説明可能な機械学習

# 回帰: 係数が「1単位増で目的変数がどれだけ動くか」
from sklearn.datasets import make_regression
from sklearn.linear_model import LinearRegression
import pandas as pd

X, y = make_regression(n_samples=300, n_features=5, noise=10, random_state=0)
model = LinearRegression().fit(X, y)

coef = pd.Series(model.coef_, index=[f"x{i}" for i in range(X.shape[1])]).sort_values(key=abs, ascending=False)
print("Intercept:", model.intercept_)
print("Coefficients:\n", coef)

# 分類: 係数の符号(+/-)と大きさでクラス方向への寄与を解釈
from sklearn.datasets import load_breast_cancer
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
import pandas as pd

data = load_breast_cancer()
pipe = Pipeline([
    ("scaler", StandardScaler()),
    ("clf", LogisticRegression(max_iter=500))
]).fit(data.data, data.target)

coef = pd.Series(pipe.named_steps["clf"].coef_[0], index=data.feature_names).sort_values(key=abs, ascending=False)
print("Coefficients (positive -> 悪性クラス方向へ寄与):\n", coef.head(10))

from sklearn.datasets import load_breast_cancer
from sklearn.tree import DecisionTreeClassifier, export_text

X, y = load_breast_cancer(return_X_y=True)
tree = DecisionTreeClassifier(max_depth=3, random_state=0).fit(X, y)

rules = export_text(tree, feature_names=load_breast_cancer().feature_names.tolist())
print(rules)  # 人が読めるif-then分岐

# scikit-learnで各特徴をスプライン変換→加法モデル（擬似GAM）
from sklearn.preprocessing import SplineTransformer
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import Ridge
from sklearn.pipeline import Pipeline
from sklearn.datasets import make_regression

X, y = make_regression(n_samples=400, n_features=3, noise=8, random_state=42)
n_features = X.shape[1]

preproc = ColumnTransformer([
    (f"spline_{i}", SplineTransformer(degree=3, n_knots=6), [i]) for i in range(n_features)
])

gam_like = Pipeline([
    ("spline", preproc),
    ("ridge", Ridge(alpha=1.0))
]).fit(X, y)

print("R^2:", gam_like.score(X, y))  # 特徴ごとに効果曲線を可視化すれば寄与が見える

from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance
import pandas as pd
import numpy as np

data = load_breast_cancer()
X, y = data.data, data.target

rf = RandomForestClassifier(n_estimators=300, random_state=0).fit(X, y)

# Gini重要度
gini_imp = pd.Series(rf.feature_importances_, index=data.feature_names).sort_values(ascending=False)
print("Gini Importance:\n", gini_imp.head(10))

# Permutation Importance（相関に頑健・解釈性◎）
pi = permutation_importance(rf, X, y, n_repeats=10, random_state=0)
perm_imp = pd.Series(pi.importances_mean, index=data.feature_names).sort_values(ascending=False)
print("\nPermutation Importance:\n", perm_imp.head(10))

# 例：XGBoost(ブラックボックス) → その予測を決定木で近似して説明
import xgboost as xgb
from sklearn.tree import DecisionTreeRegressor, export_text
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0, stratify=y)

# ブラックボックス（ここでは確率出力）
bst = xgb.XGBClassifier(n_estimators=300, max_depth=4, subsample=0.9, colsample_bytree=0.9, random_state=0)
bst.fit(X_train, y_train)
blackbox_pred = bst.predict_proba(X_train)[:, 1]

# サロゲート：回帰木で「ブラックボックスの予測」を学習
surrogate = DecisionTreeRegressor(max_depth=3, random_state=0).fit(X_train, blackbox_pred)
print(export_text(surrogate, feature_names=list(data.feature_names)))
print("Surrogate R^2 on train:", surrogate.score(X_train, blackbox_pred))

# pip install lime
from lime.lime_tabular import LimeTabularExplainer
import numpy as np

explainer = LimeTabularExplainer(
    training_data=X_train,
    feature_names=data.feature_names,
    class_names=["benign","malignant"],
    discretize_continuous=True,
    mode="classification"
)

idx = 0  # 説明したいサンプル（テストの先頭）
exp = explainer.explain_instance(
    data_row=X_test[idx],
    predict_fn=bst.predict_proba
)
print("LIME explanation for one sample:")
for feature, weight in exp.as_list()[:10]:
    print(f"{feature}: {weight:+.3f}")

# pip install shap
import shap
import numpy as np

explainer = shap.TreeExplainer(bst)
shap_values = explainer.shap_values(X_test)

# 1件のローカル説明（force_plotはJupyterで可視化）
sample_i = 0
print("Base value (expected output):", explainer.expected_value)
# printや図は環境により異なるため、ここでは要約統計のみ
contrib = shap_values[sample_i]
top_idx = np.argsort(np.abs(contrib))[-10:][::-1]
for i in top_idx:
    print(f"{data.feature_names[i]}: {contrib[i]:+.4f}")

# グローバル重要度（平均絶対SHAP値）
mean_abs = np.mean(np.abs(shap_values), axis=0)
glob_imp = pd.Series(mean_abs, index=data.feature_names).sort_values(ascending=False)
print("\nGlobal importance by mean |SHAP|:\n", glob_imp.head(10))

# “ある特徴が増えると平均的にモデル出力がどう動くか”
from sklearn.inspection import PartialDependenceDisplay
import matplotlib.pyplot as plt

features = [0, 3]  # 例: 最初と4番目の特徴
disp = PartialDependenceDisplay.from_estimator(bst, X, features=features, feature_names=data.feature_names)
plt.show()

# 参考：Grad-CAM の最小骨子（分類結果の注目領域を可視化）
# pip install torch torchvision pillow
import torch, torchvision
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms

# モデルと対象層（最後の畳み込み層）
model = torchvision.models.resnet18(pretrained=True).eval()
target_layer = model.layer4[-1].conv2  # 例：最後のブロックの畳み込み

# 入力前処理
preprocess = transforms.Compose([
    transforms.Resize((224,224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]),
])
img = Image.open("your_image.jpg").convert("RGB")
x = preprocess(img).unsqueeze(0)

# フックで特徴マップ＆勾配を取得
feats = []
grads = []
def fwd_hook(m, i, o): feats.append(o.detach())
def bwd_hook(m, gi, go): grads.append(go[0].detach())
h1 = target_layer.register_forward_hook(fwd_hook)
h2 = target_layer.register_backward_hook(bwd_hook)

# 予測 & ターゲットクラスで逆伝播
logits = model(x)
cls = logits.argmax(dim=1)
model.zero_grad()
logits[0, cls].backward()

A = feats[0][0]           # [C,H,W]
G = grads[0][0]           # [C,H,W]
w = G.mean(dim=(1,2))     # [C] → 重み
cam = (w[:,None,None] * A).sum(0)  # [H,W]
cam = F.relu(cam)
cam = (cam - cam.min()) / (cam.max() - cam.min() + 1e-6)

# cam を 224x224 に拡大し、元画像にヒートマップで重畳して保存（省略）
h1.remove(); h2.remove()