Commit Graph

860 Commits

Author SHA1 Message Date
Yinon Polak
0012fe36ca sort imports 2023-03-12 16:16:04 +02:00
Yinon Polak
cb17b36981 simplify file_type check comparisons 2023-03-12 14:50:08 +02:00
Yinon Polak
f9fdf1c31b generalize mlp model 2023-03-12 14:31:08 +02:00
Yinon Polak
1cf0e7be24 use one iteration on all test and train data for evaluation 2023-03-12 12:48:15 +02:00
initrv
82cb107520 add tensorboard category 2023-03-12 01:32:55 +03:00
Yinon Polak
8a9f2aedbb improve documentation 2023-03-09 14:55:52 +02:00
Yinon Polak
e88a0d5248 convert single quotes to double quotes 2023-03-09 13:29:11 +02:00
Yinon Polak
2ef11faba7 reformat documentation 2023-03-09 13:25:20 +02:00
Yinon Polak
c9eee2944b reformat documentation 2023-03-09 13:01:04 +02:00
Yinon Polak
6f962362f2 expand pytorch trainer documentation 2023-03-09 12:45:46 +02:00
Yinon Polak
ba5de0cd00 add documentation 2023-03-09 11:21:10 +02:00
Yinon Polak
3081b9402b add documentation 2023-03-09 11:14:54 +02:00
robcaulk
d10ee0979a ensure training_features_list is updated properly 2023-03-08 19:37:11 +01:00
Robert Caulk
85e345fc48
Update BaseReinforcementLearningModel.py 2023-03-08 19:29:39 +01:00
Yinon Polak
1597c3aa89 set class names in IStrategy.set_freqai_targets method, also save class name with model meta data 2023-03-08 18:36:44 +02:00
Yinon Polak
7d26df01b8 fix tensor type hint 2023-03-08 16:17:19 +02:00
Yinon Polak
c8296ccb2d sort imports 2023-03-08 16:13:35 +02:00
Yinon Polak
8d60327d60 add missing import 2023-03-08 16:12:47 +02:00
Yinon Polak
04564dc134 add missing import 2023-03-08 16:11:51 +02:00
Yinon Polak
6161b858c4 sort imports 2023-03-08 16:10:25 +02:00
Yinon Polak
1921a07b89 sort imports 2023-03-08 16:08:04 +02:00
Yinon Polak
dfbb2e2b35 sort imports 2023-03-08 16:03:36 +02:00
Yinon Polak
1805db2b07 change documentation and small bugfix 2023-03-08 15:38:22 +02:00
Yinon Polak
76fbec0c17 ad multiclass target names encoder to ints 2023-03-08 14:29:38 +02:00
robcaulk
29d337fa02 ensure ohlc is dropped from both train and predict 2023-03-08 11:26:28 +01:00
robcaulk
d9dc831772 allow user to drop ohlc from features in RL 2023-03-07 11:33:54 +01:00
Yinon Polak
4241bff32a type hints fixes 2023-03-06 20:15:36 +02:00
Yinon Polak
5dd60eda36 type hints fixes 2023-03-06 19:37:08 +02:00
Yinon Polak
8acdd0b47c type hints fixes 2023-03-06 19:14:54 +02:00
Yinon Polak
125085fbaf add freqai.model_exists pytorch file type support 2023-03-06 18:10:49 +02:00
Yinon Polak
7eedcb9c14 reformat code 2023-03-06 17:56:07 +02:00
Yinon Polak
e6e747bcd8 reformat code 2023-03-06 17:50:02 +02:00
Yinon Polak
348a08f1c4 add todo - currently assuming class labels are strings ['0.0', '1.0' .. n_classes]. need to resolve it per ClassifierModel 2023-03-06 16:41:47 +02:00
Yinon Polak
b1ac2bf515 use data loader, add evaluation on epoch 2023-03-06 16:16:45 +02:00
Yinon Polak
751b205618 initial commit 2023-03-05 16:59:24 +02:00
Matthias
6e9ff5fdd8
Merge pull request #8202 from freqtrade/remove-populate-any-indicators
remove populate_any_indicators
2023-03-03 06:33:25 +01:00
Matthias
