📊 Advanced Data Visualization — Professional-Grade Graphics

Create sophisticated, interactive visualizations for complex data exploration.

🎯 Seaborn for Statistical Graphics

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

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

# Distribution plots
sns.histplot(data=df, x='sepal_length', kde=True, hue='species')
sns.kdeplot(data=df, x='sepal_length', hue='species', fill=True)

# Categorical plots
sns.boxplot(data=df, x='species', y='sepal_length')
sns.violinplot(data=df, x='species', y='sepal_length', hue='species')
sns.stripplot(data=df, x='species', y='sepal_length', jitter=True)

# Relational plots
sns.scatterplot(data=df, x='sepal_length', y='sepal_width', hue='species', size='petal_length')

# Pair plots (all combinations)
sns.pairplot(df, hue='species')

# Correlation heatmap
sns.heatmap(df.corr(), annot=True, cmap='coolwarm', center=0)

plt.show()

📈 Plotly for Interactive Visualization

import plotly.graph_objects as go
import plotly.express as px
import pandas as pd

# Load data
df = px.data.gapminder().query("continent == 'Europe'")

# Interactive scatter plot
fig = px.scatter(
    df,
    x='gdpPercap',
    y='lifeExp',
    size='pop',
    color='country',
    hover_name='country',
    log_x=True,
    animation_frame='year',
    animation_group='country',
    size_max=60
)
fig.show()

# Interactive line plot
fig = px.line(
    df,
    x='year',
    y='lifeExp',
    color='country',
    title='Life Expectancy Over Time'
)
fig.show()

# Sunburst chart
df_sales = px.data.medals_wide()
fig = px.sunburst(
    df_sales,
    values='total',
    names=df_sales.index,
    title='Sales Hierarchy'
)
fig.show()

# Create custom figure
fig = go.Figure(data=[
    go.Scatter(x=[1, 2, 3], y=[10, 15, 13], name='Series 1'),
    go.Scatter(x=[1, 2, 3], y=[16, 5, 11], name='Series 2', yaxis='y2')
])

fig.update_layout(
    title='Multiple Axes Example',
    yaxis=dict(title='Y Axis 1'),
    yaxis2=dict(title='Y Axis 2', overlaying='y', side='right')
)
fig.show()

🎨 Advanced Matplotlib Customization

import matplotlib.pyplot as plt
import numpy as np

# Create figure with subplots
fig, axes = plt.subplots(2, 2, figsize=(12, 10))

# Plot 1: Custom styling
ax = axes[0, 0]
x = np.linspace(0, 10, 100)
ax.plot(x, np.sin(x), linewidth=2.5, color='#FF6B6B', label='sin(x)')
ax.fill_between(x, np.sin(x), alpha=0.3, color='#FF6B6B')
ax.set_title('Sine Wave', fontsize=14, fontweight='bold')
ax.set_xlabel('x', fontsize=12)
ax.set_ylabel('y', fontsize=12)
ax.grid(True, alpha=0.3, linestyle='--')
ax.legend(fontsize=10)

# Plot 2: Error bars
ax = axes[0, 1]
x = np.arange(5)
y = np.array([2, 4, 3, 5, 6])
errors = np.array([0.2, 0.3, 0.25, 0.15, 0.3])
ax.errorbar(x, y, yerr=errors, fmt='o', capsize=5, capthick=2)
ax.set_title('Data with Uncertainties', fontsize=14, fontweight='bold')

# Plot 3: Dual axes
ax1 = axes[1, 0]
ax2 = ax1.twinx()

x = np.arange(10)
ax1.bar(x, x**2, alpha=0.7, label='x^2', color='steelblue')
ax2.plot(x, x**3, color='coral', linewidth=2, marker='o', label='x^3')

ax1.set_ylabel('x^2', color='steelblue')
ax2.set_ylabel('x^3', color='coral')
ax1.set_title('Dual Axes Example', fontsize=14, fontweight='bold')

# Plot 4: Annotation
ax = axes[1, 1]
x = np.linspace(0, 10, 100)
y = np.sin(x) * np.exp(-x/10)
ax.plot(x, y, linewidth=2)
ax.annotate(
    'Peak',
    xy=(np.pi/2, np.sin(np.pi/2) * np.exp(-np.pi/20)),
    xytext=(np.pi/2 + 1, 0.5),
    arrowprops=dict(arrowstyle='->', color='red'),
    fontsize=12,
    color='red'
)
ax.set_title('Annotated Plot', fontsize=14, fontweight='bold')

plt.tight_layout()
plt.show()

