Update app.py

app.py

@@ -1,72 +1,93 @@
-import gradio as gr
+import streamlit as st
 import pandas as pd
-import numpy as np
 import matplotlib.pyplot as plt
 from transformers import pipeline
 import plotly.express as px
 
-# Initialize the Hugging Face model for expense categorization (use zero-shot classification)
-expense_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+# 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')
 
-# Batch categorization function for efficiency
-def categorize_transaction_batch(descriptions):
-    candidate_labels = ["Groceries", "Entertainment", "Rent", "Utilities", "Dining", "Transportation", "Shopping", "Others"]
-    return [expense_classifier(description, candidate_labels)["labels"][0] for description in descriptions]
+# List of possible expense categories
+categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation", "Salary"]
 
-# Function to process the uploaded CSV and generate visualizations
-def process_expenses(file):
-    # Read CSV data
-    df = pd.read_csv(file.name)
-    
-    # Check if required columns are present
-    if 'Date' not in df.columns or 'Description' not in df.columns or 'Amount' not in df.columns:
-        return "CSV file should contain 'Date', 'Description', and 'Amount' columns."
+# Function to categorize transactions
+def categorize_expense(description):
+    result = expense_classifier(description, candidate_labels=categories)
+    return result['labels'][0]  # Choose the most probable category
 
-    # Categorize the expenses (using batch processing to minimize model calls)
-    df['Category'] = categorize_transaction_batch(df['Description'].tolist())
+# 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.
+""")
 
-    # Create visualizations:
-    # 1. Pie chart for Category-wise spending
-    category_spending = df.groupby("Category")['Amount'].sum()
-    fig1 = px.pie(category_spending, names=category_spending.index, values=category_spending.values, title="Category-wise Spending")
-    
-    # 2. Monthly spending trends (Line plot)
-    df['Date'] = pd.to_datetime(df['Date'])
-    df['Month'] = df['Date'].dt.to_period('M')
-    monthly_spending = df.groupby('Month')['Amount'].sum()
-    fig2 = px.line(monthly_spending, x=monthly_spending.index, y=monthly_spending.values, title="Monthly Spending Trends")
-    
-    # 3. Budget vs Actual Spending (Bar chart)
-    category_list = df['Category'].unique()
-    budget_dict = {category: 500 for category in category_list}  # Default budget is 500 for each category
-    budget_spending = {category: [budget_dict[category], category_spending.get(category, 0)] for category in category_list}
-    budget_df = pd.DataFrame(budget_spending, index=["Budget", "Actual"]).T
-    fig3 = px.bar(budget_df, x=budget_df.index, y=["Budget", "Actual"], title="Budget vs Actual Spending")
-    
-    # 4. Suggested savings (only calculate if over budget)
-    savings_tips = []
-    for category, actual in category_spending.items():
-        if actual > budget_dict.get(category, 500):
-            savings_tips.append(f"- **{category}**: Over budget by ${actual - budget_dict.get(category, 500)}. Consider reducing this expense.")
-    
-    return df.head(), fig1, fig2, fig3, savings_tips
+# Upload CSV file
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+if uploaded_file is not None:
+    df = pd.read_csv(uploaded_file)
 
-# Gradio interface definition
-inputs = gr.File(label="Upload Expense CSV")
-outputs = [
-    gr.Dataframe(label="Categorized Expense Data"),
-    gr.Plot(label="Category-wise Spending (Pie Chart)"),
-    gr.Plot(label="Monthly Spending Trends (Line Chart)"),
-    gr.Plot(label="Budget vs Actual Spending (Bar Chart)"),
-    gr.Textbox(label="Savings Tips")
-]
+    # Display the first few rows of the data
+    st.subheader("Transaction Data")
+    st.dataframe(df.head())
 
-# Launch Gradio interface
-gr.Interface(
-    fn=process_expenses,
-    inputs=inputs,
-    outputs=outputs,
-    live=True,
-    title="Smart Expense Tracker",
-    description="Upload your CSV of transactions, categorize them, and view insights like spending trends and budget analysis."
-).launch()
+    # 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)
+
+        # 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)
+
+        # 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)
+
+        # 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.")
+
+        # 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']}")
+
+    else:
+        st.error("CSV file should contain 'Description', 'Amount', and 'Date' columns.")