カプラン・マイヤー曲線

import matplotlib.pyplot as plt
import numpy as np
from lifelines import KaplanMeierFitter
from lifelines.datasets import load_dd
from lifelines.statistics import logrank_test

# Data: years in office of 1,808 political leaders, by regime type
df = load_dd()
groups = {"Democracy": df[df.democracy == "Democracy"],
          "Non-democracy": df[df.democracy == "Non-democracy"]}
colors = ["#007AFF", "#FF9500"]
ticks = np.arange(0, 31, 5)

fig, (ax, tab) = plt.subplots(2, 1, figsize=(8, 6.2), sharex=True,
                              gridspec_kw=dict(height_ratios=[4.2, 1]))

# Kaplan–Meier fit per group: step curve, CI band, censoring ticks, median line
for (name, d), c in zip(groups.items(), colors):
    km = KaplanMeierFitter().fit(d.duration, d.observed, label=name)
    sf, ci = km.survival_function_[name], km.confidence_interval_
    ax.step(sf.index, sf, where="post", color=c, lw=2, label=f"{name} (n = {len(d)})")
    ax.fill_between(ci.index, ci.iloc[:, 0], ci.iloc[:, 1], step="post", color=c, alpha=0.12, lw=0)
    cens = d.loc[d.observed == 0, "duration"]
    ax.plot(cens, km.survival_function_at_times(cens), "|", color=c, ms=7, mew=1.2)
    med = km.median_survival_time_
    ax.plot([med, med], [0, 0.5], ls="--", lw=1, color=c)
    ax.text(med, 0.02, f" {med:.0f} y", color=c, fontsize=9.5, fontweight="semibold", ha="left")
    # Number at risk under the plot
    at_risk = [(d.duration >= t).sum() for t in ticks]
    for t, n in zip(ticks, at_risk):
        tab.text(t, 1 - list(groups).index(name), n, ha="center", va="center", color=c, fontsize=10)

ax.axhline(0.5, color="#8E8E93", lw=1, ls="--", zorder=1)
ax.set(ylim=(0, 1.02), xlim=(-1.2, 30.8), ylabel="Probability still in office", xlabel="Years in office")
ax.tick_params(labelbottom=True)
ax.yaxis.set_major_formatter(plt.matplotlib.ticker.PercentFormatter(1))
ax.legend(loc="upper right")

# Log-rank test
dem, non = groups["Democracy"], groups["Non-democracy"]
lr = logrank_test(dem.duration, non.duration, dem.observed, non.observed)
p_txt = "p < .001" if lr.p_value < 0.001 else f"p = {lr.p_value:.3f}"
ax.set_title("Democratic leaders lose office faster than non-democratic ones", pad=26)
ax.text(0, 1.02, f"Log-rank χ²(1) = {lr.test_statistic:.1f}, {p_txt}  ·  "
        f"Kaplan–Meier with 95% CI  ·  n = {len(df):,} leaders, {df.observed.sum():,} exits from office",
        transform=ax.transAxes, fontsize=9.5, color="#6E6E73")

# Risk table styling
tab.set(ylim=(-0.5, 1.5), xticks=ticks)
tab.tick_params(labelbottom=False)
tab.set_yticks([1, 0], list(groups))
for lbl, c in zip(tab.get_yticklabels(), colors):
    lbl.set_color(c)
tab.grid(False)
tab.spines[["left", "bottom"]].set_visible(False)
tab.set_title("Number at risk", fontsize=10, fontweight="normal", color="#6E6E73", pad=4)
plt.show()