Update app.py

app.py

@@ -1,93 +1,32 @@
-import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
-from transformers import pipeline
 import plotly.express as px
+import streamlit as st
+from transformers import pipeline
 
-# Initialize Hugging Face model pipelines for categorization and question-answering
-expense_classifier = pipeline('zero-shot-classification', model='distilbert-base-uncased')
-qa_model = pipeline('question-answering', model='distilbert-base-uncased-distilled-squad')
-
-# List of possible expense categories
-categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation", "Salary"]
-
-# Function to categorize transactions
-def categorize_expense(description):
-    result = expense_classifier(description, candidate_labels=categories)
-    return result['labels'][0]  # Choose the most probable category
-
-# Streamlit UI
-st.title("Smart Expense Tracker")
-st.write("""
-    Upload a CSV file containing your transaction data, and this app will categorize your expenses, visualize trends,
-    and provide insights on your spending habits.
-""")
+# Upload CSV file containing transaction data
+uploaded_file = st.file_uploader("Upload Expense CSV", type="csv")
 
-# Upload CSV file
-uploaded_file = st.file_uploader("Upload your CSV file", 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 data
-    st.subheader("Transaction Data")
-    st.dataframe(df.head())
-
-    # Check if 'Description', 'Amount', and 'Date' columns exist in the file
-    if 'Description' in df.columns and 'Amount' in df.columns and 'Date' in df.columns:
-        # Categorize expenses
-        df['Category'] = df['Description'].apply(categorize_expense)
-        
-        # Visualizations
-        st.subheader("Expense Distribution by Category (Pie Chart)")
-        category_expenses = df.groupby('Category')['Amount'].sum()
-        fig1 = px.pie(category_expenses, names=category_expenses.index, values=category_expenses.values, title="Category-wise Spending")
-        st.plotly_chart(fig1)
+    # Display the first few rows of the dataset
+    st.write("First few rows of the dataset:", df.head())
 
-        # Monthly spending trends (Line Chart)
-        df['Date'] = pd.to_datetime(df['Date'])
-        df['Month'] = df['Date'].dt.to_period('M')
-        monthly_expenses = df.groupby('Month')['Amount'].sum()
-        st.subheader("Monthly Spending Trends")
-        fig2 = px.line(monthly_expenses, x=monthly_expenses.index, y=monthly_expenses.values, title="Monthly Spending")
-        st.plotly_chart(fig2)
+    # Initialize Hugging Face's zero-shot text classification model
+    model_name = 'distilbert-base-uncased'
+    classifier = pipeline('zero-shot-classification', model=model_name)
 
-        # Budget vs Actual Spending (Bar Chart)
-        budgets = {
-            "Groceries": 300,
-            "Rent": 1000,
-            "Utilities": 150,
-            "Entertainment": 100,
-            "Dining": 150,
-            "Transportation": 120,
-        }
-        budget_df = pd.DataFrame({
-            'Actual': monthly_expenses,
-            'Budget': [sum(budgets.values())] * len(monthly_expenses)
-        })
-        st.subheader("Monthly Spending vs Budget")
-        fig3 = px.bar(budget_df, x=budget_df.index, y=["Actual", "Budget"], title="Budget vs Actual Spending")
-        st.plotly_chart(fig3)
+    # List of possible expense categories
+    categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation", "Salary"]
 
-        # Savings Tips (Alert if exceeding budget)
-        st.subheader("Savings Tips")
-        savings_tips = []
-        category_expenses = df.groupby("Category")['Amount'].sum()
-        for category, actual in category_expenses.items():
-            if actual > budgets.get(category, 0):
-                savings_tips.append(f"- **{category}**: Over budget by ${actual - budgets.get(category, 0)}. Consider reducing this expense.")
-        if savings_tips:
-            for tip in savings_tips:
-                st.write(tip)
-        else:
-            st.write("No categories exceeded their budget.")
+    # 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
 
-        # Question Answering Feature
-        st.subheader("Ask Questions About Your Expenses")
-        question = st.text_input("Ask a question about your expenses (e.g., 'How much did I spend on groceries?')")
-        if question:
-            knowledge_base = "\n".join(df.apply(lambda row: f"Description: {row['Description']}, Amount: {row['Amount']}, Category: {row['Category']}", axis=1))
-            answer = qa_model(question=question, context=knowledge_base)
-            st.write(f"Answer: {answer['answer']}")
+    # Apply the categorization function to the 'Description' column in the dataset
+    df['Category'] = df['Description'].apply(categorize_expense)
 
-    else:
-        st.error("CSV file should contain 'Description', 'Amount', and 'Date' columns.")
+    # Show the ca