Linear Regression Plot

Caffeine vs Reaction Time

Cognitive performance and stimulant effect study

Output
Caffeine vs Reaction Time
Python
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd

np.random.seed(415)
BG_COLOR = '#ffffff'
TEXT_COLOR = '#1f2937'

n = 60
caffeine = np.random.uniform(0, 400, n)
reaction = 350 - 0.3 * caffeine + np.random.normal(0, 30, n)
reaction = np.clip(reaction, 150, 450)

df = pd.DataFrame({'Caffeine (mg)': caffeine, 'Reaction Time (ms)': reaction})

fig, ax = plt.subplots(figsize=(10, 6), facecolor=BG_COLOR)
ax.set_facecolor(BG_COLOR)

sns.regplot(
    data=df,
    x='Caffeine (mg)',
    y='Reaction Time (ms)',
    scatter_kws={'color': '#27D3F5', 'alpha': 0.6, 's': 55, 'edgecolor': 'white', 'linewidths': 0.5},
    line_kws={'color': '#F5276C', 'linewidth': 2.5},
    ci=95,
    ax=ax
)

for collection in ax.collections[1:]:
    collection.set_facecolor('#F5276C')
    collection.set_alpha(0.15)

ax.axvspan(200, 400, alpha=0.08, color='#ef4444')
ax.text(300, 420, 'High Intake', color='#ef4444', fontsize=9, ha='center')

corr = np.corrcoef(caffeine, reaction)[0, 1]
ax.text(0.05, 0.05, 'r = %.3f' % corr, transform=ax.transAxes, fontsize=12,
        color='#F5276C', fontweight='bold', va='bottom',
        bbox=dict(boxstyle='round,pad=0.3', facecolor='#f8fafc', edgecolor='#e5e7eb'))

ax.set_xlabel('Caffeine Intake (mg)', fontsize=12, color=TEXT_COLOR, fontweight='500')
ax.set_ylabel('Reaction Time (ms)', fontsize=12, color=TEXT_COLOR, fontweight='500')
ax.set_title('Caffeine vs Reaction Time', fontsize=14, color=TEXT_COLOR, fontweight='bold', pad=15)

ax.tick_params(colors='#374151', labelsize=10)
for spine in ax.spines.values():
    spine.set_color('#e5e7eb')

plt.tight_layout()
plt.show()
Library

Matplotlib

Category

Pairwise Data

Did this help you?

Support PyLucid to keep it free & growing

Support