Iris Perceptron Classification

This task implements a custom perceptron classifier for the famous Iris dataset using a one-vs-all approach for multi-class classification.

Description

The iris_perceptroon_task.py script contains:

• A custom BioPerceptron class that implements a basic perceptron algorithm
• Multi-class classification using three binary perceptrons (one for each Iris species)
• Data preprocessing with StandardScaler
• Visualization of predictions using PCA dimensionality reduction

Requirements

• Python 3.7+
• numpy
• matplotlib
• scikit-learn

Installation

1. Clone or download this project

2. Create a virtual environment (recommended):

   python -m venv .venv
   source .venv/bin/activate  # On Linux/Mac
   # or
   .venv\Scripts\activate     # On Windows

3. Install dependencies:

   pip install -r requirements.txt

Usage

Run the perceptron classification:

python iris_perceptroon_task.py

Output

The script will:

1. Train three perceptrons (one for each Iris class: setosa, versicolor, virginica)
2. Test the model on 20% of the dataset
3. Print the accuracy percentage
4. Display a 2D PCA visualization of the predicted classes

Expected Results

The perceptron typically achieves high accuracy (often 100%) on the Iris dataset due to the dataset's linear separability, especially for the setosa class.