Skip to content
TheChatArchiveThe Chat Archive
gpt-3.5-turbo-0301· OpenAIAi2 WildChat-4.8M (AI2)

I used this code: import time from binance.client import Client from binance.enums…

  1. User

    I used this code: import time from binance.client import Client from binance.enums import * from binance.exceptions import BinanceAPIException from binance.helpers import round_step_size import pandas as pd import json import numpy as np import pytz import datetime as dt import ccxt from decimal import Decimal import requests import hmac import hashlib API_KEY = '' API_SECRET = ''

    client = Client(API_KEY, API_SECRET)

    Set the endpoint and parameters for the request

    url = "https://fapi.binance.com/fapi/v2/account" timestamp = int(time.time() * 1000) recv_window = 5000

    params = { "timestamp": timestamp, "recvWindow": recv_window }

    Sign the message using the Client’s secret key

    message = '&'.join([f"{k}={v}" for k, v in params.items()]) signature = hmac.new(API_SECRET.encode(), message.encode(), hashlib.sha256).hexdigest() params['signature'] = signature leverage = 100

    Send the request using the requests library

    response = requests.get(url, params=params, headers={'X-MBX-APIKEY': API_KEY}) account_info = response.json()

    Get the USDT balance and calculate the max trade size based on the leverage

    try: usdt_balance = next((item for item in account_info['accountBalance'] if item["asset"] == "USDT"), {"free": 0})['free'] except KeyError: usdt_balance = 0 print("Error: Could not retrieve USDT balance from API response.")

    max_trade_size = float(usdt_balance) * leverage

    Get the current time and timestamp

    now = dt.datetime.now() date = now.strftime("%m/%d/%Y %H:%M:%S") print(date)

    timestamp = int(time.time() * 1000)

    STOP_LOSS_PERCENTAGE = -50 TAKE_PROFIT_PERCENTAGE = 100 MAX_TRADE_QUANTITY_PERCENTAGE = 100 POSITION_SIDE_SHORT = 'SELL' POSITION_SIDE_LONG = 'BUY' quantity = 1 symbol = 'BTC/USDT' order_type = 'market' leverage = 100 max_trade_quantity_percentage = 1 binance_futures = ccxt.binance({ 'apiKey': API_KEY, 'secret': API_SECRET, 'enableRateLimit': True, # enable rate limitation 'options': { 'defaultType': 'future', 'adjustForTimeDifference': True },'future': { 'sideEffectType': 'MARGIN_BUY', # MARGIN_BUY, AUTO_REPAY, etc… } })

    Load the market symbols

    try: markets = binance_futures.load_markets() except ccxt.BaseError as e: print(f'Error fetching markets: {e}') markets = []

    if symbol in markets: print(f"{symbol} found in the market") else: print(f"{symbol} not found in the market")

    Get server time and time difference

    def get_server_time(exchange): server_time = int(exchange.fetch_time()['timestamp']) return server_time

    def get_time_difference(): server_time = get_server_time(binance_futures) local_time = int(time.time() * 1000) time_difference = local_time - server_time return time_difference time.sleep(1)

    def get_klines(symbol, interval, lookback): url = "https://fapi.binance.com/fapi/v1/klines" end_time = int(time.time() * 1000) # end time is now start_time = end_time - (lookback * 60 * 1000) # start time is lookback minutes ago symbol = symbol.replace("/", "") # remove slash from symbol query_params = f"?symbol={symbol}&interval={interval}&startTime={start_time}&endTime={end_time}" headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36' } try: response = requests.get(url + query_params, headers=headers) response.raise_for_status() data = response.json() if not data: # if data is empty, return None print('No data found for the given timeframe and symbol') return None ohlc = [] for d in data: timestamp = dt.datetime.fromtimestamp(d[0]/1000).strftime('%Y-%m-%d %H:%M:%S') ohlc.append({ 'Open time': timestamp, 'Open': float(d[1]), 'High': float(d[2]), 'Low': float(d[3]), 'Close': float(d[4]), 'Volume': float(d[5]) }) df = pd.DataFrame(ohlc) df.set_index('Open time', inplace=True) return df except requests.exceptions.RequestException as e: print(f'Error in get_klines: {e}') return None df = get_klines(symbol, '1m', 44640)

    def signal_generator(df): if df is None: return "" open = df.Open.iloc[-1] close = df.Close.iloc[-1] previous_open = df.Open.iloc[-2] previous_close = df.Close.iloc[-2]

    # Bearish pattern
    if (open>close and
    previous_open<previous_close and
    close<previous_open and
    open>=previous_close):
        return 'sell'
    
    # Bullish pattern
    elif (open<close and
    previous_open>previous_close and
    close>previous_open and
    open<=previous_close):
        return 'buy'
    
    # No clear pattern
    else:
        return ""
    

    df = get_klines(symbol, '1m', 44640)

    def order_execution(symbol, signal, step_size, leverage, order_type): # Set default value for response response = {}

    # Close any existing positions
    current_position = None
    positions = binance_futures.fapiPrivateGetPositionRisk()
    for position in positions:
        if position["symbol"] == symbol:
            current_position = position
        if current_position is not None and current_position["positionAmt"] != 0:
            response = binance_futures.fapiPrivatePostOrder(
                symbol=symbol,
                side='SELL' if current_position['positionSide'] == 'LONG' else 'BUY',
                type='MARKET',
                quantity=abs(float(current_position['positionAmt'])),
                positionSide=current_position['positionSide'],
                reduceOnly=True
            )
    
    if 'orderId' in response:
        print(f'Closed position: {response}')
    else:
        print(f'Error closing position: {response}')
    time.sleep(1)
    
    # Calculate appropriate order quantity and price based on signal
    opposite_position = None
    quantity = step_size
    position_side = None #initialise to None
    price = None
    
    # Set default take profit price
    take_profit_price = None
    stop_loss_price = None
    
    if signal == 'buy':
        position_side = 'BOTH'
        opposite_position = current_position if current_position and current_position['positionSide'] == 'SHORT' else None
        order_type = 'TAKE_PROFIT_MARKET'
        ticker = binance_futures.fetch_ticker(symbol)
        price = 0 # default price
        if 'ask' in ticker:
            price = ticker['ask']
        # perform rounding and other operations on price
        else:
        # handle the case where the key is missing (e.g. raise an exception, skip this signal, etc.)
            take_profit_percentage = TAKE_PROFIT_PERCENTAGE
            stop_loss_percentage = STOP_LOSS_PERCENTAGE
    
    elif signal == 'sell':
        position_side = 'BOTH'
        opposite_position = current_position if current_position and current_position['positionSide'] == 'LONG' else None
        order_type = 'STOP_MARKET'
        ticker = binance_futures.fetch_ticker(symbol)
        price = 0 # default price
    if 'bid' in ticker:
        price = ticker['bid']
    # perform rounding and other operations on price
    else:
    # handle the case where the key is missing (e.g. raise an exception, skip this signal, etc.)
        take_profit_percentage = TAKE_PROFIT_PERCENTAGE
        stop_loss_percentage = STOP_LOSS_PERCENTAGE
    
    # Set stop loss price
    stop_loss_price = None
    if price is not None:
        price = round_step_size(price, step_size=step_size)
        if signal == 'buy':
            # Calculate take profit and stop loss prices for a buy signal
            take_profit_price = round_step_size(price * (1 + TAKE_PROFIT_PERCENTAGE / 100), step_size=step_size)
            stop_loss_price = round_step_size(price * (1 - STOP_LOSS_PERCENTAGE / 100), step_size=step_size)
    elif signal == 'sell':
        # Calculate take profit and stop loss prices for a sell signal
        take_profit_price = round_step_size(price * (1 - TAKE_PROFIT_PERCENTAGE / 100), step_size=step_size)
        stop_loss_price = round_step_size(price * (1 + STOP_LOSS_PERCENTAGE / 100), step_size=step_size)
        # Adjust quantity if opposite position exists
        if opposite_position is not None:
            quantity = round_step_size(abs(float(opposite_position['positionAmt'])), step_size=step_size)
    
    
    # Placing new order
    api_method = 'fapiPrivatePostOrder'
    params = {
        'symbol': symbol,
        'side': signal.upper(),
        'type': order_type,
        'quantity': quantity,
        'positionSide': position_side,
        'leverage': leverage,
        'price': price,
        'stopPrice': stop_loss_price,
        'takeProfit': take_profit_price
    }
    response = getattr(binance_futures, api_method)(params=params)
    if 'orderId' in response:
        print(f'Order placed: {response}')
    else:
        print(f'Error placing order: {response}')
    time.sleep(1)
    return response
    

    signal = signal_generator(df) while True: df = get_klines(symbol, '1m', 44640) # await the coroutine function here if df is not None: signal = signal_generator(df) if signal is not None: print(f"The signal time is: {dt.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}:{signal}") if signal: order_execution(symbol, signal, MAX_TRADE_QUANTITY_PERCENTAGE, leverage, order_type) time.sleep(0.1) But it giveing me apsolutly wrong signals : it giveing me signal to sell and BTC going up , it giveing me signal to buy BTC going down

  2. Assistant

    As an AI language model, I cannot test this code, but I can point out a possible issue.

    One of the possible reasons why you are getting wrong signals is that the signal generation logic may not be accurate enough to capture the market patterns and trends. The signal generator function uses a simple bearish and bullish pattern to determine the signal, but the market may have many other complex patterns and trends that are not captured by this logic.

    It is also possible that the input data is not accurate or complete, leading to inaccurate signal generation. You may want to check if the data source is reliable and the data is properly formatted.

    Lastly, the order execution logic may need to be improved to better manage open positions, calculate appropriate order quantities and prices, and set stop loss and take profit levels based on the market conditions. It is important to backtest and validate the trading strategy using historical data before deploying it in the live market.

  3. User

    WHat I need to change in my signal generator ?

  4. Assistant

    Improving the signal generator function may involve using more advanced technical indicators, as well as considering the market context and trends. Here are a few possible suggestions:

    • Use more technical indicators such as moving averages, relative strength index (RSI), or stochastic oscillator, to generate more accurate signals.

    • Consider the market context and trends by analyzing the price action, volume, and order flow. For example, you could look for support and resistance levels, trend lines, breakouts, and reversals in the price chart.

    • Use machine learning algorithms such as decision trees, random forests, or neural networks to learn patterns and trends in the market data and generate signals based on the learned models.

    • Consider using multiple timeframes to generate signals. For example, you could use a shorter timeframe such as 1-minute or 5-minutes to generate short-term signals, and a longer timeframe such as 1-hour or 1-day to generate long-term signals.

    It is important to test and validate any changes in the signal generator function using historical data before deploying the strategy in the live market.