import numpy as np
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder


numeric_features = ["age", "monthly_spend"]
categorical_features = ["plan"]

train = pd.DataFrame(
    {
        "age": [25, 32, np.nan, 45],
        "monthly_spend": [120, 210, 180, np.nan],
        "plan": ["basic", "premium", "basic", np.nan],
    }
)

holdout = pd.DataFrame(
    {
        "age": [np.nan, 42],
        "monthly_spend": [190, np.nan],
        "plan": [np.nan, "premium"],
    }
)