Matplotlib Tutorial: Complete Guide to Data Visualization in Python

What is Matplotlib?

Matplotlib is Python’s most popular data visualization library. It creates static, animated, and interactive visualizations with just a few lines of code.

Installation

pip install matplotlib

import matplotlib.pyplot as plt
import numpy as np

Basic Plots

Line Plot

# Simple line plot
x = [1, 2, 3, 4, 5]
y = [2, 4, 6, 8, 10]

plt.plot(x, y)
plt.title('Simple Line Plot')
plt.xlabel('X Axis')
plt.ylabel('Y Axis')
plt.show()

Multiple Lines

x = np.linspace(0, 10, 100)

plt.figure(figsize=(10, 6))
plt.plot(x, np.sin(x), label='sin(x)', color='blue', linestyle='-')
plt.plot(x, np.cos(x), label='cos(x)', color='red', linestyle='--')
plt.plot(x, np.tan(x), label='tan(x)', color='green', linestyle=':')

plt.title('Trigonometric Functions')
plt.xlabel('x')
plt.ylabel('y')
plt.legend()
plt.grid(True, alpha=0.3)
plt.ylim(-2, 2)
plt.show()

Line Styles and Markers

x = np.array([1, 2, 3, 4, 5])
y = np.array([1, 4, 9, 16, 25])

plt.figure(figsize=(12, 4))

# Different styles
plt.subplot(1, 3, 1)
plt.plot(x, y, 'ro-')  # Red circles with line
plt.title('ro-')

plt.subplot(1, 3, 2)
plt.plot(x, y, 'b^--')  # Blue triangles with dashed line
plt.title('b^--')

plt.subplot(1, 3, 3)
plt.plot(x, y, 'gs:')  # Green squares with dotted line
plt.title('gs:')

plt.tight_layout()
plt.show()

Bar Charts

Basic Bar Chart

categories = ['Python', 'JavaScript', 'Java', 'C++', 'Go']
values = [85, 78, 72, 65, 58]

plt.figure(figsize=(10, 6))
plt.bar(categories, values, color='steelblue', edgecolor='black')
plt.title('Programming Language Popularity')
plt.xlabel('Language')
plt.ylabel('Popularity Score')
plt.show()

Horizontal Bar Chart

plt.figure(figsize=(10, 6))
plt.barh(categories, values, color='coral')
plt.title('Programming Language Popularity')
plt.xlabel('Popularity Score')
plt.show()

Grouped Bar Chart

labels = ['Q1', 'Q2', 'Q3', 'Q4']
product_a = [20, 35, 30, 35]
product_b = [25, 32, 34, 20]
product_c = [22, 30, 28, 25]

x = np.arange(len(labels))
width = 0.25

fig, ax = plt.subplots(figsize=(10, 6))
bars1 = ax.bar(x - width, product_a, width, label='Product A', color='#2ecc71')
bars2 = ax.bar(x, product_b, width, label='Product B', color='#3498db')
bars3 = ax.bar(x + width, product_c, width, label='Product C', color='#e74c3c')

ax.set_xlabel('Quarter')
ax.set_ylabel('Sales')
ax.set_title('Quarterly Sales by Product')
ax.set_xticks(x)
ax.set_xticklabels(labels)
ax.legend()

plt.tight_layout()
plt.show()

Stacked Bar Chart

labels = ['2020', '2021', '2022', '2023']
mobile = [30, 35, 40, 45]
desktop = [50, 45, 40, 35]
tablet = [20, 20, 20, 20]

plt.figure(figsize=(10, 6))
plt.bar(labels, mobile, label='Mobile', color='#3498db')
plt.bar(labels, desktop, bottom=mobile, label='Desktop', color='#2ecc71')
plt.bar(labels, tablet, bottom=np.array(mobile) + np.array(desktop),
        label='Tablet', color='#e74c3c')

plt.xlabel('Year')
plt.ylabel('Traffic Share (%)')
plt.title('Website Traffic by Device')
plt.legend()
plt.show()

Scatter Plots

Basic Scatter Plot

np.random.seed(42)
x = np.random.randn(100)
y = x + np.random.randn(100) * 0.5

plt.figure(figsize=(10, 6))
plt.scatter(x, y, alpha=0.6, edgecolors='black', linewidth=0.5)
plt.title('Scatter Plot')
plt.xlabel('X')
plt.ylabel('Y')
plt.show()

Scatter with Size and Color

np.random.seed(42)
n = 50
x = np.random.rand(n)
y = np.random.rand(n)
colors = np.random.rand(n)
sizes = 1000 * np.random.rand(n)

plt.figure(figsize=(10, 6))
scatter = plt.scatter(x, y, c=colors, s=sizes, alpha=0.5, cmap='viridis')
plt.colorbar(scatter, label='Color Value')
plt.title('Bubble Chart')
plt.xlabel('X')
plt.ylabel('Y')
plt.show()

Histograms

Basic Histogram

np.random.seed(42)
data = np.random.randn(1000)

plt.figure(figsize=(10, 6))
plt.hist(data, bins=30, color='steelblue', edgecolor='black', alpha=0.7)
plt.title('Normal Distribution')
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.show()

