Commit Graph

420 Commits

Author SHA1 Message Date
robcaulk
94cfc8e63f fix multiproc callback, add continual learning to multiproc, fix totalprofit bug in env, set eval_freq automatically, improve default reward 2022-08-25 11:46:18 +02:00
robcaulk
d1bee29b1e improve default reward, fix bugs in environment 2022-08-24 18:32:40 +02:00
robcaulk
a61821e1c6 remove monitor log 2022-08-24 16:33:13 +02:00
robcaulk
bd870e2331 fix monitor bug, set default values in case user doesnt set params 2022-08-24 16:32:14 +02:00
robcaulk
c0cee5df07 add continual retraining feature, handly mypy typing reqs, improve docstrings 2022-08-24 13:00:55 +02:00
robcaulk
b708134c1a switch multiproc thread count to rl_config definition 2022-08-24 13:00:55 +02:00
robcaulk
b26ed7dea4 fix generic reward, add time duration to reward 2022-08-24 13:00:55 +02:00
robcaulk
280a1dc3f8 add live rate, add trade duration 2022-08-24 13:00:55 +02:00
robcaulk
f9a49744e6 add strategy to the freqai object 2022-08-24 13:00:55 +02:00
richardjozsa
a2a4bc05db Fix the state profit calculation logic 2022-08-24 13:00:55 +02:00
robcaulk
29f0e01c4a expose environment reward parameters to the user config 2022-08-24 13:00:55 +02:00
robcaulk
d88a0dbf82 add sb3_contrib models to the available agents. include sb3_contrib in requirements. 2022-08-24 13:00:55 +02:00
robcaulk
8b3a8234ac fix env bug, allow example strat to short 2022-08-24 13:00:55 +02:00
mrzdev
8cd4daad0a Feat/freqai rl dev (#7)
* access trades through get_trades_proxy method to allow backtesting
2022-08-24 13:00:55 +02:00
robcaulk
3eb897c2f8 reuse callback, allow user to acces all stable_baselines3 agents via config 2022-08-24 13:00:55 +02:00
robcaulk
4b9499e321 improve nomenclature and fix short exit bug 2022-08-24 13:00:55 +02:00
sonnhfit
4baa36bdcf fix persist a single training environment for PPO 2022-08-24 13:00:55 +02:00
robcaulk
f95602f6bd persist a single training environment. 2022-08-24 13:00:55 +02:00
robcaulk
5d4e5e69fe reinforce training with state info, reinforce prediction with state info, restructure config to accommodate all parameters from any user imported model type. Set 5Act to default env on TDQN. Clean example config. 2022-08-24 13:00:55 +02:00
sonnhfit
7962a1439b remove keep low profit 2022-08-24 13:00:55 +02:00
sonnhfit
81b5aa66e8 make env keep current position when low profit 2022-08-24 13:00:55 +02:00
sonnhfit
45218faeb0 fix coding convention 2022-08-24 13:00:55 +02:00
robcaulk
b90da46b1b improve price df handling to enable backtesting 2022-08-24 13:00:55 +02:00
MukavaValkku
2080ff86ed 5ac base fixes in logic 2022-08-24 13:00:55 +02:00
robcaulk
16cec7dfbd fix save/reload functionality for stablebaselines 2022-08-24 13:00:55 +02:00
sonnhfit
0475b7cb18 remove unuse code and fix coding conventions 2022-08-24 13:00:55 +02:00
MukavaValkku
d60a166fbf multiproc TDQN with xtra callbacks 2022-08-24 13:00:55 +02:00
robcaulk
dd382dd370 add monitor to eval env so that multiproc can save best_model 2022-08-24 13:00:55 +02:00
robcaulk
69d542d3e2 match config and strats to upstream freqai 2022-08-24 13:00:55 +02:00
robcaulk
e5df39e891 ensuring best_model is placed in ram and saved to disk and loaded from disk 2022-08-24 13:00:55 +02:00
robcaulk
bf7ceba958 set cpu threads in config 2022-08-24 13:00:55 +02:00
MukavaValkku
57c488a6f1 learning_rate + multicpu changes 2022-08-24 13:00:55 +02:00
robcaulk
acf3484e88 add multiprocessing variant of ReinforcementLearningPPO 2022-08-24 13:00:55 +02:00
