Eye Care Data Analysis Final Year Project with Source Code

Project Features in this Final Year Project

• Eye care data analysis
• Ophthalmology dataset analysis
• ODIR-5K Ocular Disease Recognition dataset support
• Kaggle dataset download support
• Manual Excel dataset loading
• Sample data generation if dataset is missing
• Exploratory data analysis
• Dataset shape analysis
• Dataset information summary
• Statistical summary generation
• Missing-value checking
• Patient age analysis
• Gender demographic analysis
• Disease distribution analysis
• Disease co-occurrence analysis
• Disease-by-gender comparison
• Age-by-disease comparison
• Correlation heatmap
• Multi-class disease classification
• Random Forest model comparison
• Gradient Boosting model comparison
• Logistic Regression model comparison
• Accuracy evaluation
• F1-score evaluation
• Precision evaluation
• Recall evaluation
• Confusion matrix visualization
• Python script support
• Jupyter Notebook support
• Output plot generation
• Suitable for report writing and viva explanation

Disease Categories Covered in this Final Year Project

The project analyzes the following ocular disease categories:

• Normal — N
• Diabetes — D
• Glaucoma — G
• Cataract — C
• AMD — A
• Hypertension — H
• Myopia — M
• Other — O

Data Analytics / EDA Features in this Final Year Project

• Loads Excel dataset:

  full_data.xlsx

  or:

  data.xlsx

• Supports manual file path configuration:

  EXCEL_FILE_PATH = r"C:\path\to\full_data.xlsx"

• Uses sample dataset of 3500 records if no Excel file is found
• Displays dataset shape
• Displays dataset information
• Displays statistical summary
• Checks missing values
• Analyzes age distribution
• Analyzes gender distribution
• Analyzes ocular disease distribution
• Compares age across disease categories
• Compares disease distribution by gender
• Analyzes disease co-occurrence
• Generates healthcare analytics visualizations
• Supports medical data analysis report preparation

Visualization Features in this Final Year Project

The project generates visual outputs inside:

outputs/

1. Disease Distribution Bar Chart
   File: 1_disease_distribution_bar.png
   Shows the count or distribution of different ocular disease categories.
2. Gender Pie Chart
   File: 2_gender_pie.png
   Shows gender demographic distribution of patients.
3. Age by Disease Box Plot
   File: 3_age_by_disease_box.png
   Compares patient age spread across different disease categories.
4. Disease Correlation Heatmap
   File: 4_disease_correlation_heatmap.png
   Shows disease co-occurrence and correlation patterns.
5. Age Histogram
   File: 5_age_histogram.png
   Shows patient age distribution.
6. Disease by Gender Grouped Chart
   File: 6_disease_by_gender_grouped.png
   Compares disease categories by gender.
7. Confusion Matrix
   File: 7_confusion_matrix.png
   Shows machine learning model classification performance.

Machine Learning Features in this Final Year Project

• Multi-class disease classification
• Primary disease prediction
• Target: ocular disease category
• Features used:
  • Age
  • Sex
• Models compared:
  • Random Forest
  • Gradient Boosting
  • Logistic Regression
• Evaluates model performance using:
  • Accuracy
  • F1-score
  • Precision
  • Recall
• Generates confusion matrix
• Supports healthcare classification explanation
• Useful for medical analytics and machine learning demonstration

Dataset Details in this Final Year Project

Dataset name:
ODIR-5K Ocular Disease Recognition

Dataset source:
Kaggle

Dataset format:
Excel file

Supported Excel file names:

full_data.xlsx
data.xlsx

Dataset domain:
Eye care / ophthalmology / ocular disease recognition

Disease labels:

N, D, G, C, A, H, M, O

Dataset can be loaded by:

• Automatic Kaggle download using Kaggle API
• Manual Excel download and path configuration
• Built-in sample data fallback when Excel file is missing

Files / Modules Included in this Final Year Project

• eye_care_analysis.py — main Python script
• eye_care_analysis.ipynb — Jupyter Notebook version
• requirements.txt — Python dependency list
• README.md — project documentation
• outputs/ — generated plot folder

Project structure:

eye-care-jupiter-ml/
├── eye_care_analysis.py
├── eye_care_analysis.ipynb
├── requirements.txt
├── README.md
└── outputs/

Output Files in this Final Year Project

The project generates outputs inside:

outputs/

Expected output files:

• 1_disease_distribution_bar.png
• 2_gender_pie.png
• 3_age_by_disease_box.png
• 4_disease_correlation_heatmap.png
• 5_age_histogram.png
• 6_disease_by_gender_grouped.png
• 7_confusion_matrix.png

Console / notebook output includes:

• Dataset summary
• Missing-value report
• Statistical summary
• Disease distribution
• ML model performance
• Accuracy, F1-score, precision, and recall values

Option 1: Run Python script

1. Open terminal in the project folder:

   cd "eye-care-jupiter-ml"

2. Install dependencies:

   pip install -r requirements.txt

3. Optional Kaggle setup:
   • Create a Kaggle account
   • Download Kaggle API token

   • Place kaggle.json in:

     ~/.kaggle/

   • On Windows:

     C:\Users\<username>\.kaggle\

4. Alternative manual dataset setup:
   • Download full_data.xlsx from Kaggle

   • Set Excel path in eye_care_analysis.py:

     EXCEL_FILE_PATH = r"C:\path\to\full_data.xlsx"

5. Run the project:

   python eye_care_analysis.py

6. Check generated outputs:

   outputs/

Option 2: Run Jupyter Notebook

1. Install dependencies:

   pip install -r requirements.txt

2. Start notebook:

   jupyter notebook eye_care_analysis.ipynb

3. Or run:

   python -m notebook eye_care_analysis.ipynb

4. Run all cells in sequence.

5. Check generated plots:

   outputs/

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

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