updated

app.py

@@ -1,65 +1,95 @@
 import streamlit as st
 import pandas as pd
-import matplotlib.pyplot as plt
+import plotly.graph_objects as go
+import numpy as np
 
-# App title and description
-st.title("Monetize GHG Emissions Explorer")
-st.write("This application was developed by Daniel Rosehill. Its purpose is to help the user to explore the relationship between companies profitability and their greenhouse gas emissions. Greenhouse gas emissions are monetized at the rate of 236 per ton of carbon dioxide equivalents as proposed in 2023 by the International Foundation for valuing impacts based upon an extensive consultation process informed by the latest scientific evidence.")
+# Set page config
+st.set_page_config(layout="wide", page_title="GHG Emissions Analysis")
 
-# Load data from GitHub URL
-url = "https://raw.githubusercontent.com/danielrosehill/GHG-Emissions-Data-Pipeline/refs/heads/main/company_data.csv"
-data = pd.read_csv(url)
+# Load data
+@st.cache_data
+def load_data():
+    url = "https://raw.githubusercontent.com/danielrosehill/GHG-Emissions-Data-Pipeline/refs/heads/main/company_data.csv"
+    df = pd.read_csv(url)
+    
+    # Calculate total emissions and handle NaN values
+    df['scope_1_emissions'] = pd.to_numeric(df['scope_1_emissions'], errors='coerce').fillna(0)
+    df['scope_2_emissions'] = pd.to_numeric(df['scope_2_emissions'], errors='coerce').fillna(0)
+    df['scope_3_emissions'] = pd.to_numeric(df['scope_3_emissions'], errors='coerce').fillna(0)
+    
+    df['total_emissions'] = df['scope_1_emissions'] + df['scope_2_emissions'] + df['scope_3_emissions']
+    df['monetized_emissions'] = (df['total_emissions'] * 236) / 1000  # Convert to billions
+    df['monetized_emissions'] = df['monetized_emissions'].round(2)
+    
+    # Convert EBITDA to numeric and handle NaN values
+    df['ebitda_2022'] = pd.to_numeric(df['ebitda_2022'], errors='coerce').fillna(0)
+    
+    return df
 
-# Process data
-data['total_emissions'] = data['scope_1_emissions'] + data['scope_2_emissions'] + data['scope_3_emissions']
-data['total_monetized_emissions'] = data['total_emissions'] * 236 / 1000  # in billions of USD
+df = load_data()
 
-# Create sidebar for user input
-st.sidebar.title("Filters")
-sector_options = data['sector'].unique().tolist()
-industry_selection = st.sidebar.multiselect("Select Industry", sector_options, default=sector_options)
+# Sidebar
+st.sidebar.title("Selection Options")
+selection_mode = st.sidebar.radio("Selection Mode", ["Individual Companies", "By Sector"])
 
-# Filter data based on user selection
-filtered_data = data[data['sector'].isin(industry_selection)]
+if selection_mode == "Individual Companies":
+    selected_companies = st.sidebar.multiselect(
+        "Select Companies (max 5)",
+        options=df['company_name'].dropna().unique(),
+        max_selections=5
+    )
+    filtered_df = df[df['company_name'].isin(selected_companies)]
+else:
+    selected_sector = st.sidebar.multiselect(
+        "Select Sectors",
+        options=df['sector'].dropna().unique()
+    )
+    filtered_df = df[df['sector'].isin(selected_sector)]
 
-# Allow user to select up to 5 individual companies
-company_options = filtered_data['company_name'].unique().tolist()
-company_selection = st.sidebar.multiselect("Select Companies (max 5)", company_options, default=company_options[:5])
-if len(company_selection) > 5:
-    st.sidebar.warning("Please select up to 5 companies.")
+# Main content
+st.title("Greenhouse Gas Emissions vs Financial Performance")
 
-# Further filter data based on company selection
-final_data = filtered_data[filtered_data['company_name'].isin(company_selection)]
-
-# Display data table
-st.write("### Data Table")
-st.dataframe(final_data[['company_name', 'ebitda_2022', 'total_monetized_emissions']])
-
-# Plot bar chart
-fig, ax = plt.subplots(figsize=(12, 6))
-bar_width = 0.35
-index = range(len(final_data))
-
-# Plot profitability (positive values)
-bars1 = ax.bar(index, final_data['ebitda_2022'], bar_width, label='Profitability', color='green')
-
-# Plot monetized emissions (negative values)
-bars2 = ax.bar([p + bar_width for p in index], -final_data['total_monetized_emissions'], bar_width, label='Monetized Emissions', color='red')
-
-# Add labels and title
-ax.set_xlabel('Company')
-ax.set_ylabel('Values')
-ax.set_title('Profitability vs Monetized Emissions')
-ax.set_xticks([p + bar_width / 2 for p in index])
-ax.set_xticklabels(final_data['company_name'], rotation=45, ha='right')
-ax.legend()
-
-# Display the plot
-st.write("### Visualization")
-st.pyplot(fig)
-
-# Calculate and display correlation
-correlation = final_data['ebitda_2022'].corr(final_data['total_monetized_emissions'])
-st.write("### Correlation Calculation")
-st.write(f"The correlation between profitability and monetized emissions is: {correlation:.2f}")
-st.write("A negative correlation indicates that companies are less profitable if they emit more.")
+if not filtered_df.empty:
+    # Create visualization
+    fig = go.Figure()
+    
+    # Add EBITDA bars
+    fig.add_trace(go.Bar(
+        x=filtered_df['company_name'],
+        y=filtered_df['ebitda_2022'],
+        name='EBITDA',
+        marker_color='green'
+    ))
+    
+    # Add monetized emissions bars
+    fig.add_trace(go.Bar(
+        x=filtered_df['company_name'],
+        y=-filtered_df['monetized_emissions'],
+        name='Monetized Emissions',
+        marker_color='red'
+    ))
+    
+    fig.update_layout(
+        barmode='relative',
+        title='EBITDA vs Monetized Emissions (Billions USD)',
+        yaxis_title='Billions USD',
+        height=600,
+        showlegend=True,
+        xaxis_tickangle=-45
+    )
+    
+    st.plotly_chart(fig, use_container_width=True)
+    
+    # Calculate correlation
+    valid_data = filtered_df[['ebitda_2022', 'monetized_emissions']].dropna()
+    if len(valid_data) > 1:  # Need at least 2 points for correlation
+        correlation = np.corrcoef(valid_data['ebitda_2022'], valid_data['monetized_emissions'])[0,1]
+        st.write(f"Correlation between EBITDA and Monetized Emissions: {correlation:.2f}")
+    
+    # Display data table
+    st.subheader("Data Table")
+    display_df = filtered_df[['company_name', 'sector', 'ebitda_2022', 'monetized_emissions']]
+    display_df.columns = ['Company', 'Sector', 'EBITDA (Billions USD)', 'Monetized Emissions (Billions USD)']
+    st.dataframe(display_df)
+else:
+    st.write("Please select companies or sectors to visualize data")