Upload folder using huggingface_hub

Apple-Stock-Price-Forecasting-LSTM-Model/inference.py

@@ -0,0 +1,84 @@
+
+!pip install yfinance --quiet
+from huggingface_hub import hf_hub_download
+import tensorflow as tf
+import joblib
+import numpy as np
+import yfinance as yf
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+
+def predict_apple_stock(hf_token, days=7):
+    """
+    AAPL Stock Price Prediction using LSTM
+    
+    Args:
+        hf_token: Your Hugging Face token
+        days: Number of days to predict (default: 7)
+    
+    Returns:
+        DataFrame with predictions
+    """
+    # Download model and scaler
+    model_path = hf_hub_download(
+        repo_id="EsferSami/DataSynthis_ML_JobTask",
+        filename="Apple-Stock-Price-Forecasting-LSTM-Model/apple_stock_lstm.h5",
+        token=hf_token
+    )
+    
+    scaler_path = hf_hub_download(
+        repo_id="EsferSami/DataSynthis_ML_JobTask", 
+        filename="Apple-Stock-Price-Forecasting-LSTM-Model/scaler.joblib",
+        token=hf_token
+    )
+    
+    # Load model and scaler
+    model = tf.keras.models.load_model(model_path)
+    scaler = joblib.load(scaler_path)
+    print("Model loaded successfully!")
+    
+    # Get recent data
+    data = yf.download("AAPL", period="3mo", auto_adjust=False)
+    recent_prices = data['Adj Close'].values
+    
+    # Prepare last 60 days
+    last_60_days = recent_prices[-60:].reshape(-1, 1)
+    last_60_days_scaled = scaler.transform(last_60_days)
+    
+    # Make predictions
+    predictions = []
+    current_sequence = last_60_days_scaled.copy()
+    
+    for day in range(days):
+        input_data = current_sequence.reshape(1, 60, 1)
+        predicted_scaled = model.predict(input_data, verbose=0)
+        predicted_price = scaler.inverse_transform(predicted_scaled)[0][0]
+        predictions.append(predicted_price)
+        
+        predicted_scaled_reshaped = predicted_scaled.reshape(1, 1)
+        current_sequence = np.append(current_sequence[1:], predicted_scaled_reshaped, axis=0)
+    
+    # Create results
+    prediction_dates = pd.date_range(start=data.index[-1] + pd.Timedelta(days=1), periods=days)
+    results_df = pd.DataFrame({
+        'Date': prediction_dates,
+        'Predicted_Price': predictions
+    })
+    
+    print(f"\nAAPL Stock Price - {days}-Day Forecast")
+    print("=" * 40)
+    print(results_df.to_string(index=False))
+    
+    current_price = float(recent_prices[-1])
+    print(f"\nCurrent Price: ${current_price:.2f}")
+    print(f"Prediction Trend: {'UP ↗' if predictions[-1] > current_price else 'DOWN ↘'}")
+    
+    return results_df
+
+# Example usage:
+if __name__ == "__main__":
+    # Replace with your HF token
+    YOUR_HF_TOKEN = "your_huggingface_token_here"
+    
+    # Get 7-day prediction
+    predictions = predict_apple_stock(YOUR_HF_TOKEN, days=7)

Apple-Stock-Price-Forecasting-LSTM-Model/lstm_model/apple_stock_lstm.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246fb15049f05699372843c6d8db55d95dd97fe1d09f82ca3e8ab90981d4c079
+size 661264

Apple-Stock-Price-Forecasting-LSTM-Model/lstm_model/scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307a16526b5c9260d34cdcdeff7c50269403ff32196e119268e2d8409158bcbf
+size 719