MukavaValkku
cf0731095f type fix 2022-08-24 13:00:55 +02:00
MukavaValkku
1c81ec6016 3ac and 5ac example strategies 2022-08-24 13:00:55 +02:00
MukavaValkku
13cd18dc9a PPO policy change + verbose=1 2022-08-24 13:00:55 +02:00
robcaulk
926023935f make base 3ac and base 5ac environments. TDQN defaults to 3AC. 2022-08-24 13:00:55 +02:00
MukavaValkku
096533bcb9 3ac to 5ac 2022-08-24 13:00:55 +02:00
MukavaValkku
718c9d0440 action fix 2022-08-24 13:00:55 +02:00
robcaulk
9c78e6c26f base PPO model only customizes reward for 3AC 2022-08-24 13:00:55 +02:00
robcaulk
6048f60f13 get TDQN working with 5 action environment 2022-08-24 13:00:55 +02:00
robcaulk
d4db5c3281 ensure TDQN class is properly named 2022-08-24 13:00:55 +02:00
robcaulk
91683e1dca restructure RL so that user can customize environment 2022-08-24 13:00:55 +02:00
sonnhfit
ecd1f55abc add rl module 2022-08-24 13:00:55 +02:00
MukavaValkku
9b895500b3 initial commit - new dev branch 2022-08-24 13:00:55 +02:00
MukavaValkku
cd3fe44424 callback function and TDQN model added 2022-08-24 13:00:55 +02:00
MukavaValkku
01232e9a1f callback function and TDQN model added 2022-08-24 13:00:55 +02:00
MukavaValkku
8eeaab2746 add reward function 2022-08-24 13:00:55 +02:00
MukavaValkku
ec813434f5 ReinforcementLearningModel 2022-08-24 13:00:55 +02:00
MukavaValkku
2f4d73eb06 Revert "ReinforcementLearningModel"
This reverts commit 4d8dfe1ff1daa47276eda77118ddf39c13512a85.
2022-08-24 13:00:55 +02:00
MukavaValkku
c1e7db3130 ReinforcementLearningModel 2022-08-24 13:00:55 +02:00
robcaulk
05ed1b544f Working base for reinforcement learning model 2022-08-24 13:00:40 +02:00
th0rntwig
5ce1c69803
Improve DBSCAN epsilon identification (#7269)
* Improve DBSCAN epsilon identification
2022-08-22 19:57:20 +02:00
robcaulk
ac42c0153d deprecate indicator_max_period_candles, automatically compute startup candles for FreqAI backtesting. 2022-08-22 18:19:07 +02:00
robcaulk
96d8882f1e Plug mem leak, add training timer 2022-08-22 13:30:30 +02:00
longyu
cfa5b3f12c add new line 2022-08-19 12:39:08 +02:00
longyu
277245c69d remove line 2022-08-19 12:39:00 +02:00
longyu
f70b0bab80 remove line 2022-08-17 23:49:20 +02:00
robcaulk
5155afb4e7 clean up code remnants 2022-08-17 15:22:48 +02:00
robcaulk
0c34104e45 extract download-data from freqai to prepare for future async changes 2022-08-17 15:18:44 +02:00
longyu
9c38c27eed ignore sample itself distance for avg_mean_dist computation 2022-08-17 15:09:57 +02:00
longyu
72c34291e3 newline 2022-08-17 15:09:10 +02:00
robcaulk
4c0fda400f fix input shape warning for LGBMClassifier, add sample_weights/eval_weights 2022-08-16 11:41:53 +02:00
Matthias
c7e1719215 Fix interface import sorting 2022-08-15 06:53:02 +02:00
robcaulk
006b11e5d5 fix leftover bug in indicator population 2022-08-14 21:42:55 +02:00
robcaulk
8961b8d560 merge in inference timer and historic predictions handling improvements. 2022-08-14 20:31:15 +02:00
robcaulk
ad846cdb76 fix lock bug, update docstring 2022-08-14 20:24:29 +02:00
Matthias
464d99808f Update doc table formatting 2022-08-14 18:22:01 +02:00
Matthias
a29402ddde Rename and move analysis_lock to data_kitchen 2022-08-14 17:23:14 +02:00
Matthias
3a9ec76c91 Move "freqai.lock" to backend to simplify user interface 2022-08-14 17:19:50 +02:00
Robert Caulk
c9c128f781 finalize logo, improve doc, improve algo overview, fix base tensorflowmodel for mypy 2022-08-14 02:49:01 +02:00
