File size: 5,038 Bytes
a4b33d8 b3b327d 138ec98 b3b327d a4b33d8 33a1f42 c2ae4ec a4b33d8 33a1f42 |
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 |
import gradio as gr
import torch
from transformers import DebertaV2Model, DebertaV2Config, AutoTokenizer, PreTrainedModel
from transformers.models.deberta.modeling_deberta import ContextPooler
from transformers import pipeline
import torch.nn as nn
# -- Model definitions
BASE_MODEL = "microsoft/mdeberta-v3-base"
SENT_SUBJ_MODEL = "MatteoFasulo/mdeberta-v3-base-subjectivity-sentiment-multilingual-no-arabic"
SUBJ_ONLY_MODEL = "MatteoFasulo/mdeberta-v3-base-subjectivity-multilingual-no-arabic"
# -- Custom model builder
from functools import partial
def build_custom_model(sentiment_dim=0):
class CustomModel(PreTrainedModel):
config_class = DebertaV2Config
def __init__(self, config, *args, **kwargs):
super().__init__(config, *args, **kwargs)
self.deberta = DebertaV2Model(config)
self.pooler = ContextPooler(config)
self.dropout = nn.Dropout(0.1)
hidden_dim = self.pooler.output_dim + sentiment_dim
self.classifier = nn.Linear(hidden_dim, config.num_labels)
def forward(self, input_ids, attention_mask=None, **sent_kwargs):
x = self.deberta(input_ids=input_ids, attention_mask=attention_mask)[0]
pooled = self.pooler(x)
if sentiment_dim:
sent_feats = torch.stack((sent_kwargs['positive'], sent_kwargs['neutral'], sent_kwargs['negative']), dim=1)
pooled = torch.cat((pooled, sent_feats), dim=1)
return self.classifier(self.dropout(pooled))
return CustomModel
# -- Load models and tokenizer
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
# sentiment+subjectivity
cfg1 = DebertaV2Config.from_pretrained(SENT_SUBJ_MODEL, num_labels=2, id2label={0:'OBJ',1:'SUBJ'}, label2id={'OBJ':0,'SUBJ':1})
Model1Cls = build_custom_model(sentiment_dim=3)
model1 = Model1Cls.from_pretrained(SENT_SUBJ_MODEL, config=cfg1, ignore_mismatched_sizes=True)
# subjectivity-only
cfg2 = DebertaV2Config.from_pretrained(SUBJ_ONLY_MODEL, num_labels=2, id2label={0:'OBJ',1:'SUBJ'}, label2id={'OBJ':0,'SUBJ':1})
Model2Cls = build_custom_model(sentiment_dim=0)
model2 = Model2Cls.from_pretrained(SUBJ_ONLY_MODEL, config=cfg2)
# sentiment pipeline
sentiment_pipe = pipeline("sentiment-analysis", model="cardiffnlp/twitter-xlm-roberta-base-sentiment", tokenizer="cardiffnlp/twitter-xlm-roberta-base-sentiment", top_k=None)
def get_sentiment_scores(text):
out = sentiment_pipe(text)[0]
return {list(d.keys())[0]: list(d.values())[0] for d in out}
# -- Prediction logic
def analyze(text):
# Tokenize
inputs = tokenizer(text, truncation=True, padding=True, max_length=256, return_tensors='pt')
# Sentiment
scores = get_sentiment_scores(text)
pos, neu, neg = scores['positive'], scores['neutral'], scores['negative']
# Model1
logits1 = model1(input_ids=inputs.input_ids, attention_mask=inputs.attention_mask, positive=torch.tensor([pos]), neutral=torch.tensor([neu]), negative=torch.tensor([neg]))
p1 = torch.softmax(logits1, dim=1)[0]
# Model2
logits2 = model2(input_ids=inputs.input_ids, attention_mask=inputs.attention_mask)
p2 = torch.softmax(logits2, dim=1)[0]
# Build results
return {
'Positive': f"{pos:.2%}", 'Neutral': f"{neu:.2%}", 'Negative': f"{neg:.2%}",
'Sent-Subj OBJ': f"{p1[0]:.2%}", 'Sent-Subj SUBJ': f"{p1[1]:.2%}",
'TextOnly OBJ': f"{p2[0]:.2%}", 'TextOnly SUBJ': f"{p2[1]:.2%}"
}
# -- Build Gradio Dashboard with Blocks
dark_theme = gr.themes.Dark()
with gr.Blocks(theme=dark_theme, css="""
#result_table td { padding: 8px; font-size: 1rem; }
#header { text-align: center; font-size: 2rem; font-weight: bold; margin-bottom: 10px; }
""") as demo:
gr.Markdown("<div id='header'>🚀 Advanced Subjectivity & Sentiment Dashboard 🚀</div>")
with gr.Row():
txt = gr.Textbox(label="Enter text to analyze", placeholder="Paste news sentence here...", lines=2)
btn = gr.Button("Analyze 🔍", variant="primary")
with gr.Tabs():
with gr.TabItem("Overview 📊"):
chart = gr.BarPlot(x="category", y="value", label="Results", elem_id="result_chart")
with gr.TabItem("Raw Scores 📋"):
table = gr.Dataframe(headers=["Metric", "Value"], datatype=["str","str"], interactive=False, elem_id="result_table")
with gr.TabItem("About ℹ️"):
gr.Markdown("This dashboard uses two DeBERTa-based models (with and without sentiment integration) to detect subjectivity, alongside sentiment scores from an XLM-RoBERTa model.")
gr.Markdown("**Threshold** for subjective classification is adjustable in code (default: 0.65). Feel free to fork and customize! 🚀")
# Link inputs to outputs
btn.click(fn=analyze, inputs=txt, outputs=[chart, table])
# Add confetti effect on button click
btn.js_on_event("click", {
"type": "confetti",
"props": {"particleCount": 100, "spread": 60}
})
# -- Launch
demo.queue().launch(server_name="0.0.0.0", share=True)
|