Add Canadian Parliamentary Expenditures Explorer app

This Gradio app provides an interactive dashboard to explore and analyze
Canadian House of Commons expenditure data from 2021-2025, with filters
for year, party, and category, plus visualizations and search capabilities.

README.md

@@ -1,12 +1,31 @@
 ---
-title: ParliamentExpenditureSpace
-emoji: ⚡
-colorFrom: gray
-colorTo: indigo
+title: Canadian Parliamentary Expenditures Explorer
+emoji: 🍁
+colorFrom: red
+colorTo: yellow
 sdk: gradio
 sdk_version: 5.39.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Canadian Parliamentary Expenditures Explorer
+
+An interactive dashboard for exploring Canadian House of Commons expenditure data.
+
+## Features
+
+- 📊 Interactive visualizations of parliamentary spending patterns
+- 🔍 Filter by year, party, and expense category
+- 👥 Analyze spending by individual members of parliament
+- 📈 View spending trends over time
+- 🎯 Search and explore specific member expenses
+
+## Dataset
+
+This application uses the [Canadian Parliamentary Expenditures dataset](https://huggingface.co/datasets/irf23/canadian-parliamentary-expenditures), which contains:
+- 1.2+ million expenditure records
+- Data from 2021 Q2 to 2025 Q4
+- 450 parliament members
+- Categories: Travel, Hospitality, Contract, and Other

