Upload 4 files

app.py

@@ -0,0 +1,117 @@
+import os
+import requests
+import streamlit as st
+import pandas as pd
+from scraper import scrape_tariffs
+
+# Streamlit App: Electricity Bill & Carbon Footprint Estimator
+st.title("🔌 Electricity Bill & Carbon Footprint Estimator")
+st.sidebar.header("⚙️ User Input")
+
+# Tariff URLs for scraping
+tariff_urls = {
+    "IESCO": "https://iesco.com.pk/index.php/customer-services/tariff-guide",
+    "FESCO": "https://fesco.com.pk/tariff",
+    "HESCO": "http://www.hesco.gov.pk/htmls/tariffs.htm",
+    "KE": "https://www.ke.com.pk/customer-services/tariff-structure/",
+    "LESCO": "https://www.lesco.gov.pk/ElectricityTariffs",
+    "PESCO": "https://pesconlinebill.pk/pesco-tariff/",
+    "QESCO": "http://qesco.com.pk/Tariffs.aspx",
+    "TESCO": "https://tesco.gov.pk/index.php/electricity-traiff",
+}
+
+# Predefined appliances and their power in watts
+appliances = {
+    "LED Bulb (10W)": 10,
+    "Ceiling Fan (75W)": 75,
+    "Refrigerator (150W)": 150,
+    "Air Conditioner (1.5 Ton, 1500W)": 1500,
+    "Washing Machine (500W)": 500,
+    "Television (100W)": 100,
+    "Laptop (65W)": 65,
+    "Iron (1000W)": 1000,
+    "Microwave Oven (1200W)": 1200,
+    "Water Heater (2000W)": 2000,
+}
+
+def scrape_data():
+    """
+    Scrapes tariff data from the provided URLs.
+    """
+    st.info("🔄 Scraping tariff data... Please wait.")
+    scrape_tariffs(list(tariff_urls.values()))
+    st.success("✅ Tariff data scraping complete.")
+
+def calculate_carbon_footprint(monthly_energy_kwh):
+    """
+    Calculates the carbon footprint based on energy consumption in kWh.
+    """
+    carbon_emission_factor = 0.75  # kg CO2 per kWh
+    return monthly_energy_kwh * carbon_emission_factor
+
+# Sidebar: Scrape Tariff Data
+if st.sidebar.button("Scrape Tariff Data"):
+    scrape_data()
+
+# Sidebar: Tariff Selection
+st.sidebar.subheader("💡 Select Tariff")
+try:
+    tariff_data = pd.read_csv("data/tariffs.csv")
+    tariff_types = tariff_data["category"].unique()
+    selected_tariff = st.sidebar.selectbox("Select your tariff category:", tariff_types)
+    rate_per_kwh = tariff_data[tariff_data["category"] == selected_tariff]["rate"].iloc[0]
+    st.sidebar.write(f"Rate per kWh: **{rate_per_kwh} PKR**")
+except FileNotFoundError:
+    st.sidebar.error("⚠️ Tariff data not found. Please scrape the data first.")
+    rate_per_kwh = 0
+
+# Sidebar: User Inputs for Appliances
+st.sidebar.subheader("🏠 Add Appliances")
+selected_appliance = st.sidebar.selectbox("Select an appliance:", list(appliances.keys()))
+appliance_power = appliances[selected_appliance]
+appliance_quantity = st.sidebar.number_input(
+    "Enter quantity:", min_value=1, max_value=10, value=1
+)
+usage_hours = st.sidebar.number_input(
+    "Enter usage hours per day:", min_value=1, max_value=24, value=5
+)
+
+# Add appliance details to the main list
+if "appliance_list" not in st.session_state:
+    st.session_state["appliance_list"] = []
+
+if st.sidebar.button("Add Appliance"):
+    st.session_state["appliance_list"].append(
+        {
+            "appliance": selected_appliance,
+            "power": appliance_power,
+            "quantity": appliance_quantity,
+            "hours": usage_hours,
+        }
+    )
+
+# Display the list of added appliances
+st.subheader("📋 Added Appliances")
+if st.session_state["appliance_list"]:
+    for idx, appliance in enumerate(st.session_state["appliance_list"], start=1):
+        st.write(
+            f"{idx}. **{appliance['appliance']}** - "
+            f"{appliance['power']}W, {appliance['quantity']} unit(s), "
+            f"{appliance['hours']} hours/day"
+        )
+
+# Electricity Bill and Carbon Footprint Calculation
+if st.session_state["appliance_list"] and rate_per_kwh > 0:
+    total_daily_energy_kwh = sum(
+        (appliance["power"] * appliance["quantity"] * appliance["hours"]) / 1000
+        for appliance in st.session_state["appliance_list"]
+    )
+    monthly_energy_kwh = total_daily_energy_kwh * 30  # Assume 30 days in a month
+    bill_amount = monthly_energy_kwh * rate_per_kwh  # Dynamic tariff rate
+    carbon_footprint = calculate_carbon_footprint(monthly_energy_kwh)
+
+    st.subheader("💵 Electricity Bill & 🌍 Carbon Footprint")
+    st.write(f"💵 **Estimated Electricity Bill**: **{bill_amount:.2f} PKR**")
+    st.write(f"🌍 **Estimated Carbon Footprint**: **{carbon_footprint:.2f} kg CO2 per month**")
+else:
+    st.info("ℹ️ Add appliances to calculate the electricity bill and carbon footprint.")

