Update app.py

app.py

@@ -7,6 +7,8 @@ import plotly.graph_objects as go
 
 # Set Page Configurations
 st.set_page_config(page_title="GreenLens-AI", layout="wide")
+
+# Page title and description
 st.markdown("<h1 style='text-align: center; color: #4CAF50;'>GreenLens-AI</h1>", unsafe_allow_html=True)
 st.markdown(
     """
@@ -16,63 +18,60 @@ st.markdown(
     """, unsafe_allow_html=True)
 
 # Google Drive Dataset Link
-DATASET_URL = "https://drive.google.com/uc?id=1JMECXBOPU5UD9hdEUA0uv1g_Qm1CkWYn"
+DATASET_URL = "https://drive.google.com/file/d/1JMECXBOPU5UD9hdEUA0uv1g_Qm1CkWYn/view?usp=drive_link"
 
 # Step 1: Function to fetch and process PDF dataset
 @st.cache_data
 def fetch_and_process_pdf(url):
-    """Fetch the PDF dataset from Google Drive and process it."""
-    progress_text = "Fetching dataset from Google Drive..."
-    progress_bar = st.progress(0)
-
+    """Fetch and extract required data from the PDF dataset."""
     try:
+        # Log start of fetching
+        st.info("Fetching dataset from Google Drive...")
+        
         # Download the file
         response = requests.get(url, stream=True)
-        total_size = int(response.headers.get('content-length', 0))
-        downloaded_size = 0
-        chunks = []
-
-        for chunk in response.iter_content(chunk_size=8192):
-            downloaded_size += len(chunk)
-            progress_bar.progress(min(1.0, downloaded_size / total_size), text=progress_text)
-            chunks.append(chunk)
-
-        pdf_content = b"".join(chunks)
-        progress_bar.progress(1.0, text="Processing PDF...")
+        if response.status_code != 200:
+            raise Exception("Failed to download the file. Check the URL or permissions.")
+        
+        pdf_content = BytesIO(response.content)
 
         # Parse the PDF content
-        pdf_reader = PdfReader(BytesIO(pdf_content))
+        st.info("Processing the PDF file...")
+        pdf_reader = PdfReader(pdf_content)
         pdf_text = ""
         for page in pdf_reader.pages:
-            pdf_text += page.extract_text()
+            pdf_text += page.extract_text().strip()  # Extract and clean text
+
+        # Log extracted text for debugging
+        st.write("Extracted Text from PDF:", pdf_text[:500])  # Show first 500 characters for verification
 
-        # Extract necessary data dynamically from the PDF text
-        # Assume the PDF contains data structured like this:
-        # "FIBER_NAME, WATER (L/kg), ENERGY (MJ/kg), CARBON (kgCO2e/kg)"
+        # Extract necessary data from the text
+        # Expected format: "FIBER_NAME, WATER (L/kg), ENERGY (MJ/kg), CARBON (kgCO2e/kg)"
         lines = pdf_text.split("\n")
         fiber_impact_data = {}
         for line in lines:
             parts = line.split(",")
-            if len(parts) == 4:  # Ensure line is properly formatted
-                fiber, water, energy, carbon = parts
+            if len(parts) == 4:  # Ensure proper format
+                fiber, water, energy, carbon = map(str.strip, parts)
                 try:
-                    fiber_impact_data[fiber.strip()] = {
-                        "Water": float(water.strip()),
-                        "Energy": float(energy.strip()),
-                        "Carbon": float(carbon.strip()),
+                    fiber_impact_data[fiber] = {
+                        "Water": float(water),
+                        "Energy": float(energy),
+                        "Carbon": float(carbon),
                     }
                 except ValueError:
-                    # Skip lines that don't have valid numerical data
+                    st.warning(f"Invalid data format in line: {line}")
                     continue
 
-        st.success("Dataset loaded successfully!")
+        # Log parsed dataset
+        st.write("Parsed Fiber Impact Data:", fiber_impact_data)
         return fiber_impact_data
 
     except Exception as e:
-        st.error(f"Error fetching or processing dataset: {e}")
+        st.error(f"Error loading or processing the PDF: {e}")
         return None
 
-# Load dataset dynamically from Google Drive
+# Load dataset dynamically
 fiber_impact_data = fetch_and_process_pdf(DATASET_URL)
 
 # Sidebar for User Inputs
@@ -95,6 +94,8 @@ total_percentage = cotton_percent + polyester_percent + nylon_percent + acrylic_
 if total_percentage != 100:
     st.sidebar.error("The total of all fiber percentages must equal 100%!")
 
