Heatmaps and Correlation Matrices

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

np.random.seed(42)
df = pd.DataFrame({
    'Revenue':     np.random.normal(75000, 15000, 200),
    'Ad_Spend':    np.random.normal(12000, 3000, 200),
    'Customers':   np.random.randint(100, 500, 200),
    'Satisfaction':np.random.uniform(3, 5, 200),
    'Employees':   np.random.randint(10, 100, 200),
    'Profit':      np.random.normal(20000, 5000, 200)
})
df['Revenue'] = df['Revenue'] + df['Ad_Spend'] * 3 + df['Customers'] * 50

corr = df.corr()

fig, axes = plt.subplots(1, 2, figsize=(16, 6))

# Full correlation matrix
sns.heatmap(corr, ax=axes[0],
             annot=True, fmt='.2f',       # Show values in cells
             cmap='RdBu_r',               # Diverging: red=negative, blue=positive
             vmin=-1, vmax=1,             # Fix scale to [-1, 1]
             center=0,                    # White = 0 correlation
             square=True,                 # Square cells
             linewidths=0.5,              # Cell borders
             linecolor='white',
             cbar_kws={'shrink': 0.8})
axes[0].set_title('Correlation Matrix', fontsize=13, fontweight='bold')

# Upper triangle only (no redundancy)
mask = np.triu(np.ones_like(corr, dtype=bool))
sns.heatmap(corr, ax=axes[1],
             mask=mask,                   # Hide upper triangle
             annot=True, fmt='.2f',
             cmap='RdBu_r', vmin=-1, vmax=1, center=0,
             square=True, linewidths=0.5, linecolor='white')
axes[1].set_title('Correlation Matrix (Lower Triangle)', fontsize=13, fontweight='bold')

plt.suptitle('Business Metrics Correlation Analysis', fontsize=14, fontweight='bold')
plt.tight_layout()
plt.savefig('correlation_heatmap.png', dpi=150)
plt.show()

# Sales heatmap: month × product
months = ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']
products = ['Laptop', 'Phone', 'Monitor', 'Desk', 'Chair']
np.random.seed(42)
sales_matrix = np.random.randint(10, 120, size=(12, 5))
# Add seasonal pattern
sales_matrix[10:, :] = (sales_matrix[10:, :] * 1.8).astype(int)  # Nov-Dec spike
df_sales = pd.DataFrame(sales_matrix, index=months, columns=products)

fig, ax = plt.subplots(figsize=(12, 8))
sns.heatmap(df_sales, ax=ax,
             annot=True, fmt='d',
             cmap='YlOrRd',       # Sequential — more = darker
             linewidths=0.5, linecolor='white',
             cbar_kws={'label': 'Units Sold'})
ax.set_title('Monthly Sales by Product — Units Sold', fontsize=14, fontweight='bold')
ax.set_xlabel('Product', fontsize=12)
ax.set_ylabel('Month', fontsize=12)
plt.tight_layout()
plt.savefig('sales_heatmap.png', dpi=150)
plt.show()

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

np.random.seed(42)
depts = ['Engineering', 'Marketing', 'Sales', 'HR', 'Finance']
metrics = ['Satisfaction', 'Performance', 'Retention', 'Training_Hours', 'Absenteeism']

data = {
    'Engineering': [4.2, 4.5, 92, 40, 3],
    'Marketing':   [3.8, 3.9, 88, 30, 5],
    'Sales':       [3.5, 4.1, 78, 25, 8],
    'HR':          [4.0, 3.7, 90, 35, 4],
    'Finance':     [3.9, 4.0, 94, 32, 3]
}
df_hr = pd.DataFrame(data, index=metrics)

# Normalize each metric to 0-1 for fair comparison
df_norm = df_hr.copy().astype(float)
for metric in metrics:
    row = df_norm.loc[metric]
    if metric == 'Absenteeism':  # Lower is better
        df_norm.loc[metric] = 1 - (row - row.min()) / (row.max() - row.min())
    else:  # Higher is better
        df_norm.loc[metric] = (row - row.min()) / (row.max() - row.min())

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 6))

# Raw values
sns.heatmap(df_hr, ax=ax1, annot=True, fmt='.1f', cmap='RdYlGn',
             linewidths=0.5, linecolor='white', cbar_kws={'shrink': 0.8})
ax1.set_title('HR Metrics by Department\n(Raw Values)', fontsize=12, fontweight='bold')

# Normalized (performance score)
sns.heatmap(df_norm, ax=ax2, annot=True, fmt='.2f', cmap='RdYlGn',
             vmin=0, vmax=1, linewidths=0.5, linecolor='white', cbar_kws={'shrink': 0.8})
ax2.set_title('Normalized Performance Score\n(0=worst, 1=best)', fontsize=12, fontweight='bold')

plt.suptitle('Employee Analytics Dashboard', fontsize=14, fontweight='bold')
plt.tight_layout()
plt.savefig('hr_heatmap.png', dpi=150)
plt.show()