Lingorithm Text Classification Kit
Project description
Lingorithm Text Classification
This package is the core function for any NLP operation or pacakge used by lingorithm.
Installation
Use the package manager pip to install ltck.
pip install ltck
Usage
Data
Input data is a list of tuples
data = [
("Help me please", "commonQ.assist"),
("Is this a bot?", "commonQ.bot"),
("Is there a bot chatting to me?", "commonQ.bot")
]
import ltck
tc = ltck('en', data)
tc.train(epochs=20, batch_size=8, model_name="commonQ_v1")
classified = tc.classify("Help me please")
print(classified)
# [('commonQ.assist', 0.9737932),
# ('commonQ.not_giving', 0.012769885),
# ('commonQ.name', 0.0071987235),
# ('commonQ.how', 0.002869619),
# ('commonQ.query', 0.0023981368),
# ('commonQ.bot', 0.000478917),
# ('faq.bad_service', 0.0003706195),
# ('faq.aadhaar_missing', 5.4887507e-05),
# ('faq.apply_register', 3.3203887e-05),
# ('commonQ.just_details', 1.60179e-05),
# ('faq.biz_new', 9.965993e-06),
# ('faq.application_process', 3.101246e-06),
# ('faq.borrow_limit', 1.6019511e-06),
# ('faq.borrow_use', 1.4953373e-06),
# ('commonQ.wait', 2.9794015e-07),
# ('faq.biz_simpler', 2.6959242e-07),
# ('contact.contact', 9.587218e-08),
# ('faq.biz_category_missing', 5.7328425e-08),
# ('faq.approval_time', 5.5687766e-09),
# ('faq.banking_option_missing', 1.6084242e-09),
# ('faq.address_proof', 1.3430994e-09)]
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
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
ltck-0.1.1.tar.gz
(2.4 kB
view details)
File details
Details for the file ltck-0.1.1.tar.gz
.
File metadata
- Download URL: ltck-0.1.1.tar.gz
- Upload date:
- Size: 2.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b7ea536f65a06f3779c0c4dfeeaf19bbaceb0044d61b7dfe4e153c69c374d273 |
|
MD5 | cd63ac29757167224e1f3c0983f8c3de |
|
BLAKE2b-256 | ed40e433e9e9d291a5e6d035e248394293065f1a675c407de75a9a7c6d7bd029 |