Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/kelvintechnical/logistic-regression-for-binary-classification-


https://github.com/kelvintechnical/logistic-regression-for-binary-classification-

Last synced: 27 days ago
JSON representation

Awesome Lists containing this project

README 

        



Logistic Regression for Binary Classification



Project Overview


This project demonstrates how to implement and visualize a Logistic Regression model for binary classification using synthetic data. It covers generating and visualizing two distinct data categories, training a logistic regression model, evaluating its accuracy, and visualizing the decision boundary. Logistic Regression is a fundamental algorithm in machine learning, often used as an introduction to binary classification tasks.



Code Walkthrough



1. Importing Libraries


# Importing necessary libraries

import numpy as np  # For handling arrays and math operations

import matplotlib.pyplot as plt  # For plotting graphs

from sklearn.model_selection import train_test_split  # For splitting data into train and test sets

from sklearn.linear_model import LogisticRegression  # For logistic regression model

from sklearn.metrics import accuracy_score  # For checking model accuracy



Explanation: We begin by importing the necessary libraries:


    

      
  • 

    numpy: To handle arrays and perform mathematical operations.
    • 

      
  • 

    matplotlib.pyplot: For plotting data and visualizations.
    • 

      
  • 

    sklearn.model_selection.train_test_split: To split the data into training and test sets.
    • 

      
  • 

    sklearn.linear_model.LogisticRegression: To create a logistic regression model.
    • 

      
  • 

    sklearn.metrics.accuracy_score: To measure the accuracy of our model on test data.
    • 




2. Data Generation


# Data Generation

np.random.seed(0)

data_size = 100

category_0 = np.random.normal(2, 0.5, (data_size, 2))

category_1 = np.random.normal(4, 0.5, (data_size, 2))

X = np.vstack((category_0, category_1))

y = np.hstack((np.zeros(data_size), np.ones(data_size)))



Explanation: We generate synthetic data for two categories:


    

      
  • We set the random seed to ensure reproducibility.
    • 

      
  • 

    data_size defines the number of data points in each category.
    • 

      
  • 

    category_0 and category_1: Two clusters of data points generated with different centers (2 and 4), creating two distinct groups.
    • 

      
  • 

    X combines both categories into one dataset, and y creates labels (0 and 1) for each category.
    • 




3. Data Visualization


# Data Visualization

plt.figure(figsize=(8, 6))

plt.scatter(category_0[:, 0], category_0[:, 1], color='blue', label='Category 0')

plt.scatter(category_1[:, 0], category_1[:, 1], color='red', label='Category 1')

plt.xlabel('Feature 1')

plt.ylabel('Feature 2')

plt.title('Data Visualization')

plt.legend()

plt.show()



Explanation: We visualize the generated data to observe the two distinct categories:


    

      
  • 

    plt.scatter plots each category with a different color.
    • 

      
  • Labels and legends are added for clarity.
    • 

      
  • 

    plt.show() displays the plot, helping us understand how data points are distributed in each category.
    • 




4. Model Training


# Model Training

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

model = LogisticRegression()

model.fit(X_train, y_train)



Explanation: We split the data into training and test sets and train the logistic regression model:


    

      
  • 

    train_test_split divides the dataset (70% training and 30% testing).
    • 

      
  • 

    LogisticRegression() creates the model, and model.fit() trains it with the training data.
    • 




5. Prediction and Accuracy Evaluation


# Prediction and Accuracy Evaluation

y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)

print("Model Accuracy:", accuracy)



Explanation: We make predictions and evaluate the model’s accuracy:


    

      
  • 

    model.predict(X_test) generates predictions on the test data.
    • 

      
  • 

    accuracy_score compares predictions to actual values, and we print the accuracy.
    • 




6. Decision Boundary Visualization


# Decision Boundary Visualization

x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1

y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1

xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1), np.arange(y_min, y_max, 0.1))

Z = model.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)

plt.contourf(xx, yy, Z, alpha=0.3, cmap=plt.cm.RdYlBu)

plt.scatter(X[:, 0], X[:, 1], c=y, edgecolor='k', s=50, cmap=plt.cm.RdYlBu)

plt.xlabel('Feature 1')

plt.ylabel('Feature 2')

plt.title('Logistic Regression Decision Boundary')

plt.show()



Explanation: We visualize the decision boundary of the logistic regression model:


    

      
  • 

    meshgrid creates a grid of points covering the feature space.
    • 

      
  • We predict the category for each grid point and reshape the predictions to match the grid.
    • 

      
  • 

    contourf displays the decision boundary, showing where the model classifies each region.
    • 

      
  • The scatter plot overlays the original data points on the decision boundary for comparison.
    • 




Follow Me


Stay connected with my latest projects and insights: