Python Data Science Series Part 3: Data Visualization

Matplotlib Fundamentals

Matplotlib provides complete control over every element of a plot. It has two interfaces:

• pyplot (MATLAB-style): Quick plotting with plt.plot()
• Object-oriented (OO): Explicit figure and axes objects (recommended)

Basic Plots

import matplotlib.pyplot as plt
import numpy as np

# Line plot
x = np.linspace(0, 10, 100)
y = np.sin(x)

plt.plot(x, y)
plt.title('Sine Wave')
plt.xlabel('X axis')
plt.ylabel('Y axis')
plt.grid(True)
plt.show()

# Scatter plot
plt.scatter(x, y, alpha=0.5)
plt.show()

# Bar chart
categories = ['A', 'B', 'C', 'D']
values = [25, 40, 30, 55]
plt.bar(categories, values, color='teal')
plt.show()

Understanding plt.plot() Parameters

The plot() function is highly flexible with many parameters for customization:

# Complete signature:
# plot([x], y, [fmt], *, data=None, **kwargs)

import matplotlib.pyplot as plt
import numpy as np

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

# Basic usage - x and y explicitly
plt.plot(x, y)
plt.title('Basic: x and y explicitly')
plt.xlabel('X')
plt.ylabel('Y')
plt.grid(True, alpha=0.3)
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Format strings [marker][line][color]
plt.plot(x, y, 'ro-', label='red circles, solid')
plt.plot(x, y - 0.5, 'g^--', label='green triangles, dashed')
plt.plot(x, y - 1, 'bs:', label='blue squares, dotted')
plt.title('Format Strings: [marker][line][color]')
plt.xlabel('X')
plt.ylabel('Y')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Keyword arguments (full customization)
plt.plot(x, y, 
         color='#3B9797',           # Hex color
         linestyle='--',            # Dashed line
         linewidth=2.5,             # Line thickness
         marker='o',                # Circle markers
         markersize=8,              # Marker size
         markerfacecolor='red',     # Marker fill color
         markeredgecolor='black',   # Marker edge color
         markeredgewidth=1.5,       # Marker edge thickness
         alpha=0.7,                 # Transparency (0-1)
         label='Custom styled')     # Legend label
plt.title('Keyword Arguments: Full Customization')
plt.xlabel('X')
plt.ylabel('Y')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

Plotting NumPy Arrays

import matplotlib.pyplot as plt
import numpy as np

# Direct plotting from NumPy arrays
x = np.array([1, 2, 3, 4, 5])
y = np.array([2, 4, 6, 8, 10])

plt.plot(x, y, 'bo-', linewidth=2, label='y = 2x')
plt.title('Plotting NumPy Arrays')
plt.xlabel('X')
plt.ylabel('Y')
plt.legend()
plt.grid(True)
plt.show()

Plotting Pandas Series

import matplotlib.pyplot as plt
import pandas as pd

# Create a Pandas Series
s = pd.Series([10, 15, 13, 17, 20], 
              index=['Mon', 'Tue', 'Wed', 'Thu', 'Fri'],
              name='Temperature')

# Plot Series directly
plt.plot(s, marker='o', linestyle='--', color='red')
plt.title('Plotting Pandas Series')
plt.xlabel('Day')
plt.ylabel('Temperature (°C)')
plt.grid(True, alpha=0.3)
plt.show()

import matplotlib.pyplot as plt
import pandas as pd

# Multiple Series from DataFrame columns
df = pd.DataFrame({
    'sales': [100, 150, 120, 200, 180],
    'profit': [20, 35, 25, 50, 40],
}, index=['Q1', 'Q2', 'Q3', 'Q4', 'Q5'])

# Plot multiple columns
plt.plot(df.index, df['sales'], 'o-', label='Sales', linewidth=2)
plt.plot(df.index, df['profit'], 's--', label='Profit', linewidth=2)
plt.title('Sales vs Profit by Quarter')
plt.xlabel('Quarter')
plt.ylabel('Amount ($)')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

