Update app.py

updated table and model

app.py

@@ -1,17 +1,18 @@
 import gradio as gr
+import pandas as pd
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import torch
 import pickle
 
-# Load the model and tokenizer from Hugging Face Hub
+# Existing code for loading model and tokenizer
 model_name = "peterkros/cofogv1-bert"
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Load the label encoder
 with open('label_encoder.pkl', 'rb') as file:
     label_encoder = pickle.load(file)
 
+# Existing prediction function
 def predict(text):
     inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
     with torch.no_grad():
@@ -21,22 +22,35 @@ def predict(text):
     predicted_label = label_encoder.inverse_transform([predicted_class])[0]
     return predicted_label
 
-# Define the markdown text with bullet points
+# Function to display the metrics table
+def show_table():
+    data = {
+        "Epoch": [1, 2, 3, 4, 5],
+        "Training Loss": ["No log", "No log", "No log", "No log", "No log"],
+        "Validation Loss": [2.095209, 1.419945, 0.683810, 0.460408, 0.422096],
+        "Accuracy": [0.340764, 0.662420, 0.850318, 0.872611, 0.888535]
+    }
+    df = pd.DataFrame(data)
+    return df
+
+# Existing markdown text
 markdown_text = """
 - Trained with ~1500 rows of data on bert-large-uncased, English.
 - Input one budget line per time.
-- Accuracy of the model is ~80%.
+- Accuracy of the model is ~88%.
 """
 
+# Update the Gradio Interface to include the table
 iface = gr.Interface(
-    fn=predict, 
-    inputs=gr.components.Textbox(lines=1, placeholder="Enter Budget line here...", label="Budget Input"), 
-    outputs=gr.components.Textbox(label="Classification Output"),
+    fn=[predict, show_table], 
+    inputs=[gr.components.Textbox(lines=1, placeholder="Enter Budget line here...", label="Budget Input"), None], 
+    outputs=[gr.components.Textbox(label="Classification Output"), gr.outputs.Dataframe(type="pandas")],
     title="COFOG Level 1 Classification",
     description=markdown_text,
-    allow_flagging="auto"  # Enables flagging
+    allow_flagging="auto"
 )
 
 # Run the interface
 if __name__ == "__main__":
     iface.launch()
+