39813c572463211d05f35a0dcac56ba7bd07c725,examples/plot_investigating_dirty_categories.py,,,#,17

Before Change

// categories.
from sklearn.preprocessing import CategoricalEncoder

n_obs, n_categories = 20, 20
// employee_position_titles = values[
//     "Employee Position Title"].sort_values().to_frame()
// or

After Change

// encoding simply a subset of the observations
n_obs = 20
employee_position_titles = values["Employee Position Title"].head(
    n_obs).to_frame()
categorical_encoder = CategoricalEncoder(encoding="onehot-dense")
one_hot_encoded = categorical_encoder.fit_transform(employee_position_titles)

Instances