How dhinakaran311/food_delivery_time_prediction works
This is a Streamlit food-delivery-time prediction app. Its main workflow takes order details from a user, maps them into model features, loads a saved Linear Regression model, and presents an estimated duration and expected arrival time. The README also describes an upstream data-analysis and model-training workflow. Those stages are represented from documentation and repository files; their implementation details are not shown in the sampled source.
Main entry points: index.py Order inputs · Food_Delivery_Times.csv Delivery dataset · Dhinakaran_EDA.ipynb EDA and insights · cleaned_dataset.csv Data cleaning
Components 11
Prediction app
- Order inputs
index.py - Feature mapping
index.py - Model inference
index.py - Estimate and ETA
index.py - Delivery conditions
index.py
Model workflow
- Saved model
modellinear.pkl - Training and evaluation
Data analysis
- Delivery dataset
Food_Delivery_Times.csv - EDA and insights
Dhinakaran_EDA.ipynb - Data cleaning
cleaned_dataset.csv
Other components
- Order user
Connections 13
- Order user → Order inputs: enters details
index.py - Order inputs → Feature mapping: maps inputs
index.py - Feature mapping → Model inference: supplies features
index.py - Model inference → Saved model: loads model
index.py - Model inference → Estimate and ETA: returns estimate
index.py - Estimate and ETA → Order user: displays estimate
index.py - Order inputs → Delivery conditions: selects messages
index.py - Delivery conditions → Order user: shows guidance
index.py - Delivery dataset → EDA and insights: analyzes data
README.md - Delivery dataset → Data cleaning: cleans data
README.md - Data cleaning → Training and evaluation: prepares features
README.md - Training and evaluation → Saved model: saves model
README.md - EDA and insights → Order user: informs insights
README.md