残差诊断

import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm
import statsmodels.formula.api as smf
from scipy import stats
from statsmodels.nonparametric.smoothers_lowess import lowess
from statsmodels.stats.diagnostic import het_breuschpagan

df = sm.datasets.statecrime.load_pandas().data
model = smf.ols("violent ~ poverty + single + urban + hs_grad + white", data=df).fit()
infl = model.get_influence()
fitted, resid = model.fittedvalues, model.resid
std_r, lev, cook = infl.resid_studentized_internal, infl.hat_matrix_diag, infl.cooks_distance[0]
p = model.df_model + 1
top = np.argsort(-np.abs(std_r))[:3]                # 3 largest standardised residuals

fig, axes = plt.subplots(2, 2, figsize=(11, 7.6))
kw = dict(s=22, color="#007AFF", alpha=0.7, lw=0, zorder=2)
smooth = dict(color="#FF3B30", lw=1.8)

def label(ax, x, y, idx):
    lo, hi = ax.get_xlim()
    for i in idx:                                   # text on the side with more room
        right = (x[i] - lo) / (hi - lo) < 0.75
        ax.annotate(df.index[i], (x[i], y[i]), xytext=(6 if right else -6, 0),
                    textcoords="offset points", ha="left" if right else "right",
                    va="center", fontsize=8.5, color="#3A3A3C", zorder=1,
                    bbox=dict(boxstyle="round,pad=0.15", fc="white", ec="none", alpha=0.85))


# 1. Residuals vs fitted
ax = axes[0, 0]
ax.axhline(0, color="#8E8E93", lw=1, ls="--")
ax.scatter(fitted, resid, **kw)
ax.plot(*lowess(resid, fitted, frac=1, it=0).T, **smooth)
label(ax, fitted.values, resid.values, top)
ax.set(title="Residuals vs fitted", xlabel="Fitted values", ylabel="Residuals")

# 2. Normal Q-Q of standardised residuals
ax = axes[0, 1]
order = np.argsort(std_r)
theo = stats.norm.ppf((np.arange(1, len(std_r) + 1) - 0.5) / len(std_r))
ax.plot([-2.6, 2.6], [-2.6, 2.6], color="#8E8E93", lw=1, ls="--")
ax.scatter(theo, std_r[order], **kw)
rank = {i: k for k, i in enumerate(order)}
label(ax, {i: theo[rank[i]] for i in top}, std_r, top)
ax.set(title="Normal Q–Q", xlabel="Theoretical quantiles", ylabel="Standardised residuals")

# 3. Scale-location
ax = axes[1, 0]
root = np.sqrt(np.abs(std_r))
ax.scatter(fitted, root, **kw)
ax.plot(*lowess(root, fitted, frac=1, it=0).T, **smooth)
label(ax, fitted.values, np.abs(root), top)
ax.set(title="Scale–location", xlabel="Fitted values", ylabel="√|standardised residuals|")

# 4. Residuals vs leverage with Cook's distance contours
ax = axes[1, 1]
ax.axhline(0, color="#8E8E93", lw=1, ls="--")
ax.scatter(lev, std_r, **kw)
ax.plot(*lowess(std_r, lev, frac=1, it=0).T, **smooth)
ylim = (std_r.min() - 0.6, std_r.max() + 0.8)
h = np.linspace(0.01, 0.95, 300)
for D in (0.5, 1):
    r = np.sqrt(D * p * (1 - h) / h)
    ax.plot(h, r, color="#FF9500", lw=1, ls="--"); ax.plot(h, -r, color="#FF9500", lw=1, ls="--")
    sign = 1 if D == 1 else -1                       # label D = 1 above, D = 0.5 below
    ax.text(0.87, sign * np.sqrt(D * p * 0.13 / 0.87), f"D = {D}", color="#FF9500", fontsize=8.5,
            ha="center", va="center", bbox=dict(boxstyle="round,pad=0.15", fc="white", ec="none"))
ax.set_ylim(*ylim); ax.set_xlim(0, 0.95)
label(ax, lev, std_r, np.argsort(-cook)[:3])
ax.set(title="Residuals vs leverage", xlabel="Leverage (hat values)", ylabel="Standardised residuals")
for a in axes.flat:
    a.title.set_fontsize(12)

bp = het_breuschpagan(resid, model.model.exog)
sw = stats.shapiro(resid)
fig.text(0.01, 1.065, "Normal residuals, but variance and a few states deserve a closer look",
         fontsize=15, fontweight="semibold", va="bottom")
fig.text(0.01, 1.02, f"OLS violent crime ~ 5 predictors · n = {int(model.nobs)} · Shapiro–Wilk "
         f"W = {sw.statistic:.3f}, p = {sw.pvalue:.3f} · Breusch–Pagan χ²({p - 1:.0f}) = "
         f"{bp[0]:.1f}, p = {bp[1]:.3f} · max Cook's D = {cook.max():.2f} ({df.index[cook.argmax()]})",
         fontsize=9.5, color="#6E6E73", va="bottom")
plt.show()