A package for predicting buy and sell signals
Project description
NLP project
This is an attempt to build a language model for generating trading signals. It uses a limited vocabulary such as 'go-long', 'go-short' and 'do-nothing'. It uses the language model combined with an expert trader data also referred to as imitation learning. The assumption here is that you have data of an expert trader with at least 5 trades e.g. labeled ['go-long', 'go-short', 'do-nothing', 'go-short', 'go-long'] the model returns one of these inputs as the signal.
Usage
Install the project with:
pip install nlp-project
Then:
from nlp.imit_main import imit_signal as imit
from nlp.nlp_main import nlp_signal as nlp
The training (expert) data were simulated with imit_signal and the language model was build with a series of these inputs.
Warning
This is not financial advise. NLP project is entirely on its preliminary stages. Use it at your own risk.
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file nlp_project-0.0.9.tar.gz.
File metadata
- Download URL: nlp_project-0.0.9.tar.gz
- Upload date:
- Size: 22.8 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d09cb91cb86cf631ec847df6215e25014f828afcbd69f4424d59a955c6eee2cd
|
|
| MD5 |
ff17574bbcfb399aa859d0a527f1644f
|
|
| BLAKE2b-256 |
8518a7de1ebe8a59c3f2575d30bfc399713f8ec1831508e6b74d15d6c31eea89
|
File details
Details for the file nlp_project-0.0.9-py3-none-any.whl.
File metadata
- Download URL: nlp_project-0.0.9-py3-none-any.whl
- Upload date:
- Size: 23.4 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
74976f2c569275f915a9320e2981abb4b7b7670b385e6dba9917fa9d459e4ae9
|
|
| MD5 |
356bdaaa7485ccaac8fe58f4a9f6c680
|
|
| BLAKE2b-256 |
936c591a5b647a6db8a7a96c9fe784301c942e9d77a4df1b04c22234d2fd9646
|