Multiple Histograms

np.random.seed(42)
data1 = np.random.normal(0, 1, 1000)
data2 = np.random.normal(2, 1.5, 1000)

plt.figure(figsize=(10, 6))
plt.hist(data1, bins=30, alpha=0.5, label='Distribution 1', color='blue')
plt.hist(data2, bins=30, alpha=0.5, label='Distribution 2', color='red')
plt.title('Comparing Distributions')
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.legend()
plt.show()

Pie Charts

sizes = [35, 30, 20, 15]
labels = ['Python', 'JavaScript', 'Java', 'Others']
colors = ['#3498db', '#f1c40f', '#e74c3c', '#95a5a6']
explode = (0.05, 0, 0, 0)  # Explode first slice

plt.figure(figsize=(8, 8))
plt.pie(sizes, explode=explode, labels=labels, colors=colors,
        autopct='%1.1f%%', shadow=True, startangle=90)
plt.title('Programming Language Usage')
plt.axis('equal')
plt.show()

Subplots

Grid of Subplots

fig, axes = plt.subplots(2, 2, figsize=(12, 10))

# Plot 1: Line
x = np.linspace(0, 10, 100)
axes[0, 0].plot(x, np.sin(x))
axes[0, 0].set_title('Line Plot')

# Plot 2: Bar
categories = ['A', 'B', 'C', 'D']
values = [23, 45, 56, 78]
axes[0, 1].bar(categories, values, color='coral')
axes[0, 1].set_title('Bar Chart')

# Plot 3: Scatter
np.random.seed(42)
axes[1, 0].scatter(np.random.rand(50), np.random.rand(50))
axes[1, 0].set_title('Scatter Plot')

# Plot 4: Histogram
axes[1, 1].hist(np.random.randn(1000), bins=30, color='green', alpha=0.7)
axes[1, 1].set_title('Histogram')

plt.tight_layout()
plt.show()

Unequal Subplots

fig = plt.figure(figsize=(12, 8))

# Large plot on left
ax1 = fig.add_subplot(1, 2, 1)
ax1.plot(np.random.randn(100).cumsum())
ax1.set_title('Main Plot')

# Two small plots on right
ax2 = fig.add_subplot(2, 2, 2)
ax2.bar(['A', 'B', 'C'], [10, 20, 15])
ax2.set_title('Bar Chart')

ax3 = fig.add_subplot(2, 2, 4)
ax3.scatter(np.random.rand(20), np.random.rand(20))
ax3.set_title('Scatter')

plt.tight_layout()
plt.show()

Customization

Colors and Styles

# Using different color formats
plt.figure(figsize=(12, 4))

x = np.linspace(0, 10, 100)

plt.subplot(1, 3, 1)
plt.plot(x, np.sin(x), color='red')  # Named color
plt.title('Named Color')

plt.subplot(1, 3, 2)
plt.plot(x, np.sin(x), color='#2ecc71')  # Hex color
plt.title('Hex Color')

plt.subplot(1, 3, 3)
plt.plot(x, np.sin(x), color=(0.1, 0.2, 0.5))  # RGB tuple
plt.title('RGB Tuple')

plt.tight_layout()
plt.show()

Annotations

x = np.linspace(0, 2 * np.pi, 100)
y = np.sin(x)

plt.figure(figsize=(10, 6))
plt.plot(x, y)

# Add annotations
plt.annotate('Maximum', xy=(np.pi/2, 1), xytext=(np.pi/2 + 1, 1.2),
             arrowprops=dict(arrowstyle='->', color='red'),
             fontsize=12, color='red')

plt.annotate('Minimum', xy=(3*np.pi/2, -1), xytext=(3*np.pi/2 + 1, -1.2),
             arrowprops=dict(arrowstyle='->', color='blue'),
             fontsize=12, color='blue')

plt.title('Annotated Sine Wave')
plt.xlabel('x')
plt.ylabel('sin(x)')
plt.grid(True, alpha=0.3)
plt.show()

Custom Ticks

x = np.linspace(0, 2 * np.pi, 100)
y = np.sin(x)

plt.figure(figsize=(10, 6))
plt.plot(x, y)

# Custom x-ticks
plt.xticks([0, np.pi/2, np.pi, 3*np.pi/2, 2*np.pi],
           ['0', 'π/2', 'π', '3π/2', '2π'])

# Custom y-ticks
plt.yticks([-1, -0.5, 0, 0.5, 1])

plt.title('Sine Wave with Custom Ticks')
plt.grid(True, alpha=0.3)
plt.show()

Heatmaps

np.random.seed(42)
data = np.random.rand(10, 10)

plt.figure(figsize=(10, 8))
plt.imshow(data, cmap='viridis', aspect='auto')
plt.colorbar(label='Value')
plt.title('Heatmap')
plt.xlabel('X')
plt.ylabel('Y')
plt.show()

