Update app.py

app.py

@@ -22,7 +22,7 @@ from lime import lime_text
 
 stopwords_list = stopwords.words('english') + ['your_additional_stopwords_here']
 st.set_page_config(layout="wide")
-
+@st.cache_resource
 def load_model_and_tokenizer(model_name):
     model = AutoModelForSequenceClassification.from_pretrained(model_name)
     tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -30,7 +30,7 @@ def load_model_and_tokenizer(model_name):
 
 model, tokenizer = load_model_and_tokenizer('nlptown/bert-base-multilingual-uncased-sentiment')
 
-
+@st.cache_resource
 def load_pipeline():
     classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
     return classifier
@@ -226,7 +226,7 @@ def display_dataframe(df, df_display):
 
     st.dataframe(df_display)
     
-def important_words(reviews, model, num_words=5):
+def important_words(reviews, model, num_words=5, batch_size=50):
     # Create a LimeTextExplainer
     explainer = LimeTextExplainer(class_names=[str(i) for i in range(1, 6)])
 
@@ -241,13 +241,17 @@ def important_words(reviews, model, num_words=5):
 
     for rating in range(1, 6):
         important_words_per_rating[rating] = []
-        for review in reviews:
-            # Get the explanation for the review
-            explanation = explainer.explain_instance(review, predict_proba, num_features=num_words, labels=[rating - 1])
 
-            # Get the list of important words
-            words = [feature[0] for feature in explanation.as_list(rating - 1)]
-            important_words_per_rating[rating].extend(words)
+        # Batch processing
+        for i in range(0, len(reviews), batch_size):
+            batch_reviews = reviews[i:i+batch_size]
+            for review in batch_reviews:
+                # Get the explanation for the review
+                explanation = explainer.explain_instance(review, predict_proba, num_features=num_words, labels=[rating - 1])
+
+                # Get the list of important words
+                words = [feature[0] for feature in explanation.as_list(rating - 1)]
+                important_words_per_rating[rating].extend(words)
 
         # Keep only unique words
         important_words_per_rating[rating] = list(set(important_words_per_rating[rating]))
@@ -255,6 +259,7 @@ def important_words(reviews, model, num_words=5):
     return important_words_per_rating
 
 
+
 def display_ratings(df, review_column):
     cols = st.columns(5)