sentimany

Just a simple sentiment tool.

It just grabs a set of pre-made sentiment models that you can quickly use to attach sentiment scores to text. None of these sentiment models will be perfect, as none of them actually understand language, but they may serve well in human-in-the-loop kinds of labelling situations. Currently the tool only supports English models.

Quickstart

The goal is to whip up some sentiment models real quick. A demo is shown below.

import pandas as pd
from sentimany.sentiment import (
    vader_sentiment,
    textblob_sentiment,
    onnx_sentiment,
    roberta_sentiment,
    nlptown_sentiment,
)

# Add some text to a pandas dataframe
texts = [
    "i like dogs",
    "i hate cats",
    "stroopwafels are amazing",
    "mcdondals is horrible",
]
df = pd.DataFrame({"text": texts})

# Apply each sentiment model and attach it as a new column
(df
  .assign(vader = lambda d: vader_sentiment(d['text']), 
          textblob = lambda d: textblob_sentiment(d['text']),
          imdb_onnx = lambda d: onnx_sentiment(d['text'], "onnx/imdb-reviews.onnx"),
          amazon_onnx = lambda d: onnx_sentiment(d['text'], "onnx/amazon-reviews.onnx"),
          roberta = lambda d: roberta_sentiment(d['text']), 
          nlptown = lambda d: nlptown_sentiment(d['text'])))

This would result in a table that looks something like;

text	vader	textblob	imdb_onnx	amazon_onnx	roberta	nlptown
i like dogs	0.6806	0.5	0.5667	0.5770	0.9979	0.7335
i hate cats	0.2140	0.1	0.6835	0.3837	0.0016	0.3544
stroopwafels are amazing	0.7930	0.8	0.7374	0.8058	0.9985	0.9323
mcdondals is horrible	0.2288	0.0	0.1983	0.1522	0.0006	0.0605

Good to know

This is a repo made for utility for myself. Feel free to re-use, but don't expect maintenance in the long term.

More-over though, keep in mind that sentiment models are imperfect and brittle. In particular check this short blogpost and this huggingface stream for more details.

Just another sentiment wrapper.

Related tags

Overview

sentimany

Quickstart

Good to know

Owner

vincent d warmerdam

Python Control Systems Library

A novel dual model approach for categorization of unbalanced skin lesion image classes (Presented technical paper 📃)

Odd-Or-Even - Ask the user for a number. Depending on whether the number is even or odd, print out an appropriate message to the user

All solutions for the 2021 Advent of Code event.

Find the remote website version based on a git repository

Yet another Python Implementation of the Elo rating system.

Programa principal de la Silla C.D.P.

Simple Denial of Service Program yang di bikin menggunakan bahasa pemograman Python,

Source for the Fedora Silverblue and Kinoite variants.

pythonOS: An operating system kernel made in python and assembly

Telop - Encode and decode messages using an interpretation of the telegraphic code devised by José María Mathé

A Python script to convert your favorite TV series into an Anki deck.

A normal phoneNumber tracker made with python.

Todo-backend - Todo backend with python

Decipher using Markov Chain Monte Carlo

a simple thing that i made for fun :trollface:

Pytorch implementation of "Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates"

Combines power of torch, numerical methods to conquer and solve ALL {O,P}DEs

Learn the basics of Python. These tutorials are for Python beginners. so even if you have no prior knowledge of Python, you won’t face any difficulty understanding these tutorials.

A basic layout of atm working of my local database