756c284ecd
Merge pull request #8225 from freqtrade/ruff2
Ruff - add PTH rule and subsequent changes
2023-03-01 20:27:06 +01:00
Matthias
66c2e145cb
Merge pull request #7975 from freqtrade/improve-freqai-gap-handling
handle data gaps between FreqAI and DP better
2023-02-26 15:26:46 +01:00
Matthias
d3d7cb1b14
Merge pull request #8216 from freqtrade/close-rl-env
Close training and eval environments in ReinforcementLearner_multiproc
2023-02-26 15:20:32 +01:00
Matthias
e88bb4e05c Revert small change - otherwise the data is never updated. 2023-02-26 15:09:25 +01:00
Matthias
26315b6bc2 add PTH ruff selection 2023-02-25 17:17:05 +01:00
Matthias
521025037d
Merge pull request #8203 from freqtrade/add-bufer-train-data-candles
Add buffer_train_data_candles feature
2023-02-24 13:25:18 +01:00
robcaulk
cb80d7c26f close the multi_proc env before creating new ones in an attempt to avoid increasing processes 2023-02-24 11:19:54 +01:00
robcaulk
b8f011a2ab give users ability to decide how many models to keep in dry/live 2023-02-22 22:27:56 +01:00
robcaulk
9633081c31 remove remnants of follower, clean data-drawer, improve doc 2023-02-22 22:01:41 +01:00
Alexander Malysh
070a7efd73
* fixed filename in model_exists 2023-02-22 14:52:20 +01:00
robcaulk
986bc63e54 raise OperationalException if latest historical data candle is older than earliest dataprovider candle 2023-02-21 21:23:58 +01:00
robcaulk
2b5c11c7b4 allow users to buffer train data with buffer_train_data_candles parameter 2023-02-21 21:08:34 +01:00
robcaulk
fd4e27d889 remove populate_any_indicators 2023-02-21 14:22:40 +01:00
Matthias
b0ec35d526
Merge pull request #7904 from freqtrade/feat/shuffle_after_split
add shuffle_after_split option
2023-02-19 15:03:04 +01:00
robcaulk
be85ef2707 add documentation for shuffle_after_split, add to constants 2023-02-16 18:50:11 +01:00
robcaulk
b6a741b421 merge develop into feat/shuffle_after_split 2023-02-16 18:46:01 +01:00
robcaulk
36d65e00f9 generalize model_exists() for RL and Keras 2023-02-16 18:33:40 +01:00
robcaulk
8873a565ee expose raw features to the environment for use in calculate_reward 2023-02-10 15:48:18 +01:00
robcaulk
154b6711b3 use function level noqa ignore 2023-02-10 15:26:17 +01:00
robcaulk
4fc0edb8b7 add pair to environment for access inside calculate_reward 2023-02-10 14:45:50 +01:00
robcaulk
e569f6f6df add explicit metadata argument to example strat, include it with backtesting 2023-02-04 16:53:17 +01:00
robcaulk
5da60b718d pass metadata dictionary to feature_engineering_* and set_freqai_targets functions. Add doc 2023-02-04 13:47:11 +01:00
robcaulk
ccb4efbe88 remove follow mode in favor of producer consumer 2023-02-02 11:40:23 +01:00
Matthias
8108a48f39 Follow PEP 484 - no implicit optionals 2023-01-21 20:01:56 +01:00
Wagner Costa
2241f24290 moved deprecated warning to start function 2023-01-10 09:10:30 -03:00
robcaulk
93aff9325e improve deprecation note 2023-01-09 20:15:03 +01:00
robcaulk
a61274ae18 ensure cached corr-pairs works with new framework 2023-01-09 20:04:36 +01:00
Wagner Costa
ed99e7f857 fix corr_pairs startup candle count bug 2023-01-04 14:21:37 -03:00
