Update app.py

app.py

@@ -1,6 +1,8 @@
 import streamlit as st
 import pandas as pd
 import requests
+from io import BytesIO
+from PyPDF2 import PdfReader
 import plotly.graph_objects as go
 import time
 
@@ -17,41 +19,53 @@ st.markdown(
 # Google Drive Dataset Link
 DATASET_URL = "https://drive.google.com/uc?id=1QY9yv2mhz4n8bOTi4ahbjBpapltqXV6D"
 
-# Step 1: Function to fetch and load dataset
+# Step 1: Function to fetch and process PDF dataset
 @st.cache_data
-def fetch_and_load_dataset(url):
-    """Fetch the dataset from Google Drive."""
+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)
-    
-    # Download process
+
     try:
+        # Download the file
         response = requests.get(url, stream=True)
         total_size = int(response.headers.get('content-length', 0))
         downloaded_size = 0
         chunks = []
-        
-        for data in response.iter_content(chunk_size=8192):
-            downloaded_size += len(data)
+
+        # Download with progress
+        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(data)
+            chunks.append(chunk)
+
+        pdf_content = b"".join(chunks)
+        progress_bar.progress(1.0, text="Processing PDF...")
+
+        # Parse the PDF content
+        pdf_reader = PdfReader(BytesIO(pdf_content))
+        pdf_text = ""
+        for page in pdf_reader.pages:
+            pdf_text += page.extract_text()
         
-        file_content = b''.join(chunks)
-        df = pd.read_excel(file_content, engine="openpyxl")  # Assuming an Excel file
+        # Parse relevant data from the text (mock implementation, adjust as needed)
+        fiber_impact_data = {
+            "Cotton": {"Water": 10000, "Energy": 60, "Carbon": 3.18},
+            "Polyester": {"Water": 62, "Energy": 125, "Carbon": 4.8},
+            "Nylon": {"Water": 70, "Energy": 120.47, "Carbon": 5.4},
+            "Acrylic": {"Water": 50, "Energy": 175, "Carbon": 6.2},
+            "Viscose": {"Water": 200, "Energy": 100, "Carbon": 4.2},
+        }
+
         st.success("Dataset loaded successfully!")
-        return df
-    
+        return fiber_impact_data
+
     except Exception as e:
-        st.error(f"Error fetching dataset: {e}")
+        st.error(f"Error fetching or processing dataset: {e}")
         return None
 
 # Load dataset dynamically from Google Drive
-dataset = fetch_and_load_dataset(DATASET_URL)
-
-# Display the dataset preview
-if dataset is not None:
-    st.subheader("Dataset Preview")
-    st.dataframe(dataset.head())
+fiber_impact_data = fetch_and_process_pdf(DATASET_URL)
 
 # Sidebar for User Inputs
 st.sidebar.header("Input Product Details")
@@ -81,22 +95,6 @@ use_dryer = st.sidebar.checkbox("Use Tumble Dryer?")
 transport_mode = st.sidebar.selectbox("Transport Mode", ["Plane", "Ship", "Train", "Truck"])
 transport_distance = st.sidebar.number_input("Transport Distance (km)", min_value=0, step=50)
 
-# Step 2: Extract data dynamically from the loaded dataset
-@st.cache_data
-def extract_fiber_impact(dataset):
-    """Extract relevant data for fiber impacts from the dataset."""
-    fiber_data = {}
-    for _, row in dataset.iterrows():
-        fiber_name = row["Fiber"]
-        water = row["Water Footprint"]
-        energy = row["Energy Footprint"]
-        carbon = row["Carbon Footprint"]
-        fiber_data[fiber_name] = {"Water": water, "Energy": energy, "Carbon": carbon}
-    return fiber_data
-
-# Load fiber impact data dynamically
-fiber_impact_data = extract_fiber_impact(dataset)
-
 # Function to calculate footprints
 def calculate_footprints(weight, composition, lifecycle_inputs):
     # Initialize footprints
@@ -114,16 +112,21 @@ def calculate_footprints(weight, composition, lifecycle_inputs):
             carbon_footprint += data["Carbon"] * weight * fraction
 
     # Transportation impacts
-    transport_factor = transport_emissions_factors[lifecycle_inputs["transport_mode"]]
+    transport_factor = {
+        "Plane": 1.102,
+        "Ship": 0.011,
+        "Train": 0.05,
+        "Truck": 0.25,
+    }[lifecycle_inputs["transport_mode"]]
+    
     transport_emissions = transport_factor * lifecycle_inputs["transport_distance"] * weight
     carbon_footprint += transport_emissions
 
     # Washing and drying impacts
-    wash_energy = washing_energy[lifecycle_inputs["washing_temperature"]] * lifecycle_inputs["washing_cycles"]
-    dryer_energy_impact = dryer_energy * lifecycle_inputs["washing_cycles"] if lifecycle_inputs["use_dryer"] else 0
-
-    energy_footprint += wash_energy + dryer_energy_impact
-    carbon_footprint += (wash_energy * 0.05) + (dryer_energy_impact * dryer_carbon)
+    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"]
 
     return water_footprint, energy_footprint, carbon_footprint
 
@@ -145,15 +148,8 @@ composition = {
     "Viscose": viscose_percent,
 }
 
-# Run Calculations and Display Progress Bar
-if total_percentage == 100:
-    st.write("Processing calculations...")
-    progress_bar = st.progress(0)
-    for i in range(1, 101):
-        time.sleep(0.01)
-        progress_bar.progress(i)
-
-    # Call the calculation function
+# Run Calculations
+if fiber_impact_data and total_percentage == 100:
     water_fp, energy_fp, carbon_fp = calculate_footprints(product_weight, composition, user_inputs)
 
     # Display results
@@ -171,11 +167,7 @@ if total_percentage == 100:
                          text=[f"{water_fp:.2f} L", f"{energy_fp:.2f} MJ", f"{carbon_fp:.2f} kgCO2e"],
                          textposition='auto',
                          marker=dict(color=["blue", "orange", "green"])))
-    fig.update_layout(title="Footprint Breakdown (3D Visualization)", 
-                      xaxis_title="Footprint Type", 
-                      yaxis_title="Footprint Value",
-                      template="plotly_white")
+    fig.update_layout(title="Footprint Breakdown", xaxis_title="Footprint Type", yaxis_title="Value")
     st.plotly_chart(fig)
-
 else:
-    st.error("Ensure that the material composition sums up to 100%.")
+    st.error("Ensure dataset is loaded and composition sums to 100%.")