examples/visualization_example.py

"""
Data Visualization Example
Demonstrates various plotting libraries and techniques
"""

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.offline as pyo

print("=" * 60)
print("DATA VISUALIZATION EXAMPLE")
print("=" * 60)

# Set style
plt.style.use('default')
sns.set_palette("husl")

# Generate sample data
np.random.seed(42)
n = 1000

# Create diverse dataset
data = {
    'x': np.random.randn(n),
    'y': np.random.randn(n),
    'category': np.random.choice(['A', 'B', 'C', 'D'], n),
    'size': np.random.uniform(10, 100, n),
    'value': np.random.randn(n).cumsum(),
    'time': pd.date_range('2023-01-01', periods=n, freq='H')
}

df = pd.DataFrame(data)

print("\n📊 Dataset created with", n, "records")

# MATPLOTLIB VISUALIZATIONS
print("\n🎨 Creating Matplotlib visualizations...")

plt.figure(figsize=(20, 15))

# 1. Line plot
plt.subplot(3, 3, 1)
plt.plot(df['time'][:100], df['value'][:100])
plt.title('Time Series (Line Plot)')
plt.xlabel('Time')
plt.ylabel('Value')
plt.xticks(rotation=45)

# 2. Scatter plot
plt.subplot(3, 3, 2)
plt.scatter(df['x'], df['y'], c=df['value'], cmap='viridis', alpha=0.6)
plt.colorbar(label='Value')
plt.title('Scatter Plot with Color')
plt.xlabel('X')
plt.ylabel('Y')

# 3. Histogram
plt.subplot(3, 3, 3)
plt.hist(df['x'], bins=30, alpha=0.7, color='skyblue', edgecolor='black')
plt.title('Histogram')
plt.xlabel('X Values')
plt.ylabel('Frequency')

# 4. Box plot
plt.subplot(3, 3, 4)
categories = [df[df['category'] == c]['value'].values for c in ['A', 'B', 'C', 'D']]
plt.boxplot(categories, labels=['A', 'B', 'C', 'D'])
plt.title('Box Plot by Category')
plt.ylabel('Value')

# 5. Bar chart
plt.subplot(3, 3, 5)
category_counts = df['category'].value_counts()
plt.bar(category_counts.index, category_counts.values, color=['#FF6B6B', '#4ECDC4', '#45B7D1', '#FFA07A'])
plt.title('Category Distribution')
plt.xlabel('Category')
plt.ylabel('Count')

# 6. Area plot
plt.subplot(3, 3, 6)
plt.fill_between(range(100), df['value'][:100], alpha=0.3)
plt.plot(range(100), df['value'][:100])
plt.title('Area Plot')
plt.xlabel('Index')
plt.ylabel('Value')

# 7. Heatmap (correlation)
plt.subplot(3, 3, 7)
corr_data = df[['x', 'y', 'value']].corr()
sns.heatmap(corr_data, annot=True, cmap='coolwarm', center=0)
plt.title('Correlation Heatmap')

# 8. 3D scatter
from mpl_toolkits.mplot3d import Axes3D
ax = plt.subplot(3, 3, 8, projection='3d')
scatter = ax.scatter(df['x'][:200], df['y'][:200], df['value'][:200],
                    c=df['value'][:200], cmap='viridis')
ax.set_title('3D Scatter Plot')
ax.set_xlabel('X')
ax.set_ylabel('Y')
ax.set_zlabel('Value')

# 9. Pie chart
plt.subplot(3, 3, 9)
plt.pie(category_counts.values, labels=category_counts.index, autopct='%1.1f%%',
        colors=['#FF6B6B', '#4ECDC4', '#45B7D1', '#FFA07A'])
plt.title('Pie Chart')

plt.tight_layout()
plt.show()

# SEABORN VISUALIZATIONS
print("\n📈 Creating Seaborn visualizations...")

plt.figure(figsize=(20, 12))

# 1. Pairplot
plt.subplot(2, 3, 1)
sns.scatterplot(data=df.sample(200), x='x', y='y', hue='category')
plt.title('Seaborn Scatter Plot')

