PCA for IRIS

 # 1. Import libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler

# 2. Load dataset using read_csv

df = pd.read_csv('iris.csv')   # <-- your file name

# 3. Separate features (assuming 'species' is the label column)

X = df.drop('species', axis=1)

# 4. Scale the features

scaler = StandardScaler()

X_scaled = scaler.fit_transform(X)

# 5. Calculate covariance matrix

cov_matrix = np.cov(X_scaled.T)

# 6. Calculate eigenvalues and eigenvectors

eigenvalues, eigenvectors = np.linalg.eig(cov_matrix)

# 7. Sort eigenvalues and eigenvectors

sorted_indices = np.argsort(eigenvalues)[::-1]

eigenvalues = eigenvalues[sorted_indices]

eigenvectors = eigenvectors[:, sorted_indices]

# 8. Plot explained variance

explained_variance_ratio = eigenvalues / np.sum(eigenvalues)

plt.figure(figsize=(6,4))

plt.bar(range(1, len(explained_variance_ratio)+1), explained_variance_ratio, alpha=0.7, align='center')

plt.xlabel('Principal Components')

plt.ylabel('Explained Variance Ratio')

plt.title('Explained Variance by Components')

plt.show()

# 9. Choose first k eigenvectors (let's take 2 for 2D)

k = 2

eigenvectors_k = eigenvectors[:, :k]

# 10. Transform the original data

X_pca = X_scaled.dot(eigenvectors_k)

# 11. Plot PCA Result

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

plt.scatter(X_pca[:, 0], X_pca[:, 1], c=pd.factorize(df['species'])[0], cmap='viridis')

plt.xlabel('PC1')

plt.ylabel('PC2')

plt.title('PCA Result (Iris Dataset)')

plt.colorbar()

plt.show()