Question-Intimacy
Intro
question-intimacy is a package used to estimate the intimacy of questions. It is released with
EMNLP 2020 paper Quantifying Intimacy in Language.
Install
Use pip
If pip is installed, question-intimacy could be installed directly from it:
pip3 install question-intimacy
Dependencies
python>=3.6.0
torch>=1.6.0
transformers >= 3.1.0
numpy
math
tqdm
Usage and Example
Notes: During your first usage, the package will download a model file automatically, which is about 500MB.
Construct the Predictor Object
>>> from question_intimacy.predict_intimacy import IntimacyEstimator
>>> inti = IntimacyEstimator()
Cuda is disabled by default, to allow GPU calculation, please use
>>> from question_intimacy.predict_intimacy import IntimacyEstimator
>>> inti = IntimacyEstimator(cuda=True)
predict
predict is the core method of this package,
which takes a single text of a list of texts, and returns a list of raw values in [-1,1] (higher means more intimate, while lower means less).
# Predict intimacy for one question
>>> text = 'What is this movie ?''
>>> inti.predict(text,type='list')
-0.2737383
# Predict intimacy for a list of questions (less than a batch)
>>> text = ['What is this movie ?','Why do you hate me ?']
>>> inti.predict(text,type='list')
[-0.2737383, 0.3481976]
# Predict intimacy for a long list of questions
>>> text = [a long list of questions]
>>> inti.predict(text,type='long_list',tqdm=tqdm)
[-0.2737383, 0.3481976, ... ,-0.2737383, 0.3481976]
Contact
Jiaxin Pei (pedropei@umich.edu)
Metadata
Release files for question-intimacy 1.1
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 |
|---|---|---|---|---|
| question_intimacy-1.1.tar.gz | 2.9 kB | Without provenance | Details for question_intimacy-1.1.tar.gz |
Release files / question_intimacy-1.1.tar.gz
| Download URL | question_intimacy-1.1.tar.gz |
|---|---|
| Size | 2.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
962a0b1975f5e2de0ea6e14994e156c80ea5d86a90cd25ac409797e3195dcb66
|
|
BLAKE2b-256 checksum How to use checksums |
f288aa14c809c994180910063f6aef1d0492ddf03ea17a77bdf48c104b2eba4d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.6.1 requests/2.22.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.5
|
Security for question-intimacy 1.1
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.