import numpy as np
import pandas as pd
from time import time
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import OrdinalEncoder
from sklearn.compose import make_column_transformer, make_column_selector

rng = np.random.RandomState(0)
n_samples, n_features = 50_000, 2
X = pd.DataFrame(rng.randn(n_samples, n_features))
X[2] = np.random.choice(
    ["male", "female", "other"], size=n_samples, p=[0.49, 0.49, 0.02]
)
X[3] = np.random.choice(
    ["jan", "feb", "mar", "apr", "may", "jun",
     "jul", "aug", "sep", "oct", "nov", "dec"],
    size=n_samples,
)
y = np.random.choice(
    [0, 1, 2], size=n_samples, p=[0.01, 0.49, 0.5]
)

preprocessor = make_column_transformer(
    (OrdinalEncoder(), make_column_selector(dtype_include=object)),
    remainder="passthrough"
)
X_transformed = preprocessor.fit_transform(X)

t0 = time()
DecisionTreeClassifier().fit(X_transformed, y)
duration = time() - t0
duration