Update app.py

app.py

@@ -3,7 +3,6 @@ import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import matplotlib.pyplot as plt
 
-# Cache the loading of the tokenizer and model to speed up the app
 @st.cache_resource
 def load_model():
     tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
@@ -15,30 +14,33 @@ tokenizer, model = load_model()
 st.title("Sentiment Analysis App")
 
 text = st.text_input("Enter text to analyze:")
-if st.button("Analyze"):
-    if text:  # Ensure that the text is not empty
-        encoding = tokenizer.encode_plus(text, return_tensors="pt", padding=True, truncation=True)
-        input_ids = encoding["input_ids"]
-        attention_mask = encoding["attention_mask"]
-
-        with torch.no_grad():
-            output = model(input_ids, attention_mask)
-        prediction = int(torch.argmax(output.logits))
-
-        # Define sentiments
-        sentiments = ["Negative", "Neutral", "Positive"]
-        sentiment = sentiments[prediction]
-        st.write(f"Sentiment: {sentiment}")
-
-        # Flatten the logits tensor to a list and check dimensions
-        values = output.logits.squeeze().tolist()
-        if len(values) != len(sentiments):
-            st.error(f"Mismatch in the number of sentiments and values. Expected {len(sentiments)}, got {len(values)}")
-        else:
-            fig, ax = plt.subplots()
-            ax.bar(sentiments, values, color=['red', 'blue', 'green'])
-            ax.set_title("Sentiment Analysis Scores")
-            ax.set_ylabel("Score")
-            st.pyplot(fig)
+if st.button("Analyze") and text:
+    encoding = tokenizer.encode_plus(text, return_tensors="pt", padding=True, truncation=True)
+    input_ids = encoding["input_ids"]
+    attention_mask = encoding["attention_mask"]
+
+    with torch.no_grad():
+        output = model(input_ids, attention_mask)
+    logits = output.logits.squeeze()
+    
+    print("Logits Shape:", logits.shape)
+    print("Logits Contents:", logits)
+
+    if logits.shape[0] != 3:
+        st.error(f"Unexpected number of output values: {logits.shape[0]}")
+        st.stop()
+
+    prediction = int(torch.argmax(logits))
+
+    sentiments = ["Negative", "Neutral", "Positive"]
+    sentiment = sentiments[prediction]
+    st.write(f"Sentiment: {sentiment}")
+
+    if len(logits) != len(sentiments):
+        st.error(f"Mismatch in the number of sentiments and values. Expected {len(sentiments)}, got {len(logits)}")
     else:
-        st.error("Please enter some text to analyze.")
+        fig, ax = plt.subplots()
+        ax.bar(sentiments, logits.tolist(), color=['red', 'blue', 'green'])
+        ax.set_title("Sentiment Analysis Scores")
+        ax.set_ylabel("Score")
+        st.pyplot(fig)