Update MLCryptoForecasterAllAssetsTPSL.py

MLCryptoForecasterAllAssetsTPSL.py

@@ -9,6 +9,7 @@ from sklearn.metrics import classification_report
 import ta
 
 # Function to log results to both console and file
+# Does not insert blank lines; blank lines added explicitly after each asset block
 def log_results(message, filename="predictions_results.txt"):
     print(message)
     with open(filename, "a") as f:
@@ -56,7 +57,6 @@ def optimize_tp_sl(df, signals, side, pgrid, lgrid):
 
 # Process each symbol
 for symbol in symbols:
-    # Log header for this asset
     log_results(f"=== {symbol} ===", result_file)
 
     # Load or download historical data
@@ -86,8 +86,8 @@ for symbol in symbols:
     # Compute technical indicators
     df['rsi'] = ta.momentum.RSIIndicator(df['close'], window=14).rsi()
     df['macd'] = ta.trend.MACD(df['close']).macd()
-    for s in [10,20,50,100]: df[f'ema_{s}'] = df['close'].ewm(span=s).mean()
-    for w in [10,20,50,100]: df[f'sma_{w}'] = df['close'].rolling(window=w).mean()
+    for s in [10, 20, 50, 100]: df[f'ema_{s}'] = df['close'].ewm(span=s).mean()
+    for w in [10, 20, 50, 100]: df[f'sma_{w}'] = df['close'].rolling(window=w).mean()
     bb = ta.volatility.BollingerBands(df['close'], window=20, window_dev=2)
     df['bbw'] = (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()
@@ -102,13 +102,13 @@ for symbol in symbols:
     df.dropna(inplace=True)
 
     # Label signals based on Ichimoku cloud
-    df['signal'] = np.select(
-        [(df['close']>df['span_a'])&(df['close']>df['span_b']),
-         (df['close']<df['span_a'])&(df['close']<df['span_b'])],
-        [1,0], default=-1)
+    df['signal'] = np.select([
+        (df['close'] > df['span_a']) & (df['close'] > df['span_b']),
+        (df['close'] < df['span_a']) & (df['close'] < df['span_b'])
+    ], [1, 0], default=-1)
 
     # Train/test split
-    features = [c for c in df.columns if c not in ['open','high','low','close','volume','signal']]
+    features = [c for c in df.columns if c not in ['open', 'high', 'low', 'close', 'volume', 'signal']]
     X, y = df[features], df['signal']
     Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.2, shuffle=False)
     model = RandomForestClassifier(n_estimators=200, class_weight='balanced', random_state=42)
@@ -117,18 +117,20 @@ for symbol in symbols:
 
     # Log classification report
     report = classification_report(yte, ypr, zero_division=0)
-    log_results(f"Classification report for {symbol}:\n{report}", result_file)
+    log_results(f"Classification report for {symbol}: {report}", result_file)
 
     # Predict latest trend and log time & price
+    latest_df = X.iloc[-1:]  # DataFrame for prediction
+    trend_label = model.predict(latest_df)[0]
     pred_time = df.index[-1]
     pred_price = df['close'].iloc[-1]
-    latest = model.predict(X.iloc[-1:].values)[0]
-    trend_map = {1:'Uptrend',0:'Downtrend',-1:'Neutral'}
-    log_results(f"Time: {pred_time}, Price: {pred_price:.2f}, Prediction: {trend_map[latest]}", result_file)
+    trend_str = {1:'Uptrend', 0:'Downtrend', -1:'Neutral'}[trend_label]
+    log_results(f"Time: {pred_time}, Price: {pred_price:.2f}, Prediction: {trend_str}", result_file)
 
     # Optimize TP/SL and log results
-    hist_sign = model.predict(X.values)
-    pgrid = np.arange(0.01,0.1,0.01); lgrid = np.arange(0.01,0.1,0.01)
+    hist_sign = model.predict(X)  # Pass DataFrame to avoid warning
+    pgrid = np.arange(0.01, 0.1, 0.01)
+    lgrid = np.arange(0.01, 0.1, 0.01)
     up_tp, up_sl, _ = optimize_tp_sl(df, hist_sign, 1, pgrid, lgrid)
     dn_tp, dn_sl, _ = optimize_tp_sl(df, hist_sign, 0, pgrid, lgrid)
     log_results(f"Optimal UP TP/SL: +{up_tp*100:.1f}% / -{up_sl*100:.1f}%", result_file)