robcaulk
58de20af0f make BaseClassifierModel. Add predict_proba to lightgbm 2022-08-13 20:07:31 +02:00
robcaulk
31be707cc8 clean up code, add docstrings 2022-08-13 19:40:24 +02:00
robcaulk
3e38c1b0bd take dynamic sized tail off historic_predictions as return dataframe to strategy. 2022-08-13 19:40:24 +02:00
robcaulk
7d448fd4ac allow fit_live_predictions access to current pair 2022-08-13 19:40:24 +02:00
robcaulk
1f192be43b avoid denormalizing labels twice 2022-08-13 19:40:24 +02:00
robcaulk
b1b76a2dbe debug classifier with predict proba 2022-08-13 19:40:24 +02:00
robcaulk
23cc21ce59 add predict_proba to base classifier, improve historic predictions handling 2022-08-13 19:40:24 +02:00
robcaulk
fb4b73ce89 ensure dates are saved 2022-08-12 12:03:44 +02:00
robcaulk
2cae3c42e6 remove trade database analyzer, clean up a bit 2022-08-10 17:43:06 +02:00
robcaulk
5a16d5a512 Deactivate database analyzer if user does not use sqlite 2022-08-09 16:36:22 +02:00
robcaulk
e7de812948 Allow user to user pair_dict for persistent storage of custom data 2022-08-09 16:03:10 +02:00
robcaulk
aef086b02e Improved dict typing, timeframe parser, collect dates associated with training data points 2022-08-09 15:30:25 +02:00
Matthias
77b3b8a134 Use main exchange instead of creating a separate instance. 2022-08-08 18:34:11 +00:00
robcaulk
ea64f43e52 bring back auto DF resizing for okx 2022-08-08 01:13:13 +02:00
robcaulk
eb8bde37c1 Add lightgbm classifier, add classifier check test, fix classifier bug. 2022-08-06 17:51:21 +02:00
Matthias
47a30047eb Fix typo 2022-08-06 15:03:10 +02:00
Matthias
b16f57cb0d Minor stylistic fixes 2022-08-06 14:55:46 +02:00
Robert Caulk
c172ce1011 improve flexibility of user defined prediction dataframe 2022-08-06 13:51:19 +02:00
Robert Caulk
07763d0d4f add classifier, improve model naming scheme 2022-08-06 08:33:55 +02:00
Robert Caulk
ce8fbbf743 ensure loading historical df matches frequi indices 2022-08-06 07:25:59 +02:00
robcaulk
60d782e5c5 remove unnecessary function 2022-08-05 21:31:32 +02:00
robcaulk
a42a060ab5 fix DB once and for all. Make DBSCAN more efficient and robust. 2022-08-05 21:29:03 +02:00
Robert Caulk
a3799c4d5d start frequi with historical data if available 2022-08-05 18:27:47 +02:00
robcaulk
29b7b014e5 fix bug in DB path initialization 2022-08-05 18:19:26 +02:00
robcaulk
db1d367941 fix bug associated to fit_live_predictions_candles 2022-08-05 13:46:20 +02:00
robcaulk
05ec5c5e54 generalize database url path for any db type 2022-08-05 12:19:29 +02:00
Robert Caulk
51a6b4289f improve DBSCAN performance for subsequent trainings 2022-08-04 17:41:58 +02:00
Robert Caulk
fe1b8515a8 fix bug in DBSCAN, update doc 2022-08-04 17:00:59 +02:00
robcaulk
29225e4baf add DBSCAN outlier detection feature, add supporting documentation 2022-08-04 12:15:16 +02:00
robcaulk
eae82d0222 fix bug with database url during backtesting. comment out example trade db analysis. 2022-08-03 16:17:57 +02:00
robcaulk
95d3009a95 give user ability to analyze live trade dataframe inside custom prediction model. Add documentation to explain new functionality 2022-08-02 20:14:02 +02:00
robcaulk
946d4c7cfc fix trailing whitespace for flake8 2022-07-31 18:39:46 +02:00
robcaulk
4e68626bcb ensure convolutional window is prepended for frequi consistency 2022-07-31 17:51:19 +02:00
robcaulk
d830105605 *BREAKING CHANGE* remove unnecessary arguments from populate_any_indicators(), accommodate tests 2022-07-31 17:05:29 +02:00