+st.sidebar.write(f"Total Material Percentage: {total_percentage}%")  # Debugging sidebar inputs
+
 # Lifecycle Inputs
 st.sidebar.header("Lifecycle Details")
 washing_cycles = st.sidebar.number_input("Number of Washing Cycles", min_value=0, step=10, value=30)
@@ -105,48 +106,51 @@ transport_distance = st.sidebar.number_input("Transport Distance (km)", min_valu
 
 # Function to calculate footprints
 def calculate_footprints(weight, composition, lifecycle_inputs):
-    st.write("Inputs to calculate_footprints:", weight, composition, lifecycle_inputs)  # Log inputs for debugging
-
-    # Initialize footprints
-    water_footprint = 0
-    energy_footprint = 0
-    carbon_footprint = 0
-
-    # Fiber contributions
-    for fiber, percentage in composition.items():
-        if fiber in fiber_impact_data:
-            data = fiber_impact_data[fiber]
-            st.write(f"Processing {fiber} with percentage {percentage}%")  # Debugging
-            fraction = percentage / 100
-            water_footprint += data["Water"] * weight * fraction
-            energy_footprint += data["Energy"] * weight * fraction
-            carbon_footprint += data["Carbon"] * weight * fraction
-
-    st.write("Footprints after fiber contributions:", water_footprint, energy_footprint, carbon_footprint)  # Debug
-
-    # Transportation impacts
-    transport_factor = {
-        "Plane": 1.102,
-        "Ship": 0.011,
-        "Train": 0.05,
-        "Truck": 0.25,
-    }.get(lifecycle_inputs["transport_mode"], 0)
-    transport_emissions = transport_factor * lifecycle_inputs["transport_distance"] * weight
-    carbon_footprint += transport_emissions
-
-    st.write("Carbon footprint after transport:", carbon_footprint)  # Debug
-
-    # Washing and drying impacts
-    washing_energy = {"Cold": 0.02, "30°C": 0.1, "40°C": 0.2, "60°C": 0.5}
-    dryer_energy = 0.5 if lifecycle_inputs["use_dryer"] else 0
-    carbon_footprint += (
-        washing_energy[lifecycle_inputs["washing_temperature"]] * lifecycle_inputs["washing_cycles"] * 0.05
-    )
-    energy_footprint += dryer_energy * lifecycle_inputs["washing_cycles"]
-
-    st.write("Final footprints:", water_footprint, energy_footprint, carbon_footprint)  # Debug
-
-    return water_footprint, energy_footprint, carbon_footprint
+    """Calculate water, energy, and carbon footprints."""
+    try:
+        # Log inputs
+        st.write("Inputs to function:", weight, composition, lifecycle_inputs)
+
+        # Initialize footprints
+        water_footprint = 0
+        energy_footprint = 0
+        carbon_footprint = 0
+
+        # Fiber contributions
+        for fiber, percentage in composition.items():
+            if fiber in fiber_impact_data:
+                data = fiber_impact_data[fiber]
+                fraction = percentage / 100
+                water_footprint += data["Water"] * weight * fraction
+                energy_footprint += data["Energy"] * weight * fraction
+                carbon_footprint += data["Carbon"] * weight * fraction
+            else:
+                st.warning(f"No data found for fiber: {fiber}")
+
+        # Transportation impacts
+        transport_factor = {
+            "Plane": 1.102,
+            "Ship": 0.011,
+            "Train": 0.05,
+            "Truck": 0.25,
+        }.get(lifecycle_inputs["transport_mode"], 0)
+        carbon_footprint += transport_factor * lifecycle_inputs["transport_distance"] * weight
+
+        # Washing and drying impacts
+        washing_energy = {"Cold": 0.02, "30°C": 0.1, "40°C": 0.2, "60°C": 0.5}
+        dryer_energy = 0.5 if lifecycle_inputs["use_dryer"] else 0
+        carbon_footprint += (
+            washing_energy[lifecycle_inputs["washing_temperature"]] * lifecycle_inputs["washing_cycles"] * 0.05
+        )
+        energy_footprint += dryer_energy * lifecycle_inputs["washing_cycles"]
+
+        # Log final results
+        st.write("Calculated Results:", water_footprint, energy_footprint, carbon_footprint)
+        return water_footprint, energy_footprint, carbon_footprint
+
+    except Exception as e:
+        st.error(f"Error in calculations: {e}")
+        return None, None, None
 
 # User inputs as a dictionary
 user_inputs = {
@@ -166,11 +170,11 @@ composition = {
     "Viscose": viscose_percent,
 }
 
-# Run Calculations
-try:
-    if fiber_impact_data and total_percentage == 100:
-        water_fp, energy_fp, carbon_fp = calculate_footprints(product_weight, composition, user_inputs)
+# Run Calculations if conditions are met
+if fiber_impact_data and total_percentage == 100:
+    water_fp, energy_fp, carbon_fp = calculate_footprints(product_weight, composition, user_inputs)
 
+    if water_fp is not None:
         # Display results
         st.subheader("Calculated Results")
         st.markdown(f"""
@@ -190,7 +194,5 @@ try:
         ))
         fig.update_layout(title="Footprint Breakdown", xaxis_title="Footprint Type", yaxis_title="Value")
         st.plotly_chart(fig)
-    else:
-        st.error("Ensure dataset is loaded and the composition sums to 100%.")
-except Exception as e:
-    st.error(f"An error occurred during calculations: {e}")
+else:
+    st.error("Ensure dataset is loaded and the composition sums to 100%.")