Update app.py

app.py

@@ -1,109 +1,77 @@
 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
+# File upload
+uploaded_file = st.file_uploader("Upload your expense CSV file", type=["csv"])
+if uploaded_file:
     df = pd.read_csv(uploaded_file)
 
-    # Debug: Display the column names to check if 'Description' exists
-    st.write("Columns in the uploaded file:", df.columns)
-
-    # Check if the 'Description' column exists
-    if 'Description' not in df.columns:
-        st.error("Error: The CSV file does not contain a 'Description' column.")
-    else:
-        # 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 categorized data
-        st.write("Categorized Data:", df.head())
-
-        # Visualization 1: Pie Chart of Spending by Category
-        category_expenses = df.groupby('Category')['Amount'].sum()
-
-        # Plot pie chart for expense distribution by category
-        fig1, ax1 = plt.subplots(figsize=(8, 8))
-        category_expenses.plot(kind='pie', autopct='%1.1f%%', startangle=90, colors=plt.cm.Paired.colors, ax=ax1)
-        ax1.set_title('Expense Distribution by Category')
-        ax1.set_ylabel('')  # Hide the y-axis label
-        st.pyplot(fig1)
-
-        # Visualization 2: Monthly Spending Trends (Line Chart)
-        # Convert 'Date' to datetime and remove time part
-        df['Date'] = pd.to_datetime(df['Date']).dt.date  # Keep only the date, no time
-
-        # Extract month-year for grouping and convert the Period to string to avoid JSON serialization issues
-        df['Month'] = df['Date'].apply(lambda x: x.strftime('%Y-%m'))  # Extract Year-Month as string
-
-        # Group by month and calculate the total amount spent per month
-        monthly_expenses = df.groupby('Month')['Amount'].sum()
-
-        # Plot monthly spending trends as a line chart
-        fig2 = px.line(
-            monthly_expenses, 
-            x=monthly_expenses.index, 
-            y=monthly_expenses.values, 
-            title="Monthly Expenses", 
-            labels={"x": "Month", "y": "Amount ($)"}
-        )
-        st.plotly_chart(fig2)
-
-        # Default Budget Values
-        default_budgets = {
-            "Groceries": 300,
-            "Rent": 1000,
-            "Utilities": 150,
-            "Entertainment": 100,
-            "Dining": 150,
-            "Transportation": 120,
-        }
-
-        # Sliders for adjusting the monthly budget
-        st.write("Adjust your monthly budget for each category:")
-
-        budgets = {}
-        for category in default_budgets:
-            budgets[category] = st.slider(f"Budget for {category} ($)", 
-                                          min_value=0, 
-                                          max_value=2000, 
-                                          value=default_budgets[category], 
-                                          step=50)
-
-        # Track if any category exceeds its budget
-        df['Budget_Exceeded'] = df.apply(lambda row: row['Amount'] > budgets.get(row['Category'], 0), axis=1)
-
-        # Show which categories exceeded their budgets
-        exceeded_budget = df[df['Budget_Exceeded'] == True]
-        st.write("Categories that exceeded the budget:", exceeded_budget[['Date', 'Category', 'Amount']])
-
-        # Visualization 3: Monthly Spending vs Budget (Bar Chart)
-        # Create a figure explicitly for the bar chart
-        fig3, ax3 = plt.subplots(figsize=(10, 6))  # Create figure and axes
-        monthly_expenses_df = pd.DataFrame({
-            'Actual': monthly_expenses,
-            'Budget': [sum(budgets.values())] * len(monthly_expenses)  # Same budget for simplicity
-        })
-        monthly_expenses_df.plot(kind='bar', ax=ax3)  # Pass the axes to the plot
-        ax3.set_title('Monthly Spending vs Budget')
-        ax3.set_ylabel('Amount ($)')
-
-        # Display the plot with Streamlit
-        st.pyplot(fig3)
+    # Display Dataframe
+    st.write(df.head())
+
+    # Initialize Hugging Face model for zero-shot classification
+    classifier = pipeline('zero-shot-classification', model='distilbert-base-uncased')
+    categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation"]
+
+    # Function to categorize
+    def categorize_expense(description):
+        result = classifier(description, candidate_labels=categories)
+        return result['labels'][0]  # Most probable category
+
+    # Apply categorization
+    df['Category'] = df['Description'].apply(categorize_expense)
+    
+    # Display categorized data
+    st.write("Categorized Data", df)
+
+    # Sidebar for setting the monthly budget using sliders
+    st.sidebar.header("Set Your Monthly Budget")
+    groceries_budget = st.sidebar.slider("Groceries Budget", 0, 1000, 300)
+    rent_budget = st.sidebar.slider("Rent Budget", 0, 5000, 1000)
+    utilities_budget = st.sidebar.slider("Utilities Budget", 0, 500, 150)
+    entertainment_budget = st.sidebar.slider("Entertainment Budget", 0, 1000, 100)
+    dining_budget = st.sidebar.slider("Dining Budget", 0, 1000, 150)
+    transportation_budget = st.sidebar.slider("Transportation Budget", 0, 500, 120)
+
+    # Store the updated budget values
+    budgets = {
+        "Groceries": groceries_budget,
+        "Rent": rent_budget,
+        "Utilities": utilities_budget,
+        "Entertainment": entertainment_budget,
+        "Dining": dining_budget,
+        "Transportation": transportation_budget
+    }
+
+    # Track if any category exceeds its budget
+    df['Budget_Exceeded'] = df.apply(lambda row: row['Amount'] > budgets.get(row['Category'], 0), axis=1)
+
+    # Show categories that exceeded their budget
+    exceeded_budget = df[df['Budget_Exceeded'] == True]
+    st.write("Categories that exceeded the budget:", exceeded_budget[['Date', 'Category', 'Amount']])
+
+    # Visualizations
+
+    # 1. Pie Chart for expense distribution by category
+    category_expenses = df.groupby('Category')['Amount'].sum()
+    fig1 = px.pie(category_expenses, values=category_expenses.values, names=category_expenses.index, title="Expense Distribution by Category")
+    st.plotly_chart(fig1)
+
+    # 2. Monthly Spending Trends (Line Chart)
+    df['Date'] = pd.to_datetime(df['Date'])
+    df['Month'] = df['Date'].dt.to_period('M').astype(str)  # Convert Period to string for Plotly compatibility
+    monthly_expenses = df.groupby('Month')['Amount'].sum()
+
+    fig2 = px.line(monthly_expenses, x=monthly_expenses.index, y=monthly_expenses.values, title="Monthly Expenses", labels={"x": "Month", "y": "Amount ($)"})
+    st.plotly_chart(fig2)
+
+    # 3. Monthly Spending vs Budget (Bar Chart)
+    monthly_expenses_df = pd.DataFrame({
+        'Actual': monthly_expenses,
+        'Budget': [sum(budgets.values())] * len(monthly_expenses)  # Same budget for simplicity
+    })
+
+    fig3 = monthly_expenses_df.plot(kind='bar', figsize=(10, 6))
+    st.pyplot(fig3)