Skip to content

README.md

Latest commit

 

History

History
59 lines (44 loc) · 1.42 KB

README.md

File metadata and controls

59 lines (44 loc) · 1.42 KB

Logistic Regression Binary Classifier

Objective

This project demonstrates how to build a binary classifier using Logistic Regression in Python. The model predicts outcomes for a binary classification problem using features from a dataset.

Tools & Libraries

  • Python
  • Scikit-learn
  • Pandas
  • Matplotlib

Dataset

You can use any binary classification dataset for this task.
Example: Breast Cancer Wisconsin Dataset.

Project Steps / Mini Guide

  1. Choose a binary classification dataset.
  2. Train/test split the dataset and standardize features.
  3. Fit a Logistic Regression model to the training data.
  4. Evaluate the model using:
    • Confusion matrix
    • Precision
    • Recall
    • ROC-AUC
  5. Tune the classification threshold and explain the sigmoid function.

Key Concepts You’ll Learn

  • Binary classification
  • Evaluation metrics (precision, recall, ROC-AUC)
  • Sigmoid function and threshold tuning

Interview Questions

  1. How does logistic regression differ from linear regression?
  2. What is the sigmoid function?
  3. What is precision vs recall?
  4. What is the ROC-AUC curve?
  5. What is the confusion matrix?
  6. What happens if classes are imbalanced?
  7. How do you choose the threshold?
  8. Can logistic regression be used for multi-class problems?

How to Run

  1. Clone the repository: 
    git clone <repository-url>