Skip to content
TheChatArchiveThe Chat Archive
gpt-3.5-turbo-0613· openaiHugging Face Suzhen/CodeChat

I used your signal_generator code: import time from binance.client import Client from…

  1. User

    I used your signal_generator 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 import ntplib import os import ta import ta.volatility API_KEY = '' API_SECRET = ''

    client = Client(API_KEY, API_SECRET)

    def sync_time(): server_time = requests.get('https://api.binance.com/api/v3/time').json()['serverTime'] local_time = int(time.time() * 1000) time_difference = server_time - local_time # Set the system clock to the new time os.system(f'sudo date -s @{int(server_time/1000)}') print(f'New time: {dt.datetime.now()}')

    Sync your local time with the server time

    sync_time()

    Set the endpoint and parameters for the request

    url = "https://fapi.binance.com/fapi/v1/klines" symbol = 'COMP/USDT' interval = '1m' lookback = 44640 timestamp = int(time.time() * 1000) - 500 # subtract 500ms from local time to account for clock-drift recv_window = 60000 # increased recv_window value params = { "symbol": symbol.replace("/", ""), "interval": interval, "startTime": int((time.time() - lookback * 60) * 1000), "endTime": int(time.time() * 1000), "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

    Send the request using the requests library

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

    Check for errors in the response

    response.raise_for_status()

    STOP_LOSS_PERCENTAGE = -50 TAKE_PROFIT_PERCENTAGE = 100 MAX_TRADE_QUANTITY_PERCENTAGE = 100 POSITION_SIDE_SHORT = 'SELL' POSITION_SIDE_LONG = 'BUY' quantity = 1 symbol = 'COMP/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… } }) time.sleep(1) print(symbol) 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' } 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 df = get_klines(symbol, '1m', 44640)

    def signal_generator(df): # Calculate EMA and MA lines df['EMA5'] = df['Close'].ewm(span=5, adjust=False).mean() df['EMA10'] = df['Close'].ewm(span=10, adjust=False).mean() df['EMA20'] = df['Close'].ewm(span=20, adjust=False).mean() df['EMA50'] = df['Close'].ewm(span=50, adjust=False).mean() df['EMA100'] = df['Close'].ewm(span=100, adjust=False).mean() df['EMA200'] = df['Close'].ewm(span=200, adjust=False).mean() df['MA10'] = df['Close'].rolling(window=10).mean() df['MA20'] = df['Close'].rolling(window=20).mean() df['MA50'] = df['Close'].rolling(window=50).mean() df['MA100'] = df['Close'].rolling(window=100).mean() # Extract necessary prices from df open_price = df.Open.iloc[-1] close_price = df.Close.iloc[-1] previous_open = df.Open.iloc[-2] previous_close = df.Close.iloc[-2]

    # Calculate the last candlestick
    last_candle = df.iloc[-1]
    current_price = df.Close.iloc[-1]
    
    # Initialize analysis variables
    ema_analysis = []
    candle_analysis = []
    
    # EMA strategy - buy signal
    if df['EMA5'].iloc[-1] > df['EMA10'].iloc[-1] > df['EMA20'].iloc[-1] > df['EMA50'].iloc[-1]:
        ema_analysis.append('buy')
    
    # EMA strategy - sell signal
    elif df['EMA5'].iloc[-1] < df['EMA10'].iloc[-1] < df['EMA20'].iloc[-1] < df['EMA50'].iloc[-1]:
        ema_analysis.append('sell')
    
    # Check for bullish candlestick pattern - buy signal
    open_price = df['Open'].iloc[-1]
    close_price = df['Close'].iloc[-1]
    previous_open = df['Open'].iloc[-2]
    previous_close = df['Close'].iloc[-2]
    
    if (
        open_price < close_price and
        previous_open > previous_close and
        close_price > previous_open and
        open_price <= previous_close
    ):
        candle_analysis.append('buy')
    
