Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import torch
 from torch.nn.functional import softmax
-import shap
 import requests
 from bs4 import BeautifulSoup
 from sklearn.metrics.pairwise import cosine_similarity
@@ -10,6 +9,8 @@ from IPython.core.display import HTML
 model_dir = 'temp'
 tokenizer = RobertaTokenizer.from_pretrained(model_dir)
 model = RobertaForSequenceClassification.from_pretrained(model_dir)
+tokenizer1 = RobertaTokenizer.from_pretrained('roberta-base')
+model1 = RobertaModel.from_pretrained('roberta-base')
 #pipe = pipeline("text-classification", model="thugCodeNinja/robertatemp")
 pipe = pipeline("text-classification",model=model,tokenizer=tokenizer)
 def process_text(input_text):
@@ -57,13 +58,13 @@ def process_text(input_text):
             article_text = get_article_text(link)
             if article_text:
             # Tokenize and encode the input text and the article text
-                encoding1 = tokenizer(text, max_length=512, truncation=True, padding=True, return_tensors="pt")
-                encoding2 = tokenizer(article_text, max_length=512, truncation=True, padding=True, return_tensors="pt")
+                encoding1 = tokenizer1(text, max_length=512, truncation=True, padding=True, return_tensors="pt")
+                encoding2 = tokenizer1(article_text, max_length=512, truncation=True, padding=True, return_tensors="pt")
             
             # Calculate embeddings using the model
                 with torch.no_grad():
-                    embedding1 = model(**encoding1).last_hidden_state.mean(dim=1)
-                    embedding2 = model(**encoding2).last_hidden_state.mean(dim=1)
+                    embedding1 = model1(**encoding1).last_hidden_state.mean(dim=1)
+                    embedding2 = model1(**encoding2).last_hidden_state.mean(dim=1)
             
             # Calculate cosine similarity between the input text and the article text embeddings
                 similarity = cosine_similarity(embedding1, embedding2)[0][0]
@@ -73,16 +74,16 @@ def process_text(input_text):
         threshold = 0.5  # Adjust the threshold as needed
         return similar_articles[:5]
 
-    prediction = pipe([text])
-    explainer = shap.Explainer(pipe)
-    shap_values = explainer([text])
-    shap_plot_html = HTML(shap.plots.text(shap_values, display=False)).data
+    # prediction = pipe([text])
+    # explainer = shap.Explainer(pipe)
+    # shap_values = explainer([text])
+    # shap_plot_html = HTML(shap.plots.text(shap_values, display=False)).data
     similar_articles = find_plagiarism(text)
 
-    return processed_result, prob, final_label, shap_plot_html,similar_articles
+    return processed_result, prob, final_label,similar_articles
 
 text_input = gr.Textbox(label="Enter text")
-outputs = [gr.Textbox(label="Processed text"), gr.Textbox(label="Probability"), gr.Textbox(label="Label"), gr.HTML(label="SHAP Plot"),gr.Dataframe(label="Similar Articles", headers=["Link", "Similarity"],row_count=5)]
+outputs = [gr.Textbox(label="Processed text"), gr.Textbox(label="Probability"), gr.Textbox(label="Label"),gr.Dataframe(label="Similar Articles", headers=["Link", "Similarity"],row_count=5)]
 title = "Group 2- ChatGPT text detection module"
 description = '''Please upload text files and text input responsibly and await the explainable results. The approach in place includes finetuning a Roberta model for text classification.Once the classifications are done the decision is exaplined thorugh the SHAP text plot.
 The probability is particularly explained by the attention plots through SHAP'''