File size: 1,870 Bytes
902af77 8bd8d20 902af77 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
# Import the required Libraries
import gradio as gr
from transformers import AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
from scipy.special import softmax
# Requirements
model_path = "KwameOO/covid-tweet-sentiment-analyzer-roberta"
tokenizer = AutoTokenizer.from_pretrained(model_path)
config = AutoConfig.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)
# Preprocess text (username and link placeholders)
def preprocess(text):
new_text = []
for t in text.split(" "):
t = "@user" if t.startswith("@") and len(t) > 1 else t
t = "http" if t.startswith("http") else t
new_text.append(t)
return " ".join(new_text)
# ---- Function to process the input and return prediction
def sentiment_analysis(text):
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors = "pt") # for PyTorch-based models
output = model(**encoded_input)
scores_ = output[0][0].detach().numpy()
scores_ = softmax(scores_)
# Format output dict of scores
labels = ["Negative", "Neutral", "Positive"]
scores = {l:float(s) for (l,s) in zip(labels, scores_)}
return scores
# ---- Gradio app interface
app = gr.Interface(fn = sentiment_analysis,
inputs = gr.Textbox(label = "Write your text or tweet here..."),
outputs = gr.Label(label = "Predicted Sentiment..."),
title = "Sentiment Analysis of Tweets on COVID-19 Vaccines",
description = "To vaccinate or not? This app analyzes sentiment of text based on tweets tweets about COVID-19 Vaccines using a fine-tuned roBERTA model",
interpretation = "default",
examples = [["The idea of a vaccine in record time sure sounds interesting!"]]
)
app.launch() |