instatext is a package to train text classifiers instantly.
Project description
instatext: Train text classifiers instantly
instatext
is a Python 3 library for processing textual data. It provides a simple API for training and predicting with text classifiers.
instatext leverages fasttext
, and pandas
, for the heavy lifting
Features
- Topic Extraction
- Similarity Search
- BM25 search ( word ranking search)
- Topic Search
Get it now
$ pip install instatext
Requirements
- Python >= 3.5
Example
To train a model pass in a csv with the text and labels
text - the text to classify labels - comma seperated list of labels
text,labels
sample text,"sample"
bad stuff,"bad,sample"
good stuff,"good,sample"
import instatext
import logging
def main():
print("hello")
instatext.train_model("test_data/example.csv", "test")
instatext.predict("test", "Predict my good text",0.5)
if __name__ == "__main__":
loglevel = logging.INFO
logging.basicConfig(
format="%(asctime)s |%(levelname)s: %(message)s", level=loglevel
)
main()
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
instatext-0.0.1.tar.gz
(4.9 kB
view details)
Built Distribution
File details
Details for the file instatext-0.0.1.tar.gz
.
File metadata
- Download URL: instatext-0.0.1.tar.gz
- Upload date:
- Size: 4.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.1 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
69e577b834e3ad95965373f144098b952f44cd6b6610dc19ae0c17d2c9a24a09
|
|
MD5 |
727fe34d2bd3066b7fd5a7b187c01439
|
|
BLAKE2b-256 |
800b09eefddef5a3884f83cb55b8855bbaa74c5451755f0cbf424d403cce6fc4
|
File details
Details for the file instatext-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: instatext-0.0.1-py3-none-any.whl
- Upload date:
- Size: 8.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.25.1 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
e39ed6507db2cea81bb6d3825a22fcac3c591cfe3c8a91bf1f059d911e45ff5d
|
|
MD5 |
97b8acec59578d7ea2c8fdd860734363
|
|
BLAKE2b-256 |
901f2bc6061861fcd28df721f34a63a6456f6a48439b27eb299796386bd4772d
|