Correlation matrix visualization in Matplotlib

Introduction

A correlation matrix visualization helps you see how different things relate to each other. It shows which pairs move together or in opposite ways.

To understand relationships between different features in a dataset before building a model.

To find which variables are strongly connected in a business report.

To check if some data columns are very similar or redundant.

To explore patterns in survey or experimental data.

To communicate data insights visually to others.

Syntax

Matplotlib

import matplotlib.pyplot as plt
import seaborn as sns

corr_matrix = data.corr()
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm')
plt.show()

data.corr() calculates the correlation matrix from your data.

sns.heatmap() draws the colored grid showing correlation values.

Examples

Shows correlation with numbers inside squares and a 'viridis' color style.

Matplotlib

import seaborn as sns
import matplotlib.pyplot as plt

corr = df.corr()
sns.heatmap(corr, annot=True, cmap='viridis')
plt.show()

Colors blue to red with white at zero, highlighting positive and negative correlations.

Matplotlib

sns.heatmap(df.corr(), cmap='bwr', center=0)
plt.show()

Shows correlation values rounded to 2 decimals with lines between cells.

Matplotlib

sns.heatmap(df.corr(), annot=True, fmt='.2f', linewidths=0.5)
plt.show()

Sample Program

This code creates a small dataset with age, income, and score. It calculates how these relate and shows a colored grid with numbers.

Matplotlib

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# Create sample data
data = pd.DataFrame({
    'age': [25, 32, 47, 51, 62],
    'income': [50000, 60000, 80000, 90000, 120000],
    'score': [200, 220, 250, 270, 300]
})

# Calculate correlation matrix
corr_matrix = data.corr()

# Plot heatmap
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix')
plt.show()

Important Notes

Correlation values range from -1 (perfect opposite) to 1 (perfect match).

Colors help spot strong or weak relationships quickly.

Always check data types before calculating correlation; non-numeric columns are ignored.

Summary

A correlation matrix shows how pairs of variables move together.

Heatmaps color-code these relationships for easy understanding.

Use data.corr() and seaborn.heatmap() to create this visualization.