Scientific Data Visualization
for Reproducible Research

Sample code / prompt

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

# Generate performance scores for 5 treatment groups
np.random.seed(42)
groups = ['Control', 'Treatment A', 'Treatment B', 'Treatment C', 'Treatment D']
n_samples = 30

Sample code / prompt

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

# Create correlation matrix for financial metrics
metrics = ['Revenue', 'Profit', 'Expenses', 'ROI', 'Customers', 'AOV', 'Marketing', 'Employees']
correlation_data = np.array([
    [1.00, 0.85, -0.45, 0.72, 0.88, 0.65, 0.72, 0.55],
    [0.85, 1.00, -0.78, 0.92, 0.75, 0.58, 0.63, 0.48],

Sample code / prompt

import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import gaussian_kde, skewnorm

# Generate age data with slight right skew
np.random.seed(42)
ages = skewnorm.rvs(a=2, loc=42, scale=15, size=500)
ages = np.clip(ages, 18, 80)  # Clip to realistic range

fig, ax = plt.subplots(figsize=(12, 7))