Data Visualization with Pandas

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker

# Set global style
plt.style.use('seaborn-v0_8-whitegrid')
plt.rcParams['figure.figsize'] = (10, 6)
plt.rcParams['font.size'] = 12

# Stock price simulation
np.random.seed(42)
dates = pd.date_range('2024-01-01', periods=252, freq='B')
returns = np.random.normal(0.0005, 0.02, 252)

df_stock = pd.DataFrame({
    'AAPL': 150 * np.cumprod(1 + returns),
    'GOOGL': 130 * np.cumprod(1 + np.random.normal(0.0008, 0.022, 252)),
    'MSFT': 370 * np.cumprod(1 + np.random.normal(0.0006, 0.018, 252))
}, index=dates)

# Line chart — one line
ax = df_stock['AAPL'].plot(title='AAPL Stock Price 2024',
                            ylabel='Price ($)',
                            xlabel='Date',
                            color='#2196F3',
                            linewidth=1.5)
plt.tight_layout()
plt.savefig('aapl_stock.png', dpi=150)
plt.show()

# Multiple lines
ax2 = df_stock.plot(title='Stock Comparison 2024',
                     ylabel='Price ($)',
                     figsize=(12, 6))
plt.tight_layout()
plt.savefig('stock_comparison.png', dpi=150)
plt.show()

# Horizontal and vertical bar charts
dept_revenue = pd.Series({
    'Engineering': 245000,
    'Marketing': 128000,
    'Sales': 312000,
    'HR': 85000,
    'Finance': 167000
}).sort_values(ascending=True)

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Vertical bar
dept_revenue.sort_values(ascending=False).plot(
    kind='bar', ax=axes[0], color='#4CAF50', edgecolor='white', title='Revenue by Dept')
axes[0].set_ylabel('Revenue ($)')
axes[0].tick_params(axis='x', rotation=30)

# Horizontal bar
dept_revenue.plot(kind='barh', ax=axes[1], color='#2196F3', edgecolor='white',
                  title='Revenue by Dept (Horizontal)')
axes[1].set_xlabel('Revenue ($)')

plt.tight_layout()
plt.savefig('bar_charts.png', dpi=150)
plt.show()

# Grouped bar chart
monthly_data = pd.DataFrame({
    'Product_A': [42000, 48000, 55000, 51000],
    'Product_B': [35000, 38000, 42000, 40000],
    'Product_C': [28000, 32000, 30000, 35000]
}, index=['Q1', 'Q2', 'Q3', 'Q4'])

monthly_data.plot(kind='bar', figsize=(10, 6), title='Quarterly Revenue by Product')
plt.ylabel('Revenue ($)')
plt.xticks(rotation=0)
plt.savefig('grouped_bar.png', dpi=150)
plt.show()

# Salary distribution
np.random.seed(42)
salaries = pd.DataFrame({
    'Engineering': np.random.normal(95000, 15000, 200),
    'Marketing': np.random.normal(72000, 12000, 200),
    'Sales': np.random.normal(65000, 18000, 200)
})

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Histogram
salaries.plot(kind='hist', bins=30, alpha=0.6, ax=axes[0], title='Salary Distribution')
axes[0].set_xlabel('Salary ($)')

# Density (KDE)
salaries.plot(kind='kde', ax=axes[1], title='Salary Density', linewidth=2)
axes[1].set_xlabel('Salary ($)')

plt.tight_layout()
plt.savefig('histogram.png', dpi=150)
plt.show()

# Scatter plot — correlation visualization
df = pd.DataFrame({
    'Experience': np.random.randint(1, 20, 100),
    'Salary': np.random.normal(60000, 20000, 100)
})
df['Salary'] = df['Salary'] + df['Experience'] * 3000  # Add correlation

fig, axes = plt.subplots(1, 2, figsize=(14, 5))

df.plot.scatter(x='Experience', y='Salary', alpha=0.6, ax=axes[0],
                title='Experience vs Salary', color='#9C27B0')

# Box plot — distribution comparison
salaries.plot(kind='box', ax=axes[1], title='Salary Distribution by Dept')
axes[1].set_ylabel('Salary ($)')

plt.tight_layout()
plt.savefig('scatter_box.png', dpi=150)
plt.show()