https://github.com/msikorski93/logistic-regression-classifier-from-scratch

Logistic regression created in Python for binary classification.
https://github.com/msikorski93/logistic-regression-classifier-from-scratch

binary-classification from-scratch logistic-regression python wbcd

Last synced: 3 months ago
JSON representation

Logistic regression created in Python for binary classification.

• Host: GitHub
• URL: https://github.com/msikorski93/logistic-regression-classifier-from-scratch
• Owner: msikorski93
• Created: 2024-09-30T13:53:19.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-12-28T12:51:22.000Z (9 months ago)
• Last Synced: 2025-05-21T18:32:46.482Z (5 months ago)
• Topics: binary-classification, from-scratch, logistic-regression, python, wbcd
• Language: Jupyter Notebook
• Homepage:
• Size: 570 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Logistic-Regression-Classifier-From-Scratch

![ alt text ](https://img.shields.io/badge/license-MIT-green?style=&logo=)

![ alt text ](https://img.shields.io/badge/-Python-3776AB?logo=Python&logoColor=white)

![ alt text ](https://img.shields.io/badge/-Jupyter-F37626?logo=Jupyter&logoColor=white)

![ alt text ](https://img.shields.io/badge/-NumPy-013243?logo=Numpy&logoColor=white)

![ alt text ](https://img.shields.io/badge/-pandas-150458?logo=Pandas&logoColor=white)

Logistic regression with the ability of implementing penalty terms. The class object is dedicated to binary classification and is compatible with `scikit-learn`'s GridSearchCV method.


An example of its usage was performed on the WBCD dataset and returned the following estimates:

* Accuracy: 0.9883

* Recall: 0.9841

* Precision: 0.9841

* Error Rate: 0.0117

* F1 Score: 0.9841

* ROC: 0.9874

* Specificity: 0.9907

* Misclassified Samples: 2 (out of 171)



**Code example:**

```

from logistic_regression import LogisticRegression

log_model = LogisticRegression(learning_rate=0.01, C=0.1, num_iter=20, penalty='elasticnet', l1_ratio=0.7)

log_model.fit(X_train, y_train)

predictions = log_model.predict(X_test, threshold=0.6)

```