Wagner Costa
801ab39a24 fix get dataframe data to include startup_candle 2023-01-04 10:36:19 -03:00
robcaulk
3cbe51c3ca remove duplicated line 2023-01-04 13:58:25 +01:00
robcaulk
dc25668468 handle data gaps between FreqAI and DP better 2023-01-04 11:41:06 +01:00
Wagner Costa
314c0925bf fix get dataframe data to include startup_candle 2023-01-03 14:02:42 -03:00
Wagner Costa
c8aa7720a2 added again feature check in BT from pred files 2022-12-30 11:16:35 -03:00
Wagner Costa
b39fc6b924 remove add pair to column from docs, fix keyerror bug and adjust hybrid strategy example 2022-12-30 10:42:31 -03:00
robcaulk
b2bab68fba move price assignment to feature_engineering_standard() to reduce un-requested feature additions in RL. Ensure old method of price assignment still works, add deprecation warning to help users migrate their strategies 2022-12-30 13:02:39 +01:00
Wagner Costa
2e30bdb9b2 freqai bt - fix tests 2022-12-29 16:35:11 -03:00
Wagner Costa
2b89f643b7 adjust backtest to new feature engineering functions 2022-12-28 19:03:41 -03:00
robcaulk
6f7eb71bbb ensure RL works with new naming scheme 2022-12-28 14:52:33 +01:00
robcaulk
c2936d551b improve doc, update test strats, change function names 2022-12-28 13:25:40 +01:00
Wagner Costa
8227b4aafe freqAI Strategy - improve user experience 2022-12-27 11:37:01 -03:00
Emre
c293401b22
Add can_short to freqai base model 2022-12-16 23:19:08 +03:00
Emre
7727f31507
Add 3 Action RL env 2022-12-16 22:18:49 +03:00
Emre
dde363343c
Add can_short param to base env 2022-12-16 22:16:19 +03:00
initrv
36948e2a74 fix base4 env done condition 2022-12-16 14:14:05 +03:00
robcaulk
c9bc91c75b add shuffle_after_split option 2022-12-16 11:20:37 +01:00
robcaulk
581a5296cc fix docstrings to reflect new env_info changes 2022-12-15 16:50:08 +01:00
robcaulk
7b4abd5ef5 use a dictionary to make code more readable 2022-12-15 12:25:33 +01:00
Emre
3af2251ce8
Fix add_state_info backtesting bug 2022-12-14 22:03:23 +03:00
Emre
2018da0767
Add env_info dict to base environment 2022-12-14 22:03:05 +03:00
robcaulk
2285ca7d2a add dp to multiproc 2022-12-14 18:22:20 +01:00
Robert Caulk
e6da646e2f
Merge pull request #7866 from initrv/cleanup-tensorboard-callback
Cleanup tensorboard callback
2022-12-13 09:05:46 +01:00
initrv
f9b7d35900 add increment param for tensorboard_log 2022-12-12 14:14:23 +03:00
robcaulk
0f6b98b69a merge develop into tensorboard cleanup 2022-12-11 15:38:32 +01:00
robcaulk
0fd8e214e4 add documentation for tensorboard_log, change how users interact with tensorboard_log 2022-12-11 15:31:29 +01:00
Matthias
888ba65367
Merge branch 'develop' into fix/multioutput-bug 2022-12-11 15:23:53 +01:00
initrv
cb8fc3c8c7 custom info to tensorboard_metrics 2022-12-11 15:37:45 +03:00
robcaulk
8c7ec07951 ensure predict_proba follows suit. Remove all lib specific params from example config 2022-12-11 12:39:31 +01:00
robcaulk
85f22b5c30 fix bug in MultiOutput* with conv_width = 1 2022-12-11 12:15:19 +01:00
Emre
272c3302e3
Merge remote-tracking branch 'origin/develop' into update-freqai-tf-handling 2022-12-11 13:12:45 +03:00
