Update app.py

app.py

@@ -1,6 +1,7 @@
 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
@@ -11,9 +12,9 @@ tokenizer = RobertaTokenizer.from_pretrained(model_dir)
 model = RobertaForSequenceClassification.from_pretrained(model_dir)
 tokenizer1 = RobertaTokenizer.from_pretrained('roberta-base')
 model1 = RobertaModel.from_pretrained('roberta-base')
+threshold=0.5
 #pipe = pipeline("text-classification", model="thugCodeNinja/robertatemp")
-pipe = pipeline("text-classification",model=model,tokenizer=tokenizer)
-threshold = 0.5
+# pipe = pipeline("text-classification",model=model,tokenizer=tokenizer)
 def process_text(input_text):
     if input_text:
         text = input_text
@@ -72,11 +73,11 @@ def process_text(input_text):
                 if similarity > threshold:
                     similar_articles.append([link,similarity])
         similar_articles = sorted(similar_articles, key=lambda x: x[1], reverse=True)
-          # Adjust the threshold as needed
+        #threshold = 0.5  # Adjust the threshold as needed
         return similar_articles[:5]
 
     # prediction = pipe([text])
-    # explainer = shap.Explainer(pipe)
+    # explainer = shap.DeepExplainer(model,[text])
     # shap_values = explainer([text])
     # shap_plot_html = HTML(shap.plots.text(shap_values, display=False)).data
     similar_articles = find_plagiarism(text)