pynarrator
Template-based NLG framework for creating text narratives out of data
Installation
You can install the package from pip:
pip3 install pynarrator
import os
from pynarrator import narrate_descriptive, read_data
Basic Usage
pynarrator has a range of functions for creating template-based narratives and also embedded data set that you can use by calling read_data(). Function downloads raw data from github, if you get a SSL error when running it, please run this first:
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
sales = read_data()
narrative = narrate_descriptive(sales, measure = 'Sales', dimensions = ['Region', 'Product'], coverage = 0.5)
{'Total Sales': 'Total Sales across all Regions is 38790478.42.', 'Region by Sales': 'Outlying Regions by Sales are NA (18079736.4, 47.0%), EMEA (13555412.7, 35.0%).', 'Product by Sales': 'Outlying Products by Sales are Food & Beverage (15543469.7, 40.0%), Electronics (8608962.8, 22.0%).'}
Chat GPT
In order to use ChatGPT in pynarrator, you must specify your OpenAI API token as OPENAI_API_KEY environment variable:
os.environ['OPENAI_API_KEY'] = 'xx-xxxxxxxxxx'
from pynarrator import gpt_get_completions, enhance_narrative, translate_narrative, summarize_narrative
Improve the narrative text to make it rich with business language
enhance_narrative(narrative)
enhance_narrative(narrative, language = 'Spanish')
summarize_narrative(narrative)
Complete documentation is available at the narrator package website
1 maintainer
Metadata
1 maintainer
Release files for pynarrator 0.0.1.15
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pynarrator-0.0.1.15-py3-none-any.whl | Python 3 | none | any | Details |
Release files / pynarrator-0.0.1.15-py3-none-any.whl
| Download URL | pynarrator-0.0.1.15-py3-none-any.whl |
|---|---|
| Size | 23.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
937b9b437a0a4244657fe81dba7a6b96d8541855819cacf1c1533105464e0b70
|
|
BLAKE2b-256 checksum How to use checksums |
050faedc06a300013c7db4e28ef7c7bac36b115671589d19ae9ce703dfabff6e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.6
|
