Navigation

    Quantiacs Community

    • Register
    • Login
    • Search
    • Categories
    • News
    • Recent
    • Tags
    • Popular
    • Users
    • Groups
    1. Home
    2. Popular
    Log in to post
    • All categories
    • Support
    •      Request New Features
    • Strategy help
    • General Discussion
    • News and Feature Releases
    • All Topics
    • New Topics
    • Watched Topics
    • Unreplied Topics
    • All Time
    • Day
    • Week
    • Month
    • X

      Combining classifiers
      Strategy help • • xiaolan

      6
      0
      Votes
      6
      Posts
      440
      Views

      support

      @xiaolan That is correct, but the logic can be easily re-used. The only novel element will be the introduction of the liquidity filter at intermediate stages/at the final stage for the selection of the weights.

    • S

      Balance, order size, stop loss, open and close position price
      Support • • ScalpingAF

      6
      0
      Votes
      6
      Posts
      336
      Views

      support

      @scalpingaf Correct, all trades (buy or sell) are taken at the open of the next day you take the decision.

    • E

      Q17 Neural Networks Algo Template; is there an error in train_model()?
      Strategy help • • EDDIEE

      6
      1
      Votes
      6
      Posts
      1008
      Views

      V

      Hello colleagues.

      The solution in case of predicting one financial instrument can be the following (train_period changed)

      def load_data(period): return qndata.cryptodaily_load_data(tail=period, assets=['BTC']) def train_model(data): """ train the LSTM network """ asset_name = 'BTC' features_all = get_features(data) target_all = get_target_classes(data) model = get_model() # drop missing values: target_cur = target_all.sel(asset=asset_name).dropna('time', 'any') features_cur = features_all.sel(asset=asset_name).dropna('time', 'any') # align features and targets: target_for_learn_df, feature_for_learn_df = xr.align(target_cur, features_cur, join='inner') criterion = nn.MSELoss() # define loss function optimiser = optim.LBFGS(model.parameters(), lr=0.08) # we use an LBFGS solver as optimiser epochs = 1 # how many epochs for i in range(epochs): def closure(): # reevaluates the model and returns the loss (forward pass) optimiser.zero_grad() # input tensor in_ = torch.zeros(1, len(feature_for_learn_df.values)) in_[0, :] = torch.tensor(np.array(feature_for_learn_df.values)) # output out = model(in_) # target tensor target = torch.zeros(1, len(target_for_learn_df.values)) target[0, :] = torch.tensor(np.array(target_for_learn_df.values)) # evaluate loss loss = criterion(out, target) loss.backward() return loss optimiser.step(closure) # updates weights return model weights = qnbt.backtest_ml( load_data=load_data, train=train_model, predict=predict, train_period=1 * 365, # the data length for training in calendar days retrain_interval=365, # how often we have to retrain models (calendar days) retrain_interval_after_submit=1, # how often retrain models after submission during evaluation (calendar days) predict_each_day=False, # Is it necessary to call prediction for every day during backtesting? # Set it to true if you suspect that get_features is looking forward. competition_type='crypto_daily_long_short', # competition type lookback_period=365, # how many calendar days are needed by the predict function to generate the output start_date='2014-01-01', # backtest start date build_plots=True # do you need the chart? )
    • T

      Python
      General Discussion • • TitusBullo

      6
      0
      Votes
      6
      Posts
      496
      Views

      T

      @antinomy Ty

    • B

      Machine Learning - LSTM strategy seems to be forward-looking
      General Discussion • • black.magmar

      6
      1
      Votes
      6
      Posts
      1478
      Views

      support

      @black-magmar You are correct, but this kind of forward-looking is always present when you have all the data at your disposal. The important point is that there is no forward-looking in the live results, and that should not happen as the prediction will be done for a day for which data are not yet available.

    • S

      Systems selection for the Q16 contest
      News and Feature Releases • • Sun-73

      6
      2
      Votes
      6
      Posts
      1257
      Views

      support

      @sun-73 Yes, we will, sorry for the issue.

    • news-quantiacs

      The Q17 Contest is running!
      News and Feature Releases • • news-quantiacs

      6
      1
      Votes
      6
      Posts
      1759
      Views

      support

      @magenta-grimer Hello, you can have at most 50 running submissions in your user area. You can stop any of them any moment and replace it with another one.

