Spaces:
Running on Zero
Running on Zero
File size: 5,277 Bytes
ec6ee08 b964596 a2de67e b964596 a2de67e b964596 a2de67e b964596 a2de67e b964596 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 | import spaces
import gradio as gr
from models.bow import BowModel
from models.bertimbau import BertimbauModel
# ======================================================
# Carrega modelos
# ======================================================
bow_model = BowModel()
bert_model = None
def get_bert_model():
global bert_model
if bert_model is None:
bert_model = BertimbauModel()
return bert_model
# ======================================================
# Inferência
# ======================================================
@spaces.GPU
def predict(text):
global bert_model
text = text.strip()
if len(text) == 0:
return (
"",
{},
"",
"",
{},
""
)
# -------------------------
# BoW
# -------------------------
bow = bow_model.predict(text)
bow_prediction = (
"😊 Positivo"
if bow["prediction"] == 1
else "😞 Negativo"
)
bow_probs = {
"Positivo": bow["probabilities"][1],
"Negativo": bow["probabilities"][0]
}
if len(bow["representation"]) == 0:
bow_representation = (
"Nenhuma palavra do texto pertence ao vocabulário do modelo."
)
else:
bow_representation = "\n".join(
f"{word:<20} {count}"
for word, count in bow["representation"].items()
)
# -------------------------
# BERT
# -------------------------
bert_model = get_bert_model()
bert = bert_model.predict(text)
bert_prediction = (
"😊 Positivo"
if bert["prediction"] == 1
else "😞 Negativo"
)
bert_probs = {
"Positivo": bert["probabilities"][1],
"Negativo": bert["probabilities"][0]
}
bert_repr = "\n".join(
f"{item['token']:<15} "
f"[{', '.join(f'{v:.3f}' for v in item['vector'])}, ...]"
for item in bert["representation"]
)
return (
bow_prediction,
bow_probs,
bow_representation,
bert_prediction,
bert_probs,
bert_repr
)
# ======================================================
# Interface
# ======================================================
with gr.Blocks(
title="Sentiment Analysis Playground"
) as demo:
gr.Markdown(
"""
# Sentiment Analysis Playground
Compare como diferentes modelos processam um mesmo texto.
Atualmente a demonstração possui:
- 🟦 Bag of Words + Naive Bayes
- 🟩 BERTimbau Fine-Tuned
Digite qualquer texto em português e compare como cada modelo o representa internamente antes de classificá-lo.
"""
)
textbox = gr.Textbox(
label="Texto",
placeholder="Digite um texto...",
lines=4
)
button = gr.Button(
"Classificar",
variant="primary"
)
with gr.Row():
# =====================================================
# BoW
# =====================================================
with gr.Column():
gr.Markdown("## 🟦 Bag of Words")
bow_prediction = gr.Textbox(
label="Classe",
interactive=False
)
bow_probs = gr.Label(
label="Probabilidades",
num_top_classes=2
)
with gr.Accordion(
"Como o modelo representa o texto",
open=False
):
bow_repr = gr.Textbox(
label="Representação BoW",
lines=14,
interactive=False
)
gr.Markdown("""
### Como esse modelo funciona
- Conta palavras
- Ignora contexto
- Ignora ordem das palavras
- Baseado em frequência de termos
""")
# =====================================================
# BERT
# =====================================================
with gr.Column():
gr.Markdown("## 🟩 BERTimbau")
bert_prediction = gr.Textbox(
label="Classe",
interactive=False
)
bert_probs = gr.Label(
label="Probabilidades",
num_top_classes=2
)
with gr.Accordion(
"Como o modelo representa o texto",
open=False
):
bert_repr = gr.Textbox(
label="Tokens WordPiece",
lines=14,
interactive=False
)
gr.Markdown("""
### Como esse modelo funciona
- Usa Transformer
- Considera contexto
- Considera ordem das palavras
- Usa mecanismo de atenção
""")
button.click(
predict,
textbox,
[
bow_prediction,
bow_probs,
bow_repr,
bert_prediction,
bert_probs,
bert_repr
]
)
textbox.submit(
predict,
textbox,
[
bow_prediction,
bow_probs,
bow_repr,
bert_prediction,
bert_probs,
bert_repr
]
)
demo.launch() |