Impute missing values using Lightgbm
Project description
imputepy
Impute missing values using Lightgbm.
Installation
pip install imputepy
Features
- Automated Imputation: Utilizes LightGBM models to impute missing values, selecting between regression and classification models based on the column's data type.
- Flexible Column Exclusion: Allows specific columns to be excluded from the imputation process.
- Dynamic Filtering for Categorical Columns: Filters categorical columns based on a specified upper limit of unique values to enhance efficiency.
- Customizable Thresholds for Categorical Detection: Enables setting custom thresholds for unique value counts to refine which columns are considered categorical.
- Comprehensive Imputation Strategy: Combines missing value identification, column type determination, and the application of LightGBM models for effective imputation.
- Direct Imputation into Original DataFrame: Imputes missing values directly into the original DataFrame, maintaining the data structure for seamless data preprocessing integration.
Usage
from imputepy import LGBMimputer
import pandas as pd
import numpy as np
df = pd.read_csv('data/df.csv')
df_imp = LGBMimputer(df, filter=True, exclude=None, filter_upper_limit=50, unique_count_limit=15)
Contributing
Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.
License
imputepy
was created by Sam Fo. It is licensed under the terms of the MIT license.
Credits
imputepy
was created with cookiecutter
and the py-pkgs-cookiecutter
template.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
imputepy-1.0.1.tar.gz
(4.2 kB
view details)
Built Distribution
File details
Details for the file imputepy-1.0.1.tar.gz
.
File metadata
- Download URL: imputepy-1.0.1.tar.gz
- Upload date:
- Size: 4.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.7.1 CPython/3.9.18 Windows/10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5642aade44dc8663f3ae52a212e0ba52f014388ae8818230c77944e6b62d8edf |
|
MD5 | f055f004b4d2666225fc940ae28c7036 |
|
BLAKE2b-256 | c6c298b76f676c115134bde710fcd86f3ae30e400b905730c5387ace6103c8f3 |
File details
Details for the file imputepy-1.0.1-py3-none-any.whl
.
File metadata
- Download URL: imputepy-1.0.1-py3-none-any.whl
- Upload date:
- Size: 4.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.7.1 CPython/3.9.18 Windows/10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c3c81f71d546a1680cbc524b914303fa608a87d2380057d7093fa71f99db600f |
|
MD5 | 52129d0cb2a07b000a87df0c4603992e |
|
BLAKE2b-256 | 66a81faca5aa16c3cd3bd5456b8ec234f2e1d8c22561442ce87bb5d0b47f1e6c |