Plotting Pandas DataFrames

import matplotlib.pyplot as plt
import pandas as pd

# DataFrame with numeric columns
df = pd.DataFrame({
    'Product_A': [10, 12, 15, 20, 18],
    'Product_B': [8, 14, 16, 19, 22],
    'Product_C': [5, 9, 11, 15, 20]
}, index=['Week 1', 'Week 2', 'Week 3', 'Week 4', 'Week 5'])

# Plot all columns (each column becomes a line)
plt.figure(figsize=(10, 6))
for column in df.columns:
    plt.plot(df.index, df[column], marker='o', label=column, linewidth=2)

plt.title('Product Sales Over 5 Weeks')
plt.xlabel('Week')
plt.ylabel('Sales')
plt.legend()
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import pandas as pd

# Using DataFrame.plot() method (convenient for DataFrame visualization)
df = pd.DataFrame({
    'Open': [100, 102, 101, 105, 107],
    'Close': [102, 101, 104, 106, 108],
}, index=['Day 1', 'Day 2', 'Day 3', 'Day 4', 'Day 5'])

# Built-in DataFrame plotting
df.plot(kind='line', marker='o', figsize=(10, 6))
plt.title('Stock Prices: Open vs Close')
plt.ylabel('Price ($)')
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

Plotting Multiple Datasets

import matplotlib.pyplot as plt
import numpy as np

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

# Method 1: Multiple calls
plt.plot(x, np.sin(x), 'b-', label='sin(x)')
plt.plot(x, np.cos(x), 'r--', label='cos(x)')
plt.plot(x, np.tan(x), 'g:', label='tan(x)')
plt.legend()
plt.ylim(-2, 2)  # Limit y-axis for better visualization
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Method 2: Single call with multiple datasets
plt.plot(x, np.sin(x), 'b-', 
         x, np.cos(x), 'r--',
         x, np.tan(x), 'g:')
plt.ylim(-2, 2)
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Method 3: 2D arrays (each column is a dataset)
y_multi = np.column_stack([np.sin(x), np.cos(x), np.tan(x)])
plt.plot(x, y_multi)
plt.ylim(-2, 2)
plt.show()

Object-Oriented Interface (Preferred)

import matplotlib.pyplot as plt
import numpy as np

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

# Create figure and axes
fig, ax = plt.subplots(figsize=(10, 6))

# Plot on axes
ax.plot(x, y, label='sin(x)', color='blue', linewidth=2)
ax.plot(x, np.cos(x), label='cos(x)', color='red', linestyle='--')

# Customize
ax.set_title('Trigonometric Functions', fontsize=16)
ax.set_xlabel('X', fontsize=12)
ax.set_ylabel('Y', fontsize=12)
ax.legend()
ax.grid(True, alpha=0.3)

plt.show()

Understanding plt.subplots() Parameters

The subplots() function creates a figure and grid of axes with extensive customization options:

import matplotlib.pyplot as plt

# Complete signature:
# subplots(nrows=1, ncols=1, *, sharex=False, sharey=False, 
#          squeeze=True, width_ratios=None, height_ratios=None,
#          subplot_kw=None, gridspec_kw=None, **fig_kw)

# Basic: single subplot
fig, ax = plt.subplots()
ax.plot([1, 2, 3], [1, 4, 9])
plt.show()

import matplotlib.pyplot as plt

# Grid of subplots: 2 rows, 3 columns
fig, axes = plt.subplots(2, 3, figsize=(12, 8))
print(axes.shape)  # (2, 3)

# Access individual axes
axes[0, 0].plot([1, 2, 3], [1, 4, 9])
axes[0, 1].scatter([1, 2, 3], [1, 2, 3])
axes[1, 2].bar(['A', 'B', 'C'], [1, 2, 3])

plt.tight_layout()
plt.show()

