Introducción a la imputación basada en modelos

Copien y presten atención a la explicación!!

nhanes_model_df = (
    nhanes_df.select_columns('height','weight','gender','age')
    .sort_values(by='height')
    .transform_column(
        'weight',
        lambda x: x.ffill(),
        elementwise=False
    )
    .missing.bind_shadow_matrix(
        True,
        False,
        suffix='_imp',
        only_missing=False
    )
)
nhanes_model_df

height_ols = (
    nhanes_model_df
    .pipe(lambda df: smf.ols('height ~ weight + gender + age', data=df))
    .fit()
)

ols_imputed_values = (
    nhanes_model_df
    .pipe(
        lambda df: df[df.height.isna()]
    )
    .pipe(
        lambda df: height_ols.predict(df).round()
    )
)
ols_imputed_values

nhanes_model_df.loc[nhanes_model_df.height.isna(), ['height']] = ols_imputed_values
nhanes_model_df

(
    nhanes_model_df.missing.scatter_imputation_plot(
        x='weight',
        y='height'
    )
)