Update app.py

app.py

@@ -2,15 +2,15 @@ import pandas as pd
 import plotly.express as px
 import streamlit as st
 from transformers import pipeline
-import matplotlib.pyplot as plt
+import datetime
 
-# Function to add custom background image from a URL
+# Function to add background image to the app
 def add_bg_from_url(image_url):
     st.markdown(
         f"""
         <style>
         .stApp {{
-            background-image: url("{image_url}");
+            background-image: url({image_url});
             background-size: cover;
             background-position: center center;
             background-repeat: no-repeat;
@@ -20,23 +20,26 @@ def add_bg_from_url(image_url):
         unsafe_allow_html=True
     )
 
-# Add the background image using the provided URL
-background_image_url = 'https://huggingface.co/spaces/engralimalik/Smart-Expense-Tracker/resolve/main/top-view-finance-business-elements.jpg'
-add_bg_from_url(background_image_url)
+# Set background image (it will remain even after file upload)
+add_bg_from_url('https://huggingface.co/spaces/engralimalik/Smart-Expense-Tracker/resolve/main/colorful-abstract-textured-background-design.jpg')
 
 # File upload
 uploaded_file = st.file_uploader("Upload your expense CSV file", type=["csv"])
 if uploaded_file:
     df = pd.read_csv(uploaded_file)
 
-    # Display Dataframe
+    # Display first few rows to the user for format verification
+    st.write("Here are the first few entries in your file for format verification:")
     st.write(df.head())
 
-    # Initialize Hugging Face model for zero-shot classification (using a better model like roberta-large-mnli)
+    # Ensure 'Amount' is numeric
+    df['Amount'] = pd.to_numeric(df['Amount'], errors='coerce')
+
+    # Initialize Hugging Face model for zero-shot classification
     classifier = pipeline('zero-shot-classification', model='roberta-large-mnli')
     categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation"]
 
-    # Function to categorize expenses based on the description
+    # Function to categorize
     def categorize_expense(description):
         result = classifier(description, candidate_labels=categories)
         return result['labels'][0]  # Most probable category
@@ -44,9 +47,6 @@ if uploaded_file:
     # 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)
@@ -66,37 +66,49 @@ if uploaded_file:
         "Transportation": transportation_budget
     }
 
+    # Add a date slider for start and end date (default is the last month)
+    today = datetime.date.today()
+    last_month = today - pd.DateOffset(months=1)
+    start_date = st.sidebar.date_input("Start Date", last_month)
+    end_date = st.sidebar.date_input("End Date", today)
+
+    # Filter data by date range
+    df['Date'] = pd.to_datetime(df['Date'])
+    df_filtered = df[(df['Date'] >= pd.to_datetime(start_date)) & (df['Date'] <= pd.to_datetime(end_date))]
+
     # Track if any category exceeds its budget
-    df['Budget_Exceeded'] = df.apply(lambda row: row['Amount'] > budgets.get(row['Category'], 0), axis=1)
+    df_filtered['Budget_Exceeded'] = df_filtered.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]
+    exceeded_budget = df_filtered[df_filtered['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()
+    category_expenses = df_filtered.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()
+    df_filtered['Month'] = df_filtered['Date'].dt.to_period('M').astype(str)  # Convert Period to string for Plotly compatibility
+    monthly_expenses = df_filtered.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 ($)"})
-    st.plotly_chart(fig2)
+    # Convert monthly_expenses into DataFrame for correct plotting
+    monthly_expenses_df = monthly_expenses.reset_index()
+    if not monthly_expenses_df.empty:
+        fig2 = px.line(monthly_expenses_df, x='Month', y='Amount', title="Monthly Expenses", labels={"Month": "Month", "Amount": "Amount ($)"})
+        st.plotly_chart(fig2)
+    else:
+        st.write("No data to display for the selected date range.")
 
     # 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
-    })
-
-    # Create a matplotlib figure for the bar chart
-    fig3, ax = plt.subplots(figsize=(10, 6))
-    monthly_expenses_df.plot(kind='bar', ax=ax)
-    ax.set_title('Monthly Spending vs Budget')
-    ax.set_ylabel('Amount ($)')
-    st.pyplot(fig3)
+    if not monthly_expenses_df.empty:
+        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)
+    else:
+        st.write("No data to display for the selected date range.")