Update app.py

app.py

@@ -1,89 +1,84 @@
 import streamlit as st
 import pandas as pd
-import plotly.express as px
 import requests
 from io import BytesIO
 from PyPDF2 import PdfReader
+import plotly.graph_objects as go
 
 # Set Page Configurations
 st.set_page_config(page_title="GreenLens-AI", layout="wide")
-
-# Custom Styling for the App
+st.markdown("<h1 style='text-align: center; color: #4CAF50;'>GreenLens-AI</h1>", unsafe_allow_html=True)
 st.markdown(
     """
-    <style>
-    body {
-        background-color: #d4edda; /* Light green background */
-    }
-    .stSlider > div {
-        background-color: #50C878 !important; /* Green slider bar */
-    }
-    h1, h2, p {
-        text-align: center;
-        color: #4CAF50;
-    }
-    </style>
-    """,
-    unsafe_allow_html=True
-)
-
-# Title and Tagline
-st.markdown("<h1>GreenLens-AI</h1>", unsafe_allow_html=True)
-st.markdown("<p>A Sustainable Tool for Calculating Carbon, Energy, and Ecological Footprints 🌱</p>", unsafe_allow_html=True)
+    <p style='text-align: center; color: #4CAF50; font-size: 18px;'>
+    A Comprehensive Tool for Calculating Water, Energy, and Carbon Footprints of Textile Products 🌍
+    </p>
+    """, unsafe_allow_html=True)
 
 # Google Drive Dataset Link
-DATASET_URL = "https://drive.google.com/uc?id=1QY9yv2mhz4n8bOTi4ahbjBpapltqXV6D"
-
-# Function to fetch dataset from Google Drive
-def fetch_pdf_from_drive(url):
-    """Fetch the dataset (PDF) from Google Drive."""
-    st.info("Downloading dataset from Google Drive...")
-    response = requests.get(url, stream=True)
-    if response.status_code == 200:
+DATASET_URL = "https://drive.google.com/uc?id=1JMECXBOPU5UD9hdEUA0uv1g_Qm1CkWYn"
+
+# 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)
+
+    try:
+        # Download the file
+        response = requests.get(url, stream=True)
         total_size = int(response.headers.get('content-length', 0))
         downloaded_size = 0
         chunks = []
 
-        with st.spinner("Fetching dataset..."):
-            for chunk in response.iter_content(chunk_size=8192):
-                downloaded_size += len(chunk)
-                chunks.append(chunk)
+        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)
-        st.success("Dataset downloaded successfully!")
-        return PdfReader(BytesIO(pdf_content))
-    else:
-        st.error("Failed to fetch dataset. Please check the URL or your internet connection.")
+        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()
+
+        # 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)"
+        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
+                try:
+                    fiber_impact_data[fiber.strip()] = {
+                        "Water": float(water.strip()),
+                        "Energy": float(energy.strip()),
+                        "Carbon": float(carbon.strip()),
+                    }
+                except ValueError:
+                    # Skip lines that don't have valid numerical data
+                    continue
+
+        st.success("Dataset loaded successfully!")
+        return fiber_impact_data
+
+    except Exception as e:
+        st.error(f"Error fetching or processing dataset: {e}")
         return None
 
-# Function to extract relevant data from the PDF
-def process_pdf_data(pdf_reader):
-    """Process the PDF file and extract relevant data."""
-    st.info("Processing dataset...")
-    extracted_data = {}
-
-    for page in pdf_reader.pages:
-        text = page.extract_text()
-
-        # Example parsing rules (adjust based on the actual file format):
-        if "Global average water footprint of cotton fabric" in text:
-            extracted_data["Cotton"] = {"Water": 10000, "Energy": 60, "Carbon": 3.18}
-        if "Water footprint by region: China" in text:
-            extracted_data["China"] = {"Water": 6000}
-
-    st.success("Dataset processed successfully!")
-    return extracted_data
-
-# Step 1: Fetch dataset from Google Drive
-pdf_reader = fetch_pdf_from_drive(DATASET_URL)
-if pdf_reader:
-    fiber_impact_data = process_pdf_data(pdf_reader)
-    st.write(fiber_impact_data)  # Debugging: Display parsed data
-else:
-    st.stop()
+# Load dataset dynamically from Google Drive
+fiber_impact_data = fetch_and_process_pdf(DATASET_URL)
 
 # Sidebar for User Inputs
 st.sidebar.header("Input Product Details")
+
+# Input Section: Product-Specific Inputs
 product_type = st.sidebar.selectbox("Product Type", ["T-shirt", "Jeans", "Shirt", "Carpet"])
 product_weight = st.sidebar.number_input("Product Weight (kg)", min_value=0.01, step=0.01, value=0.25)
 
@@ -95,10 +90,10 @@ nylon_percent = st.sidebar.slider("Nylon (%)", 0, 100, 10)
 acrylic_percent = st.sidebar.slider("Acrylic (%)", 0, 100, 5)
 viscose_percent = st.sidebar.slider("Viscose (%)", 0, 100, 5)
 
-# Validate percentage
+# Validation check: Percentages must add up to 100%
 total_percentage = cotton_percent + polyester_percent + nylon_percent + acrylic_percent + viscose_percent
 if total_percentage != 100:
-    st.sidebar.warning("Material percentages must sum to 100%!")
+    st.sidebar.error("The total of all fiber percentages must equal 100%!")
 
 # Lifecycle Inputs
 st.sidebar.header("Lifecycle Details")
@@ -109,18 +104,50 @@ transport_mode = st.sidebar.selectbox("Transport Mode", ["Plane", "Ship", "Train
 transport_distance = st.sidebar.number_input("Transport Distance (km)", min_value=0, step=50)
 
 # Function to calculate footprints
-def calculate_footprints(weight, composition):
-    water_fp, energy_fp, carbon_fp = 0, 0, 0
+def calculate_footprints(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:
-            impacts = fiber_impact_data[fiber]
+            data = fiber_impact_data[fiber]
             fraction = percentage / 100
-            water_fp += impacts["Water"] * weight * fraction
-            energy_fp += impacts["Energy"] * weight * fraction
-            carbon_fp += impacts["Carbon"] * weight * fraction
-    return water_fp, energy_fp, carbon_fp
+            water_footprint += data["Water"] * weight * fraction
+            energy_footprint += data["Energy"] * weight * fraction
+            carbon_footprint += data["Carbon"] * weight * fraction
+
+    # Transportation impacts
+    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
+    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
+
+# User inputs as a dictionary
+user_inputs = {
+    "transport_mode": transport_mode,
+    "transport_distance": transport_distance,
+    "washing_temperature": washing_temperature,
+    "washing_cycles": washing_cycles,
+    "use_dryer": use_dryer,
+}
 
-# Perform calculations
+# Collect the composition dictionary
 composition = {
     "Cotton": cotton_percent,
     "Polyester": polyester_percent,
@@ -129,22 +156,28 @@ composition = {
     "Viscose": viscose_percent,
 }
 
-if total_percentage == 100:
-    water_fp, energy_fp, carbon_fp = calculate_footprints(product_weight, composition)
+# 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
     st.subheader("Calculated Results")
-    st.markdown(f"- **Water Footprint**: {water_fp:.2f} liters")
-    st.markdown(f"- **Energy Footprint**: {energy_fp:.2f} MJ")
-    st.markdown(f"- **Carbon Footprint**: {carbon_fp:.2f} kgCO2e")
-
-    # Separate Graphs for each footprint
-    fig_water = px.bar(x=["Water Footprint"], y=[water_fp], labels={"x": "Type", "y": "Liters"}, title="Water Footprint")
-    fig_energy = px.bar(x=["Energy Footprint"], y=[energy_fp], labels={"x": "Type", "y": "MJ"}, title="Energy Footprint")
-    fig_carbon = px.bar(x=["Carbon Footprint"], y=[carbon_fp], labels={"x": "Type", "y": "kgCO2e"}, title="Carbon Footprint")
-
-    st.plotly_chart(fig_water, use_container_width=True)
-    st.plotly_chart(fig_energy, use_container_width=True)
-    st.plotly_chart(fig_carbon, use_container_width=True)
+    st.markdown(f"""
+        - **Water Footprint**: {water_fp:.2f} liters  
+        - **Energy Footprint**: {energy_fp:.2f} MJ  
+        - **Carbon Footprint**: {carbon_fp:.2f} kgCO2e  
+    """)
+
+    # 3D Visualization
+    fig = go.Figure()
+    fig.add_trace(go.Bar(
+        x=["Water Footprint", "Energy Footprint", "Carbon Footprint"],
+        y=[water_fp, energy_fp, carbon_fp],
+        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", xaxis_title="Footprint Type", yaxis_title="Value")
+    st.plotly_chart(fig)
 else:
-    st.warning("Ensure that material composition totals 100%.")
+    st.error("Ensure dataset is loaded and composition sums to 100%.")