robcaulk
7b3406914c flip add_state_info 2022-12-07 19:49:39 +01:00
robcaulk
9b4364ddc3 ensure that add_state_info is deactivated during backtesting 2022-12-07 19:49:14 +01:00
initrv
58604c747e cleanup tensorboard callback 2022-12-07 14:37:55 +03:00
Robert Caulk
b9f6911a6a
Merge pull request #7843 from smarmau/develop
freqai RL agent info during training
2022-12-06 20:06:41 +01:00
Wagner Costa
c81b00fb37 Merge branch 'develop' into freqai_bt_from_predictions_improvement 2022-12-05 18:00:55 -03:00
Emre
bc48099e48
Revert changes 2022-12-05 23:52:48 +03:00
robcaulk
62c69bf2b5 fix custom_info 2022-12-05 20:22:54 +01:00
Emre
730fba956b
Ensure base tf included in include_timeframes 2022-12-05 16:16:17 +03:00
Emre
e734b39929
Make model_training_parameters optional 2022-12-05 14:54:42 +03:00
robcaulk
d8565261e1 ignore initializer type 2022-12-04 14:10:33 +01:00
robcaulk
24766928ba reorganize/generalize tensorboard callback 2022-12-04 13:54:30 +01:00
smarmau
b2edc58089
fix flake8 2022-12-03 22:31:02 +11:00
smarmau
d6f45a12ae
add multiproc fix flake8 2022-12-03 22:30:04 +11:00
smarmau
469aa0d43f
add state/action info to callbacks 2022-12-03 21:16:46 +11:00
smarmau
075c8c23c8
add state/action info to callbacks 2022-12-03 21:16:04 +11:00
Matthias
4dc591a170
Merge pull request #7834 from freqtrade/fix-data-drawer-model-load
Fix sb3_contrib loading issue
2022-12-02 06:29:23 +01:00
Wagner Costa
77dc2c92a7 performance improvevemnts - backtest freqai from saved predictions 2022-12-01 12:53:19 -03:00
robcaulk
2b3e166dc2 fix fees RL 2022-12-01 10:10:28 +01:00
Emre
396e666e9b
Keep old behavior of model loading 2022-12-01 11:03:51 +03:00
Emre
4a9982f86b
Fix sb3_contrib loading issue 2022-12-01 10:08:42 +03:00
Matthias
dac4a35be2
Merge pull request #7828 from freqtrade/fix-state-info-rl
bring back market side setting in get_state_info
2022-11-30 19:57:28 +01:00
Wagner Costa
79821ebb33 fix flake8 errors 2022-11-30 08:41:44 -03:00
robcaulk
e7f72d52b8 bring back market side setting in get_state_info 2022-11-30 12:36:26 +01:00
Wagner Costa
17cf3c7e83 bug fixes and removed fillna from fit_live_predictions 2022-11-30 08:28:45 -03:00
robcaulk
4571aedb33 consolidate and clean code 2022-11-30 00:53:35 +01:00
Wagner Costa
8ea58ab352 change BT prediction files to feather format 2022-11-29 10:38:35 -03:00
Wagner Costa
df979ece33 Merge branch 'develop' into backtest_fitlivepredictions 2022-11-29 09:39:15 -03:00
Matthias
c3daddc629
Merge pull request #7809 from richardjozsa/develop
Improve the RL learning process
2022-11-29 06:28:36 +01:00
Emre
9cbfa12011
Directly set model_type in base RL model 2022-11-28 16:02:17 +03:00
robcaulk
56518def42 isort 2022-11-27 21:06:01 +01:00
robcaulk
7fd6bc526e add randomize_starting_position to the rl_config 2022-11-27 21:03:13 +01:00
richardjozsa
64d4a52a56 Improve the RL learning process
Improve the RL learning process by selecting random start point for the agent, it can help to block the agent to only learn on the selected period of time, while improving the quality of the model.
