# !pip install lime
import pandas as pd
from xgboost import XGBClassifier
import shap
import numpy as np
from sklearn.model_selection import train_test_split

df = pd.read_csv('./data/winequality-white.csv',sep = ';')
df['quality'] = df['quality'].apply(lambda x: 0 if x <= 5 else 1)
df.head()

# 訓練集測試集分割
X = df.drop('quality', axis=1)
y = df['quality'] 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)
# 模型訓練
model = XGBClassifier(n_estimators = 100, random_state=42)
model.fit(X_train, y_train)
score = model.score(X_test, y_test)
score

import lime
from lime import lime_tabular
explainer = lime_tabular.LimeTabularExplainer(
    training_data=np.array(X_train),
    feature_names=X_train.columns,
    class_names=['bad', 'good'],
    mode='classification'
)

import lime
from lime import lime_tabular
explainer = lime_tabular.LimeTabularExplainer(
    training_data=np.array(X_train),
    feature_names=X_train.columns,
    class_names=['bad', 'good'],
    mode='classification'
)

exp = explainer.explain_instance(data_row=X_test.iloc[1], predict_fn=model.predict_proba)
exp.show_in_notebook(show_table=True)