File size: 1,160 Bytes
c6d2665 9a1a9cf c6d2665 |
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 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import pandas as pd
from fastapi import FastAPI
app=FastAPI()
splits = {'train': 'train_df.csv', 'validation': 'val_df.csv', 'test': 'test_df.csv'}
df = pd.read_csv("hf://datasets/Sp1786/multiclass-sentiment-analysis-dataset/" + splits["train"])
model_name = "tabularisai/multilingual-sentiment-analysis"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
def predict_sentiment(texts):
inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True, max_length=512)
with torch.no_grad():
outputs = model(**inputs)
probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
sentiment_map = {0: "Very Negative", 1: "Negative", 2: "Neutral", 3: "Positive", 4: "Very Positive"}
return [sentiment_map[p] for p in torch.argmax(probabilities, dim=-1).tolist()]
texts = [
# English
"I absolutely love the new design of this app!", "Cooking microwave pizzas, yummy.", "The weather is fine, nothing special.",
]
print(predict_sentiment(texts))
|