2022-11-27 20:43:50 +01:00
Matthias
f4025ee5de
Merge pull request #7289 from freqtrade/feat/freqai-rl-dev
Add reinforcement learning module to FreqAI
2022-11-27 17:15:21 +01:00
stm
51d21b413d
Fix 4ac update_total_profit
_update_total_profit() must be executed before "self._position = Positions.Neutral" because _update_total_profit() calls get_unrealized_profit(), which returns 0 if position is neutral and total_profit is not updated
2022-11-26 23:35:20 +03:00
robcaulk
dba30393fb ensure extra_returns_per_train are set properly on first hist_preds build 2022-11-26 18:04:47 +01:00
robcaulk
be890b52fd remove np import 2022-11-26 13:44:58 +01:00
robcaulk
aaaa5a5f64 add documentation for net_arch, other small changes 2022-11-26 13:44:58 +01:00
Matthias
7ebc8ee169 Fix missing Optional typehint 2022-11-26 13:32:18 +01:00
Matthias
bdfedb5fcb Improve typehints / reduce warnings from mypy 2022-11-26 13:03:07 +01:00
robcaulk
81fd2e588f ensure typing, remove unsued code 2022-11-26 12:11:59 +01:00
robcaulk
8dbfd2cacf improve docstring clarity about how to inherit from ReinforcementLearner, demonstrate inherittance with ReinforcementLearner_multiproc 2022-11-26 11:51:08 +01:00
robcaulk
2e82e6784a move data_provider cleanup to shutdown() 2022-11-24 19:07:38 +01:00
robcaulk
73c458d47b use importlib instead of __import___ 2022-11-24 19:04:35 +01:00
robcaulk
3a07749fcc fix docstring 2022-11-24 18:46:54 +01:00
robcaulk
44b042ba51 remove unused function 2022-11-24 17:53:26 +01:00
Matthias
8f1a8c752b Add freqairl docker build process 2022-11-24 07:00:12 +01:00
Wagner Costa
d09157efb8 update code to use one prediction file / pair 2022-11-22 15:15:42 -03:00
Wagner Costa
c01f25ddc9 update code to freqai_backtest_live_models only from historic predictions 2022-11-22 13:09:09 -03:00
Wagner Costa Santos
fdc82af883 fix tests - update code to backtest with historic_predictions 2022-11-19 22:27:58 -03:00
Wagner Costa Santos
80d070e9ee update code to use historic_predictions for freqai_backtest_live_models 2022-11-19 14:15:58 -03:00
robcaulk
387c905a86 merge develop into RL 2022-11-17 21:59:07 +01:00
robcaulk
60fcd8dce2 fix skipped mac test, fix RL bug in add_state_info, fix use of __import__, revise doc 2022-11-17 21:50:02 +01:00
robcaulk
91df79ff44 merge dev into backtest-live-predictions 2022-11-17 21:20:47 +01:00
Robert Caulk
cd6f87be17
Merge pull request #7728 from freqtrade/improve_timerange
Simplify timerange handling
2022-11-17 19:57:48 +01:00
Wagner Costa Santos
3903b04d3f save_live_data_backtest - added docs and tests 2022-11-17 15:20:07 -03:00
Wagner Costa Santos
99bff9cbfa backtesting_from_live_saved_files - code refactoring 2022-11-17 10:30:51 -03:00
Wagner Costa Santos
913749c81b backtesting_from_live_saved_files - code refactoring 2022-11-17 10:30:16 -03:00
Wagner Costa Santos
b01e4e3dbf change default value - save_live_data_backtest as false 2022-11-17 10:14:30 -03:00
Wagner Costa Santos
1a19d90e2e Merge branch 'develop' into backtest_fitlivepredictions 2022-11-17 10:13:11 -03:00
robcaulk
bf4d5b432a ensure model_type is defined 2022-11-13 18:50:25 +01:00
robcaulk
6394ef4558 fix docstrings 2022-11-13 17:43:52 +01:00
robcaulk
96fafb7f56 remove limit_ram_use 2022-11-13 17:14:47 +01:00
robcaulk
b421521be3 help default ReinforcementLearner users by assigning the model_type automatically 2022-11-13 17:12:17 +01:00
robcaulk
90f168d1ff remove more user references. cleanup dataprovider 2022-11-13 17:06:06 +01:00
robcaulk
388ca21200 update docs, fix bug in environment 2022-11-13 16:56:31 +01:00
robcaulk
af9e400562 add test coverage, fix bug in base environment. Ensure proper fee is used. 2022-11-13 15:31:37 +01:00
Matthias
942840da2d Improve setting wording to keep future possibilities open 2022-11-13 15:22:44 +01:00
