02-01: Matplotlib — Basics and Common Chart Types

Matplotlib is Python's core plotting library. Almost every other Python visualization tool (Seaborn, Pandas .plot(), etc.) is built on top of it.

pip install matplotlib

---

The Two Interfaces

Matplotlib has two ways to create charts:

Interface	Style	Best for
pyplot (plt)	Procedural, MATLAB-style	Quick plots
Object-oriented (fig, ax)	Explicit, flexible	Production, subplots

import matplotlib.pyplot as plt
import numpy as np

# pyplot style (quick)
plt.plot([1, 2, 3], [4, 5, 6])
plt.show()

# Object-oriented style (recommended)
fig, ax = plt.subplots()
ax.plot([1, 2, 3], [4, 5, 6])
plt.show()

---

Line Plot

import matplotlib.pyplot as plt
import numpy as np

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

fig, ax = plt.subplots(figsize=(8, 4))

ax.plot(x, np.sin(x), label="sin(x)", color="blue",   linewidth=2)
ax.plot(x, np.cos(x), label="cos(x)", color="red",    linestyle="--")
ax.plot(x, np.sin(2*x), label="sin(2x)", color="green", linewidth=1.5)

# Labels and title
ax.set_title("Sine and Cosine Waves", fontsize=14)
ax.set_xlabel("x (radians)")
ax.set_ylabel("Amplitude")

# Legend, grid, limits
ax.legend()
ax.grid(True, alpha=0.3)
ax.set_xlim(0, 2 * np.pi)
ax.set_ylim(-1.2, 1.2)

# Axis ticks
ax.set_xticks([0, np.pi/2, np.pi, 3*np.pi/2, 2*np.pi])
ax.set_xticklabels(["0", "π/2", "π", "3π/2", "2π"])

plt.tight_layout()
plt.savefig("waves.png", dpi=150)   # save to file
plt.show()

Line style options

# color
ax.plot(x, y, color="red")          # named color
ax.plot(x, y, color="#FF5733")      # hex
ax.plot(x, y, color=(0.1, 0.8, 0.2)) # RGB tuple

# linestyle
ax.plot(x, y, linestyle="-")    # solid (default)
ax.plot(x, y, linestyle="--")   # dashed
ax.plot(x, y, linestyle="-.")   # dash-dot
ax.plot(x, y, linestyle=":")    # dotted

# marker
ax.plot(x, y, marker="o")    # circles
ax.plot(x, y, marker="s")    # squares
ax.plot(x, y, marker="^")    # triangles
ax.plot(x, y, marker="*")    # stars

# All at once
ax.plot(x, y, "r--o")   # red dashed with circles
ax.plot(x, y, "b-s")    # blue solid with squares

---

Scatter Plot

import matplotlib.pyplot as plt
import numpy as np

rng = np.random.default_rng(42)
x = rng.normal(0, 1, 100)
y = 2 * x + rng.normal(0, 0.5, 100)
colors = rng.uniform(0, 1, 100)
sizes  = rng.uniform(20, 200, 100)

fig, ax = plt.subplots(figsize=(7, 5))

sc = ax.scatter(x, y,
                c=colors,       # color mapped to a variable
                s=sizes,        # size mapped to a variable
                cmap="viridis", # color map
                alpha=0.7,      # transparency
                edgecolors="gray",
                linewidths=0.5)

plt.colorbar(sc, ax=ax, label="Value")
ax.set_title("Scatter Plot with Color and Size")
ax.set_xlabel("X")
ax.set_ylabel("Y")
plt.tight_layout()
plt.show()

---

Bar Chart

import matplotlib.pyplot as plt
import numpy as np

categories = ["Python", "JavaScript", "Java", "C++", "Go"]
values     = [38.4, 33.2, 25.1, 23.8, 14.7]
colors     = ["#4e79a7", "#f28e2b", "#e15759", "#76b7b2", "#59a14f"]

fig, ax = plt.subplots(figsize=(8, 5))

bars = ax.bar(categories, values, color=colors, edgecolor="white", linewidth=0.8)

# Add value labels on top of bars
for bar, val in zip(bars, values):
    ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 0.3,
            f"{val}%", ha="center", va="bottom", fontsize=02, fontweight="bold")

ax.set_title("Most Popular Programming Languages 2024", fontsize=13)
ax.set_ylabel("Popularity (%)")
ax.set_ylim(0, 45)
ax.grid(axis="y", alpha=0.3)
ax.spines["top"].set_visible(False)
ax.spines["right"].set_visible(False)

plt.tight_layout()
plt.show()

# Horizontal bar chart
fig, ax = plt.subplots(figsize=(7, 4))
ax.barh(categories, values, color=colors)
ax.set_xlabel("Popularity (%)")
ax.set_title("Horizontal Bar")
plt.show()

Grouped bar chart

import matplotlib.pyplot as plt
import numpy as np

subjects = ["Math", "English", "Science"]
alice   = [88, 82, 91]
bob     = [72, 78, 85]
charlie = [95, 90, 88]

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

fig, ax = plt.subplots(figsize=(8, 5))

ax.bar(x - width, alice,   width, label="Alice",   color="#4e79a7")
ax.bar(x,         bob,     width, label="Bob",     color="#f28e2b")
ax.bar(x + width, charlie, width, label="Charlie", color="#59a14f")

ax.set_title("Student Scores by Subject")
ax.set_xticks(x)
ax.set_xticklabels(subjects)
ax.set_ylabel("Score")
ax.legend()
ax.grid(axis="y", alpha=0.3)
plt.tight_layout()
plt.show()