Shared Axes

import matplotlib.pyplot as plt
import numpy as np

# Share x-axis across all subplots (aligned zoom)
fig, axes = plt.subplots(2, 2, sharex=True, sharey=True, figsize=(10, 8))

# When shared, only bottom/leftmost labels show
for ax in axes.flat:
    ax.plot(np.random.rand(10))
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import numpy as np

# Share by column (x-axis shared within each column)
fig, axes = plt.subplots(2, 2, sharex='col', figsize=(10, 8))
for ax in axes.flat:
    ax.plot(np.random.rand(10))
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import numpy as np

# Share by row (y-axis shared within each row)
fig, axes = plt.subplots(2, 2, sharey='row', figsize=(10, 8))
for ax in axes.flat:
    ax.plot(np.random.rand(10))
plt.tight_layout()
plt.show()

Custom Subplot Ratios

import matplotlib.pyplot as plt

# Different width ratios
fig, axes = plt.subplots(1, 3, figsize=(12, 4),
                         width_ratios=[1, 2, 1])  # Middle subplot 2x wider
axes[0].plot([1, 2, 3])
axes[0].set_title('Narrow')
axes[1].plot([1, 2, 3])
axes[1].set_title('Wide (2x)')
axes[2].plot([1, 2, 3])
axes[2].set_title('Narrow')
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt

# Different height ratios
fig, axes = plt.subplots(3, 1, figsize=(8, 10),
                         height_ratios=[1, 3, 1])  # Middle subplot 3x taller
axes[0].plot([1, 2, 3])
axes[0].set_title('Short')
axes[1].plot([1, 2, 3])
axes[1].set_title('Tall (3x)')
axes[2].plot([1, 2, 3])
axes[2].set_title('Short')
plt.tight_layout()
plt.show()

Advanced Subplot Configuration

import matplotlib.pyplot as plt
import numpy as np

# subplot_kw: parameters for each subplot (polar projection)
fig, axes = plt.subplots(2, 2, 
                         subplot_kw={'projection': 'polar'},
                         figsize=(10, 10))

# Add some polar plots
theta = np.linspace(0, 2*np.pi, 100)
for ax in axes.flat:
    ax.plot(theta, np.abs(np.sin(theta * np.random.randint(1, 5))))
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import numpy as np

# gridspec_kw: control spacing between subplots
fig, axes = plt.subplots(2, 2, figsize=(10, 8),
                         gridspec_kw={'hspace': 0.4,    # Vertical spacing
                                     'wspace': 0.3,     # Horizontal spacing
                                     'left': 0.1,       # Left margin
                                     'right': 0.95,     # Right margin
                                     'top': 0.95,       # Top margin
                                     'bottom': 0.1})    # Bottom margin

for i, ax in enumerate(axes.flat):
    ax.plot(np.random.rand(10))
    ax.set_title(f'Plot {i+1}')
plt.show()

import matplotlib.pyplot as plt

# squeeze parameter: control return type
fig, axes = plt.subplots(2, 2, squeeze=False)  # Always returns 2D array
print(type(axes))  # numpy.ndarray, shape (2, 2)
print(axes.shape)  # (2, 2)

fig, ax = plt.subplots(1, 1, squeeze=True)     # Returns single Axes object
print(type(ax))    # matplotlib.axes._axes.Axes

import matplotlib.pyplot as plt
import numpy as np

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

# Create 2x2 grid of subplots
fig, axes = plt.subplots(2, 2, figsize=(12, 10))

axes[0, 0].plot(x, y)
axes[0, 0].set_title('Line Plot')

axes[0, 1].scatter(x, y)
axes[0, 1].set_title('Scatter Plot')

axes[1, 0].hist(y, bins=20)
axes[1, 0].set_title('Histogram')

axes[1, 1].bar(['A', 'B', 'C'], [1, 2, 3])
axes[1, 1].set_title('Bar Chart')

plt.tight_layout()  # Prevent overlap
plt.show()

