Update app.py

app.py

@@ -3,92 +3,76 @@ import gradio as gr
 import tensorflow as tf
 import joblib
 import numpy as np
-import pandas as pd
-from huggingface_hub import hf_hub_download
-
-os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
 
+# -------------------------------------------------------
+# CONFIG
+# -------------------------------------------------------
 MODEL_REPO = "munem420/stock-forecaster-lstm"
 MODEL_FILENAME = "model_lstm.h5"
 SCALER_FILENAME = "scalers.joblib"
 
-print("--- Downloading model and scalers ---")
-try:
-    model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME)
-    scalers_path = hf_hub_download(repo_id=MODEL_REPO, filename=SCALER_FILENAME)
-    print("✅ Files downloaded successfully.")
-except Exception as e:
-    print(f"❌ Error downloading files: {e}")
-    model_path, scalers_path = None, None
-
-loaded_model_lstm = None
-loaded_scalers = None
-
-if model_path and os.path.exists(model_path):
-    try:
-        loaded_model_lstm = tf.keras.models.load_model(
-            model_path,
-            custom_objects={"mse": tf.keras.losses.MeanSquaredError()}
-        )
-        print("✅ Model loaded successfully.")
-    except Exception as e:
-        print(f"❌ Error loading model: {e}")
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 
-if scalers_path and os.path.exists(scalers_path):
-    try:
-        loaded_scalers = joblib.load(scalers_path)
-        print("✅ Scalers loaded successfully.")
-    except Exception as e:
-        print(f"❌ Error loading scalers: {e}")
+# -------------------------------------------------------
+# LOAD MODEL AND SCALERS
+# -------------------------------------------------------
+print("📦 Loading model and scalers...")
 
-ticker_to_name = {'ZURVY': 'Zurich Insurance Group AG'}
-
-# Example placeholder DataFrame (replace with your actual data)
-data_df = pd.DataFrame({
-    "Date": pd.date_range(start="2024-01-01", periods=100),
-    "Close": np.linspace(100, 200, 100)
-})
-
-def get_ticker_from_input(input_name):
-    return input_name.upper().strip()
-
-def forecast_stock(input_name):
-    model = loaded_model_lstm
-    scalers_dict = loaded_scalers
-    input_width = 60
+try:
+    model_path = tf.keras.utils.get_file(
+        MODEL_FILENAME,
+        f"https://huggingface.co/{MODEL_REPO}/resolve/main/{MODEL_FILENAME}"
+    )
+    scalers_path = tf.keras.utils.get_file(
+        SCALER_FILENAME,
+        f"https://huggingface.co/{MODEL_REPO}/resolve/main/{SCALER_FILENAME}"
+    )
+
+    model = tf.keras.models.load_model(
+        model_path,
+        custom_objects={"mse": tf.keras.losses.MeanSquaredError()}
+    )
+    scalers = joblib.load(scalers_path)
+
+    print("✅ Model and scalers loaded successfully.")
+except Exception as e:
+    print(f"❌ Error loading model or scalers: {e}")
+    model, scalers = None, None
 
-    if not model or not scalers_dict:
-        return "Error: Model or scalers not loaded."
+# -------------------------------------------------------
+# FORECAST FUNCTION
+# -------------------------------------------------------
+def forecast_stock(ticker):
+    if not model or not scalers:
+        return "❌ Model or scalers not loaded properly."
 
-    ticker = get_ticker_from_input(input_name)
-    if len(data_df) < input_width:
-        return f"Error: Not enough historical data. Need {input_width} days, but only have {len(data_df)}."
+    ticker = ticker.strip().upper()
+    if ticker not in scalers:
+        return f"⚠️ No scaler found for ticker '{ticker}'. Please check spelling."
 
-    recent_data = data_df.tail(input_width)
-    close_prices = recent_data['Close'].values.reshape(-1, 1)
-    scaler = scalers_dict.get(ticker)
+    # Dummy inference example (replace with actual data fetching or preprocessing)
+    # Here we just simulate 60 normalized close prices for inference
+    scaler = scalers[ticker]
+    dummy_data = np.linspace(0.9, 1.1, 60).reshape(-1, 1)
+    X_pred = dummy_data.reshape(1, 60, 1)
 
-    if not scaler:
-        print(f"⚠️ No specific scaler for {ticker}. Using fallback.")
-        scaler = scalers_dict.get('ZURVY')
-        if not scaler:
-            return "Error: No default scaler found."
+    # Predict scaled value
+    pred_scaled = model.predict(X_pred, verbose=0)[0][0]
 
-    scaled_data = scaler.transform(close_prices)
-    X_pred = scaled_data.reshape(1, input_width, 1)
-    prediction_scaled = model.predict(X_pred, verbose=0)[0][0]
-    prediction_actual = scaler.inverse_transform(np.array([[prediction_scaled]]))[0][0]
-    last_close = recent_data['Close'].iloc[-1]
+    # Inverse transform prediction
+    pred_actual = scaler.inverse_transform(np.array([[pred_scaled]]))[0][0]
 
-    return f"Last close for {ticker}: ${last_close:.2f}\nPredicted next day close: ${prediction_actual:.2f}"
+    return f"🔮 Predicted next day close for **{ticker}**: ${pred_actual:.2f}"
 
-# ✅ Simple Gradio interface
+# -------------------------------------------------------
+# GRADIO INTERFACE
+# -------------------------------------------------------
 iface = gr.Interface(
     fn=forecast_stock,
     inputs=gr.Textbox(label="Enter Ticker or Company Name"),
-    outputs=gr.Textbox(label="Predicted Next Day Close"),
-    title="Stock Price Forecaster (LSTM)",
-    description="Enter a stock ticker or company name to predict the next day's close price."
+    outputs=gr.Markdown(label="Prediction Result"),
+    title="📊 Stock Price Forecaster (LSTM)",
+    description="Enter a stock ticker or company name to predict the next day's closing price using a trained LSTM model."
 )
 
 if __name__ == "__main__":