Update app.py

app.py

@@ -1,27 +1,17 @@
-#import streamlit as st
-#import skops.hub_utils as hub_utils
-#import pandas as pd
-import re
-from nltk.tokenize import word_tokenize
-import nltk
-
-
 
-
-import gradio as gr
+import streamlit as st
+import skops.hub_utils as hub_utils
 import pandas as pd
-from nltk.tokenize import word_tokenize
 from transformers import AutoModelForSequenceClassification
-import hub_utils  # Assuming you have a custom module for interacting with the Hugging Face model hub
+import re
+from nltk.tokenize import word_tokenize
+import nltk
 
 
 nltk.download('punkt')
 
 
 
-
-
-
 def nextwords_1(ww, inx):
     try:
         return '' if inx == len(ww) - 1 else ww[inx + 1]
@@ -123,18 +113,17 @@ def features(sentence, index):
     }
 
 
-
 # Define the function for processing user input
 def process_text(text_input):
     if text_input:
         # Prepare text (define this function)
-        prepared_text = prepare_text(text_input)
+        prepared_text = prepare_text(text_input)  # Assuming prepare_text function is defined elsewhere
         
         # Tokenize text
-        tokenized_text = word_tokenize(prepared_text)
+        tokenized_text = word_tokenize(prepared_text)  # Assuming word_tokenize function is imported
         
         # Extract features (define this function)
-        features_list = [features(tokenized_text, i) for i in range(len(tokenized_text))]
+        features_list = [features(tokenized_text, i) for i in range(len(tokenized_text))]  # Assuming features function is defined elsewhere
         
         # Create a DataFrame with the features
         data = pd.DataFrame(features_list)
@@ -143,7 +132,7 @@ def process_text(text_input):
         model_id = "Alshargi/arabic-msa-dialects-segmentation"
         model = AutoModelForSequenceClassification.from_pretrained(model_id)
         
-        # Get model output (define or import the get_model_output function)
+        # Get model output using hub_utils
         res = hub_utils.get_model_output(model, data)
         
         # Return the model output
@@ -151,9 +140,17 @@ def process_text(text_input):
     else:
         return "Please enter some text."
 
-# Define the Gradio interface
-iface = gr.Interface(fn=process_text, inputs="text", outputs="text", title="Arabic Text Segmentation")
-
-# Launch the Gradio interface
-iface.launch(share=True)
-
+def main():
+    st.title("Model Output with Streamlit")
+    
+    # Text input
+    input_text = st.text_input("Enter your text:")
+    
+    # Process the text when a button is clicked
+    if st.button("Process"):
+        output = process_text(input_text)
+        st.write("Model Output:")
+        st.write(output)
+
+if __name__ == "__main__":
+    main()