Comparaison entre groupes

from itertools import combinations

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import statsmodels.api as sm
from scipy import stats
from statsmodels.stats.multitest import multipletests
from statsmodels.stats.oneway import anova_oneway

# Data: % of students above the national math median, by district low-income tercile
df = sm.datasets.star98.load_pandas().data
df["above"] = 100 * df.NABOVE / (df.NABOVE + df.NBELOW)
groups = ["Least poor third", "Middle third", "Poorest third"]
df["poverty"] = pd.qcut(df.LOWINC, 3, labels=groups)
data = [df.loc[df.poverty == g, "above"].to_numpy() for g in groups]
palette = ["#007AFF", "#FF9500", "#34C759"]

# Welch's ANOVA + omega squared
res = anova_oneway(data, use_var="unequal")
k, n = len(data), sum(len(d) for d in data)
omega2 = (res.statistic - 1) * (k - 1) / ((res.statistic - 1) * (k - 1) + n)

# Pairwise Welch t-tests, Holm-corrected
pairs = list(combinations(range(k), 2))
raw_p = [stats.ttest_ind(data[i], data[j], equal_var=False).pvalue for i, j in pairs]
adj_p = multipletests(raw_p, method="holm")[1]

fig, ax = plt.subplots(figsize=(8, 5.4))
rng = np.random.default_rng(1)
for i, (d, c) in enumerate(zip(data, palette)):
    v = ax.violinplot(d, positions=[i], widths=0.8, showextrema=False)
    for body in v["bodies"]:
        body.set(facecolor=c, alpha=0.15, edgecolor="none")
    ax.boxplot(d, positions=[i], widths=0.12, showfliers=False, patch_artist=True,
               boxprops=dict(facecolor="white", edgecolor="#3A3A3C", lw=1),
               medianprops=dict(color="#3A3A3C", lw=1.5),
               whiskerprops=dict(color="#3A3A3C"), capprops=dict(visible=False))
    ax.scatter(i + rng.uniform(-0.22, 0.22, len(d)) * 0.9, d, s=14, color=c, alpha=0.55, lw=0)
    ax.scatter(i, d.mean(), s=90, color=c, edgecolor="white", lw=2, zorder=5)
    ax.annotate(f"μ = {d.mean():.0f}%", (i + 0.09, d.mean()), xytext=(10, 0), textcoords="offset points",
                va="center", bbox=dict(boxstyle="round,pad=0.25", fc="white", ec="none", alpha=0.9), fontsize=9.5, fontweight="semibold", color=c)

# Significance brackets
top, step = max(map(np.max, data)), 8
for h, ((i, j), p) in enumerate(sorted(zip(pairs, adj_p), key=lambda t: t[0][1] - t[0][0])):
    y = top + 4 + h * step
    ax.plot([i, i, j, j], [y - 1.5, y, y, y - 1.5], color="#8E8E93", lw=1)
    label = "p < .001" if p < 0.001 else f"p = {p:.3f}"
    ax.text((i + j) / 2, y + 0.8, label, ha="center", va="bottom", fontsize=9, color="#3A3A3C")

lowinc = df.groupby("poverty", observed=True).LOWINC.agg(["min", "max"])
ax.set_xticks(range(k), [f"{g}\n{lowinc.loc[g, 'min']:.0f}–{lowinc.loc[g, 'max']:.0f}% low-income"
                         f"\n(n = {len(d)})" for g, d in zip(groups, data)])
ax.set_ylabel("Students above the national\nmath median (% of district)")
ax.set_ylim(top=top + 4 + len(pairs) * step + 2)
ax.set_yticks(range(0, 101, 20))
ax.set_title(f"The poorer the district, the fewer students above the math median "
             f"({data[0].mean():.0f}% vs {data[-1].mean():.0f}%)", pad=26)
ax.text(0, 1.02, f"Welch's F({res.df_num:.0f}, {res.df_denom:.1f}) = {res.statistic:.1f}, "
        f"p = {res.pvalue:.1e}, ω² = {omega2:.2f}  ·  pairwise: Welch t-tests, Holm-adjusted",
        transform=ax.transAxes, fontsize=9.5, color="#6E6E73")
plt.show()