Navigation

    Backtrader Community

    • Register
    • Login
    • Search
    • Categories
    • Recent
    • Tags
    • Popular
    • Users
    • Groups
    • Search
    For code/output blocks: Use ``` (aka backtick or grave accent) in a single line before and after the block. See: http://commonmark.org/help/

    Some trouble with tutorial algorithmic trading using Sentiment analysis

    Indicators/Strategies/Analyzers
    2
    4
    486
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • Florian Aversin
      Florian Aversin last edited by

      Hi everyone,

      I'm new in backtrader and i would like to reproduce the tutorial based on these links :

      https://towardsdatascience.com/https-towardsdatascience-com-algorithmic-trading-using-sentiment-analysis-on-news-articles-83db77966704
      https://github.com/jasonyip184/StockSentimentTrading

      Moreover i have some problem when i launch the code with this error :
      TypeError: 'module' object is not callable or must be real number, not LineBuffer (if i change the data i want to feed)

      Someone please can help me ? I think the tutorial is really interesting so i would like to run it :/

      B 1 Reply Last reply Reply Quote 0
      • B
        backtrader administrators @Florian Aversin last edited by

        @Florian-Aversin said in Some trouble with tutorial algorithmic trading using Sentiment analysis:

        (if i change the data i want to feed

        That's probably the problem. You change something. Nobody can help you if nobody knows what you have changed.

        1 Reply Last reply Reply Quote 0
        • Florian Aversin
          Florian Aversin last edited by

          Well ... sorry for the mistake. Here is my complete code :

          import warnings
          warnings.filterwarnings('ignore')
          from nltk.sentiment.vader import SentimentIntensityAnalyzer
          # nltk.download('vader_lexicon')
          sia = SentimentIntensityAnalyzer()
          
          from urllib.request import urlopen
          from bs4 import BeautifulSoup
          from datetime import datetime, timedelta
          import time
          import pprint
          
          date_sentiments = {}
          
          for i in range(1,11):
              page = urlopen('https://www.businesstimes.com.sg/search/facebook?page='+str(i)).read()
              soup = BeautifulSoup(page, features="html.parser")
              posts = soup.findAll("div", {"class": "media-body"})
              for post in posts:
                  time.sleep(1)
                  url = post.a['href']
                  date = post.time.text
                  print(date, url)
                  try:
                      link_page = urlopen(url).read()
                  except:
                      url = url[:-2]
                      link_page = urlopen(url).read()
                  link_soup = BeautifulSoup(link_page)
                  sentences = link_soup.findAll("p")
                  passage = ""
                  for sentence in sentences:
                      passage += sentence.text
                  sentiment = sia.polarity_scores(passage)['compound']
                  date_sentiments.setdefault(date, []).append(sentiment)
          
          date_sentiment = {}
          
          for k,v in date_sentiments.items():
              date_sentiment[datetime.strptime(k, '%d %b %Y').date() + timedelta(days=1)] = round(sum(v)/float(len(v)),3)
          earliest_date = min(date_sentiment.keys())
          print(date_sentiment)
          
          from __future__ import (absolute_import, division, print_function,
                                      unicode_literals)
          
          import backtrader as bt
          import backtrader.indicators as btind
          import datetime
          import os.path
          import sys
          
          class Sentiment(bt.Indicator):
              lines = ('sentiment',)
              plotinfo = dict(
                  plotymargin=0.15,
                  plothlines=[0],
                  plotyticks=[1.0, 0, -1.0])
              
              def next(self):
                  self.date = self.data.datetime
                  date = bt.num2date(self.date[0]).date()
                  prev_sentiment = self.sentiment
                  if date in date_sentiment:
                      self.sentiment = date_sentiment[date]
                  self.lines.sentiment[0] = self.sentiment
          
          
          class SentimentStrat(bt.Strategy):
              params = (
                  ('period', 15),
                  ('printlog', True),
              )
          
              def log(self, txt, dt=None, doprint=False):
                  ''' Logging function for this strategy'''
                  if self.params.printlog or doprint:
                      dt = dt or self.datas[0].datetime.date(0)
                      print('%s, %s' % (dt.isoformat(), txt))
          
              def __init__(self):
                  # Keep a reference to the "close" line in the data[0] dataseries
                  self.dataclose = self.datas[0].close
                  # Keep track of pending orders
                  self.order = None
                  self.buyprice = None
                  self.buycomm = None
                  self.sma = bt.indicators.SimpleMovingAverage(
                      self.datas[0], period=self.params.period)
                  self.date = self.data.datetime
                  self.sentiment = None
                  Sentiment(self.data)
                  
              def notify_order(self, order):
                  if order.status in [order.Submitted, order.Accepted]:
                      # Buy/Sell order submitted/accepted to/by broker - Nothing to do
                      return
                  
