update app.py

app.py

@@ -1,16 +1,17 @@
 from spacy.lang.en import English
-
-nlp = English()
-nlp.add_pipe("sentencizer")
-
 import pandas as pd
 import gradio as gr
-
 from transformers import pipeline
 from gradio.themes.utils.colors import red, green
 
+# Initialize the NLP pipeline
+nlp = English()
+nlp.add_pipe("sentencizer")
+
+# Initialize the text classification pipeline
 detector = pipeline(task='text-classification', model='SJTU-CL/RoBERTa-large-ArguGPT-sent')
 
+# Define color map for highlighted text
 color_map = {
     '0%': green.c400,
     '10%': green.c300,
@@ -25,9 +26,7 @@ color_map = {
     '100%': red.c500
 }
 
-
 def predict_doc(doc):
-    # sents = sent_tokenize(doc)
     sents = [s.text for s in nlp(doc).sents]
     data = {'sentence': [], 'label': [], 'score': []}
     res = []
@@ -41,72 +40,83 @@ def predict_doc(doc):
         else:
             data['label'].append('Machine')
 
-        if prob < 0.1:
-            label = '0%'
-        elif prob < 0.2:
-            label = '10%'
-        elif prob < 0.3:
-            label = '20%'
-        elif prob < 0.4:
-            label = '30%'
-        elif prob < 0.5:
-            label = '40%'
-        elif prob < 0.6:
-            label = '50%'
-        elif prob < 0.7:
-            label = '60%'
-        elif prob < 0.8:
-            label = '70%'
-        elif prob < 0.9:
-            label = '80%'
-        elif prob < 1:
-            label = '90%'
-        else:
-            label = '100%'
+        if prob < 0.1: label = '0%'
+        elif prob < 0.2: label = '10%'
+        elif prob < 0.3: label = '20%'
+        elif prob < 0.4: label = '30%'
+        elif prob < 0.5: label = '40%'
+        elif prob < 0.6: label = '50%'
+        elif prob < 0.7: label = '60%'
+        elif prob < 0.8: label = '70%'
+        elif prob < 0.9: label = '80%'
+        elif prob < 1: label = '90%'
+        else: label = '100%'
         res.append((sent, label))
 
     df = pd.DataFrame(data)
     df.to_csv('result.csv')
     overall_score = df.score.mean()
-    sum_str = ''
-    if overall_score <= 0.5:
-        overall_label = 'Human'
-    else:
-        overall_label = 'Machine'
-    sum_str = f'The essay is probably written by {overall_label}. The probability of being generated by AI is {overall_score}'
+    overall_label = 'Human' if overall_score <= 0.5 else 'Machine'
+    sum_str = f'The essay is probably written by {overall_label}. The probability of being generated by AI is {overall_score:.2f}'
 
     return sum_str, res, df, 'result.csv'
 
-
 def predict_one_sent(sent):
-    '''
-    convert to prob
-    LABEL_1, 0.66 -> 0.66
-    LABEL_0, 0.66 -> 0.34
-    '''
     res = detector(sent)[0]
     org_label, prob = res['label'], res['score']
     if org_label == 'LABEL_0': prob = 1 - prob
     return prob
 
+# Custom CSS for modern look
+custom_css = """
+.gradio-container {
+    font-family: 'Arial', sans-serif;
+}
+.gradio-header {
+    background-color: #4CAF50;
+    color: white;
+    padding: 10px;
+    text-align: center;
+}
+.gradio-button {
+    background-color: #4CAF50;
+    color: white;
+    border: none;
+    padding: 10px 20px;
+    text-align: center;
+    text-decoration: none;
+    display: inline-block;
+    font-size: 16px;
+    margin: 4px 2px;
+    cursor: pointer;
+    border-radius: 5px;
+}
+.gradio-button:hover {
+    background-color: #45a049;
+}
+"""
 
-with gr.Blocks() as demo:
+with gr.Blocks(css=custom_css) as demo:
+    gr.Markdown("## AI vs Human Essay Detector")
+    gr.Markdown("This tool helps you determine whether an essay is written by a human or generated by AI.")
+    
     with gr.Row():
         with gr.Column():
             text_in = gr.Textbox(
-                lines=5,
-                label='Essay input',
-                info='Please enter the essay in the textbox'
+                lines=5, 
+                label='Essay Input', 
+                info='Please enter the essay in the textbox',
+                placeholder="Paste your essay here..."
             )
-            btn = gr.Button('Predict who writes this essay!')
+            btn = gr.Button('Predict who writes this essay!', variant="primary")
 
         sent_res = gr.HighlightedText(label='Labeled Result', color_map=color_map)
-
+    
     with gr.Row():
-        summary = gr.Text(label='Result summary')
-        csv_f = gr.File(label='CSV file storing data with all sentences.')
+        summary = gr.Text(label='Result Summary')
+        csv_f = gr.File(label='CSV File Storing Data with All Sentences')
 
     tab = gr.Dataframe(label='Table with Probability Score', row_count=100)
     btn.click(predict_doc, inputs=[text_in], outputs=[summary, sent_res, tab, csv_f], api_name='predict_doc')
 
-demo.launch()
+demo.launch()