Update app.py

app.py

@@ -1,167 +1,3 @@
-# import streamlit as st
-# from transformers import pipeline
-
-# class BiasAndGrammarCorrectionPipeline:
-#     def __init__(self, grammar_correction_pipeline, bias_detection_pipeline):
-#         self.grammar_correction_pipeline = grammar_correction_pipeline
-#         self.bias_detection_pipeline = bias_detection_pipeline
-
-#     def __call__(self, text):
-#         # Perform grammar correction
-#         corrected_text = self.grammar_correction_pipeline(text, num_beams=5, max_length=1000)[0]["generated_text"]
-
-#         # Perform bias detection
-#         result = self.bias_detection_pipeline(corrected_text)
-
-#         # Determine if bias is detected based on the bias score
-#         bias_detected = False
-#         bias_score = None
-
-#         if isinstance(result, list):
-#             for item in result:
-#                 if "score" in item:
-#                     if item["score"] >= 0.5:
-#                         bias_detected = True
-#                         bias_score = item["score"]
-#                         break
-#         else:
-#             if "score" in result:
-#                 bias_detected = result["score"] >= 0.5
-#                 bias_score = result["score"]
-
-#         return corrected_text, bias_detected, bias_score
-
-# # Load the grammar correction model pipeline
-# corrector = pipeline("text2text-generation", model="vennify/t5-base-grammar-correction")
-
-# # Load the text classification model pipeline
-# classifier = pipeline("text-classification", model="Alicewuu/bias_detection", return_all_scores=True)
-
-# # Instantiate the combined pipeline
-# combined_pipeline = BiasAndGrammarCorrectionPipeline(corrector, classifier)
-
-# # Streamlit application title
-# st.title("Text Bias Detection")
-# st.write("Detection for 2 classes")
-
-# # Text input for user to enter the text to classify
-# text = st.text_area("Enter the text to detect", "")
-# corrected_text, bias_detected, bias_score = combined_pipeline(text)
-
-# # Perform text classification when the user clicks the "Detect" button
-# if st.button("Detect"):
-#     # Display the results
-#     st.write("Corrected Text:", corrected_text)
-#     st.write("Bias Detected:", bias_detected)
-#     if bias_score is not None:
-#         st.write("Bias Score:", bias_score)
-
-
-# import streamlit as st
-# from transformers import pipeline
-# # from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-
-# class BiasAndGrammarCorrectionPipeline:
-#     def __init__(self, grammar_correction_pipeline, bias_detection_pipeline):
-#         self.grammar_correction_pipeline = grammar_correction_pipeline
-#         self.bias_detection_pipeline = bias_detection_pipeline
-
-#     def __call__(self, text):
-#         # Perform grammar correction
-#         corrected_text = self.grammar_correction_pipeline(text, num_beams=5, max_length=1000)[0]["generated_text"]
-
-#         # Perform bias detection
-#         result = self.bias_detection_pipeline(corrected_text)
-#         bias_score = result[0]["score"]
-
-#         # Determine if bias is detected based on the bias score
-#         bias_detected = bias_score >= 0.5
-
-#         return corrected_text, bias_detected, bias_score
-
-# # Load the grammar correction model pipeline
-# # tokenizer = AutoTokenizer.from_pretrained("vennify/t5-base-grammar-correction")
-# # model = AutoModelForSeq2SeqLM.from_pretrained("vennify/t5-base-grammar-correction")
-# # corrector = pipeline("text2text-generation", model=model, tokenizer = tokenizer)
-# corrector = pipeline("text2text-generation", model="vennify/t5-base-grammar-correction")
-
-# # Load the text classification model pipeline
-# classifier = pipeline("text-classification", model="Alicewuu/bias_detection", return_all_scores=True)
-
-# # Instantiate the combined pipeline
-# combined_pipeline = BiasAndGrammarCorrectionPipeline(corrector, classifier)
-
-# # Streamlit application title
-# st.title("Text Bias Detection")
-# st.write("Detection for 2 classes")
-
-# # Text input for user to enter the text to classify
-# text = st.text_area("Enter the text to detect", "")
-
-# # Perform text classification when the user clicks the "Classify" button
-# if st.button("Detect"):
-    
-#     corrected_text, bias_detected, bias_score = combined_pipeline(text)
-
-#     # Display the classification result
-#     st.write("The text with correct grammar:", corrected_text)
-#     st.write("Biased:", bias_detected)
-#     st.write("Score:", bias_score)
-    
-    # # Perform text classification on the input text
-    # results = classifier(text)[0]
-
-    # # Find the label with the highest score
-    # max_label = max(results, key=lambda x: x['score'])
-
-    # # Display the classification result
-    # st.write("Text:", text)
-    # st.write("Label:", max_label['label'])
-    # st.write("Score:", max_label['score'])
-
-
-
-# import streamlit as st
-# from transformers import pipeline
-
-# # Load the grammar correction model pipeline
-# corrector = pipeline("text2text-generation", model="vennify/t5-base-grammar-correction")
-
-# # Load the text classification model pipeline
-# classifier = pipeline("text-classification", model="Alicewuu/bias_detection", return_all_scores=True)
-
-# # Function to perform bias and grammar correction detection
-# def detect_bias_and_grammar_correction(text):
-#     # Perform grammar correction
-#     corrected_text = corrector(text, num_beams=5, max_length=1000)[0]["generated_text"]
-
-#     # Perform bias detection
-#     result = classifier(corrected_text)
-#     bias_score = result[0][0]["score"]
-
-#     # Determine if bias is detected based on the bias score
-#     bias_detected = bias_score >= 0.5
-
-#     return corrected_text, bias_detected, bias_score
-
-# # Streamlit application title
-# st.title("Text Bias Detection")
-# st.write("Detection for 2 classes")
-
-# # Text input for user to enter the text to classify
-# text = st.text_area("Enter the text to detect", "")
-
-# # Perform text classification when the user clicks the "Detect" button
-# if st.button("Detect"):
-#     corrected_text, bias_detected, bias_score = detect_bias_and_grammar_correction(text)
-
-#     # Display the classification result
-#     st.write("The text with correct grammar:", corrected_text)
-#     st.write("Biased:", bias_detected)
-#     st.write("Score:", bias_score)
-
-
-
 import streamlit as st
 from transformers import pipeline
 
@@ -193,5 +29,3 @@ if st.button("Detect"):
     st.write("The text with correct grammar:", corrected_text)
     st.write("Biased:", bias_detected)
     st.write("Score:", bias_score)
-
-