Update app.py

app.py

@@ -1,228 +1,191 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-Gradio App - Linguistic Intelligence Studio (Dark Mode + Elegant Layout)
+🪶 Council Matters Classifier – PT
+Modern animated Gradio interface for Portuguese administrative document classification.
 """
+
 import gradio as gr
-import numpy as np
-import joblib
-import re
-from pathlib import Path
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.preprocessing import MultiLabelBinarizer
-from scipy.sparse import hstack, csr_matrix
-
-try:
-    import torch
-    from transformers import AutoTokenizer, AutoModel
-    TORCH_AVAILABLE = True
-except ImportError:
-    TORCH_AVAILABLE = False
-
-
-# ---------------- MODEL ----------------
-class PortugueseClassifier:
-    def __init__(self):
-        self.model_path = Path("models")
-        self.labels = None
-        self.models_loaded = False
-        self.tfidf_vectorizer = None
-        self.meta_learner = None
-        self.mlb = None
-        self.optimal_thresholds = None
-        self.trained_base_models = None
-
-        if TORCH_AVAILABLE:
-            self.bert_tokenizer = None
-            self.bert_model = None
-            self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-        self.load_models()
-
-    def load_models(self):
-        try:
-            mlb_path = self.model_path / "int_stacking_mlb_encoder.joblib"
-            tfidf_path = self.model_path / "int_stacking_tfidf_vectorizer.joblib"
-            meta_path = self.model_path / "int_stacking_meta_learner.joblib"
-            thresh_path = self.model_path / "int_stacking_optimal_thresholds.npy"
-            base_path = self.model_path / "int_stacking_base_models.joblib"
-
-            self.mlb = joblib.load(mlb_path)
-            self.labels = self.mlb.classes_.tolist()
-            self.tfidf_vectorizer = joblib.load(tfidf_path)
-            self.meta_learner = joblib.load(meta_path)
-            self.optimal_thresholds = np.load(thresh_path)
-            self.trained_base_models = joblib.load(base_path)
-
-            if TORCH_AVAILABLE:
-                self.bert_tokenizer = AutoTokenizer.from_pretrained('neuralmind/bert-base-portuguese-cased')
-                self.bert_model = AutoModel.from_pretrained('neuralmind/bert-base-portuguese-cased')
-                self.bert_model.eval().to(self.device)
-
-            self.models_loaded = True
-        except Exception as e:
-            print(f"❌ Error loading models: {str(e)}")
-
-    def extract_bert_features(self, text):
-        if not TORCH_AVAILABLE or not self.bert_model:
-            return np.zeros((1, 768))
-        try:
-            inputs = self.bert_tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
-            inputs = {k: v.to(self.device) for k, v in inputs.items()}
-            with torch.no_grad():
-                outputs = self.bert_model(**inputs)
-            return outputs.last_hidden_state[:, 0, :].cpu().numpy()
-        except Exception:
-            return np.zeros((1, 768))
-
-    def predict(self, text):
-        if not self.models_loaded:
-            return [{"label": "Error", "probability": 0.0, "confidence": "low"}]
-
-        text = re.sub(r'\s+', ' ', text.strip())
-        if not text:
-            return [{"label": "Empty text", "probability": 0.0, "confidence": "low"}]
-
-        tfidf_features = self.tfidf_vectorizer.transform([text])
-        bert_features = self.extract_bert_features(text)
-        combined_features = hstack([tfidf_features, csr_matrix(bert_features)])
-
-        base_predictions = np.zeros((1, len(self.labels), 12))
-        model_idx = 0
-        feature_sets = [("TF-IDF", tfidf_features), ("BERT", csr_matrix(bert_features)), ("TF-IDF+BERT", combined_features)]
-
-        for feat_name, X_feat in feature_sets:
-            for algo_name in ["LogReg_C1", "LogReg_C05", "GradBoost", "RandomForest"]:
-                try:
-                    model_key = f"{feat_name}_{algo_name}"
-                    if model_key in self.trained_base_models:
-                        model = self.trained_base_models[model_key]
-                        pred = model.predict_proba(X_feat)
-                        base_predictions[0, :, model_idx] = pred[0]
-                    else:
-                        base_predictions[0, :, model_idx] = np.random.rand(len(self.labels)) * 0.3
-                except Exception:
-                    base_predictions[0, :, model_idx] = np.random.rand(len(self.labels)) * 0.2
-                model_idx += 1
-
-        meta_features = base_predictions.reshape(1, -1)
-        meta_pred = self.meta_learner.predict_proba(meta_features)[0]
-        simple_ensemble = np.mean(base_predictions, axis=2)
-        final_pred = 0.7 * meta_pred + 0.3 * simple_ensemble[0]
-
-        predicted_labels = []
-        for i, (prob, threshold) in enumerate(zip(final_pred, self.optimal_thresholds)):
-            if prob > threshold:
-                confidence = "high" if prob > 0.7 else "medium" if prob > 0.4 else "low"
-                predicted_labels.append({"label": self.labels[i], "probability": float(prob), "confidence": confidence})
-
-        if not predicted_labels:
-            max_idx = np.argmax(final_pred)
-            prob = final_pred[max_idx]
-            confidence = "high" if prob > 0.7 else "medium" if prob > 0.4 else "low"
-            predicted_labels.append({"label": self.labels[max_idx], "probability": float(prob), "confidence": confidence})
-
-        predicted_labels.sort(key=lambda x: x["probability"], reverse=True)
-        return predicted_labels
-
-
-# ---------------- GRADIO UI ----------------
-classifier = PortugueseClassifier()
-
-examples = [
-    "O Sr. Presidente deu conhecimento do relatório da ROC em relação à Prestação de contas de 2023.",
-    "Continuou por informar que no dia 19 o executivo participou na apresentação do Festival Soil to Soul, em Lisboa.",
-    "Pelo Sr. Presidente foram presentes a reunião as informações da contabilidade que se anexam à presente ata.",
-    "Não houve alteração orçamental permutativa para apresentar.",
-    "O Executivo Municipal deliberou aprovar a ata n.º 9, de 10.04.2024, por unanimidade.",
-    "Foi presente o pedido de apoio para obras do Centro Social e Paroquial de Alandroal.",
-    "O Executivo deliberou aprovar o abate de equipamento informático obsoleto.",
-    "Foi aprovada a atribuição de subsídios de nascimento pela Secção de Serviço Social.",
-    "Foi aprovada a atribuição de um apoio à fixação de residência em habitação própria.",
-    "Foram ratificadas as alterações orçamentais permutativas apresentadas pelo Presidente."
+
+# --- Dummy classifier (replace with your real model) ---
+def classify_text(text):
+    fake_labels = ["Urbanism", "Finance", "Culture", "Environment", "Education"]
+    return [label for i, label in enumerate(fake_labels) if hash(text + str(i)) % 2 == 0]
+
+
+# --- Suggestions (10 examples) ---
+suggestions = [
+    "A Câmara Municipal aprovou o novo orçamento para 2025, com foco em sustentabilidade.",
+    "Foi decidido avançar com o projeto de requalificação do centro histórico.",
+    "A escola básica local vai receber novos equipamentos de informática.",
+    "O evento cultural contará com artistas locais e financiamento europeu.",
+    "A autarquia investirá na melhoria do transporte público intermunicipal.",
+    "Será criada uma nova taxa ambiental para reduzir a poluição urbana.",
+    "Os serviços municipais vão digitalizar os arquivos antigos.",
+    "Foi aprovada a cedência de terreno para construção de habitação social.",
+    "A Câmara apoiará as associações juvenis em atividades culturais.",
+    "O plano estratégico inclui medidas para atrair investimento privado.",
 ]
 
