#%%
import numpy as np
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.compose import ColumnTransformer
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.datasets import fetch_openml
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

X, y = fetch_openml("titanic", version=1, as_frame=True, return_X_y=True)
rng = np.random.RandomState(41)
X['random_cat'] = rng.randint(3, size=X.shape[0])
X['random_num'] = rng.randn(X.shape[0])

categorical_columns = ['pclass', 'sex', 'embarked', 'random_cat']
numerical_columns = ['age', 'sibsp', 'parch', 'fare', 'random_num']

X = X[categorical_columns + numerical_columns]

X_train, X_test, y_train, y_test = train_test_split(
    X, y, stratify=y, random_state=42)

categorical_pipe = Pipeline([
    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])
numerical_pipe = Pipeline([
    ('imputer', SimpleImputer(strategy='mean')),
    ('selector', PCA())
])

preprocessing = ColumnTransformer(
    [('cat', categorical_pipe, categorical_columns),
     ('num', numerical_pipe, numerical_columns)])

pipe = Pipeline([
    ('preprocess', preprocessing),
    ('classifier', RandomForestClassifier(random_state=42))
])

param_grid = {'preprocess__num__selector': [PCA(), SelectKBest(k=3)]}
grid_search = GridSearchCV(pipe, param_grid, cv=2)
grid_search.fit(X, y)