Update app.py

app.py

@@ -1,95 +1,107 @@
 import os
+import streamlit as st
 import pandas as pd
 import numpy as np
-import streamlit as st
 from groq import Groq
+from sentence_transformers import SentenceTransformer
+import faiss
 
 GROQ_API_KEY = "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"
-
-# Initialize Groq API client
+# Initialize Groq API Client
 client = Groq(api_key=GROQ_API_KEY)
 
-# Function to analyze energy usage
-def analyze_energy_usage(data, household_id=None):
-    if household_id:
-        # Filter data for a specific household
-        household_data = data[data["Household ID"] == household_id]
-    else:
-        household_data = data
-
-    # Check if the filtered data is empty
-    if household_data.empty:
-        return "No data available for the specified Household ID.", None
+# Load Pretrained Embedding Model
+embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
 
-    # Aggregate data
-    total_usage = household_data["Energy Usage (kWh)"].sum()
-    avg_cost = household_data["Cost"].mean()
-    peak_time_period = (
-        household_data.groupby("Time Period")["Energy Usage (kWh)"]
-        .sum()
-        .idxmax()
-    )
+# Initialize global variables
+uploaded_file = None
+faiss_index = None
+dataframe = None
 
-    # Generate a summary report
-    report_summary = f"""
-    Total Energy Usage: {total_usage} kWh
-    Average Cost: ${avg_cost:.2f}
-    Peak Usage Time Period: {peak_time_period}
-    """
-    return report_summary, household_data
+# Function to load and preprocess dataset
+def load_dataset(file):
+    global dataframe, faiss_index
+    dataframe = pd.read_csv(file)
+    st.success("Dataset loaded successfully!")
+    # Create FAISS index for the dataset
+    embeddings = embedding_model.encode(dataframe["Energy Usage (kWh)"].astype(str).tolist())
+    faiss_index = faiss.IndexFlatL2(embeddings.shape[1])
+    faiss_index.add(np.array(embeddings))
 
-# Function to generate recommendations using Groq's API
-def generate_recommendations(context):
-    try:
-        response = client.chat.completions.create(
-            messages=[
-                {
-                    "role": "user",
-                    "content": f"Based on the following data:\n{context}\nProvide energy-saving recommendations and insights."
-                }
-            ],
-            model="llama3-8b-8192",
-            stream=False,
-        )
-        return response.choices[0].message.content
-    except Exception as e:
-        return f"An error occurred: {e}"
+# Function to retrieve relevant rows
+def retrieve_relevant_data(query, top_k=5):
+    if dataframe is None or faiss_index is None:
+        st.error("Please upload a dataset first.")
+        return []
+    query_embedding = embedding_model.encode([query])
+    distances, indices = faiss_index.search(np.array(query_embedding), top_k)
+    relevant_rows = dataframe.iloc[indices[0]].to_dict(orient="records")
+    return relevant_rows
 
-# Streamlit App
-st.title("Energy Usage Analysis Report Generator")
+# Function to analyze data and generate cost-saving recommendations
+def generate_cost_saving_recommendations(data):
+    if not data:
+        return "No relevant data found for recommendations."
+    
+    total_energy_usage = sum(row["Energy Usage (kWh)"] for row in data)
+    avg_energy_usage = total_energy_usage / len(data)
+    total_cost = sum(row["Cost"] for row in data)
+    
+    recommendations = [
+        f"Total energy usage: {total_energy_usage:.2f} kWh",
+        f"Average energy usage per household: {avg_energy_usage:.2f} kWh",
+        f"Total cost: ${total_cost:.2f}",
+        "Recommendations:",
+        "- Implement energy-efficient appliances.",
+        "- Use renewable energy sources like solar or wind.",
+        "- Schedule high-energy tasks during off-peak hours.",
+        "- Conduct regular maintenance to reduce energy wastage."
+    ]
+    return "\n".join(recommendations)
 
-# Upload Dataset
-uploaded_file = st.file_uploader("Upload your energy usage dataset (CSV)", type="csv")
-if uploaded_file:
-    # Load dataset
-    data = pd.read_csv(uploaded_file)
-    st.write("Dataset Preview:", data.head())
+# Function to generate a detailed analysis report
+def generate_report(query):
+    relevant_data = retrieve_relevant_data(query)
+    context = "\n".join([str(row) for row in relevant_data])
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": f"Based on the following query: '{query}' and context:\n{context}\nProvide an energy usage analysis report."
+            }
+        ],
+        model="llama3-8b-8192",
+        stream=False,
+    )
+    detailed_report = chat_completion.choices[0].message.content
+    cost_saving_recommendations = generate_cost_saving_recommendations(relevant_data)
+    return detailed_report, cost_saving_recommendations
 
-    # User Input
-    household_id = st.text_input("Enter Household ID for specific analysis (optional)")
+# Streamlit app configuration
+st.title("Energy Usage Analysis & Cost-Saving Report Generator")
+st.sidebar.header("Upload Dataset")
 
-    # Analyze Data
-if st.button("Analyze Energy Usage"):
-    with st.spinner("Analyzing..."):
-        report_summary, filtered_data = analyze_energy_usage(data, household_id)
-        
-        if filtered_data is None:
-            st.warning(report_summary)  # Display message for no data
-        else:
-            st.subheader("Energy Usage Summary")
-            st.text(report_summary)
+# File upload
+uploaded_file = st.sidebar.file_uploader("Upload your energy usage dataset (CSV)", type=["csv"])
+if uploaded_file is not None:
+    load_dataset(uploaded_file)
 
-            # Generate recommendations
-            st.subheader("Recommendations")
-            context = filtered_data.to_string(index=False)
-            recommendations = generate_recommendations(context)
-            st.text(recommendations)
+# Query input
+st.header("Generate Energy Usage Report")
+query = st.text_input("Enter your query (e.g., 'Analyze peak usage times in urban areas')")
 
-# Footer
-st.sidebar.title("About")
-st.sidebar.info(
-    """
-    This app generates energy usage reports and recommendations based on uploaded data.
-    Built with Streamlit and powered by Groq's language model.
-    """
-)
+if st.button("Generate Report"):
+    if uploaded_file is None:
+        st.error("Please upload a dataset first.")
+    elif query.strip() == "":
+        st.error("Please enter a query.")
+    else:
+        with st.spinner("Generating report..."):
+            try:
+                detailed_report, cost_saving_recommendations = generate_report(query)
+                st.subheader("Energy Usage Analysis Report")
+                st.write(detailed_report)
+                st.subheader("Cost-Saving Recommendations")
+                st.write(cost_saving_recommendations)
+            except Exception as e:
+                st.error(f"An error occurred: {e}")