Update app.py

app.py

@@ -5,66 +5,40 @@ import matplotlib.pyplot as plt
 from transformers import pipeline
 import plotly.express as px
 
-# Initialize the Hugging Face model for expense categorization
+# Initialize the Hugging Face model for expense categorization (use zero-shot classification)
 expense_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 
-# Function to categorize expenses
+# 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]
 
 # Function to process the uploaded CSV and generate visualizations
 def process_expenses(file):
+    # Read CSV data
     df = pd.read_csv(file.name)
-
-    # Check required columns
+    
+    # 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."
 
-    # Categorize the expenses
+    # Categorize the expenses (using batch processing to minimize model calls)
     df['Category'] = categorize_transaction_batch(df['Description'].tolist())
 
-    # Pie chart for Category-wise spending
+    # 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")
     
-    # Monthly spending trends (Line plot)
+    # 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")
     
-    # Budget vs Actual Spending (Bar chart)
+    # 3. Budget vs Actual Spending (Bar chart)
     category_list = df['Category'].unique()
-    budget_dict = {category: 500 for category in category_list}  # Set default budget of 500 for each category
+    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")
-
-    # Suggested savings
-    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
-
-# 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")
-]
-
-# 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()  # Correct method name: launch() instead of launc
+    fig3 = px.bar(budget_df, x=budget_df.index, y=["Budget", "Actual"], title=