Commit Graph

729 Commits

Author SHA1 Message Date
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