app.py

import datasets
import numpy as np
import torch
import transformers
from config import epochs, batch_size, learning_rate, id2label
from model import tokenizer, multitask_model
from mtm import MultitaskTrainer, NLPDataCollator, DataLoaderWithTaskname
import pandas as pd
from datasets import Dataset, DatasetDict
from data_predict import convert_to_stsb_features,convert_to_features
import gradio as gr
from huggingface_hub import hf_hub_download,snapshot_download

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Version 1 -  Croatian Document + Slovenian Document.
model_link = hf_hub_download(repo_id="FFZG-cleopatra/Croatian-Document-News-Sentiment-Classifier-V2",filename = "pytorch_model.bin")

multitask_model.load_state_dict(torch.load(model_link, map_location=device))
multitask_model.to(device)

def predict_sentiment(sentence = "Volim ti"):
    # gather everyone if you want to have a single DatasetDict
    document = DatasetDict({
        # "train": Dataset.from_pandas(df_document_sl_hr_train),
        # "valid": Dataset.from_pandas(df_document_sl_hr_valid),
        "test": Dataset.from_dict({"content":[sentence]})
    })
    
    dataset_dict = {
        "document": document,
    }
    
    for task_name, dataset in dataset_dict.items():
        print(task_name)
        print(dataset_dict[task_name]["test"][0])
        print()
    
    
    convert_func_dict = {
        "document": convert_to_stsb_features,
        # "paragraph": convert_to_stsb_features,
        # "sentence": convert_to_stsb_features,
    }
    
    features_dict = convert_to_features(dataset_dict, convert_func_dict)
   
    predictions = []
    
    for _, batch in enumerate(features_dict["document"]['test']):
        for key, value in batch.items():
            batch[key] = batch[key].to(device)
        
        task_model = multitask_model.get_model("document")
        classifier_output = task_model.forward(
                torch.unsqueeze(batch["input_ids"], 0),
                torch.unsqueeze(batch["attention_mask"], 0),)
        
        print(tokenizer.decode(batch["input_ids"],skip_special_tokens=True))
        print("logits:",classifier_output.logits)
        prediction =torch.max(classifier_output.logits, axis=1)
        predictions.append(prediction.indices.item())
    
    print("predictions:", predictions[0] , id2label[predictions[0]] )
    return id2label[predictions[0]]


interface = gr.Interface(
    fn=predict_sentiment,
    inputs='text',
    outputs=['label'],
    title='Croatian News Sentiment Analysis 2.0',
    description='Get the positive/neutral/negative sentiment for the given input.'
)


interface.launch(inline = False)