Build and test a variety of text multi-class classification models.
Project description
lazy-text-classifiers
Build and test a variety of text multi-class classification models.
Installation
Stable Release: pip install lazy-text-classifiers
Development Head: pip install git+https://github.com/evamaxfield/lazy-text-classifiers.git
Quickstart
from lazy_text_classifiers import LazyTextClassifiers
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split
# Example data from sklearn
# `x` should be an iterable of strings
# `y` should be an iterable of string labels
data = fetch_20newsgroups(subset="all", remove=("header", "footers", "quotes"))
x = data.data[:1000]
y = data.target[:1000]
y = [data.target_names[id_] for id_ in y]
# Split the data into train and test
x_train, x_test, y_train, y_test = train_test_split(
x,
y,
test_size=0.4,
random_state=12,
)
# Init and fit all models
ltc = LazyTextClassifiers(random_state=12)
results = ltc.fit(x_train, x_test, y_train, y_test)
# Results is a dataframe
# | model | accuracy | balanced_accuracy | precision | recall | f1 | time |
# |:-----------------------|-----------:|--------------------:|------------:|---------:|---------:|--------:|
# | semantic-logit | 0.73 | 0.725162 | 0.734887 | 0.73 | 0.728247 | 13.742 |
# | tfidf-logit | 0.70625 | 0.700126 | 0.709781 | 0.70625 | 0.702073 | 187.217 |
# | fine-tuned-transformer | 0.11125 | 0.1118 | 0.10998 | 0.11125 | 0.109288 | 220.105 |
# Get a specific model
semantic_logit = ltc.fit_models["semantic-logit"]
# either an scikit-learn Pipeline or a custom Transformer wrapper class
# All models have a `save` function which will store into the normal format
# * pickle for scikit-learn pipelines
# * torch model directory for Transformers
Documentation
For full package documentation please visit evamaxfield.github.io/lazy-text-classifiers.
Acknowledgements
This package was heavily inspired by lazypredict.
Development
See CONTRIBUTING.md for information related to developing the code.
MIT License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for lazy-text-classifiers-0.1.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 95388c7b7d9b6dba55939ce31d2e74678b3bc5fab990ff78c1c5639bb520a495 |
|
MD5 | e81e402d223cdbc2939ab0ed9bc6b3ce |
|
BLAKE2b-256 | 3474ae5e5bc3776e635ff71a1ccafbcf713ebbba6d10ab0f13c92f00dfdae085 |
Close
Hashes for lazy_text_classifiers-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | afc2327105e2a008bc0552cab4dd3630817d3d19721916364f33c02e4b4a5b5e |
|
MD5 | 41764e69d49e02a3355f485d72f99329 |
|
BLAKE2b-256 | cfa4f5483621060970cf0ab50cf2166a4b0f51b098dc716667a0745adaffb8a9 |