الاعتماد الجزئي ومنحنيات ICE

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.inspection import PartialDependenceDisplay
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

class="tok-comment"># ── Dataset ───────────────────────────────────────────────────────────────────
np.random.seed(class="tok-num">0)
n = class="tok-num">2000
X = pd.DataFrame({
    class="tok-str">"income":       np.random.normal(class="tok-num">50, class="tok-num">15, n).clip(class="tok-num">15, class="tok-num">120),
    class="tok-str">"age":          np.random.randint(class="tok-num">18, class="tok-num">70, n).astype(float),
    class="tok-str">"credit_score": np.random.normal(class="tok-num">650, class="tok-num">80, n).clip(class="tok-num">300, class="tok-num">850),
})
y = (class="tok-num">0.5*(X[class="tok-str">"income"]>class="tok-num">55) + class="tok-num">0.3*(X[class="tok-str">"credit_score"]>class="tok-num">660) + class="tok-num">0.2*(X[class="tok-str">"age"]>class="tok-num">40)) > class="tok-num">0.5

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=class="tok-num">0.2)

class="tok-comment"># ── Train model ───────────────────────────────────────────────────────────────
clf = GradientBoostingClassifier(n_estimators=class="tok-num">200, max_depth=class="tok-num">4, random_state=class="tok-num">42)
clf.fit(X_train, y_train)

class="tok-comment"># ── class="tok-num">1. Standard PDP for class="tok-num">3 features ────────────────────────────────────────────
fig, axes = plt.subplots(class="tok-num">1, class="tok-num">3, figsize=(class="tok-num">15, class="tok-num">4))
PartialDependenceDisplay.from_estimator(
    clf, X_train,
    features=[class="tok-str">"income", class="tok-str">"age", class="tok-str">"credit_score"],   class="tok-comment"># feature names or indices
    kind=class="tok-str">"average",           class="tok-comment"># class="tok-str">"average" = PDP only
    grid_resolution=class="tok-num">50,       class="tok-comment"># number of grid points
    ax=axes,
)
plt.suptitle(class="tok-str">"Partial Dependence Plots (PDP)")
plt.tight_layout()
plt.show()

class="tok-comment"># ── class="tok-num">2. PDP + ICE overlay ─────────────────────────────────────────────────────
fig, axes = plt.subplots(class="tok-num">1, class="tok-num">3, figsize=(class="tok-num">15, class="tok-num">4))
PartialDependenceDisplay.from_estimator(
    clf, X_train,
    features=[class="tok-str">"income", class="tok-str">"age", class="tok-str">"credit_score"],
    kind=class="tok-str">"both",              class="tok-comment"># class="tok-str">"both" = PDP (bold) + ICE (faint)
    subsample=class="tok-num">100,            class="tok-comment"># sample class="tok-num">100 ICE curves for readability
    alpha=class="tok-num">0.3,                class="tok-comment"># ICE line transparency
    ax=axes,
)
plt.suptitle(class="tok-str">"PDP + ICE Curves — divergence reveals interactions")
plt.tight_layout()
plt.show()

class="tok-comment"># ── class="tok-num">3. Centered ICE (c-ICE) — removes intercept bias ─────────────────────────
fig, axes = plt.subplots(class="tok-num">1, class="tok-num">3, figsize=(class="tok-num">15, class="tok-num">4))
PartialDependenceDisplay.from_estimator(
    clf, X_train,
    features=[class="tok-str">"income", class="tok-str">"age", class="tok-str">"credit_score"],
    kind=class="tok-str">"individual",        class="tok-comment"># ICE only
    centered=True,            class="tok-comment"># anchor each curve at its leftmost value
    subsample=class="tok-num">150,
    alpha=class="tok-num">0.2,
    ax=axes,
)
plt.suptitle(class="tok-str">"Centered ICE (c-ICE) — interaction shapes visible")
plt.tight_layout()
plt.show()

class="tok-comment"># ── class="tok-num">4. 2D interaction PDP (heatmap) ──────────────────────────────────────────
fig, ax = plt.subplots(figsize=(class="tok-num">6, class="tok-num">5))
PartialDependenceDisplay.from_estimator(
    clf, X_train,
    features=[(class="tok-str">"income", class="tok-str">"credit_score")],  class="tok-comment"># tuple = 2D PDP
    ax=ax,
)
plt.title(class="tok-str">"2D PDP: income × credit_score interaction")
plt.tight_layout()
plt.show()

class="tok-comment"># ── class="tok-num">5. Manual PDP computation (educational) ──────────────────────────────────
grid = np.linspace(X_train[class="tok-str">"income"].quantile(class="tok-num">0.05),
                   X_train[class="tok-str">"income"].quantile(class="tok-num">0.95), class="tok-num">50)
pdp_vals = []
for v in grid:
    X_mod = X_train.copy()
    X_mod[class="tok-str">"income"] = v
    pdp_vals.append(clf.predict_proba(X_mod)[:, class="tok-num">1].mean())

plt.figure(figsize=(class="tok-num">6, class="tok-num">3))
plt.plot(grid, pdp_vals, lw=class="tok-num">2, color=class="tok-str">"class="tok-comment">#8b5cf6")
plt.xlabel(class="tok-str">"income")
plt.ylabel(class="tok-str">"Avg predicted P(default=class="tok-num">1)")
plt.title(class="tok-str">"Manual PDP — income effect")
plt.tight_layout()
plt.show()