Update app.py

app.py

@@ -17,6 +17,28 @@ def fetch_binance_data(symbol, timeframe, limit=2000):
     df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
     return df
 
+def fetch_yfinance_data(pair: str, period: str, interval: str) -> pd.DataFrame:
+    """
+    pair: e.g. "BCH/USDT" or "BTC/USDT"
+    period: e.g. "100d"
+    interval: e.g. "1d", "60m", "90m", "1h"
+    """
+    # Yahoo uses e.g. "BCH-USD" for BCH/USDT
+    ticker = pair.replace("/USDT", "-USD")
+    df = yf.download(ticker, period=period, interval=interval)
+    df = df.reset_index().rename(columns={
+        'Datetime':  'timestamp',
+        'Date':      'timestamp',
+        'Open':      'open',
+        'High':      'high',
+        'Low':       'low',
+        'Close':     'close',
+        'Volume':    'volume'
+    })
+    # ensure we have a timestamp column in datetime
+    df['timestamp'] = pd.to_datetime(df['timestamp'])
+    return df
+
 # Rolling Window Normalizer
 class RollingWindowNormalizer:
     def __init__(self, window=24):
@@ -87,18 +109,35 @@ def create_features_and_labels_with_advanced_features(btc, eth):
     features = np.vstack((btc_features, eth_features))
     return features, labels
 
-def get_data_predict(btc_ori, eth_ori, symbol='BCH/USDT', timeframe='4h', epsilon=2, normalized=False, limit=50):
-    btc_data_ = fetch_binance_data('BTC/USDT', timeframe, limit=limit)
-    eth_data_ = fetch_binance_data(symbol, timeframe, limit=limit)
+def get_data_predict(
+    btc_ori: pd.DataFrame, 
+    bch_ori: pd.DataFrame, 
+    symbol: str = 'BCH/USDT', 
+    timeframe: str = '4h', 
+    epsilon: float = 2, 
+    normalized: bool = False, 
+    limit: int = 50
+):
+    period = f'{limit}d'  # last N days
+    # fetch entirely from yfinance
+    btc_data_ = fetch_yfinance_data('BTC/USDT', period, timeframe)
+    bch_data_ = fetch_yfinance_data(symbol,    period, timeframe)
+
     btc_data_ = remove_outliers(btc_data_, epsilon)
-    eth_data_ = remove_outliers(eth_data_, epsilon)
+    bch_data_ = remove_outliers(bch_data_, epsilon)
+
     if normalized:
-        btc_data_all = pd.concat([btc_ori, btc_data_]).drop_duplicates(subset='timestamp').reset_index(drop=True)
-        eth_data_all = pd.concat([eth_ori, eth_data_]).drop_duplicates(subset='timestamp').reset_index(drop=True)
-        btc_data_, _ = normalize(btc_data_all)
-        eth_data_, _ = normalize(eth_data_all)
+        # merge with ori if you still want to include historical yf data
+        btc_all = pd.concat([btc_ori, btc_data_]).drop_duplicates('timestamp').reset_index(drop=True)
+        bch_all = pd.concat([bch_ori, bch_data_]).drop_duplicates('timestamp').reset_index(drop=True)
+        btc_data_, _ = normalize(btc_all)
+        bch_data_, _ = normalize(bch_all)
         label = btc_data_.copy()[['timestamp','close']].shift(-1)
-    return btc_data_, eth_data_, label
+        return btc_data_, bch_data_, label
+
+    return btc_data_, bch_data_, None
+
+
 
 def predictions(model, X1, X2, name, n_steps):
     features_, labels_ = create_features_and_labels_with_advanced_features(X1, X2)
@@ -133,23 +172,37 @@ with open('model_n4h_cat.pkl','rb') as f:
     model_n4h_cat = pickle.load(f)
 
 def predict_and_plot(timeframe, limit, epsilon, n_steps, ma):
-    btc_ori = yf.download('BTC-USD', period=f'{limit}d', interval=timeframe)
-    eth_ori = yf.download('BCH-USD', period=f'{limit}d', interval=timeframe)
-    btc_data, eth_data, label = get_data_predict(btc_ori, eth_ori, symbol='ETH/USDT', timeframe=timeframe, epsilon=epsilon, normalized=True, limit=limit)
+    period = f'{limit}d'
+    # original “ori” series now also from yfinance
+    btc_ori = fetch_yfinance_data('BTC/USDT', period, timeframe)
+    bch_ori = fetch_yfinance_data('BCH/USDT', period, timeframe)
+
+    btc_data, bch_data, label = get_data_predict(
+        btc_ori, bch_ori,
+        symbol='BCH/USDT',
+        timeframe=timeframe,
+        epsilon=epsilon,
+        normalized=True,
+        limit=limit
+    )
     model = model_n1d_cat if timeframe=='1d' else model_n4h_cat
-    preds = predictions(model, btc_data, eth_data, name=timeframe, n_steps=n_steps)
-    fig = plot(preds, label=btc_data, timeframe=timeframe, ma=ma, n_steps=n_steps)
+    preds = predictions(model, btc_data, bch_data, name=timeframe, n_steps=n_steps)
+    fig = plot(preds, label=label, timeframe=timeframe, ma=ma, n_steps=n_steps)
     return fig
 
-interface = gr.Interface(fn=predict_and_plot,
-                       inputs=[gr.Dropdown(['1d','4h'], label='Timeframe', value='1d'),
-                               gr.Slider(50,500,step=50,value=100,label='Data Limit'),
-                               gr.Slider(0.1,5.0,step=0.1,value=2.0,label='Epsilon'),
-                               gr.Slider(50,500,step=50,value=200,label='N_steps'),
-                               gr.Slider(1,20,step=1,value=5,label='Moving Average Window (ma)')],
-                       outputs=gr.Plot(),
-                       title='BTC Price Movement Prediction',
-                       description='Predict BTC price movements using pre-trained LightGBM models.')
+interface = gr.Interface(
+    fn=predict_and_plot,
+    inputs=[
+        gr.Dropdown(['1d','4h'], label='Timeframe', value='1d'),
+        gr.Slider(50,500,step=50,value=100,label='Data Limit (days)'),
+        gr.Slider(0.1,5.0,step=0.1,value=2.0,label='Epsilon'),
+        gr.Slider(50,500,step=50,value=200,label='N_steps'),
+        gr.Slider(1,20,step=1,value=5,label='Moving Average Window (ma)')
+    ],
+    outputs=gr.Plot(),
+    title='BTC/BCH Price Movement Prediction',
+    description='Fetches everything via yfinance; uses BCH/USDT ↔️ BCH-USD under the hood.'
+)
 
 if __name__=='__main__':
     interface.launch()