Update app.py

app.py

@@ -1,174 +1,174 @@
-import json
-import random
-import pickle
-import numpy as np
-import re
-from flask import Flask, request, jsonify
-from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
-
-class ImprovedBPJSChatbot:
-    def __init__(self):
-        self.load_models()
-        self.load_intents()
-        
-    def load_models(self):
-        """Load semua model yang diperlukan"""
-        print("Memuat model dan konfigurasi...")
-        
-        # Load konfigurasi
-        with open('model_config.pkl', 'rb') as f:
-            config = pickle.load(f)
-        
-        # Load sentence transformer
-        self.st_model = SentenceTransformer(config['model_name'])
-        self.preprocessing_enabled = config['preprocessing_enabled']
-        
-        # Load classifier
-        with open('svm_model.pkl', 'rb') as f:
-            self.clf = pickle.load(f)
-        
-        # Load label encoder
-        with open('label_encoder.pkl', 'rb') as f:
-            self.label_encoder = pickle.load(f)
-            
-        print("Semua model berhasil dimuat!")
-    
-    def load_intents(self):
-        """Load data intents untuk responses"""
-        with open('intents.json', 'r', encoding='utf-8') as f:
-            self.intents_data = json.load(f)
-        
-        self.tag_responses = {intent['tag']: intent['responses'] for intent in self.intents_data['intents']}
-        
-        # Buat embeddings untuk semua patterns (untuk similarity fallback)
-        self.pattern_embeddings = []
-        self.pattern_tags = []
-        
-        for intent in self.intents_data['intents']:
-            for pattern in intent['patterns']:
-                processed_pattern = self.preprocess_text(pattern) if self.preprocessing_enabled else pattern
-                embedding = self.st_model.encode(processed_pattern)
-                self.pattern_embeddings.append(embedding)
-                self.pattern_tags.append(intent['tag'])
-                
-        self.pattern_embeddings = np.array(self.pattern_embeddings)
-    
-    def preprocess_text(self, text):
-        """Preprocessing teks yang sama dengan training"""
-        text = text.lower()
-        
-        # Normalisasi singkatan
-        text = re.sub(r'\bjkk\b', 'jaminan kecelakaan kerja', text)
-        text = re.sub(r'\bjkm\b', 'jaminan kematian', text)
-        text = re.sub(r'\bjht\b', 'jaminan hari tua', text)
-        text = re.sub(r'\bjp\b', 'jaminan pensiun', text)
-        text = re.sub(r'\bbpjs\b', 'bpjs ketenagakerjaan', text)
-        
-        # Hapus karakter khusus
-        text = re.sub(r'[^\w\s]', ' ', text)
-        text = re.sub(r'\s+', ' ', text).strip()
-        
-        return text
-    
-    def get_prediction_confidence(self, msg_embedding):
-        """Dapatkan prediksi dengan confidence score"""
-        # Prediksi probabilitas
-        probabilities = self.clf.predict_proba(msg_embedding)[0]
-        max_prob = np.max(probabilities)
-        predicted_class = np.argmax(probabilities)
-        predicted_tag = self.label_encoder.inverse_transform([predicted_class])[0]
-        
-        return predicted_tag, max_prob
-    
-    def similarity_fallback(self, msg_embedding, threshold=0.7):
-        """Fallback menggunakan cosine similarity"""
-        similarities = cosine_similarity(msg_embedding, self.pattern_embeddings)[0]
-        max_similarity_idx = np.argmax(similarities)
-        max_similarity = similarities[max_similarity_idx]
-        
-        if max_similarity >= threshold:
-            return self.pattern_tags[max_similarity_idx], max_similarity
-        
-        return 'fallback', max_similarity
-    
-    def get_contextual_response(self, tag, user_message):
-        """Pilih response yang paling kontekstual"""
-        responses = self.tag_responses.get(tag, self.tag_responses['fallback'])
-        
-        # Jika hanya ada satu response, return langsung
-        if len(responses) == 1:
-            return responses[0]
-        
-        # Pilih response berdasarkan kata kunci dalam pesan user
-        user_words = set(user_message.lower().split())
-        
-        best_response = responses[0]
-        best_score = 0
-        
-        for response in responses:
-            response_words = set(response.lower().split())
-            # Hitung kesamaan kata
-            common_words = user_words.intersection(response_words)
-            score = len(common_words)
-            
-            if score > best_score:
-                best_score = score
-                best_response = response
-        
-        # Jika tidak ada yang cocok, pilih random
-        if best_score == 0:
-            return random.choice(responses)
-        
-        return best_response
-    
-    def generate_response(self, message):
-        """Generate response dengan multiple strategies"""
-        if not message.strip():
-            return "Tolong kirim sebuah pesan."