# 2. Violin plot
plt.subplot(2, 3, 2)
sns.violinplot(data=df, x='category', y='value')
plt.title('Violin Plot')

# 3. Joint plot
plt.subplot(2, 3, 3)
sns.scatterplot(data=df.sample(200), x='x', y='y')
sns.regplot(data=df.sample(200), x='x', y='y', scatter=False, color='red')
plt.title('Scatter with Regression Line')

# 4. Swarm plot
plt.subplot(2, 3, 4)
sns.swarmplot(data=df.sample(300), x='category', y='value')
plt.title('Swarm Plot')

# 5. KDE plot
plt.subplot(2, 3, 5)
sns.kdeplot(data=df.sample(500), x='x', y='y', fill=True)
plt.title('Kernel Density Estimate')

# 6. Count plot
plt.subplot(2, 3, 6)
sns.countplot(data=df, x='category', palette='husl')
plt.title('Count Plot')

plt.tight_layout()
plt.show()

# PLOTLY INTERACTIVE VISUALIZATIONS
print("\n🚀 Creating Plotly interactive visualizations...")

# 1. Interactive scatter plot
fig1 = px.scatter(df.sample(500), x='x', y='y', color='category',
                  size='size', hover_data=['value'],
                  title='Interactive Scatter Plot')
fig1.show()

# 2. Interactive 3D scatter
fig2 = px.scatter_3d(df.sample(500), x='x', y='y', z='value',
                     color='category', size='size',
                     title='Interactive 3D Scatter Plot')
fig2.show()

# 3. Line chart
fig3 = px.line(df[:100], x='time', y='value',
               title='Interactive Time Series')
fig3.show()

# 4. Box plot
fig4 = px.box(df, x='category', y='value',
              title='Interactive Box Plot')
fig4.show()

# 5. Violin plot
fig5 = px.violin(df, x='category', y='value',
                 box=True, title='Interactive Violin Plot')
fig5.show()

# 6. Subplot example
fig6 = make_subplots(
    rows=2, cols=2,
    subplot_titles=('Scatter', 'Line', 'Bar', 'Box'),
    specs=[[{"secondary_y": True}, {"secondary_y": False}],
           [{"secondary_y": False}, {"secondary_y": False}]]
)

# Add traces
fig6.add_trace(go.Scatter(x=df['x'][:200], y=df['y'][:200],
                         mode='markers', name='Scatter'), row=1, col=1)
fig6.add_trace(go.Line(x=range(100), y=df['value'][:100],
                      name='Line'), row=1, col=2)
fig6.add_trace(go.Bar(x=category_counts.index, y=category_counts.values,
                     name='Bar'), row=2, col=1)
fig6.add_trace(go.Box(y=df['value'], name='Box'), row=2, col=2)

fig6.update_layout(height=600, title_text="Subplot Example")
fig6.show()

# ADDITIONAL EXAMPLES
print("\n✨ Creating additional visualization examples...")

# Animated scatter plot (plotly)
fig7 = px.scatter(df.sample(100), x='x', y='y', animation_frame='category',
                  size='size', color='value',
                  title='Animated Scatter Plot')
fig7.show()

# Sunburst chart
fig8 = px.sunburst(df, path=['category'], values='value',
                   title='Sunburst Chart')
fig8.show()

# Treemap
fig9 = px.treemap(df, path=['category'], values='value',
                  title='Treemap')
fig9.show()

# Summary
print("\n" + "=" * 60)
print("VISUALIZATION SUMMARY")
print("=" * 60)
print("✅ Matplotlib plots: 9 different chart types")
print("✅ Seaborn plots: 6 statistical visualizations")
print("✅ Plotly plots: 9 interactive visualizations")
print("✅ Total: 24 unique visualization examples")
print("\n📚 Visualization libraries demonstrated:")
print("   - matplotlib: Static, publication-quality plots")
print("   - seaborn: Statistical data visualization")
print("   - plotly: Interactive, web-based visualizations")
print("   - numpy/pandas: Data generation and manipulation")
print("\n🎨 Visualization types covered:")
print("   - Line charts, Scatter plots, Histograms")
print("   - Box plots, Violin plots, Bar charts")
print("   - Heatmaps, KDE plots, 3D plots")
print("   - Interactive plots, Animations")
print("   - Sunburst, Treemap, Subplots")