python解释模型库Shap实现机器学习模型输出可视化

pip install shap

df = pd.read_csv('/content/Diabetes.csv')
features = ['Pregnancies', 'Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']
Y = df['Outcome']
X =  df[features]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 1234)
xgb_model = xgb.XGBRegressor(random_state=42)
xgb_model.fit(X_train, Y_train)

df = pd.read_csv('/content/Diabetes.csv')
features = ['Pregnancies', 'Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']
Y = df['Outcome']
X =  df[features]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 1234)
xgb_model = xgb.XGBRegressor(random_state=42)
xgb_model.fit(X_train, Y_train)

explainer = shap.Explainer(xgb_model)
shap_values = explainer(X_test)

shap.plots.bar(shap_values, max_display=10)

shap.plots.bar(shap_values.cohorts(2).abs.mean(0))

shap.plots.heatmap(shap_values[1:100])

shap.plots.waterfall(shap_values[0]) # For the first observation

shap.initjs()
explainer = shap.TreeExplainer(xgb_model)
shap_values = explainer.shap_values(X_test)
def p(j):
    return(shap.force_plot(explainer.expected_value, shap_values[j,:], X_test.iloc[j,:]))
p(0)

shap_values = explainer.shap_values(X_test)[1]
print("The expected value is ", expected_value)
print("The final prediction is ", xgb_model.predict(X_test)[1])
shap.decision_plot(expected_value, shap_values, X_test)