app.py

@@ -0,0 +1,270 @@
+import gradio as gr
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from datasets import load_dataset
+
+# Load the dataset
+print("Loading dataset...")
+dataset = load_dataset("irf23/canadian-parliamentary-expenditures")
+
+# Convert to pandas DataFrames
+expenditures_df = dataset['expenditures'].to_pandas()
+members_df = dataset['members'].to_pandas()
+
+# Convert date columns
+expenditures_df['date_incurred'] = pd.to_datetime(expenditures_df['date_incurred'])
+expenditures_df['amount'] = pd.to_numeric(expenditures_df['amount'])
+
+print(f"Loaded {len(expenditures_df)} expenditure records")
+
+def create_overview_plots(year_filter, party_filter, category_filter):
+    # Apply filters
+    filtered_df = expenditures_df.copy()
+    if year_filter:
+        filtered_df = filtered_df[filtered_df['period_year'].isin(year_filter)]
+    if party_filter:
+        filtered_df = filtered_df[filtered_df['party'].isin(party_filter)]
+    if category_filter:
+        filtered_df = filtered_df[filtered_df['category'].isin(category_filter)]
+    
+    # Calculate metrics
+    total_spending = filtered_df['amount'].sum()
+    num_records = len(filtered_df)
+    avg_expense = filtered_df['amount'].mean()
+    num_members = filtered_df['member_id'].nunique()
+    
+    metrics_text = f"""
+    ### Key Metrics
+    - **Total Spending**: ${total_spending:,.2f}
+    - **Number of Records**: {num_records:,}
+    - **Average Expense**: ${avg_expense:,.2f}
+    - **Active Members**: {num_members}
+    """
+    
+    # Create spending by category pie chart
+    category_spending = filtered_df.groupby('category')['amount'].sum().reset_index()
+    fig_category = px.pie(
+        category_spending,
+        values='amount',
+        names='category',
+        title='Spending by Category'
+    )
+    
+    # Create spending by party bar chart
+    party_spending = filtered_df.groupby('party')['amount'].sum().sort_values(ascending=False).reset_index()
+    fig_party = px.bar(
+        party_spending,
+        x='party',
+        y='amount',
+        title='Total Spending by Party',
+        labels={'amount': 'Total Amount ($)', 'party': 'Party'}
+    )
+    
+    # Create quarterly trend line chart
+    quarterly = filtered_df.groupby(['period_year', 'period_quarter'])['amount'].sum().reset_index()
+    quarterly['period'] = quarterly['period_year'].astype(str) + '-Q' + quarterly['period_quarter'].astype(str)
+    fig_trend = px.line(
+        quarterly,
+        x='period',
+        y='amount',
+        title='Quarterly Spending Trend',
+        labels={'amount': 'Total Amount ($)', 'period': 'Period'},
+        markers=True
+    )
+    
+    return metrics_text, fig_category, fig_party, fig_trend
+
+def get_top_spenders(n_top, year_filter, party_filter, category_filter):
+    # Apply filters
+    filtered_df = expenditures_df.copy()
+    if year_filter:
+        filtered_df = filtered_df[filtered_df['period_year'].isin(year_filter)]
+    if party_filter:
+        filtered_df = filtered_df[filtered_df['party'].isin(party_filter)]
+    if category_filter:
+        filtered_df = filtered_df[filtered_df['category'].isin(category_filter)]
+    
+    # Get top spenders
+    top_spenders = filtered_df.groupby(['member_name', 'party'])['amount'].sum().sort_values(ascending=False).head(n_top).reset_index()
+    
+    fig = px.bar(
+        top_spenders,
+        x='amount',
+        y='member_name',
+        color='party',
+        orientation='h',
+        title=f'Top {n_top} Spenders',
+        labels={'amount': 'Total Amount ($)', 'member_name': 'Member'},
+        height=max(400, n_top * 25)
+    )
+    fig.update_layout(yaxis={'categoryorder': 'total ascending'})
+    
+    return fig
+
+def analyze_member(member_name):
+    if not member_name:
+        return "Please select a member", None
+    
+    member_df = expenditures_df[expenditures_df['member_name'] == member_name]
+    
+    if member_df.empty:
+        return "No data found for this member", None
+    
+    # Calculate metrics
+    total = member_df['amount'].sum()
+    count = len(member_df)
+    avg = member_df['amount'].mean()
+    party = member_df['party'].iloc[0]
+    
+    info = f"""
+    ### {member_name} ({party})
+    - **Total Expenses**: ${total:,.2f}
+    - **Number of Expenses**: {count:,}
+    - **Average Expense**: ${avg:,.2f}
+    """
+    
+    # Create category breakdown
+    category_breakdown = member_df.groupby('category')['amount'].sum().reset_index()
+    fig = px.pie(
+        category_breakdown,
+        values='amount',
+        names='category',
+        title=f'Expense Categories for {member_name}'
+    )
+    
+    return info, fig
+
+def search_expenses(member_search, min_amount, max_amount, category_filter):
+    filtered_df = expenditures_df.copy()
+    
+    if member_search:
+        filtered_df = filtered_df[filtered_df['member_name'].str.contains(member_search, case=False, na=False)]
+    
+    filtered_df = filtered_df[(filtered_df['amount'] >= min_amount) & (filtered_df['amount'] <= max_amount)]
+    
+    if category_filter and category_filter != "All":
+        filtered_df = filtered_df[filtered_df['category'] == category_filter]
+    
+    # Get top 100 results
+    result = filtered_df.nlargest(100, 'amount')[['member_name', 'party', 'category', 'amount', 'description', 'supplier', 'date_incurred']]
+    
+    return result
+
+# Get unique values for filters
+years = sorted(expenditures_df['period_year'].unique().tolist())
+parties = sorted(expenditures_df['party'].unique().tolist())
+categories = sorted(expenditures_df['category'].unique().tolist())
+member_names = sorted(expenditures_df['member_name'].unique().tolist())
+
+# Create Gradio interface
+with gr.Blocks(title="Canadian Parliamentary Expenditures", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🍁 Canadian Parliamentary Expenditures Explorer")
+    gr.Markdown("Explore spending data from the Canadian House of Commons (2021-2025)")
+    
+    # Filters
+    with gr.Row():
+        year_filter = gr.CheckboxGroup(
+            choices=years,
+            value=years[-2:],
+            label="Select Years"
+        )
+        party_filter = gr.CheckboxGroup(
+            choices=parties,
+            value=parties,
+            label="Select Parties"
+        )
+        category_filter = gr.CheckboxGroup(
+            choices=categories,
+            value=categories,
+            label="Select Categories"
+        )
+    
+    # Overview Tab
+    with gr.Tab("Overview"):
+        overview_btn = gr.Button("Update Overview", variant="primary")
+        metrics_display = gr.Markdown()
+        
+        with gr.Row():
+            category_plot = gr.Plot()
+            party_plot = gr.Plot()
+        
+        trend_plot = gr.Plot()
+        
+        overview_btn.click(
+            create_overview_plots,
+            inputs=[year_filter, party_filter, category_filter],
+            outputs=[metrics_display, category_plot, party_plot, trend_plot]
+        )
+    
+    # Top Spenders Tab
+    with gr.Tab("Top Spenders"):
+        n_slider = gr.Slider(10, 50, value=20, step=5, label="Number of top spenders")
+        spenders_btn = gr.Button("Show Top Spenders", variant="primary")
+        spenders_plot = gr.Plot()
+        
+        spenders_btn.click(
+            get_top_spenders,
+            inputs=[n_slider, year_filter, party_filter, category_filter],
+            outputs=spenders_plot
+        )
+    
+    # Member Analysis Tab
+    with gr.Tab("Member Analysis"):
+        member_dropdown = gr.Dropdown(
+            choices=member_names,
+            label="Select a Member",
+            searchable=True
+        )
+        member_info = gr.Markdown()
+        member_plot = gr.Plot()
+        
+        member_dropdown.change(
+            analyze_member,
+            inputs=member_dropdown,
+            outputs=[member_info, member_plot]
+        )
+    
+    # Search Tab
+    with gr.Tab("Search Expenses"):
+        with gr.Row():
+            search_member = gr.Textbox(label="Member Name (partial match)", placeholder="e.g., Trudeau")
+            search_category = gr.Dropdown(
+                choices=["All"] + categories,
+                value="All",
+                label="Category"
+            )
+        
+        with gr.Row():
+            min_amount_input = gr.Number(value=0, label="Minimum Amount ($)")
+            max_amount_input = gr.Number(value=1000000, label="Maximum Amount ($)")
+        
+        search_btn = gr.Button("Search", variant="primary")
+        results_table = gr.Dataframe(
+            headers=["Member", "Party", "Category", "Amount", "Description", "Supplier", "Date"],
+            datatype=["str", "str", "str", "number", "str", "str", "str"]
+        )
+        
+        search_btn.click(
+            search_expenses,
+            inputs=[search_member, min_amount_input, max_amount_input, search_category],
+            outputs=results_table
+        )
+    
+    # Footer
+    gr.Markdown("""
+    ---
+    **Data Source**: Canadian House of Commons  
+    **Dataset**: [irf23/canadian-parliamentary-expenditures](https://huggingface.co/datasets/irf23/canadian-parliamentary-expenditures)  
+    **License**: CC0-1.0 (Public Domain)
+    """)
+    
+    # Load initial overview
+    demo.load(
+        create_overview_plots,
+        inputs=[year_filter, party_filter, category_filter],
+        outputs=[metrics_display, category_plot, party_plot, trend_plot]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+pandas==2.2.0
+plotly==5.19.0
+datasets==2.17.0
+pyarrow>=10.0.0