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.24.0
+beautifulsoup4==4.12.2
+requests==2.31.0
+pandas==1.5.3
+torch==2.1.0  # PyTorch required for embeddings
+transformers==4.34.0  # Hugging Face Transformers for loading the model
+huggingface_hub>=0.16.4  # Handling Hugging Face API (already included for model loading)
+faiss-cpu==1.7.4  # Optional, for similarity queries on embeddings if needed

scraper.py

@@ -0,0 +1,75 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import time
+from random import randint
+
+def scrape_tariffs(urls):
+    data = []
+    
+    # Ensure the 'data' directory exists before saving the CSV
+    os.makedirs("data", exist_ok=True)
+    
+    for url in urls:
+        try:
+            response = requests.get(url, timeout=10)  # Added timeout
+            response.raise_for_status()  # Raise exception for bad status codes (4xx, 5xx)
+
+            # Scrape data if the response is OK
+            if response.status_code == 200:
+                soup = BeautifulSoup(response.content, "html.parser")
+                rows = soup.find_all("tr")
+
+                for row in rows:
+                    cells = row.find_all("td")
+                    if len(cells) >= 2:
+                        try:
+                            data.append({
+                                "category": cells[0].text.strip(),
+                                "rate": float(cells[1].text.strip().replace(",", "")),
+                            })
+                        except ValueError:
+                            continue
+
+        except requests.exceptions.RequestException as e:
+            print(f"Error fetching data from {url}: {e}")
+            print("Retrying...")
+
+            # Retry logic in case of failure (max 3 retries with random delay)
+            retries = 3
+            while retries > 0:
+                time.sleep(randint(1, 3))  # Sleep for a random time before retrying
+                retries -= 1
+                try:
+                    response = requests.get(url, timeout=10)
+                    response.raise_for_status()
+                    if response.status_code == 200:
+                        soup = BeautifulSoup(response.content, "html.parser")
+                        rows = soup.find_all("tr")
+
+                        for row in rows:
+                            cells = row.find_all("td")
+                            if len(cells) >= 2:
+                                try:
+                                    data.append({
+                                        "category": cells[0].text.strip(),
+                                        "rate": float(cells[1].text.strip().replace(",", "")),
+                                    })
+                                except ValueError:
+                                    continue
+                        break
+                except requests.exceptions.RequestException:
+                    print(f"Retry failed: {e}")
+                    continue
+
+        # Sleep between requests to avoid hitting the servers too quickly
+        time.sleep(randint(2, 5))
+
+    if data:
+        df = pd.DataFrame(data)
+        # Save the scraped data to the 'data' directory
+        df.to_csv("data/tariffs.csv", index=False)
+        print("Tariff data saved successfully.")
+    else:
+        print("No tariff data found.")

utils.py

@@ -0,0 +1,21 @@
+import faiss
+import numpy as np
+
+def generate_faiss_index(embeddings):
+    # Ensure that the embeddings are converted to np.float32 (FAISS expects float32)
+    embeddings = np.array(embeddings, dtype=np.float32)
+    index = faiss.IndexFlatL2(768)  # Assuming 768-dimensional embeddings for a model like MiniLM
+    index.add(embeddings)
+    return index
+
+def load_faiss_index_to_gpu(index):
+    # If you're using GPU, ensure the index is moved to the GPU
+    res = faiss.StandardGpuResources()  # Create resources for the GPU
+    gpu_index = faiss.index_cpu_to_gpu(res, 0, index)  # Load into GPU (assuming GPU 0 is available)
+    return gpu_index
+
+def query_faiss_index(query_embedding, gpu_index):
+    # Query the FAISS index with the query embedding
+    query_embedding = np.array(query_embedding, dtype=np.float32)  # Ensure the query is a np.array with the right type
+    distances, indices = gpu_index.search(query_embedding.reshape(1, -1), 1)  # Reshaping as FAISS expects 2D array
+    return indices, distances