robcaulk
dd8288c090 expose full parameter set for SVM outlier detection. Set default shuffle to false to improve reproducibility 2022-07-30 13:40:05 +02:00
robcaulk
f22b140782 fix backtesting bug, undo move of label stat calc, fix example strat exit logic 2022-07-29 17:27:35 +02:00
robcaulk
59624181bd isort BaseRegressionModel imports 2022-07-29 08:23:44 +02:00
robcaulk
c84d54b35e Fix typing issue, avoid using .get() when unnecessary, convert to fstrings 2022-07-29 08:12:50 +02:00
Matthias
efbd83c56d Small type and typo fixes in freqai_interface 2022-07-28 07:24:30 +02:00
Matthias
a2a0d35a24 Update missing typehints 2022-07-28 07:07:40 +02:00
Matthias
f31106dc61 Minor comment fixes 2022-07-27 07:27:24 +02:00
Matthias
bc760b7eb2 Simplify small segment in datadrawer 2022-07-26 19:41:49 +02:00
robcaulk
324e54c015 fix possible memory leak associated with Catboost Pool object 2022-07-26 17:29:29 +02:00
robcaulk
3f149c4067 fix return type in BaseTensorFlowModel 2022-07-26 16:01:54 +02:00
robcaulk
ad25a4cb56 reduce number of pair_dict lookups, remove coin_first 2022-07-26 15:58:40 +02:00
robcaulk
fb4e8430cd isort auto import sorting 2022-07-26 10:51:39 +02:00
robcaulk
e213d0ad55 isolate data_drawer functions from data_kitchen, accommodate tests, add new test 2022-07-26 10:24:14 +02:00
robcaulk
56b17e6f3c allow user to pass test_size = 0 and avoid using eval sets in prediction models 2022-07-25 19:40:13 +02:00
Robert Caulk
897f18a8c8 ensure proper integer type casting for timestamps. Add check test for backtesting subdaily time periods 2022-07-25 15:07:09 +02:00
Robert Caulk
7b105532d1 fix mypy error and add test for principal component analysis 2022-07-25 11:46:59 +02:00
Robert Caulk
c9d46a5237 finish bringing follow_mode up to date 2022-07-25 09:24:40 +02:00
Robert Caulk
ab587747fb first fix for follower path bug 2022-07-24 23:32:24 +02:00
Matthias
520ee3f7a1 Convert freqAI into packages 2022-07-24 17:07:45 +02:00
Matthias
1885deb632 More docstring changes 2022-07-24 16:54:39 +02:00
Matthias
70b7a254af Update some areas to use default docstring formatting 2022-07-24 16:51:48 +02:00
Matthias
61c41fd919 Merge branch 'develop' into feat/freqai 2022-07-24 16:18:58 +02:00
Robert Caulk
88e10f7306 add exception for not passing timerange. Remove hard coded arguments for CatboostPredictionModels. Update docs 2022-07-24 09:01:23 +02:00
Robert Caulk
fff39eff9e fix multitarget bug 2022-07-24 08:42:50 +02:00
robcaulk
f3d46613ee move prediction denormalization into datakitchen. remove duplicate associated code. avoid normalization/denormalization for string dtypes. 2022-07-23 17:14:33 +02:00
Matthias
8fa6e8b4ba Remove freqAI model bridge in favor of self.freqai 2022-07-23 17:08:05 +02:00
robcaulk
c91e23dc50 let user avoid normalizing labels 2022-07-23 16:14:13 +02:00
robcaulk
50d630a155 remove unnecessary comments from data_drawer.py 2022-07-23 13:35:44 +02:00
robcaulk
a1cff377ec add record of contribution to data_kitchen.py 2022-07-23 13:32:04 +02:00
robcaulk
c2d6a0e891 add record of contribution to doc and source 2022-07-23 13:04:06 +02:00
robcaulk
5559e605b8 small PR conversation resolutions 2022-07-22 17:46:14 +02:00
robcaulk
40f00196eb use cloudpickle in place of pickle. define Paths once in data_drawer. 2022-07-22 17:37:51 +02:00
robcaulk
98c8a447b2 add LightGBMPredictionMultiModel 2022-07-22 12:40:51 +02:00
robcaulk
