Principal Components Analysis (PCA)#

Principal Component Analysis (PCA) is a popular dimensionality reduction technique that is widely used in various fields including machine learning, computer vision, biology, and engineering. It is a linear method that transforms high-dimensional data into a low-dimensional space, preserving the most important features of the data. The main goal of PCA is to identify the underlying structure in the data, extract the most significant features, and reduce the noise and complexity of the data.

How Does PCA Work?#

PCA works by finding the principal components of the data, which are linear combinations of the original features that capture the most variation in the data. These principal components are ranked in terms of their contribution to the total variance in the data, and the first few components are selected for the low-dimensional representation. The resulting transformed data can then be used for further analysis or visualization.


PCA is a simple and fast algorithm that can be used for a variety of applications, including data compression, visualization, noise reduction, and feature selection. It has a number of advantages over other dimensionality reduction methods, including its linearity, efficiency, and interpretability.


PCA also has some limitations, such as its sensitivity to the scale of the features and its assumption of linear relationships between the features.

Example Code#

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA

# Load the iris dataset
iris = load_iris()
X =
y =
target_names = iris.target_names

# Apply PCA to the iris dataset
pca = PCA(n_components=2)
X_r =

# Plot the first two components
for c, i, target_name in zip("rgb", [0, 1, 2], target_names):
    plt.scatter(X_r[y == i, 0], X_r[y == i, 1], c=c, label=target_name)
plt.title("PCA of Iris dataset")


In conclusion, principal component analysis (PCA) is a popular and widely used dimensionality reduction technique in the field of machine learning. It is especially useful for dealing with high dimensional data by transforming it into a lower-dimensional space while retaining most of the information. PCA is a linear technique that works by finding the directions of maximum variance in the data and projecting the data onto a lower-dimensional subspace along these directions. By reducing the number of features, PCA makes it easier to visualize and analyze the data, and can also help to improve the performance of machine learning algorithms. With the help of scikit-learn’s PCA implementation, it is easy to apply PCA to any dataset, and this technique is a valuable tool for any data scientist or machine learning practitioner.

Where to Learn More#

I’ve covered PCA in-depth in the following course:

Unsupervised Deep Learning in Python