-        
-        # Preprocessing
-        processed_msg = self.preprocess_text(message) if self.preprocessing_enabled else message
-        msg_embedding = self.st_model.encode(processed_msg).reshape(1, -1)
-        
-        # Strategy 1: SVM prediction dengan confidence
-        predicted_tag, confidence = self.get_prediction_confidence(msg_embedding)
-        
-        # Strategy 2: Similarity fallback jika confidence rendah
-        if confidence < 0.6:  # Threshold bisa di-adjust
-            fallback_tag, similarity = self.similarity_fallback(msg_embedding)
-            if similarity > confidence:
-                predicted_tag = fallback_tag
-        
-        # Strategy 3: Contextual response selection
-        response = self.get_contextual_response(predicted_tag, message)
-        
-        # Logging untuk debugging
-        print(f"Input: {message}")
-        print(f"Processed: {processed_msg}")
-        print(f"Predicted tag: {predicted_tag} (confidence: {confidence:.3f})")
-        
-        return response
-
-# Inisialisasi chatbot
-chatbot = ImprovedBPJSChatbot()
-
-# Flask app
-app = Flask(__name__)
-
-@app.route('/chat', methods=['POST'])
-def chat():
-    try:
-        msg = request.json.get("message", "").strip()
-        response = chatbot.generate_response(msg)
-        return jsonify({"reply": response})
-    except Exception as e:
-        print(f"Error: {e}")
-        return jsonify({"reply": "Maaf, terjadi kesalahan sistem. Silakan coba lagi."})
-
-@app.route('/health', methods=['GET'])
-def health():
-    return jsonify({"status": "healthy", "model": "BPJS Chatbot Improved"})
-
-if __name__ == '__main__':
+import json
+import random
+import pickle
+import numpy as np
+import re
+from flask import Flask, request, jsonify
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+class ImprovedBPJSChatbot:
+    def __init__(self):
+        self.load_models()
+        self.load_intents()
+        
+    def load_models(self):
+        """Load semua model yang diperlukan"""
+        print("Memuat model dan konfigurasi...")
+        
+        # Load konfigurasi
+        with open('model_config.pkl', 'rb') as f:
+            config = pickle.load(f)
+        
+        # Load sentence transformer
+        self.st_model = SentenceTransformer("./local_st_model")
+        self.preprocessing_enabled = config['preprocessing_enabled']
+        
+        # Load classifier
+        with open('svm_model.pkl', 'rb') as f:
+            self.clf = pickle.load(f)
+        
+        # Load label encoder
+        with open('label_encoder.pkl', 'rb') as f:
+            self.label_encoder = pickle.load(f)
+            
+        print("Semua model berhasil dimuat!")