Correlation Matrix

# Simulated correlation matrix
np.random.seed(42)
n_vars = 5
labels = ['Var A', 'Var B', 'Var C', 'Var D', 'Var E']
corr = np.random.rand(n_vars, n_vars)
corr = (corr + corr.T) / 2  # Make symmetric
np.fill_diagonal(corr, 1)  # Diagonal = 1

plt.figure(figsize=(8, 6))
plt.imshow(corr, cmap='coolwarm', vmin=-1, vmax=1)
plt.colorbar(label='Correlation')
plt.xticks(range(n_vars), labels, rotation=45)
plt.yticks(range(n_vars), labels)

# Add correlation values
for i in range(n_vars):
    for j in range(n_vars):
        plt.text(j, i, f'{corr[i, j]:.2f}', ha='center', va='center')

plt.title('Correlation Matrix')
plt.tight_layout()
plt.show()

Box Plots

np.random.seed(42)
data = [np.random.normal(0, std, 100) for std in range(1, 5)]

plt.figure(figsize=(10, 6))
bp = plt.boxplot(data, labels=['Group 1', 'Group 2', 'Group 3', 'Group 4'],
                  patch_artist=True)

# Customize colors
colors = ['#3498db', '#2ecc71', '#e74c3c', '#f1c40f']
for patch, color in zip(bp['boxes'], colors):
    patch.set_facecolor(color)

plt.title('Box Plot Comparison')
plt.ylabel('Values')
plt.grid(True, alpha=0.3)
plt.show()

Saving Figures

# Create a figure
fig, ax = plt.subplots(figsize=(10, 6))
ax.plot([1, 2, 3, 4], [1, 4, 2, 3])
ax.set_title('Sample Plot')

# Save as different formats
fig.savefig('plot.png', dpi=300, bbox_inches='tight')
fig.savefig('plot.pdf', bbox_inches='tight')
fig.savefig('plot.svg', bbox_inches='tight')

# Save with transparent background
fig.savefig('plot_transparent.png', dpi=300, transparent=True, bbox_inches='tight')

Practical Examples

Sales Dashboard

fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Monthly sales trend
months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun']
sales = [120, 135, 125, 140, 155, 170]
axes[0, 0].plot(months, sales, marker='o', color='#3498db', linewidth=2)
axes[0, 0].fill_between(months, sales, alpha=0.3)
axes[0, 0].set_title('Monthly Sales Trend')
axes[0, 0].set_ylabel('Sales ($K)')

# Sales by category
categories = ['Electronics', 'Clothing', 'Food', 'Books']
cat_sales = [45, 30, 15, 10]
axes[0, 1].pie(cat_sales, labels=categories, autopct='%1.1f%%',
               colors=['#3498db', '#2ecc71', '#e74c3c', '#f1c40f'])
axes[0, 1].set_title('Sales by Category')

# Regional comparison
regions = ['North', 'South', 'East', 'West']
q1 = [25, 30, 20, 25]
q2 = [30, 28, 25, 27]
x = np.arange(len(regions))
width = 0.35
axes[1, 0].bar(x - width/2, q1, width, label='Q1', color='#3498db')
axes[1, 0].bar(x + width/2, q2, width, label='Q2', color='#2ecc71')
axes[1, 0].set_xticks(x)
axes[1, 0].set_xticklabels(regions)
axes[1, 0].set_title('Regional Sales Comparison')
axes[1, 0].legend()

# Daily distribution
np.random.seed(42)
daily_sales = np.random.normal(5000, 1000, 100)
axes[1, 1].hist(daily_sales, bins=20, color='#9b59b6', edgecolor='black')
axes[1, 1].set_title('Daily Sales Distribution')
axes[1, 1].set_xlabel('Sales ($)')

plt.tight_layout()
plt.show()

Time Series Plot

# Generate time series data
np.random.seed(42)
dates = np.arange('2023-01', '2024-01', dtype='datetime64[D]')
values = np.cumsum(np.random.randn(len(dates))) + 100

plt.figure(figsize=(14, 6))
plt.plot(dates, values, color='#3498db', linewidth=1)
plt.fill_between(dates, values, alpha=0.3)

# Add moving average
window = 30
ma = np.convolve(values, np.ones(window)/window, mode='valid')
plt.plot(dates[window-1:], ma, color='#e74c3c', linewidth=2, label=f'{window}-day MA')

plt.title('Stock Price Over Time')
plt.xlabel('Date')
plt.ylabel('Price ($)')
plt.legend()
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

Quick Reference

Function	Description
plt.plot()	Line plot
plt.bar() / plt.barh()	Bar chart
plt.scatter()	Scatter plot
plt.hist()	Histogram
plt.pie()	Pie chart
plt.boxplot()	Box plot
plt.imshow()	Heatmap/image
plt.subplot()	Create subplots
plt.savefig()	Save figure

Summary

Matplotlib is essential for:

1. Exploratory analysis - quick data visualization
2. Publication-quality figures - customizable and professional
3. Dashboard creation - combining multiple plots
4. Integration - works with Pandas, NumPy, scikit-learn

Master Matplotlib to effectively communicate insights from your data.