import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
import streamlit as st
from transformers import pipeline

# Upload CSV file containing transaction data
uploaded_file = st.file_uploader("Upload Expense CSV", type="csv")

if uploaded_file is not None:
    # Load the file into a DataFrame
    df = pd.read_csv(uploaded_file)

    # Display the first few rows of the dataset
    st.write("First few rows of the dataset:", df.head())

    # Initialize Hugging Face's zero-shot text classification model
    model_name = 'distilbert-base-uncased'
    classifier = pipeline('zero-shot-classification', model=model_name)

    # List of possible expense categories
    categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation", "Salary"]

    # Function to classify transaction descriptions into categories
    def categorize_expense(description):
        result = classifier(description, candidate_labels=categories)
        return result['labels'][0]  # Choose the most probable category

    # Apply the categorization function to the 'Description' column in the dataset
    df['Category'] = df['Description'].apply(categorize_expense)

    # Show the ca