Croatian-News-Sentiment-Classifier-V2

Build error

App Files Files Community

Croatian-News-Sentiment-Classifier-V2 / app.py

thak123

Update app.py

fb09861 about 1 year ago

raw history blame contribute delete

No virus

2.69 kB

	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)