Update app.py

app.py

@@ -8,31 +8,56 @@ from darts.dataprocessing.transformers import Scaler
 from sklearn.preprocessing import LabelEncoder
 import numpy as np
 import io
+import os
 
 # ----------------------------
-# Load Dataset
+# SAFE DATASET LOADER
+# ----------------------------
+def load_dataset(path="dataset.csv", url=None):
+    try:
+        # Try UTF-8
+        return pd.read_csv(path, encoding="utf-8")
+    except UnicodeDecodeError:
+        try:
+            # Fallback to Latin1
+            return pd.read_csv(path, encoding="latin1")
+        except Exception as e:
+            if url:
+                # If file missing, try URL
+                try:
+                    return pd.read_csv(url, encoding="utf-8")
+                except UnicodeDecodeError:
+                    return pd.read_csv(url, encoding="latin1")
+            else:
+                raise e
+
+# Path or fallback URL
+url = "https://raw.githubusercontent.com/yourusername/yourrepo/main/dataset.csv"
+if os.path.exists("dataset.csv"):
+    df = load_dataset("dataset.csv")
+else:
+    df = load_dataset(url=url)
+
+# ----------------------------
+# Preprocessing
 # ----------------------------
-df = pd.read_csv("dataset.csv")   # <-- replace with your dataset file
 df['datetime'] = pd.to_datetime(df['datetime'])
 df = df.sort_values("datetime")
 
-# Encode weather icons (categorical -> numeric)
+# Encode weather icons
 encoder = LabelEncoder()
-df['icon_encoded'] = encoder.fit_transform(df['icon'])
+if "icon" in df.columns:
+    df['icon_encoded'] = encoder.fit_transform(df['icon'])
 
-# ----------------------------
-# Preprocessing for Forecasting
-# ----------------------------
+# Create timeseries
 series = TimeSeries.from_dataframe(df, "datetime", "pv_output_kWh")
 scaler = Scaler()
 series_scaled = scaler.fit_transform(series)
 
-# Pre-trained model (you can switch between TFT and N-BEATS)
-model = TFTModel.load_from_checkpoint("tft_pretrained", work_dir="./") \
-        if TFTModel.exists("tft_pretrained", work_dir="./") else None
-
-if model is None:
-    # fallback: train small model (for demo)
+# Pre-trained or fallback model
+try:
+    model = TFTModel.load_from_checkpoint("tft_pretrained", work_dir="./")
+except Exception:
     model = NBEATSModel(input_chunk_length=30, output_chunk_length=7, n_epochs=10)
     model.fit(series_scaled)
 
@@ -78,7 +103,7 @@ def forecast_pv(horizon, weather_condition):
     forecast = model.predict(steps)
     forecast = scaler.inverse_transform(forecast)
 
-    # Adjust for weather condition
+    # Weather impact adjustment
     adjustment = {
         "Clear": 1.0,
         "Partly Cloudy": 0.85,
@@ -91,11 +116,11 @@ def forecast_pv(horizon, weather_condition):
     adj_factor = adjustment.get(weather_condition, 1.0)
     forecast_adj = forecast * adj_factor
 
-    # Plot forecast
+    # Plot
     plt.figure(figsize=(10,4))
-    series[-7*24:].plot(label="History")  # last 7 days history
+    series[-7*24:].plot(label="History")  # last week history
     forecast.plot(label="Forecast (Base)")
-    forecast_adj.plot(label=f"Forecast (Adjusted for {weather_condition})")
+    forecast_adj.plot(label=f"Forecast (Adjusted: {weather_condition})")
     plt.legend()
     plt.title(f"PV Forecast for {horizon}")
     plt.tight_layout()
@@ -108,7 +133,7 @@ def forecast_pv(horizon, weather_condition):
     return plt.gcf(), peak_info
 
 # ----------------------------
-# GRADIO INTERFACE
+# GRADIO DASHBOARD
 # ----------------------------
 eda_tab = gr.TabbedInterface(
     [