Update app.py

app.py

@@ -38,22 +38,28 @@ data = {
 }
 df = pd.DataFrame(data)
 
+# Encoding the contexts using One-Hot Encoding (memory-efficient)
+encoder = OneHotEncoder(handle_unknown='ignore', sparse=True)
+contexts_encoded = encoder.fit_transform(df[['context']])
+
 # Encoding emotions
 emotions_target = pd.Categorical(df['emotion']).codes
 emotion_classes = pd.Categorical(df['emotion']).categories
 
 # Load pre-trained BERT model for emotion prediction
 emotion_prediction_model = AutoModelForSequenceClassification.from_pretrained("bhadresh-savani/distilbert-base-uncased-emotion")
+emotion_prediction_tokenizer = AutoTokenizer.from_pretrained("bhadresh-savani/distilbert-base-uncased-emotion")
 
 # Lazy loading for the fine-tuned language model
-def predict_emotion(context):
-    tokenizer = AutoTokenizer.from_pretrained("bhadresh-savani/distilbert-base-uncased-emotion")
-    emotion_prediction_pipeline = pipeline('text-classification', model=emotion_prediction_model, tokenizer=tokenizer, return_all_scores=True)
-    predictions = emotion_prediction_pipeline(context)
-    emotion_scores = predictions[0]
-    emotion_pred = max(emotion_scores, key=emotion_scores.get)
-    return emotion_pred
-
+_finetuned_lm_tokenizer = None
+_finetuned_lm_model = None
+def get_finetuned_lm_model():
+    global _finetuned_lm_tokenizer, _finetuned_lm_model
+    if _finetuned_lm_tokenizer is None or _finetuned_lm_model is None:
+        finetuned_lm_model_name = "microsoft/DialoGPT-large"  # Replace with your fine-tuned language model name
+        _finetuned_lm_tokenizer = AutoTokenizer.from_pretrained(finetuned_lm_model_name)
+        _finetuned_lm_model = AutoModelForCausalLM.from_pretrained(finetuned_lm_model_name, device_map="auto", low_cpu_mem_usage=True)
+    return _finetuned_lm_tokenizer, _finetuned_lm_model
 
 # Enhanced Emotional States
 emotions = {
@@ -122,7 +128,8 @@ def evolve_emotions():
     toolbox.register("attr_float", random.uniform, 0, 20)
     toolbox.register("attr_intensity", random.uniform, 0, 10)
     toolbox.register("individual", tools.initCycle, creator.Individual,
-                     (toolbox.attr_float,) * (len(emotions) - 1) + 
+                     (toolbox.attr_float,) * (len(emotions) - 1)
+    + 
                      (toolbox.attr_intensity,) * len(emotions) +
                      (lambda: 100,), n=1)
     toolbox.register("population", tools.initRepeat, list, toolbox.individual)
@@ -147,7 +154,7 @@ def evolve_emotions():
     emotions['ideal_state']['percentage'] = ideal_state
 
 def predict_emotion(context):
-    emotion_prediction_pipeline = pipeline('text-classification', model=emotion_prediction_model, return_all_scores=True)
+    emotion_prediction_pipeline = pipeline('text-classification', model=emotion_prediction_model, tokenizer=emotion_prediction_tokenizer, return_all_scores=True)
     predictions = emotion_prediction_pipeline(context)
     emotion_scores = predictions[0]
     emotion_pred = max(emotion_scores, key=emotion_scores.get)