Averbis REST API client for Python.
Project description
Averbis is a leading text mining and machine learning company in Healthcare and Life Sciences. We extract information from texts, automate intellectual processes and make meaningful predictions.
The Averbis Python API allows convenient access to the REST API of Averbis products. This includes in particular the ability to interact with the text mining pipelines offered by these products, e.g. to use these in data science environments such as Jupyter notebooks or for integration of the Averbis products in other enterprise systems.
Supported products are:
Status
The Averbis Python API is currently in an open alpha development stage. We try to keep breaking changes minimal but they may happen on the way to the first stable release.
Features
Currently supported features are:
Managing projects
Managing pipelines
Managing terminologies
Analysing text using a server-side text mining pipeline
Classifying texts using a server-side classifier
Installation
The library can be installed easily via pip
pip install averbis-python-api
Documentation
To get an overview over the methods provided with the client and the corresponding documentation, we refer to our readthedocs API reference.
Moreover, we will provide a number of example jupyter notebooks that showcase the usage of the client to solve different use cases in an upcoming release.
Usage
Connecting the client to a platform
from averbis import Client
client = Client('http://localhost:8400/health-discovery')
client.regenerate_api_token('YOUR_USERNAME', 'YOUR_PASSWORD')
# or
client = Client('http://localhost:8400/health-discovery', api_token='YOUR_API_TOKEN')
Connecting to a pipeline and assure that it is started
pipeline = client.get_project('YOUR_PROJECT_NAME').get_pipeline('YOUR_PIPELINE_NAME')
pipeline.ensure_started()
Analysing a string
document = 'This is the string we want to analyse.'
annotations = pipeline.analyse_text(document, language='en')
for annotation in annotations:
print(annotation)
Analysing a text file
with open('/path/to/text_file.txt', 'rb') as document:
annotations = pipeline.analyse_text(document, language='en')
for annotation in annotations:
print(annotation)
Restricting returned annotation types
annotations = pipeline.analyse_text(document, language='en',
annotation_types='*Diagnosis') # will return only annotations that end with 'Diagnosis'
Development
To set up a local development environment, check out the repository, set up a virtual environment
and install the required dependencies (if --no-site-packages
does not work on your system, omit it):
virtualenv venv --python=python3 --no-site-packages
source venv/bin/activate
pip install -e ".[test, dev, doc]"
To install the latest development version of the library directly from GitHub, you can use the following command:
$ pip install --upgrade git+https://github.com/averbis/averbis-python-api.git
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.