Update app.py

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+import plotly.express as px
+
+# -----------------------------
+# CONFIGURATION
+# -----------------------------
+st.set_page_config(page_title="Smart Energy AI", layout="wide")
+
+st.title("⚡ Smart Energy AI Chatbot")
+st.subheader("Energy Consumption Analysis, Prediction & Sustainability Recommendations")
+
+# -----------------------------
+# FILE UPLOAD SAFETY FIX
+# -----------------------------
+uploaded_file = st.file_uploader("Upload your energy consumption CSV", type=["csv"])
+
+try:
+    if uploaded_file is not None:
+        df = pd.read_csv(uploaded_file)
+    else:
+        df = pd.read_csv("energy_data.csv")
+except Exception as e:
+    st.error("⚠️ Dataset not found or invalid file. Please upload a CSV.")
+    st.stop()
+
+# -----------------------------
+# DATA PREPROCESSING
+# -----------------------------
+df['date'] = pd.to_datetime(df['date'], errors='coerce')
+df['usage_kwh'] = pd.to_numeric(df['usage_kwh'], errors='coerce')
+df.dropna(inplace=True)
+
+if df.empty:
+    st.warning("No valid data available.")
+    st.stop()
+
+# -----------------------------
+# SIDEBAR FILTERS
+# -----------------------------
+st.sidebar.header("Filters")
+
+appliance_list = df['appliance'].dropna().unique()
+
+appliance_filter = st.sidebar.multiselect(
+    "Select Appliance",
+    options=appliance_list,
+    default=appliance_list
+)
+
+filtered_df = df[df['appliance'].isin(appliance_filter)]
+
+# -----------------------------
+# DAILY ANALYSIS
+# -----------------------------
+daily_usage = filtered_df.groupby('date')['usage_kwh'].sum().reset_index()
+
+total_consumption = filtered_df['usage_kwh'].sum()
+avg_consumption = filtered_df['usage_kwh'].mean()
+
+if not daily_usage.empty:
+    peak_day = daily_usage.loc[daily_usage['usage_kwh'].idxmax()]
+else:
+    peak_day = {"date": pd.Timestamp.today(), "usage_kwh": 0}
+
+# -----------------------------
+# METRICS
+# -----------------------------
+col1, col2, col3 = st.columns(3)
+col1.metric("Total Consumption (kWh)", f"{total_consumption:.2f}")
+col2.metric("Average Usage (kWh)", f"{avg_consumption:.2f}")
+col3.metric("Peak Usage Day", str(peak_day['date'].date()))
+
+# -----------------------------
+# LINE CHART (SAFE)
+# -----------------------------
+st.subheader("📈 Daily Energy Consumption Trend")
+
+if not daily_usage.empty:
+    fig = px.line(daily_usage, x='date', y='usage_kwh', markers=True)
+    st.plotly_chart(fig, use_container_width=True)
+else:
+    st.info("Not enough data for chart")
+
+# -----------------------------
+# APPLIANCE CHART
+# -----------------------------
+st.subheader("🔌 Appliance Usage")
+
+appliance_usage = filtered_df.groupby('appliance')['usage_kwh'].sum().reset_index()
+
+if not appliance_usage.empty:
+    fig2 = px.pie(appliance_usage, names='appliance', values='usage_kwh')
+    st.plotly_chart(fig2, use_container_width=True)
+
+# -----------------------------
+# SIMPLE PREDICTION
+# -----------------------------
+st.subheader("🔮 Prediction")
+
+if len(daily_usage) > 1:
+    daily_usage['day'] = np.arange(len(daily_usage))
+
+    X = daily_usage[['day']]
+    y = daily_usage['usage_kwh']
+
+    model = LinearRegression()
+    model.fit(X, y)
+
+    next_day = np.array([[len(daily_usage)]])
+    prediction = model.predict(next_day)[0]
+
+    st.success(f"Predicted next usage: {prediction:.2f} kWh")
+else:
+    st.info("Not enough data for prediction")
+
+# -----------------------------
+# FOOTER
+# -----------------------------
+st.caption("Built with Streamlit | AI + Sustainability + Data Analytics")