                  # Check if an order has been completed
                  # Attention: broker could reject order if not enough cash
                  if order.status in [order.Completed]:
                      if order.isbuy():
                          self.log(
                              'BUY EXECUTED, Price: %.2f, Cost: %.2f, Comm %.2f' %
                              (order.executed.price,
                               order.executed.value,
                               order.executed.comm))
                          self.buyprice = order.executed.price
                          self.buycomm = order.executed.comm
                      else:  # Sell
                          self.log('SELL EXECUTED, Price: %.2f, Cost: %.2f, Comm %.2f' %
                                   (order.executed.price,
                                    order.executed.value,
                                    order.executed.comm))
                          
                      self.bar_executed = len(self)     
                      
                  elif order.status in [order.Canceled, order.Margin, order.Rejected]:
                      self.log('Order Canceled/Margin/Rejected')
                      
                  # Write down: no pending order
                  self.order = None
                  
              def notify_trade(self, trade):
                  if not trade.isclosed:
                      return
          
                  self.log('OPERATION PROFIT, GROSS %.2f, NET %.2f' %
                           (trade.pnl, trade.pnlcomm))
              
              ### Main Strat ###
              def next(self):
                  # log closing price of the series from the reference
                  self.log('Close, %.2f' % self.dataclose[0])
                  
                  date = bt.num2date(self.date[0]).date()
                  prev_sentiment = self.sentiment
                  if date in date_sentiment:
                      self.sentiment = date_sentiment[date]
                  
                  # Check if an order is pending. if yes, we cannot send a 2nd one
                  if self.order:
                      return
                  print(self.sentiment)
                  # If not in the market and previous sentiment not none
                  if not self.position and prev_sentiment:
                      # buy if current close more than sma AND sentiment increased by >= 0.5
                      if self.dataclose[0] > self.sma[0] and self.sentiment - prev_sentiment >= 0.5:
                          self.log('BUY CREATE, %.2f' % self.dataclose[0])
                          self.order = self.buy()
                          
                  # Already in the market and previous sentiment not none
                  elif prev_sentiment:
                      # sell if current close less than sma AND sentiment decreased by >= 0.5
                      if self.dataclose[0] < self.sma[0] and self.sentiment - prev_sentiment <= -0.5:
                          self.log('SELL CREATE, %.2f' % self.dataclose[0])
                          self.order = self.sell()
          
              def stop(self):
                  self.log('(MA Period %2d) Ending Value %.2f' %
                           (self.params.period, self.broker.getvalue()), doprint=True)
                  
          
          if __name__ == '__main__':
              cerebro = bt.Cerebro()
              
              # Strategy
              cerebro.addstrategy(SentimentStrat)
          
              # Data Feed
              data = bt.feeds.YahooFinanceData(
                  dataname = 'FB',
                  fromdate = earliest_date,
                  todate = datetime.datetime(2018,11,25),
                  reverse = False
              )
              
              cerebro.adddata(data)
          
              cerebro.broker.setcash(100000.0)
              cerebro.addsizer(bt.sizers.FixedSize, stake=10)
              cerebro.broker.setcommission(commission=0.001)
              print('Starting Portfolio Value: %.2f' % cerebro.broker.getvalue())
              cerebro.run()
              print('Final Portfolio Value: %.2f' % cerebro.broker.getvalue())
              
              cerebro.plot()
          
          1 Reply Last reply Reply Quote 0
          • B
            backtrader administrators last edited by

            I don't know if you are expecting to read the entire code.

            What did you actually change? What's the difference with the original?

            1 Reply Last reply Reply Quote 0
            • 1 / 1
            • First post
              Last post
            Copyright © 2016, 2017, 2018 NodeBB Forums | Contributors
            $(document).ready(function () { app.coldLoad(); }); }