afcb0bec00 clean up obsolete comments, move remove_features_from_df to datakitchen 2022-07-22 12:29:20 +02:00
robcaulk
3205788bce extend doc to include descriptions of the return values from FreqAI to the strategy 2022-07-21 22:11:46 +02:00
robcaulk
8033e0bf23 add counter to backtesting log so users know how many more pairs and how many more models will need to be trained 2022-07-21 13:22:12 +02:00
robcaulk
183dec866a remove ability to backtest open ended timeranges (safer) 2022-07-21 13:02:52 +02:00
robcaulk
e694ea1cfd make sure backtesting gets the populated indicators with slimmed down user strat 2022-07-21 12:48:09 +02:00
robcaulk
ca4dd58642 remove superceded function from datakitchen 2022-07-21 12:40:54 +02:00
robcaulk
8f86b0deaa *breaking change* simplify user strat by consolidating feature loops into backend 2022-07-21 12:24:22 +02:00
robcaulk
e7337728bf add separator in folder name just incase an asset ends in an integer 2022-07-21 11:25:28 +02:00
robcaulk
921a7ef216 add requirements-freqai.txt to builds 2022-07-20 15:51:25 +02:00
robcaulk
d43c146676 add more tests for datakitchen functionalities, add regression tests for freqai_interface train/backtest 2022-07-20 12:56:46 +02:00
lolong
9c051958a6
Feat/freqai (#7105)
Vectorize weight setting, log training dates

Co-authored-by: robcaulk <rob.caulk@gmail.com>
2022-07-19 17:49:18 +02:00
robcaulk
714d9534b6 start adding tests 2022-07-19 16:16:44 +02:00
lolong
ed0f8b1189
Improve FreqAI documentation (#7072)
Improve doc + some other small fixes

Co-authored-by: robcaulk <rob.caulk@gmail.com>
2022-07-18 11:57:52 +02:00
Robert Caulk
921f3899f0 revert pickle reading for historic predictions 2022-07-17 16:06:36 +02:00
Robert Caulk
41eeb99177 load pickle file for writing 2022-07-17 10:05:21 +02:00
Robert Caulk
9d184586f1 fix bug in historic prediction saving 2022-07-16 21:16:59 +02:00
Wagner Costa Santos
ca2029a46b fix issue when bot restarts with same identifier, does not load prediction history 2022-07-14 18:55:24 -03:00
robcaulk
4141d165ff add BaseTensorFlowModel class 2022-07-12 19:10:09 +02:00
robcaulk
ef409dd345 Add ground work for TensorFlow models, add protections from common mistakes 2022-07-12 18:09:17 +02:00
Robert Caulk
fea63fba12 Fix saving/loading historic predictions 2022-07-12 10:12:50 +02:00
Robert Caulk
8ce6b18318 start collecting indefinite history of predictions. Allow user to generate statistics on these predictions. Direct FreqAI to save these to disk and reload them if available. 2022-07-11 22:01:48 +02:00
Matthias
3fc92b1b21 Create BaseRegression model - designed to reduce code duplication across currently available models. 2022-07-11 11:33:59 +02:00
Robert Caulk
607455919e Change config parameter names to improve clarity and consistency throughout the code (!!breaking change, please check discord support channel for migration instructions or review templates/FreqaiExampleStrategy.py config_examples/config_freqai_futures.example.json file changes!!) 2022-07-10 12:35:44 +02:00
Matthias
819cc9c0e4 Fully align LightGBM with Catboost 2022-07-10 11:06:18 +02:00
Matthias
58b18770e3 Fix LightGBM missing argument in predict method 2022-07-10 11:05:35 +02:00
Matthias
2e1061af64 Fix faulty LightGBM model 2022-07-09 08:21:42 +00:00
robcaulk
d9acdc9767 remove excess, increase no model warning clarity 2022-07-06 18:20:21 +02:00
robcaulk
4cac67fd66 Catch infrequent issue associated with grabbing first candle 2022-07-05 12:43:33 +02:00
robcaulk
