Update app.py

app.py

@@ -1,7 +1,7 @@
 #%%writefile debias_app.py
-
 import streamlit as st
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification, pipeline
+import pandas as pd
 
 # Define the BiasPipeline class with text processing methods
 class BiasPipeline:
@@ -24,18 +24,6 @@ class BiasPipeline:
         """Clean up the text by removing any redundant spaces."""
         return ' '.join(text.split())
 
-    def complete_sentence(self, text):
-        """If the text ends mid-sentence, remove all words after the last full stop."""
-        sentences = text.split(". ")
-        if len(sentences) > 1 and not sentences[-1].endswith("."):
-            return ". ".join(sentences[:-1]) + "."
-        return text
-
-    def create_token_limit(self, text):
-        words = text.split()
-        max_length = round(len(words) + 1.5 * len(words))
-        return max_length
-
     def process(self, texts):
         """Process texts to classify and find named entities."""
         classification_results = self.classifier(texts)
@@ -50,23 +38,7 @@ st.title('UnBIAS App')
 # List of preloaded example sentences
 example_sentences = [
     "Women are just too emotional to be leaders.",
-    "All young people are lazy and addicted to their phones.",
-    "People from that country are always dishonest and corrupt.",
-    "Men are inherently better at science and math than women.",
-    "The elderly are just burdens to society; they contribute nothing.",
-    "All poor people are lazy and don't want to work.",
-    "People who follow that religion are all terrorists.",
-    "Immigrants are taking all our jobs and ruining the country.",
-    "All wealthy people achieved success only through manipulation and deceit.",
-    "People with tattoos are not professional.",
-    "All politicians are liars and cannot be trusted.",
-    "Blue-collar workers don't have any real skills.",
-    "Anyone who doesn't attend college is unintelligent.",
-    "Only people from the city are sophisticated.",
-    "Rural folks have backward mindsets and don't understand progress.",
-    "All artists are always broke and unreliable.",
-    "Anyone from that region is uneducated and narrow-minded.",
-    "People without jobs are simply not trying hard enough."
+    # More examples...
 ]
 
 # Dropdown for selecting an example sentence or entering your own
@@ -77,7 +49,13 @@ if st.button("Process Text"):
     if input_text:
         cleaned_text = pipeline.clean_text(input_text)
         classification_results, ner_results = pipeline.process(cleaned_text)
-        st.write("Classification Results:", classification_results)
-        st.write("Named Entity Recognition Results:", ner_results)
+        label = classification_results[0]['label']
+        score = classification_results[0]['score']
+        st.write(f"**Classification:** {label} (Confidence: {score:.2f})")
+
+        # Extract biased words from NER results
+        biased_words = [result['word'] for result in ner_results if result['entity'].startswith('B-BIAS')]
+        st.write("**Biased Words Identified:**")
+        st.write(", ".join(biased_words))
     else:
         st.write("Please enter some text to process.")