Plot Customization

Colors, Styles & Markers

import matplotlib.pyplot as plt
import numpy as np

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

# Color specifications
plt.figure(figsize=(10, 6))
plt.plot(x, y, color='#3B9797', linewidth=2, label='Hex color')
plt.plot(x, y - 0.5, color='teal', linewidth=2, label='Color name')
plt.plot(x, y - 1, color=(0.2, 0.4, 0.6), linewidth=2, label='RGB tuple')
plt.legend()
plt.title('Color Specifications')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Line styles
plt.figure(figsize=(10, 6))
plt.plot(x, y, linestyle='-', linewidth=2, label='Solid')
plt.plot(x, y - 0.5, linestyle='--', linewidth=2, label='Dashed')
plt.plot(x, y - 1, linestyle=':', linewidth=2, label='Dotted')
plt.plot(x, y - 1.5, linestyle='-.', linewidth=2, label='Dash-dot')
plt.legend()
plt.title('Line Styles')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 10, 50)
y = np.sin(x)

# Markers
plt.figure(figsize=(10, 6))
plt.plot(x, y, marker='o', linewidth=2, markersize=6, label='Circles')
plt.plot(x, y - 0.5, marker='s', linewidth=2, markersize=6, label='Squares')
plt.plot(x, y - 1, marker='^', linewidth=2, markersize=6, label='Triangles')
plt.legend()
plt.title('Marker Styles')
plt.show()

Themes and Styles

import matplotlib.pyplot as plt

# Available styles
print(plt.style.available)
# ['Solarize_Light2', '_classic_test_patch', '_mpl-gallery', '_mpl-gallery-nogrid', 'bmh', 'classic', 'dark_background', 'fast', 'fivethirtyeight', 'ggplot', 'grayscale', 'petroff10', 'seaborn-v0_8', 'seaborn-v0_8-bright', 'seaborn-v0_8-colorblind', 'seaborn-v0_8-dark', 'seaborn-v0_8-dark-palette', 'seaborn-v0_8-darkgrid', 'seaborn-v0_8-deep', 'seaborn-v0_8-muted', 'seaborn-v0_8-notebook', 'seaborn-v0_8-paper', 'seaborn-v0_8-pastel', 'seaborn-v0_8-poster', 'seaborn-v0_8-talk', 'seaborn-v0_8-ticks', 'seaborn-v0_8-white', 'seaborn-v0_8-whitegrid', 'tableau-colorblind10']

import matplotlib.pyplot as plt
import numpy as np

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

# Apply style globally
plt.style.use('seaborn-v0_8-whitegrid')
plt.plot(x, y)
plt.title('Seaborn Style')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

# Temporarily use style (context manager)
with plt.style.context('ggplot'):
    plt.plot(x, y)
    plt.title('ggplot Style (temporary)')
    plt.show()

Figure-Level Customization

import matplotlib.pyplot as plt
import numpy as np

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

# Create figure with custom size and DPI
fig = plt.figure(figsize=(12, 6), dpi=100, facecolor='white')

# Add subplot with specific position [left, bottom, width, height]
ax1 = fig.add_axes([0.1, 0.1, 0.8, 0.8])  # Main axes
ax2 = fig.add_axes([0.65, 0.65, 0.2, 0.2])  # Inset axes

ax1.plot(x, y, 'b-', linewidth=2)
ax1.set_title('Main Plot')
ax1.set_xlabel('X')
ax1.set_ylabel('Y')

ax2.plot(x, y**2, 'r-', linewidth=1.5)
ax2.set_title('Inset: y²', fontsize=10)

plt.show()

Axis Control

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0.1, 10, 100)
y = np.sin(x)

fig, ax = plt.subplots(figsize=(10, 6))
ax.plot(x, y, linewidth=2)