+    
+    def load_intents(self):
+        """Load data intents untuk responses"""
+        with open('intents.json', 'r', encoding='utf-8') as f:
+            self.intents_data = json.load(f)
+        
+        self.tag_responses = {intent['tag']: intent['responses'] for intent in self.intents_data['intents']}
+        
+        # Buat embeddings untuk semua patterns (untuk similarity fallback)
+        self.pattern_embeddings = []
+        self.pattern_tags = []
+        
+        for intent in self.intents_data['intents']:
+            for pattern in intent['patterns']:
+                processed_pattern = self.preprocess_text(pattern) if self.preprocessing_enabled else pattern
+                embedding = self.st_model.encode(processed_pattern)
+                self.pattern_embeddings.append(embedding)
+                self.pattern_tags.append(intent['tag'])
+                
+        self.pattern_embeddings = np.array(self.pattern_embeddings)
+    
+    def preprocess_text(self, text):
+        """Preprocessing teks yang sama dengan training"""
+        text = text.lower()
+        
+        # Normalisasi singkatan
+        text = re.sub(r'\bjkk\b', 'jaminan kecelakaan kerja', text)
+        text = re.sub(r'\bjkm\b', 'jaminan kematian', text)
+        text = re.sub(r'\bjht\b', 'jaminan hari tua', text)
+        text = re.sub(r'\bjp\b', 'jaminan pensiun', text)
+        text = re.sub(r'\bbpjs\b', 'bpjs ketenagakerjaan', text)
+        
+        # Hapus karakter khusus
+        text = re.sub(r'[^\w\s]', ' ', text)
+        text = re.sub(r'\s+', ' ', text).strip()
+        
+        return text
+    
+    def get_prediction_confidence(self, msg_embedding):
+        """Dapatkan prediksi dengan confidence score"""
+        # Prediksi probabilitas
+        probabilities = self.clf.predict_proba(msg_embedding)[0]
+        max_prob = np.max(probabilities)
+        predicted_class = np.argmax(probabilities)
+        predicted_tag = self.label_encoder.inverse_transform([predicted_class])[0]
+        
+        return predicted_tag, max_prob
+    
+    def similarity_fallback(self, msg_embedding, threshold=0.7):
+        """Fallback menggunakan cosine similarity"""
+        similarities = cosine_similarity(msg_embedding, self.pattern_embeddings)[0]
+        max_similarity_idx = np.argmax(similarities)
+        max_similarity = similarities[max_similarity_idx]
+        
+        if max_similarity >= threshold:
+            return self.pattern_tags[max_similarity_idx], max_similarity
+        
+        return 'fallback', max_similarity
+    
+    def get_contextual_response(self, tag, user_message):
+        """Pilih response yang paling kontekstual"""
+        responses = self.tag_responses.get(tag, self.tag_responses['fallback'])
+        
+        # Jika hanya ada satu response, return langsung
+        if len(responses) == 1:
+            return responses[0]
+        
+        # Pilih response berdasarkan kata kunci dalam pesan user
+        user_words = set(user_message.lower().split())
+        
+        best_response = responses[0]
+        best_score = 0
+        
+        for response in responses:
+            response_words = set(response.lower().split())
+            # Hitung kesamaan kata
+            common_words = user_words.intersection(response_words)
+            score = len(common_words)
+            
+            if score > best_score:
+                best_score = score
+                best_response = response
+        
+        # Jika tidak ada yang cocok, pilih random
+        if best_score == 0:
+            return random.choice(responses)
+        
+        return best_response
+    
+    def generate_response(self, message):
+        """Generate response dengan multiple strategies"""
+        if not message.strip():
+            return "Tolong kirim sebuah pesan."
+        
+        # Preprocessing
+        processed_msg = self.preprocess_text(message) if self.preprocessing_enabled else message
+        msg_embedding = self.st_model.encode(processed_msg).reshape(1, -1)
+        
+        # Strategy 1: SVM prediction dengan confidence
+        predicted_tag, confidence = self.get_prediction_confidence(msg_embedding)
+        
+        # Strategy 2: Similarity fallback jika confidence rendah
+        if confidence < 0.6:  # Threshold bisa di-adjust
+            fallback_tag, similarity = self.similarity_fallback(msg_embedding)
+            if similarity > confidence:
+                predicted_tag = fallback_tag
+        
+        # Strategy 3: Contextual response selection
+        response = self.get_contextual_response(predicted_tag, message)
+        
+        # Logging untuk debugging
+        print(f"Input: {message}")
+        print(f"Processed: {processed_msg}")
+        print(f"Predicted tag: {predicted_tag} (confidence: {confidence:.3f})")
+        
+        return response
+
+# Inisialisasi chatbot
+chatbot = ImprovedBPJSChatbot()
+
+# Flask app
+app = Flask(__name__)
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    try:
+        msg = request.json.get("message", "").strip()
+        response = chatbot.generate_response(msg)
+        return jsonify({"reply": response})
+    except Exception as e:
+        print(f"Error: {e}")
+        return jsonify({"reply": "Maaf, terjadi kesalahan sistem. Silakan coba lagi."})
+
+@app.route('/health', methods=['GET'])
+def health():
+    return jsonify({"status": "healthy", "model": "BPJS Chatbot Improved"})
+
+if __name__ == '__main__':
     app.run(port=7860, debug=False) #ganti dari 5000 ke 7860