Seaborn

# Seaborn Common Use Cases and Examples

This document provides practical examples for common data visualization scenarios using seaborn.

## Exploratory Data Analysis

### Quick Dataset Overview

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

# Load data
df = pd.read_csv('data.csv')

# Pairwise relationships for all numeric variables
sns.pairplot(df, hue='target_variable', corner=True, diag_kind='kde')
plt.suptitle('Dataset Overview', y=1.01)
plt.savefig('overview.png', dpi=300, bbox_inches='tight')
```

### Distribution Exploration

```python
# Multiple distributions across categories
g = sns.displot(
    data=df,
    x='measurement',
    hue='condition',
    col='timepoint',
    kind='kde',
    fill=True,
    height=3,
    aspect=1.5,
    col_wrap=3,
    common_norm=False
)
g.set_axis_labels('Measurement Value', 'Density')
g.set_titles('{col_name}')
```

### Correlation Analysis

```python
# Compute correlation matrix
corr = df.select_dtypes(include='number').corr()

# Create mask for upper triangle
mask = np.triu(np.ones_like(corr, dtype=bool))

# Plot heatmap
fig, ax = plt.subplots(figsize=(10, 8))
sns.heatmap(
    corr,
    mask=mask,
    annot=True,
    fmt='.2f',
    cmap='coolwarm',
    center=0,
    square=True,
    linewidths=1,
    cbar_kws={'shrink': 0.8}
)
plt.title('Correlation Matrix')
plt.tight_layout()
```

## Scientific Publications

### Multi-Panel Figure with Different Plot Types

```python
# Set publication style
sns.set_theme(style='ticks', context='paper', font_scale=1.1)
sns.set_palette('colorblind')

# Create figure with custom layout
fig = plt.figure(figsize=(12, 8))
gs = fig.add_gridspec(2, 3, hspace=0.3, wspace=0.3)

# Panel A: Time series
ax1 = fig.add_subplot(gs[0, :2])
sns.lineplot(
    data=timeseries_df,
    x='time',
    y='expression',
    hue='gene',
    style='treatment',
    markers=True,
    dashes=False,
    ax=ax1
)
ax1.set_title('A. Gene Expression Over Time', loc='left', fontweight='bold')
ax1.set_xlabel('Time (hours)')
ax1.set_ylabel('Expression Level (AU)')

# Panel B: Distribution comparison
ax2 = fig.add_subplot(gs[0, 2])
sns.violinplot(
    data=expression_df,
    x='treatment',
    y='expression',
    inner='box',
    ax=ax2
)
ax2.set_title('B. Expression Distribution', loc='left', fontweight='bold')
ax2.set_xlabel('Treatment')
ax2.set_ylabel('')

# Panel C: Correlation
ax3 = fig.add_subplot(gs[1, 0])
sns.scatterplot(
    data=correlation_df,
    x='gene1',
    y='gene2',
    hue='cell_type',
    alpha=0.6,
    ax=ax3
)
sns.regplot(
    data=correlation_df,
    x='gene1',
    y='gene2',
    scatter=False,
    color='black',
    ax=ax3
)
ax3.set_title('C. Gene Correlation', loc='left', fontweight='bold')
ax3.set_xlabel('Gene 1 Expression')
ax3.set_ylabel('Gene 2 Expression')

# Panel D: Heatmap
ax4 = fig.add_subplot(gs[1, 1:])
sns.heatmap(
    sample_matrix,
    cmap='RdBu_r',
    center=0,
    annot=True,
    fmt='.1f',
    cbar_kws={'label': 'Log2 Fold Change'},
    ax=ax4
)
ax4.set_title('D. Treatment Effects', loc='left', fontweight='bold')
ax4.set_xlabel('Sample')
ax4.set_ylabel('Gene')

# Clean up
sns.despine()
plt.savefig('figure.pdf', dpi=300, bbox_inches='tight')
plt.savefig('figure.png', dpi=300, bbox_inches='tight')
```

### Box Plot with Significance Annotations

```python
import numpy as np
from scipy import stats

# Create plot
fig, ax = plt.subplots(figsize=(8, 6))
sns.boxplot(
    data=df,
    x='treatment',
    y='response',
    order=['Control', 'Low', 'Medium', 'High'],
    palette='Set2',
    ax=ax
)

# Add individual points
sns.stripplot(
    data=df,
    x='treatment',
    y='response',
    order=['Control', 'Low', 'Medium', 'High'],
    color='black',
    alpha=0.3,
    size=3,
    ax=ax
)

# Add significance bars
def add_significance_bar(ax, x1, x2, y, h, text):
    ax.plot([x1, x1, x2, x2], [y, y+h, y+h, y], 'k-', lw=1.5)
    ax.text((x1+x2)/2, y+h, text, ha='center', va='bottom')

y_max = df['response'].max()
add_si