Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+import pandas as pd
+import transformers
+from transformers import BertTokenizer, BertForSequenceClassification
+import torch
+
+# Load pre-trained BERT model and tokenizer
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
+model.eval()
+
+# Create a persistent DataFrame to store classification results
+results_df = pd.DataFrame(columns=['Text', 'Toxicity'])
+
+def classify_text(text):
+    # Tokenize input text
+    inputs = tokenizer(text, return_tensors='pt', padding=True, truncation=True)
+    input_ids = inputs['input_ids']
+    attention_mask = inputs['attention_mask']
+
+    # Perform inference with BERT model
+    with torch.no_grad():
+        outputs = model(input_ids, attention_mask=attention_mask)
+        logits = outputs.logits
+        probabilities = torch.softmax(logits, dim=1)
+        toxicity_score = probabilities[0][1].item()  # Extract toxicity score
+
+    return toxicity_score
+
+def add_to_results(text, toxicity):
+    global results_df
+    results_df = results_df.append({'Text': text, 'Toxicity': toxicity}, ignore_index=True)
+
+# Streamlit app
+def main():
+    st.title('Toxicity Classification App')
+
+    # Input text box for user to enter text
+    user_text = st.text_area('Enter text:', '')
+
+    # Button to classify text
+    if st.button('Classify'):
+        if user_text:
+            toxicity_score = classify_text(user_text)
+            st.write('Toxicity Score:', toxicity_score)
+            add_to_results(user_text, toxicity_score)
+
+    # Display classification results
+    st.header('Classification Results')
+    st.dataframe(results_df)
+
+if __name__ == '__main__':
+    main()