# Set axis limits
ax.set_xlim(0, 10)
ax.set_ylim(-1.5, 1.5)

# Grid customization
ax.grid(True, which='both', linestyle='--', linewidth=0.5, alpha=0.7)
ax.minorticks_on()  # Enable minor ticks

ax.set_title('Axis Limits and Grid')
ax.set_xlabel('X')
ax.set_ylabel('Y')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0.1, 10, 100)
y = x**2

fig, ax = plt.subplots(figsize=(10, 6))
ax.plot(x, y, linewidth=2)

# Set axis scales
ax.set_xscale('log')    # Logarithmic x-axis
ax.set_yscale('log')    # Logarithmic y-axis

ax.set_title('Logarithmic Scales')
ax.set_xlabel('X (log scale)')
ax.set_ylabel('Y (log scale)')
ax.grid(True, alpha=0.3)
plt.show()

import matplotlib.pyplot as plt
import numpy as np

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

fig, ax = plt.subplots(figsize=(8, 8))
ax.plot(x, y, linewidth=2)

# Equal aspect ratio for circle
ax.set_aspect('equal')
ax.set_title('Circle (equal aspect ratio)')
ax.grid(True, alpha=0.3)
plt.show()

Annotations and Text

import matplotlib.pyplot as plt
import numpy as np

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

fig, ax = plt.subplots(figsize=(10, 6))
ax.plot(x, y, linewidth=2)

# Add text at specific coordinates
ax.text(5, 0.5, 'Peak Region', fontsize=12, color='red', fontweight='bold')

# Add annotation with arrow
ax.annotate('Maximum', 
            xy=(np.pi/2, 1),           # Point to annotate
            xytext=(np.pi/2 + 1, 0.5), # Text location
            arrowprops=dict(arrowstyle='->', 
                           connectionstyle='arc3,rad=0.3',
                           color='red', lw=2),
            fontsize=12, 
            bbox=dict(boxstyle='round', facecolor='wheat', alpha=0.5))

# Add horizontal/vertical lines
ax.axhline(y=0, color='k', linestyle='--', linewidth=0.8, label='y=0')
ax.axvline(x=np.pi, color='r', linestyle='--', linewidth=0.8, label='x=π')

# Shade regions
ax.axhspan(-0.5, 0.5, alpha=0.2, color='green', label='Middle range')
ax.axvspan(2, 4, alpha=0.2, color='blue', label='Region 2-4')

ax.set_title('Annotations, Lines, and Shaded Regions')
ax.set_xlabel('X')
ax.set_ylabel('Y')
ax.legend()
ax.grid(True, alpha=0.3)
plt.show()

Multiple Y-Axes (Twinx)

import matplotlib.pyplot as plt
import numpy as np

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

fig, ax1 = plt.subplots(figsize=(10, 6))

# First y-axis (left)
ax1.plot(x, np.sin(x), 'b-', linewidth=2, label='sin(x)')
ax1.set_xlabel('X', fontsize=12)
ax1.set_ylabel('sin(x)', color='b', fontsize=12)
ax1.tick_params(axis='y', labelcolor='b')
ax1.grid(True, alpha=0.3)

# Second y-axis (right) - shares x-axis
ax2 = ax1.twinx()
ax2.plot(x, np.exp(x/5), 'r-', linewidth=2, label='exp(x/5)')
ax2.set_ylabel('exp(x/5)', color='r', fontsize=12)
ax2.tick_params(axis='y', labelcolor='r')

plt.title('Dual Y-Axes Example', fontsize=14)
fig.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import numpy as np
from matplotlib.gridspec import GridSpec

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

fig = plt.figure(figsize=(12, 8))
gs = GridSpec(3, 3, figure=fig, hspace=0.3, wspace=0.3)