robcaulk
81f800a79b switch to using FT calc_profi_pct, reverse entry/exit fees 2022-11-13 13:41:17 +01:00
robcaulk
e71a8b8ac1 add ability to integrate state info or not, and prevent state info integration during backtesting 2022-11-12 18:46:48 +01:00
Wagner Costa Santos
27fa9f1f4e backtest saved dataframe from live 2022-11-12 14:37:23 -03:00
Wagner Costa Santos
f9c6c538be Merge branch 'develop' into backtest_fitlivepredictions 2022-11-12 09:37:45 -03:00
robcaulk
9c6b97c678 ensure normalization acceleration methods are employed in RL 2022-11-12 12:01:59 +01:00
robcaulk
6746868ea7 store dataprovider to self instead of strategy 2022-11-12 11:33:03 +01:00
robcaulk
7a4bb040a5 merge develop into feat/freqai-rl-dev 2022-11-12 10:54:34 +01:00
robcaulk
214c622475 move dataframe converter to converter.py 2022-11-12 10:38:25 +01:00
robcaulk
9617d8143d Merge remote-tracking branch 'origin/develop' into add-single-precision-freqai 2022-11-12 10:21:38 +01:00
Matthias
e6172a68d7
Merge pull request #7730 from freqtrade/fix-metric-tracker
fix loading of metric tracker from disk
2022-11-11 20:01:26 +01:00
Robert Caulk
833578716c
Merge pull request #7644 from markdregan/multi-target-classifier
Support for multi target multi-class classification (FreqaiMultiOutputRegressor for Classification)
2022-11-11 18:48:38 +01:00
robcaulk
790ff2a84b merge develop into add-single-prec 2022-11-11 18:08:51 +01:00
robcaulk
e46a57bbd0 move mem logs to debug 2022-11-11 18:05:32 +01:00
robcaulk
66514e84e4 add LightGBMClassifierMultiTarget. add test 2022-11-11 17:45:53 +01:00
robcaulk
054133955b fix loading of metric tracker from disk 2022-11-11 17:24:09 +01:00
Matthias
0f9c5f8d41 Simplify timerange handling 2022-11-10 18:28:18 +01:00
Matthias
57313dd961 Update some usages of timerange to new, simplified method 2022-11-10 18:11:39 +01:00
Wagner Costa Santos
4f0f3e5b64 removed unnecessary code 2022-11-09 10:07:24 -03:00
Wagner Costa Santos
8ee95db927 refactoring backtesting_fit_live_predictions function 2022-11-09 09:51:42 -03:00
Wagner Costa Santos
3e57c18ac6 add fix_live_predictions function to backtesting 2022-11-08 18:20:39 -03:00
Wagner Costa Santos
8d9988a942 enforce date column in backtesting freqai predictions files 2022-11-08 11:06:23 -03:00
Wagner Costa Santos
9c5ba0732a save predictions with date and merge by date 2022-11-08 10:32:18 -03:00
Matthias
884014a4b9 Fix some minor typos 2022-11-07 18:35:28 +00:00
Wagner Costa Santos
6559384286 Merge branch 'develop' into backtest_live_models 2022-11-07 15:14:10 -03:00
Emre
43bdd34964
Optimize reduce_dataframe_footprint function 2022-11-05 19:13:02 +03:00
robcaulk
53df607067 avoid duplicating features with okx/gateio, ensure inference timer gets logged 2022-11-05 15:42:19 +01:00
robcaulk
257c833831 add doc for single precision, dont allow half precision, add test 2022-11-04 18:10:04 +01:00
robcaulk
3ccc120f92 add option to force single precision 2022-11-04 17:42:10 +01:00
robcaulk
8bdc99a3d6 fix self-imposed bug 2022-11-04 16:41:38 +01:00
robcaulk
19d90b813a improve readibility in start_backtesting() 2022-11-04 16:10:46 +01:00
Wagner Costa Santos
8008c63319 Merge branch 'develop' into backtest_live_models 2022-11-04 09:09:39 -03:00
Wagner Costa Santos
a7acfb7ab7 fix dict key error 2022-11-04 09:02:28 -03:00
robcaulk
90c5bfb4b5 add default conv_width 2022-11-03 21:35:12 +01:00
robcaulk
05b309caf2 ensure colon replaced for cached attach 2022-11-03 21:17:48 +01:00
robcaulk
6938ed6584 change default conv_width to 1 2022-11-03 21:11:26 +01:00
robcaulk
444a068481 merge develop into track-current-candle 2022-11-03 21:09:08 +01:00
robcaulk
db942321ad fix bug with lightgbm and colons 2022-11-03 21:03:48 +01:00
robcaulk
d721b50230 flake8 2022-11-03 19:13:24 +01:00