Scatter Plots and Correlation Analysis

import matplotlib.pyplot as plt
import numpy as np
from scipy import stats

np.random.seed(42)
ad_spend  = np.random.uniform(10000, 100000, 100)
sales     = ad_spend * 0.45 + np.random.normal(0, 8000, 100) + 20000

fig, ax = plt.subplots(figsize=(10, 6))
ax.scatter(ad_spend, sales, alpha=0.6, s=60, color='#2196F3', edgecolors='white', linewidth=0.5)

# Regression line
slope, intercept, r, p, _ = stats.linregress(ad_spend, sales)
x_line = np.linspace(ad_spend.min(), ad_spend.max(), 100)
ax.plot(x_line, slope * x_line + intercept, 'r-', linewidth=2, label=f'Regression (r²={r**2:.3f})')

ax.set_title('Advertising Spend vs Sales Revenue', fontsize=14, fontweight='bold')
ax.set_xlabel('Ad Spend ($)')
ax.set_ylabel('Sales Revenue ($)')
ax.xaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f'${x/1000:.0f}K'))
ax.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f'${x/1000:.0f}K'))
ax.legend(fontsize=11)
ax.grid(True, alpha=0.3)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

# Add correlation text
r2 = r**2
interpretation = 'Strong' if abs(r) > 0.7 else 'Moderate' if abs(r) > 0.4 else 'Weak'
ax.text(0.05, 0.95, f'Pearson r = {r:.3f}\n{interpretation} positive correlation',
        transform=ax.transAxes, fontsize=11, va='top',
        bbox=dict(boxstyle='round', facecolor='lightyellow', alpha=0.8))
plt.tight_layout()
plt.savefig('scatter_basic.png', dpi=150)
plt.show()

np.random.seed(42)
experience = np.random.randint(1, 20, 150)
salary     = experience * 4000 + np.random.normal(0, 8000, 150) + 30000
dept       = np.random.choice(['Engineering', 'Marketing', 'Sales'], 150, p=[0.4, 0.3, 0.3])

dept_colors = {'Engineering': '#1565C0', 'Marketing': '#E91E63', 'Sales': '#2E7D32'}
colors_list = [dept_colors[d] for d in dept]

fig, ax = plt.subplots(figsize=(10, 6))
for d, color in dept_colors.items():
    mask = dept == d
    ax.scatter(experience[mask], salary[mask], label=d, color=color,
               alpha=0.7, s=70, edgecolors='white', linewidth=0.5)

ax.set_title('Experience vs Salary by Department', fontsize=14, fontweight='bold')
ax.set_xlabel('Years of Experience')
ax.set_ylabel('Annual Salary ($)')
ax.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f'${x:,.0f}'))
ax.legend(title='Department', framealpha=0.8)
ax.grid(True, alpha=0.3)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('scatter_colored.png', dpi=150)
plt.show()

countries = ['USA', 'China', 'Germany', 'Japan', 'UK', 'India', 'Brazil', 'France']
gdp   = [25.5, 17.7, 4.3, 4.2, 3.1, 3.7, 2.1, 2.9]      # Trillion USD
hdi   = [0.926, 0.788, 0.942, 0.920, 0.929, 0.633, 0.754, 0.910]  # HDI
co2   = [14.9, 7.6, 8.2, 8.5, 5.5, 1.9, 6.5, 5.4]         # CO2 per capita
pop   = [331, 1412, 84, 126, 67, 1380, 213, 68]             # Population (M)

fig, ax = plt.subplots(figsize=(11, 7))
scatter = ax.scatter(gdp, hdi, s=[p * 0.2 for p in pop],
                      c=co2, cmap='YlOrRd', alpha=0.8,
                      edgecolors='gray', linewidth=0.8)

for i, country in enumerate(countries):
    ax.annotate(country, (gdp[i], hdi[i]),
                xytext=(5, 5), textcoords='offset points', fontsize=9)

plt.colorbar(scatter, label='CO₂ per capita (tonnes)')
ax.set_xlabel('GDP (Trillion USD)', fontsize=12)
ax.set_ylabel('Human Development Index', fontsize=12)
ax.set_title('GDP vs HDI\n(Bubble size = Population, Color = CO₂ emissions)',
              fontsize=13, fontweight='bold')
ax.grid(True, alpha=0.3)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.savefig('bubble_chart.png', dpi=150)
plt.show()