Create MLCryptoForecasterAllAssets.py

MLCryptoForecasterAllAssets.py

@@ -0,0 +1,107 @@
+import os
+import pandas as pd
+import numpy as np
+from datetime import timedelta
+from binance.client import Client
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import classification_report
+import ta
+
+# Initialize Binance client (insert API keys if needed)
+client = Client()
+
+# Settings
+interval = Client.KLINE_INTERVAL_4HOUR
+
+# Retrieve all trading symbols quoted in USDT
+exchange_info = client.get_exchange_info()
+symbols = [s['symbol'] for s in exchange_info['symbols'] 
+           if s['status'] == 'TRADING' and s['quoteAsset'] == 'USDT']
+
+# Function to process a single symbol
+def process_symbol(symbol):
+    data_file = f"{symbol}_data_4h_full.csv"
+    # Load or download data
+    if os.path.exists(data_file):
+        df = pd.read_csv(data_file, index_col=0, parse_dates=True)
+        last_ts = df.index[-1]
+        start_time = last_ts + timedelta(hours=4)
+        start_str = start_time.strftime("%d %B %Y %H:%M:%S")
+        new_klines = client.get_historical_klines(symbol, interval, start_str)
+        if new_klines:
+            new_df = pd.DataFrame(new_klines, columns=[
+                'timestamp','open','high','low','close','volume',
+                'close_time','quote_av','trades','tb_base_av','tb_quote_av','ignore'
+            ])
+            new_df = new_df[['timestamp','open','high','low','close','volume']]
+            new_df[['open','high','low','close','volume']] = new_df[['open','high','low','close','volume']].astype(float)
+            new_df['timestamp'] = pd.to_datetime(new_df['timestamp'], unit='ms')
+            new_df.set_index('timestamp', inplace=True)
+            df = pd.concat([df, new_df])
+            df = df[~df.index.duplicated(keep='first')]
+            df.to_csv(data_file)
+    else:
+        klines = client.get_historical_klines(symbol, interval, "01 December 2021")
+        df = pd.DataFrame(klines, columns=[
+            'timestamp','open','high','low','close','volume',
+            'close_time','quote_av','trades','tb_base_av','tb_quote_av','ignore'
+        ])
+        df = df[['timestamp','open','high','low','close','volume']]
+        df[['open','high','low','close','volume']] = df[['open','high','low','close','volume']].astype(float)
+        df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
+        df.set_index('timestamp', inplace=True)
+        df.to_csv(data_file)
+
+    # Feature Engineering
+    df['rsi'] = ta.momentum.RSIIndicator(df['close'], window=14).rsi()
+    df['macd'] = ta.trend.MACD(df['close']).macd()
+    for span in [10, 20, 50, 100]:
+        df[f'ema_{span}'] = df['close'].ewm(span=span, adjust=False).mean()
+    for window in [10, 20, 50, 100]:
+        df[f'sma_{window}'] = df['close'].rolling(window=window).mean()
+    bb = ta.volatility.BollingerBands(df['close'], window=20, window_dev=2)
+    df['bb_width'] = (bb.bollinger_hband() - bb.bollinger_lband()) / bb.bollinger_mavg()
+    df['atr'] = ta.volatility.AverageTrueRange(df['high'], df['low'], df['close'], window=14).average_true_range()
+    df['adx'] = ta.trend.ADXIndicator(df['high'], df['low'], df['close'], window=14).adx()
+    stoch = ta.momentum.StochasticOscillator(df['high'], df['low'], df['close'], window=14)
+    df['stoch_k'] = stoch.stoch()
+    df['stoch_d'] = stoch.stoch_signal()
+    df['williams_r'] = ta.momentum.WilliamsRIndicator(df['high'], df['low'], df['close'], lbp=14).williams_r()
+    df['cci'] = ta.trend.CCIIndicator(df['high'], df['low'], df['close'], window=20).cci()
+    df['momentum'] = df['close'] - df['close'].shift(10)
+    ichi = ta.trend.IchimokuIndicator(df['high'], df['low'], window1=9, window2=26, window3=52)
+    df['ichimoku_senkou_span_a'] = ichi.ichimoku_a()
+    df['ichimoku_senkou_span_b'] = ichi.ichimoku_b()
+
+    # Trend Label
+    conditions = [
+        (df['close'] > df['ichimoku_senkou_span_a']) & (df['close'] > df['ichimoku_senkou_span_b']),
+        (df['close'] < df['ichimoku_senkou_span_a']) & (df['close'] < df['ichimoku_senkou_span_b'])
+    ]
+    df['cloud_trend'] = np.select(conditions, [1, 0], default=-1)
+    df.dropna(inplace=True)
+
+    # Model Training
+    features = df.drop(columns=['open','high','low','close','volume','cloud_trend']).columns
+    X, y = df[features], df['cloud_trend']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=False)
+    model = RandomForestClassifier(n_estimators=200, class_weight='balanced', random_state=42)
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+
+    print(f"\n=== {symbol} ===")
+    print(classification_report(y_test, y_pred, zero_division=0))
+
+    # Latest prediction
+    latest_feat = X.iloc[-1].values.reshape(1, -1)
+    pred = model.predict(latest_feat)[0]
+    labels = {1: 'Uptrend', 0: 'Downtrend', -1: 'Neutral'}
+    print(f"Predicted next trend for {symbol}: {labels[pred]}")
+
+# Main loop
+for s in symbols:
+    try:
+        process_symbol(s)
+    except Exception as e:
+        print(f"Error processing {s}: {e}")