Update core/data.py

core/data.py

@@ -1,25 +1,41 @@
+# core/data.py
+
 import pandas as pd
-yf_available = True
+import numpy as np
+import torch
+from sklearn.preprocessing import StandardScaler
+
 try:
     import yfinance as yf
-except:
-    yf_available = False
-
-# core/data.py
-import yfinance as yf
-import pandas as pd
+except ImportError:
+    raise ImportError("yfinance must be installed to fetch financial data.")
 
-def load_data(ticker, start, end):
+def load_data(ticker="AAPL", start="2020-01-01", end="2023-01-01"):
     df = yf.download(ticker, start=start, end=end)
 
     if df.empty:
         raise ValueError(f"No data found for ticker '{ticker}'. Please check the symbol or try another.")
 
-    # Select only the 'Close' column and drop missing values
     df = df[['Close']].dropna()
     df = df.rename(columns={'Close': 'value'})
-
-    # Ensure index is datetime and reset if necessary
     df.reset_index(inplace=True)
+    return df
+
+def preprocess_data(df, window_size=30):
+    values = df['value'].values.reshape(-1, 1)
+
+    scaler = StandardScaler()
+    scaled = scaler.fit_transform(values)
+
+    X, y = [], []
+    for i in range(len(scaled) - window_size):
+        X.append(scaled[i:i + window_size])
+        y.append(scaled[i + window_size])
+
+    X = np.array(X)
+    y = np.array(y)
+
+    X = torch.tensor(X, dtype=torch.float32)
+    y = torch.tensor(y, dtype=torch.float32)
 
-    return df
+    return X, y