# Subplot spanning multiple cells
ax1 = fig.add_subplot(gs[0, :])    # Top row, all columns
ax2 = fig.add_subplot(gs[1, :-1])  # Middle row, first 2 columns
ax3 = fig.add_subplot(gs[1:, -1])  # Right column, last 2 rows
ax4 = fig.add_subplot(gs[-1, 0])   # Bottom left
ax5 = fig.add_subplot(gs[-1, 1])   # Bottom middle

ax1.plot(x, np.sin(x), linewidth=2)
ax1.set_title('Wide Plot (spans 3 columns)')
ax1.grid(True, alpha=0.3)

ax2.plot(x, np.cos(x), linewidth=2)
ax2.set_title('Main Plot (2 columns)')
ax2.grid(True, alpha=0.3)

ax3.hist(np.random.randn(1000), orientation='horizontal', bins=30)
ax3.set_title('Tall Plot (2 rows)')

ax4.scatter(np.random.rand(50), np.random.rand(50), alpha=0.6)
ax4.set_title('Scatter')
ax4.grid(True, alpha=0.3)

ax5.bar(['A', 'B', 'C'], [1, 2, 3])
ax5.set_title('Bar Chart')
ax5.grid(True, alpha=0.3, axis='y')

plt.show()

Seaborn: Statistical Graphics

Seaborn builds on Matplotlib, providing beautiful defaults and high-level functions for statistical visualizations. It integrates seamlessly with Pandas DataFrames.

import seaborn as sns

# Set seaborn theme
sns.set_theme(style='whitegrid')

# Load sample dataset
tips = sns.load_dataset('tips')
print(tips.head())
#    total_bill   tip     sex smoker  day    time  size
# 0       16.99  1.01  Female     No  Sun  Dinner     2
# 1       10.34  1.66    Male     No  Sun  Dinner     3
# ...

Why Seaborn?

• ✅ Beautiful defaults (colors, fonts, spacing)
• ✅ Built for Pandas DataFrames (column names as labels)
• ✅ Statistical visualizations in one line
• ✅ Automatic legends and color schemes

Seaborn Datasets: Load and Explore

Seaborn provides built-in sample datasets perfect for learning and testing visualizations:

import seaborn as sns

# Get list of all available datasets
available_datasets = sns.get_dataset_names()
print("Available datasets:")
print(available_datasets)
# ['anagrams', 'anagrams_long', 'answer_keys', 'attention', 'brain_networks', 
#  'car_crashes', 'diamonds', 'dots', 'dowjones', 'exercise', 'flights', 
#  'fmri', 'gammas', 'geyser', 'glue', 'healthexp', 'iris', 'penguins', 'planets', 
#  'taxis', 'titanic', 'tips', ...]

import seaborn as sns
import pandas as pd

# Load a specific dataset
iris = sns.load_dataset('iris')
print(iris.info())
print("\nDataset shape:", iris.shape)
print(iris.describe())

# Another popular dataset
titanic = sns.load_dataset('titanic')
print("Titanic columns:", titanic.columns.tolist())
print("Titanic shape:", titanic.shape)

import seaborn as sns
import pandas as pd

# Load and explore diamonds dataset
diamonds = sns.load_dataset('diamonds')
print("Diamond columns:", diamonds.columns.tolist())
#  ['carat', 'cut', 'color', 'clarity', 'depth', 'table', 'price', 'x', 'y', 'z']
print("Data types:")
print(diamonds.dtypes)
print("\nSample rows:")
print(diamonds.head())

Visualizing Distributions

Histograms and KDE Plots

import matplotlib.pyplot as plt
import seaborn as sns

# Load sample dataset
tips = sns.load_dataset('tips')

# Histogram with KDE overlay
sns.histplot(tips['total_bill'], bins=20, kde=True)
plt.title('Distribution of Total Bill')
plt.xlabel('Total Bill ($)')
plt.ylabel('Frequency')
plt.show()

KDE (Kernel Density Estimate) Plots - Detailed Parameters

kdeplot() creates smooth probability density curves. Key parameters for customization:

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Basic KDE plot
sns.kdeplot(data=tips, x='total_bill')
plt.title('KDE Plot: Total Bill Distribution')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# KDE with filled area and custom color
sns.kdeplot(data=tips, x='total_bill', 
            fill=True,              # Fill under curve (shade=True in older versions)
            color='teal',           # Line/fill color
            linewidth=2.5,          # Line thickness
            alpha=0.6)              # Transparency
plt.title('KDE with Custom Styling')
plt.xlabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Bandwidth adjustment (controls smoothness)
fig, axes = plt.subplots(1, 3, figsize=(14, 4))

for ax, bw in zip(axes, [0.2, 0.5, 1.0]):
    sns.kdeplot(data=tips, x='total_bill', bw_adjust=bw, 
                fill=True, color='teal', ax=ax)
    ax.set_title(f'Bandwidth Adjust: {bw}')
    ax.set_xlabel('Total Bill ($)')

plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Multiple distributions by category (hue parameter)
sns.kdeplot(data=tips, x='total_bill', hue='sex',
            fill=True,              # Fill curves
            common_norm=False)      # Each hue normalized separately
plt.title('Total Bill Distribution by Gender')
plt.xlabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# 2D KDE (bivariate density)
sns.kdeplot(data=tips, x='total_bill', y='tip',
            fill=True,              # Fill contours
            cmap='viridis',         # Color map for contour levels
            levels=10)              # Number of contour levels
plt.title('2D Density: Bill vs Tip')
plt.show()

Box Plots - Detailed Parameters & Customization

boxplot() shows quartiles, median, and outliers. Essential for statistical comparison.

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Basic box plot (shows median, Q1, Q3, whiskers, outliers)
sns.boxplot(data=tips, x='day', y='total_bill')
plt.title('Bill Distribution by Day of Week')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Box plot with hue (grouping variable)
sns.boxplot(data=tips, x='day', y='total_bill', hue='sex',
            palette='Set2')          # Color palette
plt.title('Bill Distribution by Day and Gender')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Detailed customization
sns.boxplot(data=tips, x='day', y='total_bill', hue='sex',
            palette='husl',         # Color palette
            width=0.6,              # Box width (0-1)
            linewidth=2,            # Line thickness
            fliersize=8,            # Outlier marker size
            dodge=True,             # Separate boxes by hue
            showmeans=True,         # Show mean point
            meanprops=dict(marker='D', markerfacecolor='red', 
                          markersize=8, markeredgecolor='black'))
plt.title('Bill Distribution (Customized)')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Violin plot (box + distribution shape)
sns.violinplot(data=tips, x='day', y='total_bill', hue='sex', 
               split=False,         # False=overlay, True=split (only 2 hues)
               palette='muted',     # Soft color palette
               inner='quartile',    # Shows quartiles ('box', 'point', 'stick', None)
               cut=0,               # Extend density to data range
               linewidth=2)
plt.title('Bill Distribution by Day and Gender (Violin)')
plt.ylabel('Total Bill ($)')
plt.show()

Additional Distribution Plots: Strip and Swarm

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Strip plot (scatter plot with jitter for categorical x)
sns.stripplot(data=tips, x='day', y='total_bill', hue='sex',
              size=8,               # Point size
              jitter=True,          # Add random jitter to avoid overlap
              palette='Set1')
plt.title('Individual Points by Day (Strip Plot)')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Swarm plot (strip plot with smart separation to avoid overlap)
sns.swarmplot(data=tips, x='day', y='total_bill', hue='sex',
              size=7,               # Point size
              palette='husl',
              dodge=True)           # Separate by hue
plt.title('Non-overlapping Points by Day (Swarm Plot)')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Combine violin plot with strip plot (show distribution + raw data)
fig, ax = plt.subplots(figsize=(10, 6))

sns.violinplot(data=tips, x='day', y='total_bill', hue='sex',
               palette='muted', ax=ax)
sns.stripplot(data=tips, x='day', y='total_bill', hue='sex',
              size=5, alpha=0.4, palette='dark', dodge=True, ax=ax)