bd3a6ba2fe update backtesting to handle new output framework 2022-07-03 17:34:44 +02:00
robcaulk
8ac8d53c32 All LGBMRegressor model parameters are now set in config 2022-07-03 16:30:01 +02:00
robcaulk
4ff0ef7359 fix bug returning multiple targets for training 2022-07-03 12:15:59 +02:00
robcaulk
ffb39a5029 black formatting on freqai files 2022-07-03 10:59:38 +02:00
robcaulk
106131ff0f Rehaul organization of return values 2022-07-02 18:09:38 +02:00
robcaulk
93e1410ed9 first step toward cleaning output and enabling multimodel training per pair 2022-07-01 14:00:30 +02:00
robcaulk
6c7d02cb18 expose nu in the SVM outlier detection via svm_nu in config 2022-06-28 15:12:25 +02:00
robcaulk
7dfbd432d1 fix config saving bug, assign priorities to pairs in scanning, sleep the scanning loop to reduce CPU usage 2022-06-27 11:35:33 +02:00
robcaulk
68bafa9517 archive config to the model folder, filter out features before returning dataframe to strategy (to alleviate frequi issues)` 2022-06-26 23:03:48 +02:00
robcaulk
051b99791d reduce unnecessary verbosity, fix error on first training sweep, add LightGBMPredictionModel 2022-06-26 19:04:23 +02:00
Robert Caulk
852706cd6b
Fix default behavior for expiration_hours 2022-06-21 08:12:51 +02:00
robcaulk
b35c64b6c0 fix bug in backtest, typo in example strat 2022-06-19 16:41:09 +02:00
robcaulk
3599d18ff6 fix bug in follow_mode, thanks @blood4rc 2022-06-18 12:05:28 +02:00
robcaulk
6da7a98857 add docstrings to new functions, remove superceded code 2022-06-17 16:16:23 +02:00
robcaulk
f631ae911b add model expiration feature, fix bug in DI return values 2022-06-17 14:55:40 +02:00
robcaulk
0b0688a91e ensure scanning purges models 2022-06-16 16:12:38 +02:00
robcaulk
c5de0c49e4 first functional scanning commit 2022-06-16 00:24:18 +02:00
robcaulk
4d472a0ea1 merging datarehaul into scanning branch 2022-06-16 00:22:49 +02:00
Matthias
c981ad4608 Fix missing space 2022-06-12 08:31:02 +02:00
robcaulk
eb47c74096 merge datarehaul into main freqai branch 2022-06-10 20:26:19 +02:00
robcaulk
d9b79d94e4 increase candle update flexibility to allow long sequential trainings that may last more than one candle 2022-06-07 20:57:10 +02:00
robcaulk
66800c7a45 ensure newest candles are always appended 2022-06-07 20:24:23 +02:00
robcaulk
15d049cffe detect if upper tf candles are new or not, append if so. Correct the epoch for candle update check 2022-06-07 19:49:20 +02:00
robcaulk
cab8f517b4 add lock to datadrawer 2022-06-07 01:07:30 +02:00
robcaulk
4b26b6aaec add lock to any historic data access 2022-06-07 00:54:18 +02:00
Robert Caulk
2451ed8c88
Quick bug fix 2022-06-06 15:11:54 -06:00
robcaulk
d6b8801f41 fix follower bug 2022-06-05 04:40:58 +02:00
robcaulk
e8c0dcf9f3 add debug message to timerange 2022-06-03 17:14:07 +02:00
robcaulk
f2762e3b4b fix bug in return_values() 2022-06-03 16:58:51 +02:00
robcaulk
16b4a5b71f rehaul of backend data management - increasing performance by holding history in memory, reducing load on the ratelimit by only pinging exchange once per candle. Improve code readability. 2022-06-03 15:19:46 +02:00
robcaulk
15a971346d catch infinity values when filtering 2022-06-02 17:13:20 +02:00
robcaulk
ace951bf7e another queue bug fix for fresh starts 2022-06-02 13:28:06 +02:00
robcaulk
833d25bda0 Save data after queue reorg 2022-06-01 08:05:38 +02:00
robcaulk
0b0dd8dd80 Force high priority pair to be trained before anything else. 2022-06-01 07:55:05 +02:00