Update app.py

app.py

@@ -1,3 +1,13 @@
+# Upload your dataset
+uploaded = files.upload()
+
+# Load the dataset
+filename = next(iter(uploaded))  # Automatically get the first uploaded file's name
+df = pd.read_excel(filename)  # Read the uploaded Excel file
+
+# Display the columns in the uploaded DataFrame to help identify correct names
+print("Columns in the dataset:", df.columns.tolist())
+
 import os
 os.system('pip install transformers')
 # Import the necessary libraries
@@ -5,9 +15,11 @@ import os
 os.system('pip install torch')
 # Import the necessary libraries
 # Import the necessary libraries
+# Import the necessary libraries
 from transformers import AutoModel, AutoTokenizer
 import torch
 from torch.utils.data import DataLoader, Dataset
+from sklearn.model_selection import train_test_split
 import pandas as pd
 import gradio as gr
 
@@ -17,11 +29,11 @@ tokenizer = AutoTokenizer.from_pretrained("Alibaba-NLP/gte-multilingual-base", t
 
 # Function to load the dataset
 def load_dataset():
-    df = pd.read_excel("your_dataset.xlsx")  # Ensure the file name and path are correct
+    df = pd.read_excel("data.xlsx")  # Ensure the file name and path are correct
     print("Columns in the dataset:", df.columns.tolist())
     return df
 
-# Example function to search by name and return the PEC number
+# Function to search by name and return the PEC number
 def search_by_name(name, df):
     name_matches = df[df['Name'].str.contains(name, case=False, na=False)]
     if not name_matches.empty: