Transformer-Text-AutoEncoder
Transformer Text AutoEncoder: An autoencoder is a type of artificial neural network used to learn efficient encodings of unlabeled data, the same is employed for textual data employing pre-trained models from the hugging-face library.
Installation:
pip install Transformer-Text-AutoEncoder
Execution:
from Transformer_Text_AutoEncoder.AutoEncoder import TTAE
def read(path='./data/FinancialNews.txt'):
with open(path, "r", encoding='utf-8', errors='ignore') as f:
data = [i.strip() for i in f.readlines()]
return data
sentences = read()
print(sentences[:3])
ttae = TTAE(sentences)
ttae.train(10, batch_size=1)
print(ttae.predict("According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing ."))
returns the predicted sentence as well as the embeddings.
Cite Work:
@inproceedings{ttae,
title = {Transformer-Text-AutoEncoder},
author = {Aman Priyanshu},
year = {2022},
publisher = {{GitHub}},
url = {https://github.com/AmanPriyanshu/Transformer-Text-AutoEncoder/}
}
1 maintainer
Metadata
1 maintainer
Release files for Transformer-Text-AutoEncoder 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| Transformer_Text_AutoEncoder-0.0.4.tar.gz | 4.2 kB | Without provenance | Details for Transformer_Text_AutoEncoder-0.0.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| Transformer_Text_AutoEncoder-0.0.4-py3-none-any.whl | Python 3 | none | any | Details for Transformer_Text_AutoEncoder-0.0.4-py3-none-any.whl |
Total release size: 8.9 kB
Release files / Transformer_Text_AutoEncoder-0.0.4.tar.gz
| Download URL | Transformer_Text_AutoEncoder-0.0.4.tar.gz |
|---|---|
| Size | 4.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
038d04495cb0cb38ad6521a31f06f5712a6a2f633bf65ada4383bc6a18f7a0ec
|
|
BLAKE2b-256 checksum How to use checksums |
19f97dd9d36ec8d1b362238d71b12813a4e282aacab1fc1eeeb8040243c8f0b4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.13
|
Release files / Transformer_Text_AutoEncoder-0.0.4-py3-none-any.whl
| Download URL | Transformer_Text_AutoEncoder-0.0.4-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
132bf0aacf2f5d9a9a696cde6f1757d68b7c7bab6e3f3ef90c5a8a370f8bed8b
|
|
BLAKE2b-256 checksum How to use checksums |
c00c91417d99b8968adc6ff8979ca0de471cee8057e28bb2a1650ee1f54c84ee
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.13
|
Security for Transformer-Text-AutoEncoder 0.0.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
