Binary Classification Project

This project performs binary classification using the Pima Indians Diabetes Dataset. The aim is to predict whether a patient is likely to have diabetes based on various medical attributes such as glucose level, blood pressure, insulin level, BMI, etc.

📁 Dataset

The dataset used in this project is sourced from YBI Foundation GitHub Datasets.
It contains the following features:

• pregnancies
• glucose
• diastolic
• triceps
• insulin
• bmi
• dpf (diabetes pedigree function)
• age
• diabetes (target label: 0 or 1)

🔧 Steps Implemented

1. Import Libraries

   • pandas
   • sklearn (for train/test split, logistic regression, metrics)

2. Data Loading & Exploration

   • Loaded dataset with pd.read_csv()
   • Used .head(), .info(), .describe() for initial analysis

3. Preprocessing

   • Defined features X and target y
   • Split data into training and testing sets (80/20 split)

4. Model Training

   • Used LogisticRegression model from sklearn
   • Trained the model on the training data

5. Prediction & Evaluation

   • Made predictions on the test set
   • Evaluated model with confusion_matrix, accuracy_score, and classification_report

📈 Results

• Accuracy: ~76.6%
• Precision, Recall, F1-score available for both classes in the report.

📊 Sample Output

              precision    recall  f1-score   support

           0       0.76      0.92      0.83       145
           1       0.79      0.52      0.63        86

    accuracy                           0.77       231
   macro avg       0.78      0.72      0.73       231
weighted avg       0.77      0.77      0.76       231
✅ Conclusion
The logistic regression model performs reasonably well in predicting diabetes based on the given features. The dataset is imbalanced, which slightly affects the recall for class 1.

👤 Author
Bijaya Kumar Rout
📧 bijayakumarrout2005@gmail.com

📌 Note
This notebook is a part of the YBI Foundation Data Science Project on binary classification. You can open the notebook locally or on a Jupyter-supported platform for better rendering of plots and outputs.