Update app.py

app.py

@@ -1,34 +1,10 @@
 import gradio as gr
 import joblib
-import os
-import csv
-from datetime import datetime
-
 
 model = joblib.load('arabic_text_classifier.pkl')
 vectorizer = joblib.load('tfidf_vectorizer.pkl')
 label_encoder = joblib.load('label_encoder.pkl')
 
-
-LOG_FILE = "predictions_log.csv"
-
-
-def log_prediction(input_text, predicted_label):
-    
-    file_exists = os.path.isfile(LOG_FILE)
-
-    
-    with open(LOG_FILE, mode='a', newline='', encoding='utf-8') as file:
-        writer = csv.writer(file)
-
-        
-        if not file_exists:
-            writer.writerow(["Timestamp", "User Input", "Predicted Category"])
-
-        
-        writer.writerow([datetime.now().strftime("%Y-%m-%d %H:%M:%S"), input_text, predicted_label])
-
-
 def predict_category(text):
     text_vector = vectorizer.transform([text])
     probabilities = model.predict_proba(text_vector)[0]
@@ -37,16 +13,15 @@ def predict_category(text):
 
     
     if max_prob < 0.5:
-        predicted_label = "Other"  
-    else:
-        predicted_label = label_encoder.inverse_transform([predicted_category])[0]
+        return "Other"  
 
-    # Log the prediction
-    log_prediction(text, predicted_label)
-
-    # Return the predicted label
+    
+    predicted_label = label_encoder.inverse_transform([predicted_category])[0]
     return predicted_label
 
+HF_TOKEN = os.getenv("classification")
+hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced-text-classification-data")
+
 iface = gr.Interface(
     fn=predict_category,
     inputs=gr.Textbox(
@@ -56,8 +31,10 @@ iface = gr.Interface(
     ),
     outputs=gr.Label(label="Predicted Category"),  
     title="Arabic Text Classification", 
-    description="Enter an Arabic text to get its classification based on the trained model.", 
+    description="Enter an Arabic text to get its classification based on the trained model.",
+    allow_flagging="auto",
+    flagging_callback=hf_writer,
 )
 
 
-iface.launch()
+iface.launch(share=True)