ggwp: Prepare Fast, Analyze Faster
What is ggwp?
ggwp is a Python package for fast and easy data analytics.
It aims to make a data model that can be applied for some use cases
such as customer analytics. The data model created by ggwp is designed
directly from my personal experiences, which will be more and more data models
in the future. In addition, ggwp now has some new features for
logging, modeling and evaluating your models, which of these can speed up your workflow
FOR REAL!!
Main Features
Here are current features available in ggwp
from ggwp.EzDataModel import *
Example codes ->
- DataModel: prepare your raw data for a general data model
- RFMT: create RFMT dataset
- Cohort: create Cohort dataset
- CustomerMovement: create Customer Movement dataset
- BasketEvolving: create Basket Evolving dataset
from ggwp.EzModeling import *
Example codes ->
- Check: check your data quality and more
- Log: log your data, its status and your remark, so you know what you've done for each stage
- Evaluation: evaluate your model using traditional (R2, RMSE, F-1, ACC, ROC) and practical metrics (Cost&Benefit, Lift)
- BenchMark: benchmark your models' performances giving you some intuition
from ggwp.EzPipeline import *
Example codes ->
- GroupImputer: impute your value with multiple subsets (as you desire)
- ConvertVariables: convert all of your columns in one command
- ColumnAssignment: adding a new column in your pipeline is now available
- OneHotTransformer: the brand-new One-Hot-Encoding is now at your service
- DataFrameTransformer: write your own function and use it along with your pipeline seamlessly
Where to get ggwp
The source code is currently hosted at GitHub:
https://github.com/datanooblol/ggwp
The latest version is available at
Python Package Index (PyPI)
# pip
pip install ggwp
Dependencies
- numpy
- pandas
- sklearn
- xgboost
Disclaimer
ggwp is now in devoping phase. Hence, if you experience any inconveniences, please be patient...
1 maintainer
Release files for ggwp 0.0.49
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ggwp-0.0.49.tar.gz | 15.4 kB | Details |
Release files / ggwp-0.0.49.tar.gz
| Download URL | ggwp-0.0.49.tar.gz |
|---|---|
| Size | 15.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
428049b3175766b6680c20e9147f4ede248c5fb5aafbd4fcc7ccb886479ebf68
|
|
BLAKE2b-256 checksum How to use checksums |
c9e03640a6234d45ac198cee0d86de95689c81a3178a845c5c8a0bb825e4426b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.24.0 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.8.5
|
