Coffee Origin Quality ANOVA

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

np.random.seed(1515)

# Cupping scores (0-100)
ethiopia = np.random.normal(87, 3, 60)
colombia = np.random.normal(84, 3.5, 60)
brazil = np.random.normal(82, 4, 60)
guatemala = np.random.normal(85, 3.2, 60)
kenya = np.random.normal(88, 2.8, 60)

ethiopia = np.clip(ethiopia, 75, 95)
colombia = np.clip(colombia, 72, 93)
brazil = np.clip(brazil, 70, 92)
guatemala = np.clip(guatemala, 73, 94)
kenya = np.clip(kenya, 78, 96)

F_stat, p_value = stats.f_oneway(ethiopia, colombia, brazil, guatemala, kenya)

fig, ax = plt.subplots(figsize=(13, 7), facecolor='#ffffff')
ax.set_facecolor('#ffffff')

colors = ['#6CF527', '#F5B027', '#C82909', '#27D3F5', '#F5276C']
data = [ethiopia, colombia, brazil, guatemala, kenya]

bp = ax.boxplot(data, positions=[1, 2, 3, 4, 5], widths=0.55, patch_artist=True,
                medianprops={'color': '#1f2937', 'linewidth': 2},
                whiskerprops={'color': '#9ca3af', 'linewidth': 1.5},
                capprops={'color': '#9ca3af', 'linewidth': 1.5},
                flierprops={'marker': 'o', 'markerfacecolor': '#d1d5db', 'markersize': 4})

for patch, color in zip(bp['boxes'], colors):
    patch.set_facecolor(color)
    patch.set_alpha(0.6)
    patch.set_edgecolor(color)
    patch.set_linewidth(2)

labels = ['Ethiopia', 'Colombia', 'Brazil', 'Guatemala', 'Kenya']

# Specialty coffee threshold
ax.axhspan(85, 100, alpha=0.1, color='#22c55e')
ax.axhline(y=85, color='#22c55e', linestyle='--', alpha=0.7, linewidth=1.5)
ax.text(5.45, 85, 'Specialty', fontsize=7, color='#22c55e', va='center')

# Price per kg
prices = ['$28', '$22', '$15', '$24', '$32']
for i, (d, price, color) in enumerate(zip(data, prices, colors)):
    ax.text(i+1, 68, f'μ={d.mean():.1f} | {price}/kg', ha='center', fontsize=8, color=color)

# Stats header
stats_text = f"ANOVA: F={F_stat:.2f}, p={p_value:.4f} | Top Quality: Kenya (μ={kenya.mean():.1f})"
bbox = dict(boxstyle="round,pad=0.3", facecolor='#fef3c7', edgecolor='#F5B027', lw=2)
ax.text(0.5, 1.02, stats_text, transform=ax.transAxes, fontsize=9, color='#1f2937',
        ha='center', va='bottom', fontfamily='monospace', bbox=bbox)

ax.set_xticks([1, 2, 3, 4, 5])
ax.set_xticklabels(labels, fontsize=10, color='#1f2937')
ax.set_ylabel('Cupping Score (SCA)', fontsize=12, color='#1f2937', fontweight='500')
ax.set_title('Single-Origin Coffee Quality\nQ-Grader Evaluation Results', 
             fontsize=14, color='#1f2937', fontweight='bold', pad=25)

ax.tick_params(colors='#374151')
for spine in ax.spines.values():
    spine.set_color('#e5e7eb')
ax.yaxis.grid(True, color='#f3f4f6', linewidth=0.8)
ax.set_axisbelow(True)
ax.set_ylim(65, 98)

plt.tight_layout()
plt.show()