      Before the end of the Q17 submission phase, you should select at most 15 of them. These will take part to the live contest.

    • S

      Q16 where to put is_liquid in ML template
      Strategy help • • Sheikh

      6
      0
      Votes
      6
      Posts
      1006
      Views

      S

      Hi @support,
      Thanks for getting back. No worries, I was able to get 6 strategies into the Q16 competition so far.
      qnt3.PNG

    • N

      Q21 contest results
      News and Feature Releases • • neural.exeggutor

      6
      0
      Votes
      6
      Posts
      1212
      Views

      support

      @theflyingdutchman Hi, sorry for the delay, yes, all fine, more details by e-mail

    • magenta.grimer

      Optimize the Trend Following strategy with custom args
      Strategy help • • magenta.grimer

      6
      0
      Votes
      6
      Posts
      579
      Views

      support

      Hello.

      I checked this problem. The script which cut "###DEBUG###" cells was incorrect. I fixed this and resent your strategies (filtered by time out) to checking.

      Regards.

    • illustrious.felice

      Translating code from Quantiacs Legacy
      Support • • illustrious.felice

      6
      0
      Votes
      6
      Posts
      315
      Views

      illustrious.felice

      @vyacheslav_b Thank you so much

    • W

      sliding 3d array
      Strategy help • • wool.dewgong

      6
      0
      Votes
      6
      Posts
      694
      Views

      support

      @wool-dewgong Hello! We added one template which should address your issue and allow you to perform a rolling fast ML training with retraining. It is available in your user space in the Examples section and you can read it here also in the public docs:

      https://quantiacs.com/documentation/en/examples/machine_learning_with_a_voting_classifier.html

    • C

      Setup an environment at Google Colab
      Support • • cortezkwan

      5
      2
      Votes
      5
      Posts
      400
      Views

      C

      @support Great help! Thank you so much!

    • C

      How to fix this error
      Support • • cyan.gloom

      5
      0
      Votes
      5
      Posts
      1483
      Views

      C

      @antinomy
      Thanks for your advice !

    • S

      How to install Python Talib
      Support • • spancham

      5
      0
      Votes
      5
      Posts
      1530
      Views

      support

      @sheikh It is fine, please just submit, check the result and let us know if you see any issue. It should work fine.

    • A

      I've just lost a notebook that contains my entire algorithm
      Support • • aybber

      5
      0
      Votes
      5
      Posts
      585
      Views

      A

      @support no worries, I've been able to recover the strategy thank you!

    • E

      Strategy Optimization in local development environment is not working
      Support • • EDDIEE

      5
      0
      Votes
      5
      Posts
      502
      Views

      V

      @eddiee

      This code works for me. I can give you ideas on what to try.

      Update the qnt library or reinstall.

      If it doesn't help, clone the repository

      https://github.com/quantiacs/toolbox

      git clone https://github.com/quantiacs/toolbox.git

      run
      qnt/examples/005-01-optimizer.py
      and other examples.

      You may need to specify API_KEY

      You might be able to see exactly where the error occurs in the code.
      And you can modify the library code by adding logging for optimize_strategy

    • N

      KeyError: "cannot represent labeled-based slice indexer for coordinate 'time' with a slice over integer positions; the index is unsorted or non-unique"
      Support • • newbiequant96

      5
      0
      Votes
      5
      Posts
      345
      Views

      M

      @newbiequant96 no problem.
      I think the issue now is unrelated to the the previous issue. If you can show what is written above return code 1, I can maybe help.
      It seems to be an issue in the code.
      Regards

    • cespadilla

      Leaderboard not updating?
      Support • competition leaderboard q16 • • cespadilla

      5
      1
      Votes
      5
      Posts
      1346
      Views

      cespadilla

      @support Hi again guys, I think the leaderboard is not updating again 😳

    • M

      Missed call to write_output although had included it
      Support • • multi_byte.wildebeest

      5
      0
      Votes
      5
      Posts
      335
      Views

      V

      @illustrious-felice Hello. please look at this post
      https://quantiacs.com/community/topic/515/what-is-forward-looking-and-why-it-s-effective-badly-to-strategy/6?_=1711712434795

    • Documentation
    • About
    • Career
    • My account
    • Privacy policy
    • Terms and Conditions
    • Cookies policy
    Home
    Copyright © 2014 - 2021 Quantiacs LLC.
    Powered by NodeBB | Contributors