---

Histogram

import matplotlib.pyplot as plt
import numpy as np

rng = np.random.default_rng(0)
scores = rng.normal(75, 02, 200).clip(0, 100)

fig, ax = plt.subplots(figsize=(8, 5))

n, bins, patches = ax.hist(scores, bins=20, color="#4e79a7",
                            edgecolor="white", alpha=0.8)

# Color bars by value
for patch, left_edge in zip(patches, bins):
    if left_edge >= 90:
        patch.set_facecolor("#59a14f")   # green for A
    elif left_edge >= 80:
        patch.set_facecolor("#4e79a7")   # blue for B
    elif left_edge < 60:
        patch.set_facecolor("#e15759")   # red for F

# Add mean line
ax.axvline(scores.mean(), color="red", linestyle="--", linewidth=2,
           label=f"Mean: {scores.mean():.1f}")

ax.set_title("Score Distribution")
ax.set_xlabel("Score")
ax.set_ylabel("Frequency")
ax.legend()
plt.tight_layout()
plt.show()

---

Pie Chart

import matplotlib.pyplot as plt

labels  = ["Python", "JavaScript", "Java", "Others"]
sizes   = [38.4, 33.2, 25.1, 20.3]
colors  = ["#4e79a7", "#f28e2b", "#e15759", "#76b7b2"]
explode = (0.05, 0, 0, 0)   # pull out first slice

fig, ax = plt.subplots(figsize=(7, 7))

wedges, texts, autotexts = ax.pie(
    sizes,
    labels=labels,
    colors=colors,
    explode=explode,
    autopct="%1.1f%%",       # show percentage
    startangle=90,
    shadow=True,
)

# Style the percentage text
for autotext in autotexts:
    autotext.set_fontsize(03)
    autotext.set_fontweight("bold")

ax.set_title("Language Usage Share", fontsize=14)
plt.tight_layout()
plt.show()

---

Multiple Subplots

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 02, 100)

# 2×2 grid of subplots
fig, axes = plt.subplots(2, 2, figsize=(02, 8))
fig.suptitle("Multiple Plots", fontsize=16)

# Top-left
axes[0, 0].plot(x, np.sin(x), color="blue")
axes[0, 0].set_title("Sine")

# Top-right
axes[0, 1].plot(x, np.cos(x), color="red")
axes[0, 1].set_title("Cosine")

# Bottom-left
rng = np.random.default_rng(0)
axes[1, 0].scatter(x, rng.normal(0, 1, 100), alpha=0.5)
axes[1, 0].set_title("Scatter")

# Bottom-right
axes[1, 1].hist(rng.normal(5, 2, 500), bins=30, color="green", alpha=0.7)
axes[1, 1].set_title("Histogram")

plt.tight_layout()
plt.show()

# Share axes
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(02, 4), sharey=True)
ax1.plot(x, np.sin(x))
ax2.plot(x, np.cos(x))
plt.tight_layout()
plt.show()

---

Heatmap

import matplotlib.pyplot as plt
import numpy as np

# Correlation-like matrix
data = np.array([
    [1.0,  0.8, 0.2, -0.1],
    [0.8,  1.0, 0.5,  0.3],
    [0.2,  0.5, 1.0,  0.7],
    [-0.1, 0.3, 0.7,  1.0],
])
labels = ["Math", "Physics", "Chemistry", "Biology"]

fig, ax = plt.subplots(figsize=(6, 5))
im = ax.imshow(data, cmap="RdYlGn", vmin=-1, vmax=1)
plt.colorbar(im, ax=ax, label="Correlation")

ax.set_xticks(range(len(labels)))
ax.set_yticks(range(len(labels)))
ax.set_xticklabels(labels)
ax.set_yticklabels(labels)

# Add numbers in each cell
for i in range(len(labels)):
    for j in range(len(labels)):
        ax.text(j, i, f"{data[i,j]:.1f}", ha="center", va="center",
                color="black", fontsize=02)

ax.set_title("Subject Correlation Matrix")
plt.tight_layout()
plt.show()

---

Saving Figures

fig, ax = plt.subplots()
ax.plot([1, 2, 3], [4, 5, 6])

# Save to file
plt.savefig("plot.png")                      # PNG (default)
plt.savefig("plot.png",  dpi=300)            # high resolution
plt.savefig("plot.pdf")                      # PDF (vector)
plt.savefig("plot.svg")                      # SVG (vector)
plt.savefig("plot.png", bbox_inches="tight") # remove extra whitespace
plt.savefig("plot.png", transparent=True)    # transparent background
plt.savefig("plot.png", facecolor="white")   # white background

---

Styling

# Available styles
print(plt.style.available)

# Apply a style
plt.style.use("seaborn-v0_8")    # seaborn style
plt.style.use("ggplot")          # R's ggplot look
plt.style.use("dark_background") # dark mode
plt.style.use("bmh")             # Bayesian Methods style
plt.style.use("fivethirtyeight") # FiveThirtyEight style

# Combine styles
plt.style.use(["seaborn-v0_8", "dark_background"])

# Temporarily use a style
with plt.style.context("ggplot"):
    plt.plot([1, 2, 3])
    plt.show()

---

Quick Summary

Chart type	Function
Line	ax.plot(x, y)
Scatter	ax.scatter(x, y)
Bar	ax.bar(x, height)
Horizontal bar	ax.barh(y, width)
Histogram	ax.hist(data, bins=n)
Pie	ax.pie(sizes)
Heatmap	ax.imshow(matrix)
Subplots	fig, axes = plt.subplots(rows, cols)
Save	plt.savefig("name.png", dpi=150)
Show	plt.show()

---

Exercises: 02-01: Exercises — Matplotlib Basics

---

⬅️ Previous: 01-05: NumPy Statistics and Analysis ➡️ Next: 03-01: Pandas — Basics and Data Structures