plt.title('Violin Plot with Raw Data Points')
plt.ylabel('Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Basic scatter
sns.scatterplot(data=tips, x='total_bill', y='tip')
plt.title('Total Bill vs Tip')
plt.xlabel('Total Bill ($)')
plt.ylabel('Tip ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# With categories (color, style, size by different variables)
sns.scatterplot(data=tips, x='total_bill', y='tip', 
                hue='sex', style='smoker', size='size')
plt.title('Bill vs Tip Analysis (multi-dimensional)')
plt.xlabel('Total Bill ($)')
plt.ylabel('Tip ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Scatter with regression line
sns.regplot(data=tips, x='total_bill', y='tip')
plt.title('Linear Regression: Bill vs Tip')
plt.xlabel('Total Bill ($)')
plt.ylabel('Tip ($)')
plt.show()

import seaborn as sns

tips = sns.load_dataset('tips')

# Linear model with confidence interval (by category)
sns.lmplot(data=tips, x='total_bill', y='tip', hue='sex', height=6)
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Compute correlation matrix
corr = tips[['total_bill', 'tip', 'size']].corr()

# Heatmap
sns.heatmap(corr, annot=True, cmap='coolwarm', center=0, vmin=-1, vmax=1, 
            square=True, linewidths=1)
plt.title('Correlation Matrix')
plt.show()

import seaborn as sns

tips = sns.load_dataset('tips')

# All pairwise relationships
sns.pairplot(tips, hue='sex', diag_kind='kde')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Count by category
sns.countplot(data=tips, x='day', hue='sex')
plt.title('Customer Count by Day')
plt.xlabel('Day of Week')
plt.ylabel('Count')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Mean with 95% confidence interval
sns.barplot(data=tips, x='day', y='total_bill', hue='sex', ci=95)
plt.title('Average Bill by Day and Gender')
plt.xlabel('Day of Week')
plt.ylabel('Average Total Bill ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

tips = sns.load_dataset('tips')

# Show point estimates and confidence intervals
sns.pointplot(data=tips, x='day', y='tip', hue='sex')
plt.title('Average Tip by Day and Gender')
plt.xlabel('Day of Week')
plt.ylabel('Average Tip ($)')
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

# Load data
df = sns.load_dataset('iris')

# 1. Distribution of features
fig, axes = plt.subplots(2, 2, figsize=(12, 10))

sns.histplot(df['sepal_length'], kde=True, ax=axes[0,0])
axes[0,0].set_title('Sepal Length Distribution')

sns.histplot(df['sepal_width'], kde=True, ax=axes[0,1])
axes[0,1].set_title('Sepal Width Distribution')

sns.histplot(df['petal_length'], kde=True, ax=axes[1,0])
axes[1,0].set_title('Petal Length Distribution')

sns.histplot(df['petal_width'], kde=True, ax=axes[1,1])
axes[1,1].set_title('Petal Width Distribution')

plt.suptitle('Iris Dataset: Feature Distributions', fontsize=16, y=1.00)
plt.tight_layout()
plt.show()

import seaborn as sns

df = sns.load_dataset('iris')

# 2. Pairwise relationships
sns.pairplot(df, hue='species', height=2.5)
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

df = sns.load_dataset('iris')

# 3. Correlation heatmap
corr = df.drop('species', axis=1).corr()
sns.heatmap(corr, annot=True, cmap='viridis', square=True, linewidths=1)
plt.title('Iris Dataset: Feature Correlations')
plt.show()

# Save as PNG (for web/presentations)
plt.savefig('figure.png', dpi=300, bbox_inches='tight')

# Save as PDF (for publications)
plt.savefig('figure.pdf', bbox_inches='tight')

# Save as SVG (vector, scalable)
plt.savefig('figure.svg', bbox_inches='tight')