App → Overview Page: renders
app.py - Flask App → Trends Page: renders
app.py - Flask App → Categories Page: renders
app.py - Flask App → Performance Page: renders
app.py - Business KPIs → Overview Page: supplies metrics
app.py - Business KPIs → Trends Page: supplies metrics
app.py - Business KPIs → Categories Page: supplies metrics
app.py - Business KPIs → Performance Page: supplies metrics
app.py - Analytics Plotting → Trends Page: supplies trend
app.py - Analytics Plotting → Categories Page: supplies revenue charts
app.py - Analytics Plotting → Performance Page: supplies comparison
app.py - Dashboard User → Sales Prediction: submits details
README.md - Dashboard Styling → Overview Page: styles
- Dashboard Styling → Trends Page: styles
- Dashboard Styling → Categories Page: styles
- Dashboard Styling → Performance Page: styles