A/B Test Results Matrix

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

np.random.seed(42)

# Variants and metrics
variants = ['Control', 'Variant A', 'Variant B', 'Variant C', 'Variant D']
metrics = ['CTR', 'Conv Rate', 'AOV', 'Bounce Rate', 'Time on Site', 'Pages/Session']

# Lift vs control (%)
lift = np.zeros((len(variants), len(metrics)))
lift[0, :] = 0  # Control baseline
lift[1, :] = [5.2, 8.1, -2.3, -12.5, 15.2, 10.1]  # Variant A
lift[2, :] = [2.1, 3.5, 12.4, 5.2, -3.1, 2.5]    # Variant B
lift[3, :] = [-3.2, -1.5, 5.2, 8.1, -8.5, -5.2]  # Variant C
lift[4, :] = [12.5, 15.2, 8.1, -18.2, 22.1, 18.5] # Variant D (winner)

df = pd.DataFrame(lift, index=variants, columns=metrics)

# Diverging colormap (red negative, green positive)
neon_div = LinearSegmentedColormap.from_list('neon_div', ['#F5276C', '#ffffff', '#6CF527'])

fig, ax = plt.subplots(figsize=(10, 5), facecolor='#ffffff')
ax.set_facecolor('#ffffff')

# Format annotations with + for positive
def fmt_pct(x):
    return f'+{x:.1f}%' if x > 0 else f'{x:.1f}%'

annot = df.applymap(fmt_pct).values

sns.heatmap(df, cmap=neon_div, center=0, annot=annot, fmt='', 
            linewidths=2, linecolor='#ffffff',
            annot_kws={'size': 11, 'fontweight': '600'},
            cbar_kws={'shrink': 0.8, 'label': 'Lift vs Control (%)'}, ax=ax)

ax.set_title('A/B Test Results Summary', color='#1f2937', fontsize=14, fontweight='bold', pad=15)
ax.set_xlabel('Metric', color='#1f2937', fontsize=11)
ax.set_ylabel('Variant', color='#1f2937', fontsize=11)
ax.tick_params(colors='#374151', labelsize=10)
ax.set_xticklabels(ax.get_xticklabels(), rotation=30, ha='right')

plt.tight_layout()
plt.show()