Online Food Ordering Data Analysis Final Year Project with Source Code

Project Features in this Final Year Project

• Online food ordering dataset analysis
• Food delivery order history analysis
• Kaggle dataset loading support
• Local CSV loading support
• Data cleaning and preprocessing
• Feature engineering
• Delivery distance parsing
• Line item count generation
• Order timestamp parsing
• Distance bucket creation
• Numeric field preparation
• Exploratory data analysis
• Summary statistics generation
• Correlation analysis
• Order total distribution analysis
• Restaurant-wise order analysis
• Subzone-wise order analysis
• Order status breakdown
• Kitchen preparation time analysis
• Rider wait time analysis
• Bill subtotal analysis
• Packaging charge analysis
• Discount and total amount analysis
• 12 visualization chart types
• Random Forest regression model
• Kitchen preparation time prediction
• Model evaluation using MAE, RMSE, and R²
• Predicted vs actual plot
• Feature importance visualization
• PNG chart export support
• Jupyter Notebook workflow

Data Analytics / EDA Features in this Final Year Project

• Dataset loading using kagglehub

• Local fallback loading from:

  data/order_history_kaggle_data.csv

• Summary statistics
• Missing value inspection
• Restaurant distribution analysis
• Subzone distribution analysis
• Order status analysis
• Order amount distribution
• Distance-based order grouping
• Daily order volume analysis
• Kitchen preparation time distribution
• Rider wait time distribution
• Restaurant-wise amount comparison
• Subzone-wise KPT comparison
• Correlation matrix analysis
• Numeric feature preparation for ML

Visualization Features in this Final Year Project

The project includes 12 different visualization types for report comparison:

1. Histogram — order total distribution
2. Vertical bar chart — orders by subzone
3. Horizontal bar chart — orders by status
4. Pie chart — share by restaurant
5. Box plot — kitchen preparation time by subzone
6. Violin plot — total amount by restaurant
7. Scatter plot — bill subtotal vs kitchen preparation time
8. Heatmap — correlation matrix
9. Line chart — daily order volume
10. Count plot — orders by distance bucket
11. KDE plot — kitchen preparation time vs rider wait distributions
12. Stacked bar chart — average subtotal plus packaging by restaurant

Additional ML visualizations:

• Predicted vs actual KPT plot
• Feature importance plot

Output folder:

output/

Export format:
PNG images at 150 DPI.

Machine Learning Features in this Final Year Project

• Predicts kitchen preparation time
• Target variable: KPT duration in minutes
• Uses delivered orders with known KPT
• Random Forest Regressor model
• Feature preparation from order attributes
• Model training and testing workflow
• MAE evaluation
• RMSE evaluation
• R² score evaluation
• Predicted vs actual comparison
• Feature importance analysis
• Useful for understanding factors affecting preparation time
• Supports report-ready ML explanation

Dataset Details in this Final Year Project

Dataset name:
Food Delivery Order History Data

Dataset source:
Kaggle

Dataset author:
sujalsuthar

Dataset size:
Approximately 21,000+ order rows

Dataset focus:
Online food delivery / ordering data from multiple restaurants and subzones in Delhi NCR.

Typical fields include:

• Restaurant
• Subzone
• Order time
• Order status
• Delivery distance
• Items
• Bill subtotal
• Packaging charges
• Discounts
• Total amount
• Ratings
• Kitchen preparation time
• Rider wait time
• Customer ID

Primary CSV file:

order_history_kaggle_data.csv

Files / Modules Included in this Final Year Project

• online_food_ordering_analysis.ipynb — full Jupyter Notebook analysis
• requirements.txt — Python dependencies
• README.md — project documentation
• data/order_history_kaggle_data.csv — optional local dataset path
• output/ — generated PNG chart output folder

Output Files

All generated figures are exported to:

output/

Expected exported files are named from:

01_...png

to:

13_...png

The output files include EDA charts and machine learning result charts, making them useful for project reports, presentations, and viva demonstration.

Option 1: Run with automatic Kaggle download

1. Open terminal in the project folder:

   cd "online-food-ordering-data-analysis-v2"

2. Create virtual environment:

   python -m venv .venv

3. Activate virtual environment on Windows:

   .\.venv\Scripts\Activate.ps1

4. Install dependencies:

   pip install -r requirements.txt

5. Start Jupyter Notebook:

   jupyter notebook online_food_ordering_analysis.ipynb

6. Or start JupyterLab:

   jupyter lab online_food_ordering_analysis.ipynb

7. Run all cells:

   Kernel → Restart & Run All

8. Check generated charts:

   output/

Option 2: Run with manual CSV dataset

1. Download the CSV file:

   order_history_kaggle_data.csv

2. Create this folder structure:

   online-food-ordering-data-analysis-v2/
     data/
       order_history_kaggle_data.csv
     online_food_ordering_analysis.ipynb
     requirements.txt
     README.md

3. Open the project folder:

   cd "online-food-ordering-data-analysis-v2"

4. Install dependencies:

   pip install -r requirements.txt

5. Start notebook:

   jupyter notebook online_food_ordering_analysis.ipynb

6. Run all cells.

7. View exported charts in:

   output/

This project has no login credentials because it is not a web application.

Credential note:
No admin panel, user login, password, or database authentication is included. The project runs locally as a Python data analysis notebook.