This repository contains a comprehensive data mining project focused on diabetes prediction and analysis using various machine learning algorithms. The project follows a structured pipeline from data cleaning to advanced classification and clustering.
The goal of this project is to analyze diabetes data using both supervised and unsupervised learning techniques to identify patterns and predict outcomes with high accuracy.
The project is divided into the following phases:
- Data Preprocessing:
1-Data Cleaning Part.py- Handling missing values, normalization, and preparing the dataset for analysis.
- Classification (Supervised Learning):
2-Decision Three Part.py: Implementation of Decision Tree algorithm.3-Support Vector Machine Part.py: Using SVM for robust classification.4-Evaluation Svm va DT plus ai.py: Comparative analysis and performance metrics for SVM and Decision Tree.
- Clustering (Unsupervised Learning):
5-Kmeans Part.py: Grouping data using K-Means clustering.6-Hierarchical Clustring Part.py: Analyzing data structures via hierarchical methods.
cleaned_diabetes_prediction_data.csv: The processed data used for training.modified_diabetes_prediction_data.csv: Version of the data with specific modifications for clustering.
To run these scripts, you need Python installed along with the following libraries:
- pandas
- scikit-learn
- matplotlib / seaborn
This project was developed as part of a Software Engineering / Data Mining research study to explore the effectiveness of different ML models in healthcare analytics.
This project is licensed under the MIT License - see the LICENSE file for details.