    # Check for bearish candlestick pattern - sell signal
    elif (
        open_price > close_price and
        previous_open < previous_close and
        close_price < previous_open and
        open_price >= previous_close
    ):
        candle_analysis.append('sell')
    
    # Determine final signal
    if 'buy' in ema_analysis and 'buy' in candle_analysis and df['Close'].iloc[-1] > df['EMA50'].iloc[-1]:
        final_signal = 'buy'
    elif 'sell' in ema_analysis and 'sell' in candle_analysis and df['Close'].iloc[-1] < df['EMA50'].iloc[-1]:
        final_signal = 'sell'
    else:
        final_signal = ''
    return final_signal
    

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

    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}") time.sleep(1) But it gave me wrong signal , plase can you give me more good code which will give me right signals , and please can you add in my EMA analysis EMA 100 and EMA 200 lines please

  2. Assistant

    Certainly! Here is an updated version of your code with the additional EMA lines (100 and 200) added to the EMA analysis in the signal_generator function:

    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
    import ntplib
    import os
    import ta
    import ta.volatility
    
    API_KEY = ''
    API_SECRET = ''
    
    client = Client(API_KEY, API_SECRET)
    
    def sync_time():
        server_time = requests.get('https://api.binance.com/api/v3/time').json()['serverTime']
        local_time = int(time.time() * 1000)
        time_difference = server_time - local_time
        # Set the system clock to the new time
        os.system(f'sudo date -s @{int(server_time/1000)}')
        print(f'New time: {dt.datetime.now()}')
    
    # Sync your local time with the server time
    sync_time()
    
    # Set the endpoint and parameters for the request
    url = "https://fapi.binance.com/fapi/v1/klines"
    symbol = 'COMP/USDT'
    interval = '1m'
    lookback = 44640
    timestamp = int(time.time() * 1000) - 500 # subtract 500ms from local time to account for clock-drift
    recv_window = 60000 # increased recv_window value
    params = {
        "symbol": symbol.replace("/", ""),
        "interval": interval,
        "startTime": int((time.time() - lookback * 60) * 1000),
        "endTime": int(time.time() * 1000),
        "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
    
    # Send the request using the requests library
    response = requests.get(url, params=params, headers={'X-MBX-APIKEY': API_KEY})
    
    # Check for errors in the response
    response.raise_for_status()
    
    STOP_LOSS_PERCENTAGE = -50
    TAKE_PROFIT_PERCENTAGE = 100
    MAX_TRADE_QUANTITY_PERCENTAGE = 100
    POSITION_SIDE_SHORT = 'SELL'
    POSITION_SIDE_LONG = 'BUY'
    quantity = 1
    symbol = 'COMP/USDT'
    order_type = 'market'
    leverage = 100
    max_trade_quantity_percentage = 1
    binance_futures = ccxt.binance({
        'apiKey': API_KEY,
        'secret': API_SECRET,
        'enableRateLimit': True,
        'options': {
        'defaultType': 'future',
        'adjustForTimeDifference': True
        },'future': {
        'sideEffectType': 'MARGIN_BUY',
    }
    })
    time.sleep(1)
    print(symbol)
    
    def get_klines(symbol, interval, lookback):
        url = "https://fapi.binance.com/fapi/v1/klines"
        end_time = int(time.time() * 1000)
        start_time = end_time - (lookback * 60 * 1000)
        symbol = symbol.replace("/", "")
        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'
        }
        response = requests.get(url + query_params, headers=headers)
        response.raise_for_status()
        data = response.json()
        if not data:
            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
    
    df = get_klines(symbol, '1m', 44640)
    