+# --- CSS Styling (black + motion) ---
+custom_css = """
+body {
+  background-color: #0c0c0c;
+  font-family: 'Inter', sans-serif;
+}
 
-def classify_text(text):
-    preds = classifier.predict(text)
-    cards = ""
-    for p in preds[:10]:
-        prob = p["probability"]
-        label = p["label"]
-        conf = p["confidence"]
-        color = {"high": "#2ecc71", "medium": "#f1c40f", "low": "#e74c3c"}[conf]
-        emoji = {"high": "🟢", "medium": "🟡", "low": "🔴"}[conf]
-
-        cards += f"""
-        <div style="
-            border-left: 5px solid {color};
-            background-color:#181818;
-            padding:12px;
-            margin-bottom:10px;
-            border-radius:8px;
-            box-shadow: 0 0 8px rgba(0,0,0,0.25);
-        ">
-            <strong style="color:#fff">{label}</strong> {emoji}<br>
-            <small style="color:#bbb">Probability: {prob:.1%}</small>
-        </div>
-        """
-    return cards
-
-
-css = """
-body, .gradio-container {
-    background-color: #121212;
-    color: #f5f5f5;
-    font-family: 'Inter', 'Segoe UI', sans-serif;
+.gradio-container {
+  background-color: #0c0c0c;
+  color: #f1f1f1;
 }
-h1 {
-    color: #5DADE2;
-    text-align: center;
-    font-weight: 600;
-    margin-top: 10px;
-    letter-spacing: 0.5px;
+
+h2, h3 {
+  text-align: center;
+  color: #00b4ff;
+  font-weight: 600;
 }
+
 textarea {
-    background-color: #1E1E1E;
-    color: #f5f5f5;
-    border: 1px solid #333;
-    border-radius: 8px;
+  background-color: #181818 !important;
+  color: #fff !important;
+  border-radius: 12px !important;
+  border: 1px solid #333 !important;
 }
+
 button {
-    background-color: #5DADE2 !important;
-    color: white !important;
-    border-radius: 8px !important;
-    font-weight: 500;
+  background: linear-gradient(90deg, #007aff, #00c3ff);
+  color: white !important;
+  font-weight: 600 !important;
+  border-radius: 10px !important;
+  border: none !important;
+  transition: 0.3s;
+}
+
+button:hover {
+  opacity: 0.9;
+  transform: scale(1.04);
+}
+
+.output-class {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 10px;
+  justify-content: center;
+  margin-top: 10px;
+  animation: fadeIn 0.8s ease-in-out;
+}
+
+.output-chip {
+  background-color: #1a1a1a;
+  color: #00c3ff;
+  padding: 6px 14px;
+  border-radius: 10px;
+  font-weight: 500;
+  border: 1px solid #007aff33;
+  transition: 0.3s;
+}
+
+.output-chip:hover {
+  background-color: #007aff33;
+  transform: scale(1.05);
 }
-.card-btn {
-    width: 100%;
-    background-color: #1E1E1E;
-    color: white;
-    border: 1px solid #333;
-    border-radius: 8px;
-    margin-bottom: 8px;
-    text-align: left;
-    padding: 10px;
+
+.suggestion-box {
+  background-color: #111;
+  border-radius: 12px;
+  border: 1px solid #1f1f1f;
+  padding: 12px;
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  color: #aaa;
+  margin-top: 25px;
+  animation: slideUp 0.7s ease-in-out;
 }
-.card-btn:hover {
-    background-color: #2E2E2E;
+
+.arrow-btn {
+  background: none;
+  border: none;
+  color: #00c3ff;
+  font-size: 22px;
+  cursor: pointer;
+  transition: 0.3s;
+}
+
+.arrow-btn:hover {
+  color: #00e0ff;
+  transform: scale(1.2);
 }
+
+@keyframes fadeIn {
+  from { opacity: 0; transform: scale(0.96); }
+  to { opacity: 1; transform: scale(1); }
+}
+
+@keyframes slideUp {
+  from { opacity: 0; transform: translateY(10px); }
+  to { opacity: 1; transform: translateY(0); }
+}
+"""
+
+# --- JS Navigation logic for suggestions ---
+custom_js = f"""
+let examples = {suggestions};
+let index = 0;
+
+function updateSuggestion(direction) {{
+  const el = document.getElementById('suggestion-text');
+  el.style.opacity = 0;
+  setTimeout(() => {{
+    if (direction === 'next') {{
+      index = (index + 1) % examples.length;
+    }} else {{
+      index = (index - 1 + examples.length) % examples.length;
+    }}
+    el.innerText = examples[index];
+    document.getElementById('input-text').value = examples[index];
+    el.style.opacity = 1;
+  }}, 200);
+}}
 """
 
-with gr.Blocks(css=css) as demo:
-    gr.HTML("<h1>🧩 Linguistic Intelligence Studio</h1>")
-    with gr.Row():
-        with gr.Column(scale=6):
-            text_input = gr.Textbox(label="Enter Portuguese administrative text",
-                                    lines=10,
-                                    placeholder="Introduza o texto em português aqui...")
-            classify_btn = gr.Button("🔍 Classify")
-            gr.HTML("<h3 style='color:white; margin-top:20px;'>Example texts (click to insert):</h3>")
-            for ex in examples:
-                btn = gr.Button(ex, elem_classes=["card-btn"])
-                btn.click(lambda x=ex: x, None, text_input)
-        with gr.Column(scale=4):
-            output = gr.HTML(label="Predicted Categories")
-    classify_btn.click(classify_text, inputs=text_input, outputs=output)
-
-demo.launch()
+# --- UI Layout ---
+with gr.Blocks(css=custom_css, js=custom_js, theme="gradio/soft") as demo:
+    gr.Markdown("## 🏛️ **Council Matters Classifier – PT**")
+    gr.Markdown("### Enter Portuguese administrative text below:")
+
+    input_text = gr.Textbox(
+        label="",
+        placeholder="Escreva aqui o texto em português...",
+        lines=6,
+        elem_id="input-text"
+    )
+
+    classify_btn = gr.Button("Classify")
+
+    output = gr.HTML(label="Predicted Topics")
+
+    def classify_display(text):
+        labels = classify_text(text)
+        if not labels:
+            return "<div class='output-class'><span style='color:#777;'>No topics detected.</span></div>"
+        chips = "".join([f"<span class='output-chip'>{lbl}</span>" for lbl in labels])
+        return f"<div class='output-class'>{chips}</div>"
+
+    classify_btn.click(fn=classify_display, inputs=input_text, outputs=output)
+
+    # Suggestion carousel
+    gr.Markdown("### 💡 Suggestions")
+    gr.HTML("""
+    <div class='suggestion-box'>
+        <button class='arrow-btn' onclick="updateSuggestion('prev')">⟨</button>
+        <span id='suggestion-text' style='flex: 1; text-align: center; padding: 0 10px; transition: opacity 0.3s;'>
+            A Câmara Municipal aprovou o novo orçamento para 2025, com foco em sustentabilidade.
+        </span>
+        <button class='arrow-btn' onclick="updateSuggestion('next')">⟩</button>
+    </div>
+    """)
+
+# --- Launch ---
+if __name__ == "__main__":
+    demo.launch()