randomforestML.py

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 (Fill your own API keys if live)
# client = Client(api_key, api_secret)
client = Client()

# File to store the historical data
DATA_FILE = "btc_data.csv"
symbol = "BTCUSDT"
interval = Client.KLINE_INTERVAL_4HOUR

# Load existing data or download fresh
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]
    # Binance gives data in 15min intervals, so move forward
    start_time = last_timestamp + timedelta(minutes=15)
    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')
        
        # Append and remove any duplicates (just in case)
        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: Add technical indicators
df['rsi'] = ta.momentum.RSIIndicator(df['close'], window=14).rsi()
df['sma_fast'] = df['close'].rolling(window=5).mean()
df['sma_slow'] = df['close'].rolling(window=20).mean()
df['macd'] = ta.trend.MACD(df['close']).macd()
df['ema'] = df['close'].ewm(span=10, adjust=False).mean()

# Create target: 1 if next close > current close, else 0
df['target'] = np.where(df['close'].shift(-1) > df['close'], 1, 0)

# Drop rows with NaN values
df = df.dropna()

# Features and Target
features = ['rsi', 'sma_fast', 'sma_slow', 'macd', 'ema']
X = df[features]
y = df['target']

# 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
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Evaluate
y_pred = model.predict(X_test)
print(classification_report(y_test, y_pred))

# Predict next movement
latest_features = X.iloc[-1].values.reshape(1, -1)
predicted_direction = model.predict(latest_features)
print(f"Predicted next movement: {'UP' if predicted_direction[0] == 1 else 'DOWN'}")