    def signal_generator(df):
        df['EMA5'] = df['Close'].ewm(span=5, adjust=False).mean()
        df['EMA10'] = df['Close'].ewm(span=10, adjust=False).mean()
        df['EMA20'] = df['Close'].ewm(span=20, adjust=False).mean()
        df['EMA50'] = df['Close'].ewm(span=50, adjust=False).mean()
        df['EMA100'] = df['Close'].ewm(span=100, adjust=False).mean()
        df['EMA200'] = df['Close'].ewm(span=200, adjust=False).mean()
        df['MA10'] = df['Close'].rolling(window=10).mean()
        df['MA20'] = df['Close'].rolling(window=20).mean()
        df['MA50'] = df['Close'].rolling(window=50).mean()
        df['MA100'] = df['Close'].rolling(window=100).mean()
         
        open_price = df.Open.iloc[-1]
        close_price = df.Close.iloc[-1]
        previous_open = df.Open.iloc[-2]
        previous_close = df.Close.iloc[-2]
    
        last_candle = df.iloc[-1]
        current_price = df.Close.iloc[-1]
    
        ema_analysis = []
        candle_analysis = []
    
        if df['EMA5'].iloc[-1] > df['EMA10'].iloc[-1] > df['EMA20'].iloc[-1] > df['EMA50'].iloc[-1] > df['EMA100'].iloc[-1] > df['EMA200'].iloc[-1]:
            ema_analysis.append('buy')
        elif df['EMA5'].iloc[-1] < df['EMA10'].iloc[-1] < df['EMA20'].iloc[-1] < df['EMA50'].iloc[-1] < df['EMA100'].iloc[-1] < df['EMA200'].iloc[-1]:
            ema_analysis.append('sell')
    
        if (
            open_price < close_price and
            previous_open > previous_close and
            close_price > previous_open and
            open_price <= previous_close
        ):
            candle_analysis.append('buy')
        elif (
            open_price > close_price and
            previous_open < previous_close and
            close_price < previous_open and
            open_price >= previous_close
        ):
            candle_analysis.append('sell')
    
        if 'buy' in ema_analysis and 'buy' in candle_analysis and df['Close'].iloc[-1] > df['EMA200'].iloc[-1]:
            final_signal = 'buy'
        elif 'sell' in ema_analysis and 'sell' in candle_analysis and df['Close'].iloc[-1] < df['EMA200'].iloc[-1]:
            final_signal = 'sell'
        else:
            final_signal = ''
        
        return final_signal
    
    df = get_klines(symbol, '1m', 44640)
    
    while True:
        df = get_klines(symbol, '1m', 44640)
        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}")
            time.sleep(1)
    

    This code should give you more accurate signals by considering the EMA lines 100 and 200 in the analysis.

  3. User

    I tryed your code , but it gave me loss , listean me please I have stop loss -10% I need to code which position whcih position will doesn't touch this stop loss

  4. Assistant

    To prevent your position from touching the stop loss at -10%, you can modify the signal_generator() function to include a check for the current position and adjust the signal accordingly. Here's an updated version of the code that incorporates this logic:

    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
    import ntplib
    import os
    import ta
    import ta.volatility
    
    API_KEY = ''
    API_SECRET = ''
    
    client = Client(API_KEY, API_SECRET)
    
    def sync_time():
        server_time = requests.get('https://api.binance.com/api/v3/time').json()['serverTime']
        local_time = int(time.time() * 1000)
        time_difference = server_time - local_time
        # Set the system clock to the new time
        os.system(f'sudo date -s @{int(server_time/1000)}')
        print(f'New time: {dt.datetime.now()}')
    
    # Sync your local time with the server time
    sync_time()
    
    # Set the endpoint and parameters for the request
    url = "https://fapi.binance.com/fapi/v1/klines"
    symbol = 'COMP/USDT'
    interval = '1m'
    lookback = 44640
    timestamp = int(time.time() * 1000) - 500 # subtract 500ms from local time to account for clock-drift
    recv_window = 60000 # increased recv_window value
    params = {
        "symbol": symbol.replace("/", ""),
        "interval": interval,
        "startTime": int((time.time() - lookback * 60) * 1000),
        "endTime": int(time.time() * 1000),
        "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
    
    # Send the request using the requests library
    response