scikit-learn-contrib/category_encoders

Handle missing in one hot encoder

Open

#400 opened on Mar 12, 2023

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (2,322 stars) (397 forks)batch import
buggood first issue

Description

Expected Behavior

Currently, handle_missing=value adds a new column although the documentation says 'value' will encode a new value as 0 in every dummy column. Furthermore, we need a test for this

Actual Behavior

adds a column instead of using all 0

Steps to Reproduce the Problem

from category_encoders import OneHotEncoder
import pandas as pd

he = OneHotEncoder(handle_missing="value")

data = [("foo", 1), ("bar", 2), (None, 6)]
data = pd.DataFrame(data, columns=["c1", "c2"])
print(he.fit_transform(data))

Specifications

  • Version: 2.6
  • Platform: linux

Contributor guide

Tech stack
pythonpandas
Domain
datatesting
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Basic PythonPandasUnderstanding of one hot encodingFamiliarity with scikit learn API
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60
Research direction
Look at the OneHotEncoder implementation, likely in category encoders/encoders/one hot.py, to find how handle missing='value' is handled. The bug is that it adds a new column instead of filling 0 in all dummy columns. Write a test that reproduces the issue using the provided example, then fix the logic so that missing values are encoded as 0 in all columns. Also ensure that the existing tests pass. Update documentation if needed.
Handle missing in one hot encoder · scikit-learn-contrib/category_encoders#400 | Good First Issue