sciblox was designed to make data science and machine learning easier.
It features similar modules to R’s CARET, and draws inspiration from many other packages.
To use it:
from sciblox import * %matplotlib notebook
What’s included?
CARET like preprocessing (scaling, normalising, dummify, outlier removal, unskew, etc)
Processor modules - you can fit onto testing data!
LightGBM and RandomForest support - later will add more
More analysis methods: outlier detection, skewness methods, auto unskewing etc
3D automatic plots in NEW cool analyse function!
BPCA, MICE, KNN, Boosting, Forest, SVD imputation
Easy sequential text mining and automatic text mining
Jupyter Notebooks integrated
What’s in construction?
More machine learning libraries - Extra Trees, Neural Networks, SVM etc
Advanced data and text mining
CV, Auto machine learning
Multiprocessing support
Demonstration
If you want to see sciblox in action, please visit https://danielhanchen.github.io/
1 maintainer
Release files for sciblox 0.2.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sciblox-0.2.8.tar.gz | 18.9 kB | Details |
Release files / sciblox-0.2.8.tar.gz
| Download URL | sciblox-0.2.8.tar.gz |
|---|---|
| Size | 18.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
71f358a59f0ca37d17e5d18461b688b21cadcb3edc8e53cdf8c07a159937989b
|
|
BLAKE2b-256 checksum How to use checksums |
f4114cfbace4bf72c36ad3b171f9b115137f73d7ee3a0e0d20a8fc1c60c6ee4e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
