Pre-release
This release is a pre-release and may not be stable for production use.
Chinese Sentiment Measures
A toolkit for estimating Chinese sentiment scores with multiple measures.
pip install cn-sentiment-measures
Measures
- Absolute Proportional Difference - APD. Bounds: [-1, 1]
- Relative Proportional Difference - RPD. Bounds: [-1, 1]
- Logit scale - LC. Bounds: [-infinity, +infinity]
Improved versions of the above measures by integrating degree words are marked with _with_degree in the toolkit.
Examples
from cn_sentiment_measures.sentiment_measures import SentimentMeasures
sm = SentimentMeasures()
word_list=["我","今天","很","高兴"]
print("Here are measure values with normal measures!")
print('APD = ',sm.APD(word_list))
print('RPD = ',sm.RPD(word_list))
print('LS = ',sm.LS(word_list))
print()
print("Here are measure values optimized by using adverb words!")
print('APD* = ',sm.APD_with_degree(word_list))
print('RPD* = ',sm.RPD_with_degree(word_list))
print('LS* = ',sm.LS_with_degree(word_list))
License
The project is provided by Donghua Chen.
1 maintainer
Metadata
1 maintainer
Release files for cn-sentiment-measures 1.0.0.dev5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| cn-sentiment-measures-1.0.0.dev5.tar.gz | 198.5 kB | Details |
Release files / cn-sentiment-measures-1.0.0.dev5.tar.gz
| Download URL | cn-sentiment-measures-1.0.0.dev5.tar.gz |
|---|---|
| Size | 198.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
79a00e74269cb0a9c44952b3daeb964a35787c2dab50acde38233f1f548c7eb4
|
|
BLAKE2b-256 checksum How to use checksums |
1aebbc1c17226122a20c5bfc1253f5f7ddfe877be70c1a305b6261836d0beb2b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.21.0 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.6
|
