Courbes précision–rappel

import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import average_precision_score, precision_recall_curve
from sklearn.model_selection import StratifiedKFold, cross_val_predict
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

# Data: 6,366 married women (1974 survey); 1 = reports any extramarital affair (a minority class)
d = sm.datasets.fair.load_pandas().data
X = d.drop(columns="affairs")
y = (d["affairs"] > 0).astype(int).to_numpy()
prevalence = y.mean()

models = {
    "Random forest": RandomForestClassifier(n_estimators=300, random_state=0),
    "Logistic regression": make_pipeline(StandardScaler(), LogisticRegression(max_iter=2000)),
}
palette = ["#007AFF", "#FF9500"]
cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)
recall = {}

fig, ax = plt.subplots(figsize=(8, 5.2))
for (name, model), c in zip(models.items(), palette):
    score = cross_val_predict(model, X, y, cv=cv, method="predict_proba")[:, 1]
    prec, rec, thr = precision_recall_curve(y, score)
    ap = average_precision_score(y, score)
    ax.step(rec, prec, where="post", color=c, lw=2.2, label=f"{name}  (AP = {ap:.3f})")
    k = np.argmin(np.abs(thr - 0.5))  # the default threshold
    recall[name] = rec[k]
    ax.scatter(rec[k], prec[k], s=70, color=c, edgecolor="white", lw=1.5, zorder=4)
    ax.annotate(f"threshold 0.5\nP = {prec[k]:.2f}, R = {rec[k]:.2f}", (rec[k], prec[k]),
                xytext=(14, -42 if c == palette[0] else 26), textcoords="offset points",
                ha="left", fontsize=9, color=c,
                arrowprops=dict(arrowstyle="-", color=c, lw=0.8))

ax.axhline(prevalence, color="#8E8E93", ls="--", lw=1.4)
ax.text(0.01, prevalence + 0.015, f"no skill = prevalence ({prevalence:.1%})", fontsize=9, color="#6E6E73")
ax.set_xlim(0, 1.01)
ax.set_ylim(0, 1.03)
ax.set_xlabel("Recall (share of women reporting an affair who are flagged)")
ax.set_ylabel("Precision (share of flagged women who report one)")
ax.grid(axis="x")
ax.legend(loc="lower right")
ax.set_title(f"At the default 0.5 threshold, logistic regression flags only {recall['Logistic regression']:.0%} "
             "of women reporting an affair", pad=26)
ax.text(0, 1.02, f"Out-of-fold scores, 5-fold CV · n = {len(y):,} women, {y.sum():,} report an affair · "
        "AP = average precision", transform=ax.transAxes, fontsize=9.5, color="#6E6E73")
plt.show()