Could you add skip columns?

[keonho-kim]

Hi :) I'm big fan of this library!

I'm trying to change source code to make it run in the way I want, but it is not that easy :(

I'm currently working on Kaggle competition with huge size of dataset including missing values.

Although this nice library and LGBM is pretty fast, but I want to fill columns which only have missing values, not for all columns.

my suggestion is adding list to specify columns in mice method.

instead of

for variable in self.variable_training_order:

put new variable

for var in self.variable_people_select

Also I'm wondering just adding one parameter to mice method, like,

    def mice(
        self,
        iterations=2,
        verbose=False,
        variable_parameters=None,
        compile_candidates=False,
        user_specified_columns=None, <- 
        **kwlgb,
    ):

Thank you for your awesome library ;)

[AnotherSamWilson]

By default, the process should only be imputing columns that have missing values. If you're seeing models being run for any columns that don't have missing values (and train_nonmissing is set to False), then can you post a reproducible example?

As an aside, you can specify which variables get imputed, by using the variable_schema parameter, or you can get more complicated with it if you want to built models on non-missing data by setting train_nonmissing to True and setting a combination of imputation_order and variable_schema parameters.

[AnotherSamWilson]

See this example:

from sklearn.datasets import load_boston
import pandas as pd
import numpy as np
import miceforest as mf

random_state = np.random.RandomState(5)
boston = pd.DataFrame(load_boston(return_X_y=True)[0])
boston.columns = [str(i) for i in boston.columns]
boston["3"] = boston["3"].map({0: 'a', 1: 'b'}).astype('category')
boston["8"] = boston["8"].astype("category")
boston_amp = mf.ampute_data(boston, perc=0.25, random_state=random_state, variables=["4"])

kernel = mf.ImputationKernel(
    data=boston_amp,
    datasets=2,
    save_models=1
)
kernel.mice(iterations=2, compile_candidates=True, verbose=True)

Only variable 4 gets a model run because only that variable had missing values.

[keonho-kim]

@AnotherSamWilson

Oooh.. I didn't set train_nomissing as False :)

I missed variable_schema parameter!

Problem solved! Thank you for quick reponse!