Trjtdtk

Describing a chess game in a novel

What (if any) is the reason to buy in small local stores?

Pronounciation of the combination "st" in spanish accents

What does Jesus mean regarding "Raca," and "you fool?" - is he contrasting them?

In Aliens, how many people were on LV-426 before the Marines arrived​?

Synchronized implementation of a bank account in Java

Generic TVP tradeoffs?

Fewest number of steps to reach 200 using special calculator

Why is there so much iron?

How to define limit operations in general topological spaces? Are nets able to do this?

What is the significance behind "40 days" that often appears in the Bible?

What exactly term 'companion plants' means?

I seem to dance, I am not a dancer. Who am I?

Help prove this basic trig identity please!

Does .bashrc contain syntax errors?

Do native speakers use "ultima" and "proxima" frequently in spoken English?

HP P840 HDD RAID 5 many strange drive failures

A Ri-diddley-iley Riddle

Deletion of copy-ctor & copy-assignment - public, private or protected?

Print a physical multiplication table

How is the partial sum of a geometric sequence calculated?

Suggestions on how to spend Shaabath (constructively) alone

Probably overheated black color SMD pads

What can I do if I am asked to learn different programming languages very frequently?

Target Encoding: missing value imputation before or after encoding

Missing Categorical Features - no imputationMissing data imputation with KNNImputation of missing values and dealing with categorical valuesWhat approach for creating a multi-classification model based on all categorical features (1 with 5,000 levels)?Removing Categorial Features in Linear RegressionMissing value in continuous variable: Indicator variable vs. Indicator valueHow to handle large number of features in machine learning?Predicting a cyclic targetMissing Values In New DataTarget encoding with cross validation

1

$begingroup$

I want to perform a target encoding for my categorical features although I am not sure when to perform the data imputation if any of them has missing values.
Let's say I have a few continuous features, Cnt1-Cnt5 (without NA's) and two categorical features, Cat1 and Cat2, with Cat2 having missing values. Let's also assume that I want to use Random Forest as an imputation method. Which approach would be the correct one?

1. Impute Cat2 treating Cat1 and Cnt1-Cnt5 as predictors in RF and then perform target encoding on categorical variables.




2. Target encode Cat2 for non missing and Cat1, build RF and impute missings for Cat2 (which is now numeric, not categorical).




3. Any other approach?

We can generalize this question and ask whether we should impute missings for any kind of variable (including continuous) before or after target encoding?

I see at least one benefit of imputation after target encoding - if there are unseen levels of categorical variable present in the test data (which will result in NA's in the test set after performing target encoding), those would be easily imputed by RF built on training data, without any potential error due to new levels.

feature-engineering encoding data-imputation

share|improve this question

edited yesterday

MarkSt

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

1

$begingroup$

I want to perform a target encoding for my categorical features although I am not sure when to perform the data imputation if any of them has missing values.
Let's say I have a few continuous features, Cnt1-Cnt5 (without NA's) and two categorical features, Cat1 and Cat2, with Cat2 having missing values. Let's also assume that I want to use Random Forest as an imputation method. Which approach would be the correct one?

1. Impute Cat2 treating Cat1 and Cnt1-Cnt5 as predictors in RF and then perform target encoding on categorical variables.




2. Target encode Cat2 for non missing and Cat1, build RF and impute missings for Cat2 (which is now numeric, not categorical).




3. Any other approach?

We can generalize this question and ask whether we should impute missings for any kind of variable (including continuous) before or after target encoding?

I see at least one benefit of imputation after target encoding - if there are unseen levels of categorical variable present in the test data (which will result in NA's in the test set after performing target encoding), those would be easily imputed by RF built on training data, without any potential error due to new levels.

feature-engineering encoding data-imputation

share|improve this question

edited yesterday

MarkSt

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

I want to perform a target encoding for my categorical features although I am not sure when to perform the data imputation if any of them has missing values.
Let's say I have a few continuous features, Cnt1-Cnt5 (without NA's) and two categorical features, Cat1 and Cat2, with Cat2 having missing values. Let's also assume that I want to use Random Forest as an imputation method. Which approach would be the correct one?

1. Impute Cat2 treating Cat1 and Cnt1-Cnt5 as predictors in RF and then perform target encoding on categorical variables.




2. Target encode Cat2 for non missing and Cat1, build RF and impute missings for Cat2 (which is now numeric, not categorical).




3. Any other approach?

We can generalize this question and ask whether we should impute missings for any kind of variable (including continuous) before or after target encoding?

I see at least one benefit of imputation after target encoding - if there are unseen levels of categorical variable present in the test data (which will result in NA's in the test set after performing target encoding), those would be easily imputed by RF built on training data, without any potential error due to new levels.

feature-engineering encoding data-imputation

share|improve this question

edited yesterday

MarkSt

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

edited yesterday

MarkSt

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

edited yesterday

MarkSt

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked yesterday

MarkStMarkSt

62

New contributor

MarkSt is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked yesterday

MarkStMarkSt

62