Version 2.2

app.py

@@ -7,12 +7,14 @@ def load_model(selected_model):
         loaded_model = pickle.load(file)
     return loaded_model
 
-def predict(model, text):
-    encoder = {
-        0:'assets/negative.jpeg',
-        1:'assets/neutral.jpeg',
-        2:'assets/positive.jpeg'
+encoder = {
+        'negative':'assets/negative.jpeg',
+        'neutral':'assets/neutral.jpeg',
+        'positive':'assets/positive.jpeg'
     }
+
+def predict(model, text):
+    
     selected_model = None
     with open('vectorizer.pkl', 'rb') as file:
         vectorizer = pickle.load(file)
@@ -36,11 +38,13 @@ def predict(model, text):
     
 classifier = pipeline(task="zero-shot-classification", model="facebook/bart-large-mnli")
 def analyze_sentiment(text):
-  results = classifier(text, ["positive", "negative", "neutral"], multi_label=True)
-  sentiment = max(results['labels'], key=results['scores'].__getitem__)
-  return sentiment
+  results = classifier(text,["positive","negative",'neutral'],multi_label=True)
+  mx = max(results['scores'])
+  ind = results['scores'].index(mx)
+  result = results['labels'][ind]
+  return encoder[result]
 
 # models = gr.Radio(['Random Forest', 'Logistic Regression','Naive Bayes','Decision Tree','KNN'], label="Choose model")
 # demo = gr.Interface(fn=predict, inputs=[models,"text"], outputs="image", title="Sentiment Analysis") 
-demo = gr.Interface(fn=analyze_sentiment, inputs="text", outputs="text", title="Sentiment Analysis") 
-demo.launch()
+demo = gr.Interface(fn=analyze_sentiment, inputs="text", outputs="image", title="Sentiment Analysis") 
+demo.launch(share=True)