1 件の予測に対する SHAP ウォーターフォール

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)]
fmt = {"LOWINC": "{:.0f}%", "PERASIAN": "{:.0f}%", "PERBLACK": "{:.0f}%", "PERHISP": "{:.0f}%",
       "AVYRSEXP": "{:.1f}", "AVSALK": "{:.1f}", "PERSPENK": "{:.2f}", "PTRATIO": "{:.1f}",
       "PCTAF": "{:.0f}%", "PCTYRRND": "{:.0f}%"}
model = GradientBoostingRegressor(learning_rate=0.05, n_estimators=300, max_depth=2,
                                  subsample=0.8, random_state=0).fit(X, y)

explainer = shap.TreeExplainer(model)
base = float(np.ravel(explainer.expected_value)[0])
all_sv = explainer.shap_values(X)
# A struggling district whose explanation has pushes in both directions
low = np.where(all_sv.sum(axis=1) < -20)[0]
p = int(low[np.argmax(all_sv[low].max(axis=1))])
sv = all_sv[p]

# Largest contributions first; pool the rest
k = 6
idx = np.argsort(np.abs(sv))[::-1]
top, rest = idx[:k], idx[k:]
labels = [f"{names[X.columns[j]]} = {fmt[X.columns[j]].format(X.iloc[p, j])}" for j in top]
values = list(sv[top])
if len(rest):
    labels.append(f"{len(rest)} other features")
    values.append(sv[rest].sum())

fig, ax = plt.subplots(figsize=(8, 5.2))
start = base
for i, (lab, v) in enumerate(zip(labels, values)):
    c = "#FF3B30" if v > 0 else "#007AFF"
    ax.barh(i, v, left=start, color=c, alpha=0.85, height=0.62)
    ax.text(start + v + (0.5 if v > 0 else -0.5), i, f"{v:+.1f}", va="center",
            ha="left" if v > 0 else "right", fontsize=9.5, color=c, fontweight="semibold")
    if i < len(values) - 1:
        ax.plot([start + v] * 2, [i + 0.31, i + 0.69], color="#8E8E93", lw=0.8)
    start += v
ax.axvline(base, color="#8E8E93", ls="--", lw=1)
ax.axvline(start, color="#1d1d1f", lw=1.2)
bottom = len(labels) - 0.45
ax.text(base, bottom, f"base value {base:.0f}%", ha="center", va="top", fontsize=9, color="#6E6E73",
        bbox=dict(fc="white", ec="none", pad=1))
ax.text(start, bottom, f"prediction {start:.0f}%", ha="center", va="top", fontsize=9,
        color="#1d1d1f", fontweight="semibold", bbox=dict(fc="white", ec="none", pad=1))
ax.set_yticks(range(len(labels)), labels)
ax.set_ylim(len(labels) + 0.2, -0.6)
lo_x = min(base, *(base + np.cumsum(values)))
ax.set_xlim(lo_x - 8, max(base, *(base + np.cumsum(values))) + 8)
ax.set_xlabel("Predicted % of students above the national median in maths")
ax.grid(axis="x"); ax.grid(axis="y", visible=False)
ax.set_title(f"Why this district's predicted maths results are {base - start:.0f} points below average", pad=26)
ax.text(0, 1.02, f"District #{p} · gradient boosting · SHAP values sum exactly from base value to prediction "
        f"(observed: {y.iloc[p]:.0f}%)", transform=ax.transAxes, fontsize=9.5, color="#6E6E73")
plt.show()