📊 Dashboard Creation

import plotly.subplots as sp
import plotly.graph_objects as go
import pandas as pd
import numpy as np

# Create sample data
dates = pd.date_range('2024-01-01', periods=100)
df = pd.DataFrame({
    'date': dates,
    'sales': np.cumsum(np.random.randn(100) * 10 + 20),
    'costs': np.cumsum(np.random.randn(100) * 8 + 15),
    'profit': None
})
df['profit'] = df['sales'] - df['costs']

# Create subplots
fig = sp.make_subplots(
    rows=2, cols=2,
    subplot_titles=('Sales Trend', 'Profit vs Cost', 'Monthly Distribution', 'Key Metrics'),
    specs=[[{}, {}], [{'colspan': 2}, None]]
)

# Sales trend
fig.add_trace(
    go.Scatter(x=df['date'], y=df['sales'], name='Sales', mode='lines'),
    row=1, col=1
)

# Profit vs Cost
fig.add_trace(
    go.Scatter(x=df['date'], y=df['profit'], name='Profit', mode='lines'),
    row=1, col=2
)
fig.add_trace(
    go.Scatter(x=df['date'], y=df['costs'], name='Costs', mode='lines'),
    row=1, col=2
)

# Distribution
fig.add_trace(
    go.Histogram(x=df['sales'], name='Sales Distribution', nbinsx=20),
    row=2, col=1
)

# Update layout
fig.update_layout(
    title_text='Sales Dashboard',
    height=800,
    showlegend=True
)

fig.show()

🎯 Statistical Visualizations

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

# Generate sample data
np.random.seed(42)
df = pd.DataFrame({
    'category': np.repeat(['A', 'B', 'C'], 100),
    'value': np.concatenate([
        np.random.normal(100, 15, 100),
        np.random.normal(110, 20, 100),
        np.random.normal(95, 18, 100)
    ]),
    'group': np.tile(np.repeat(['Group1', 'Group2'], 50), 3)
})

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

# Joint plot distribution
ax = axes[0, 0]
sns.histplot(data=df, x='value', hue='category', kde=True, ax=ax)
ax.set_title('Distribution by Category')

# Box plot with points
ax = axes[0, 1]
sns.boxplot(data=df, x='category', y='value', ax=ax)
sns.stripplot(data=df, x='category', y='value', color='red', alpha=0.5, ax=ax)
ax.set_title('Box Plot with Points')

# Violin plot
ax = axes[1, 0]
sns.violinplot(data=df, x='category', y='value', hue='group', split=False, ax=ax)
ax.set_title('Violin Plot')

# Count plot
ax = axes[1, 1]
sns.countplot(data=df, x='category', hue='group', ax=ax)
ax.set_title('Count Plot')

plt.tight_layout()
plt.show()

🔀 Faceted Visualization

import plotly.express as px
import pandas as pd

# Create sample data
df = pd.DataFrame({
    'month': ['Jan', 'Feb', 'Mar'] * 4,
    'product': ['A', 'A', 'A', 'B', 'B', 'B', 'C', 'C', 'C', 'D', 'D', 'D'],
    'region': ['North', 'North', 'North', 'North', 'North', 'North',
               'South', 'South', 'South', 'South', 'South', 'South'],
    'sales': [100, 120, 115, 150, 160, 155, 80, 85, 90, 200, 210, 205]
})

# Faceted bar chart
fig = px.bar(
    df,
    x='month',
    y='sales',
    color='product',
    facet_col='region',
    title='Sales by Region and Product'
)
fig.show()

# Seaborn facet grid
g = sns.FacetGrid(df, col='region', hue='product', height=4)
g.map(sns.barplot, 'month', 'sales')
plt.show()

🔑 Key Takeaways

• ✅ Use Seaborn for statistical graphics and quick EDA

• ✅ Use Plotly for interactive, web-friendly visualizations

• ✅ Master custom styling in Matplotlib for publication-quality plots

• ✅ Use subplots for comparing multiple visualizations

• ✅ Annotate important features and outliers

• ✅ Create dashboards with multiple synchronized plots

• ✅ Use faceting to compare across categories

• ✅ Choose appropriate chart types for your data and audience

Complete the learning path: Challenges | Solutions