Spaces:
Runtime error
Runtime error
File size: 3,671 Bytes
e497f96 38c8b99 40124a1 752ecd5 e497f96 752ecd5 e497f96 68c7c10 cb6d49d e497f96 |
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 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import streamlit as st
import torch
import torch.nn as nn
from transformers import BertTokenizer,BertModel, get_linear_schedule_with_warmup, AdamW
import pytorch_lightning as pl
BERT_MODEL_NAME = 'bert-base-cased'
LABEL_COLUMNS = ['anger','joy','fear','surprise','sadness', 'neutral']
class EmotionTagger(pl.LightningModule):
def __init__(self, n_classes: int, n_training_steps=None, n_warmup_steps=None):
super().__init__()
self.bert = BertModel.from_pretrained(BERT_MODEL_NAME, return_dict=True)
self.classifier = nn.Linear(self.bert.config.hidden_size, n_classes)
self.n_training_steps = n_training_steps
self.n_warmup_steps = n_warmup_steps
self.criterion = nn.BCELoss()
def forward(self, input_ids, attention_mask, labels=None):
output = self.bert(input_ids, attention_mask=attention_mask)
output = self.classifier(output.pooler_output)
output = torch.sigmoid(output)
loss = 0
if labels is not None:
loss = self.criterion(output, labels)
return loss, output
def training_step(self, batch, batch_idx):
input_ids = batch["input_ids"]
attention_mask = batch["attention_mask"]
labels = batch["labels"]
loss, outputs = self(input_ids, attention_mask, labels)
self.log("train_loss", loss, prog_bar=True, logger=True)
return {"loss": loss, "predictions": outputs, "labels": labels}
def validation_step(self, batch, batch_idx):
input_ids = batch["input_ids"]
attention_mask = batch["attention_mask"]
labels = batch["labels"]
loss, outputs = self(input_ids, attention_mask, labels)
self.log("val_loss", loss, prog_bar=True, logger=True)
return loss
def test_step(self, batch, batch_idx):
input_ids = batch["input_ids"]
attention_mask = batch["attention_mask"]
labels = batch["labels"]
loss, outputs = self(input_ids, attention_mask, labels)
self.log("test_loss", loss, prog_bar=True, logger=True)
return loss
for i, name in enumerate(LABEL_COLUMNS):
class_roc_auc = pytorch_lightning.metrics.functional.auroc(predictions[:, i], labels[:, i])
self.logger.experiment.add_scalar(f"{name}_roc_auc/Train", class_roc_auc, self.current_epoch)
def configure_optimizers(self):
optimizer = AdamW(self.parameters(), lr=2e-5)
scheduler = get_linear_schedule_with_warmup(
optimizer,
num_warmup_steps=self.n_warmup_steps,
num_training_steps=self.n_training_steps
)
return dict(
optimizer=optimizer,
lr_scheduler=dict(
scheduler=scheduler,
interval='step'
)
)
tokenizer = BertTokenizer.from_pretrained(BERT_MODEL_NAME)
model = torch.load("./model.pt")
st.title("Analisis de Sentimientos")
txt = st.text_area(label="Please write what you want to analyze...")
def run_sentiment_analysis (txt) :
THRESHOLD = 0.5
encoding = tokenizer.encode_plus(
txt,
add_special_tokens=True,
max_length=512,
return_token_type_ids=False,
padding="max_length",
return_attention_mask=True,
return_tensors='pt',
)
_, test_prediction = model(encoding["input_ids"], encoding["attention_mask"])
test_prediction = test_prediction.flatten().numpy()
predictions = []
print('-------------------- Predictions ---------------------')
for label, prediction in zip(LABEL_COLUMNS, test_prediction):
if prediction < THRESHOLD:
continue
predictions.append(" ".join([label,str(prediction)]))
return predictions
print(txt)
if(txt):
predictions = run_sentiment_analysis(txt)
for prediction in predictions:
st.write(prediction)
|