# load packages and data
import dalex as dx
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVR
from numpy import log

data = dx.datasets.load_fifa()
X = data.drop(columns=['overall', 'potential', 'value_eur', 'wage_eur', 'nationality'], axis=1)
y = log(data.value_eur)

# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y)

# fit a pipeline model
model = Pipeline([('scale', StandardScaler()), ('svm', SVR())])
model.fit(X_train, y_train)

# create an explainer for the model
explainer = dx.Explainer(model, data=X_test, y=y_test, label='scikit-learn')

# pack the explainer into a pickle file
explainer.dump(open('explainer_scikitlearn.pickle', 'wb'))

# load packages and data
import dalex as dx
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from lightgbm import LGBMClassifier

data = dx.datasets.load_titanic()
X = data.drop(columns='survived')
y = data.survived

# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y)

# fit a pipeline model
numerical_features = ['age', 'fare', 'sibsp', 'parch']
numerical_transformer = Pipeline(
  steps=[
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler())
  ]
)
categorical_features = ['gender', 'class', 'embarked']
categorical_transformer = Pipeline(
  steps=[
    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
  ]
)

preprocessor = ColumnTransformer(
  transformers=[
    ('num', numerical_transformer, numerical_features),
    ('cat', categorical_transformer, categorical_features)
  ]
)

classifier = LGBMClassifier(n_estimators=300)

model = Pipeline(
  steps=[
    ('preprocessor', preprocessor),
    ('classifier', classifier)
  ]
)
model.fit(X_train, y_train)

# create an explainer for the model
explainer = dx.Explainer(model, data=X_test, y=y_test, label='lightgbm')

# pack the explainer into a pickle file
explainer.dump(open('explainer_lightgbm.pickle', 'wb'))