Create MLCryptoForecasterICH.py

MLCryptoForecasterICH.py

@@ -0,0 +1,148 @@
+import os
+import pandas as pd
+import numpy as np
+from datetime import datetime, 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
+
+# Connect to Binance
+client = Client()
+
+# Settings
+DATA_FILE = "btc_data_4h_full.csv"
+symbol = "BTCUSDT"
+interval = Client.KLINE_INTERVAL_4HOUR
+
+# Load or download data
+if os.path.exists(DATA_FILE):
+    print("Loading existing data...")
+    df = pd.read_csv(DATA_FILE, index_col=0, parse_dates=True)
+    last_timestamp = df.index[-1]
+    start_time = last_timestamp + timedelta(hours=4)
+    start_str = start_time.strftime("%d %B %Y %H:%M:%S")
+    
+    print(f"Downloading new data from {start_str}...")
+    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 = new_df.set_index('timestamp')
+        df = pd.concat([df, new_df])
+        df = df[~df.index.duplicated(keep='first')]
+        df.to_csv(DATA_FILE)
+else:
+    print("Downloading all data from scratch...")
+    klinesT = client.get_historical_klines(symbol, interval, "01 December 2021")
+    df = pd.DataFrame(klinesT, 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 = df.set_index('timestamp')
+    df.to_csv(DATA_FILE)
+
+# Feature Engineering - Maximum Indicators
+# (RSI, MACD, EMAs, SMAs, BB, ATR, ADX, Stochastic, Williams %R, CCI, Momentum)
+
+# RSI (Relative Strength Index)
+df['rsi'] = ta.momentum.RSIIndicator(df['close'], window=14).rsi()
+
+# MACD (Moving Average Convergence Divergence)
+df['macd'] = ta.trend.MACD(df['close']).macd()
+
+# EMA (Exponential Moving Averages)
+df['ema_10'] = df['close'].ewm(span=10, adjust=False).mean()
+df['ema_20'] = df['close'].ewm(span=20, adjust=False).mean()
+df['ema_50'] = df['close'].ewm(span=50, adjust=False).mean()
+df['ema_100'] = df['close'].ewm(span=100, adjust=False).mean()
+
+# SMA (Simple Moving Averages)
+df['sma_10'] = df['close'].rolling(window=10).mean()
+df['sma_20'] = df['close'].rolling(window=20).mean()
+df['sma_50'] = df['close'].rolling(window=50).mean()
+df['sma_100'] = df['close'].rolling(window=100).mean()
+
+# Bollinger Bands
+bb_indicator = ta.volatility.BollingerBands(df['close'], window=20, window_dev=2)
+df['bb_bbm'] = bb_indicator.bollinger_mavg()
+df['bb_bbh'] = bb_indicator.bollinger_hband()
+df['bb_bbl'] = bb_indicator.bollinger_lband()
+df['bb_width'] = (df['bb_bbh'] - df['bb_bbl']) / df['bb_bbm']
+
+# Average True Range (ATR)
+df['atr'] = ta.volatility.AverageTrueRange(df['high'], df['low'], df['close'], window=14).average_true_range()
+
+# ADX - Average Directional Index (Trend strength)
+df['adx'] = ta.trend.ADXIndicator(df['high'], df['low'], df['close'], window=14).adx()
+
+# Stochastic Oscillator
+stoch = ta.momentum.StochasticOscillator(df['high'], df['low'], df['close'], window=14)
+df['stoch_k'] = stoch.stoch()
+df['stoch_d'] = stoch.stoch_signal()
+
+# Williams %R
+df['williams_r'] = ta.momentum.WilliamsRIndicator(df['high'], df['low'], df['close'], lbp=14).williams_r()
+
+# CCI (Commodity Channel Index)
+df['cci'] = ta.trend.CCIIndicator(df['high'], df['low'], df['close'], window=20).cci()
+
+# Momentum (manual calculation)
+df['momentum'] = df['close'] - df['close'].shift(10)  # Simple momentum calculation
+
+# Ichimoku Cloud Indicators
+ichimoku = ta.trend.IchimokuIndicator(df['high'], df['low'], window1=9, window2=26, window3=52)
+df['ichimoku_tenkan_sen'] = ichimoku.ichimoku_conversion_line()
+df['ichimoku_kijun_sen'] = ichimoku.ichimoku_base_line()
+df['ichimoku_senkou_span_a'] = ichimoku.ichimoku_a()
+df['ichimoku_senkou_span_b'] = ichimoku.ichimoku_b()
+df['ichimoku_chikou_span'] = df['close'].shift(-26)
+
+# Create Uptrend/Downtrend labels based on cloud (1 = Uptrend, 0 = Downtrend, -1 = Neutral)
+def ichimoku_trend_label(row):
+    if row['close'] > row['ichimoku_senkou_span_a'] and row['close'] > row['ichimoku_senkou_span_b']:
+        return 1  # Uptrend
+    elif row['close'] < row['ichimoku_senkou_span_a'] and row['close'] < row['ichimoku_senkou_span_b']:
+        return 0  # Downtrend
+    else:
+        return -1  # Neutral
+
+# Apply function to create 'cloud_trend' labels
+df['cloud_trend'] = df.apply(ichimoku_trend_label, axis=1)
+
+# Drop rows with NaN values
+df = df.dropna()
+
+# Features and Target
+features = df.drop(columns=['open', 'high', 'low', 'close', 'volume', 'cloud_trend']).columns
+X = df[features]
+y = df['cloud_trend']  # Now predicting cloud trend: up, down, or neutral
+
+# Train/Test Split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=False)
+
+# Train Random Forest (with class balancing)
+model = RandomForestClassifier(n_estimators=200, class_weight="balanced", random_state=42)
+model.fit(X_train, y_train)
+
+# Evaluate
+y_pred = model.predict(X_test)
+print(classification_report(y_test, y_pred))
+
+# Predict latest movement
+latest_features = X.iloc[-1].values.reshape(1, -1)
+predicted_trend = model.predict(latest_features)
+trend_label = predicted_trend[0]
+
+# Print trend prediction
+if trend_label == 1:
+    print("Predicted next trend: Uptrend")
+elif trend_label == 0:
+    print("Predicted next trend: Downtrend")
+else:
+    print("Predicted next trend: Neutral (inside the cloud)")