SHAP サマリー（ビースウォーム）

import matplotlib.pyplot as plt
import numpy as np
import shap
import statsmodels.api as sm
from sklearn.ensemble import GradientBoostingRegressor

# Data: 303 California school districts; outcome = % of students above the national median in maths
d = sm.datasets.star98.load_pandas().data
y = 100 * d["NABOVE"] / (d["NABOVE"] + d["NBELOW"])
names = {"LOWINC": "% low-income students", "PERASIAN": "% Asian students", "PERBLACK": "% Black students",
         "PERHISP": "% Hispanic students", "AVYRSEXP": "Teacher experience (years)",
         "AVSALK": "Teacher salary ($000)", "PERSPENK": "Spending per pupil ($000)",
         "PTRATIO": "Pupils per teacher", "PCTAF": "% in college-prep courses",
         "PCTYRRND": "% year-round schools"}
X = d[list(names)]
model = GradientBoostingRegressor(learning_rate=0.05, n_estimators=300, max_depth=2,
                                  subsample=0.8, random_state=0).fit(X, y)

# Exact SHAP values for tree ensembles
sv = shap.TreeExplainer(model).shap_values(X)          # shape: (districts, features)
importance = np.abs(sv).mean(axis=0)
order = np.argsort(importance)                          # least important at the bottom

fig, ax = plt.subplots(figsize=(8, 5.6))
rng = np.random.default_rng(0)
cmap = plt.get_cmap("coolwarm")
for i, j in enumerate(order):
    v = sv[:, j]
    xv = X.iloc[:, j].rank(pct=True).to_numpy()         # colour = percentile of the feature value
    # Beeswarm-style vertical jitter: wider where the points are denser
    hist, edges = np.histogram(v, bins=60)
    dens = hist[np.clip(np.digitize(v, edges) - 1, 0, len(hist) - 1)] / hist.max()
    jitter = rng.uniform(-1, 1, len(v)) * 0.38 * np.sqrt(dens)
    ax.scatter(v, i + jitter, c=xv, cmap=cmap, s=9, alpha=0.85, lw=0, vmin=0, vmax=1)
    ax.text(1.01, i, f"{importance[j]:.1f}", transform=ax.get_yaxis_transform(), va="center",
            fontsize=9.5, color="#3A3A3C")
ax.axvline(0, color="#3A3A3C", lw=0.8)
ax.set_yticks(range(len(order)), [names[X.columns[j]] for j in order])
ax.set_xlabel("SHAP value (percentage points)")
ax.grid(axis="x"); ax.grid(axis="y", visible=False)
ax.text(1.01, len(order) - 0.35, "mean\n|SHAP|", transform=ax.get_yaxis_transform(),
        fontsize=8.5, color="#6E6E73", va="bottom")

cb = fig.colorbar(plt.cm.ScalarMappable(cmap=cmap), ax=ax, pad=0.09, aspect=40, ticks=[0, 1])
cb.ax.set_yticklabels(["low", "high"])
cb.set_label("Feature value (percentile)", fontsize=9.5)
cb.outline.set_visible(False)

low = sv[:, list(X.columns).index("LOWINC")]
ax.set_title(f"The share of low-income students moves predictions from {low.min():+.0f} to {low.max():+.0f} points", pad=26)
ax.text(0, 1.02, f"Gradient boosting · exact tree SHAP · n = {len(X)} districts · "
        f"base value = {model.predict(X).mean():.0f}%", transform=ax.transAxes, fontsize=9.5,
        color="#6E6E73")
plt.show()