c3daddc629
Merge pull request #7809 from richardjozsa/develop
...
Improve the RL learning process
2022-11-29 06:28:36 +01:00
9cbfa12011
Directly set model_type in base RL model
2022-11-28 16:02:17 +03:00
56518def42
isort
2022-11-27 21:06:01 +01:00
7fd6bc526e
add randomize_starting_position to the rl_config
2022-11-27 21:03:13 +01:00
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
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
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
dba30393fb
ensure extra_returns_per_train are set properly on first hist_preds build
2022-11-26 18:04:47 +01:00
be890b52fd
remove np import
2022-11-26 13:44:58 +01:00
aaaa5a5f64
add documentation for net_arch, other small changes
2022-11-26 13:44:58 +01:00
7ebc8ee169
Fix missing Optional typehint
2022-11-26 13:32:18 +01:00
bdfedb5fcb
Improve typehints / reduce warnings from mypy
2022-11-26 13:03:07 +01:00
81fd2e588f
ensure typing, remove unsued code
2022-11-26 12:11:59 +01:00
8dbfd2cacf
improve docstring clarity about how to inherit from ReinforcementLearner, demonstrate inherittance with ReinforcementLearner_multiproc
2022-11-26 11:51:08 +01:00
2e82e6784a
move data_provider cleanup to shutdown()
2022-11-24 19:07:38 +01:00
73c458d47b
use importlib instead of __import___
2022-11-24 19:04:35 +01:00
3a07749fcc
fix docstring
2022-11-24 18:46:54 +01:00
44b042ba51
remove unused function
2022-11-24 17:53:26 +01:00
8f1a8c752b
Add freqairl docker build process
2022-11-24 07:00:12 +01:00
d09157efb8
update code to use one prediction file / pair
2022-11-22 15:15:42 -03:00
c01f25ddc9
update code to freqai_backtest_live_models only from historic predictions
2022-11-22 13:09:09 -03:00
fdc82af883
fix tests - update code to backtest with historic_predictions
2022-11-19 22:27:58 -03:00
80d070e9ee
update code to use historic_predictions for freqai_backtest_live_models
2022-11-19 14:15:58 -03:00
387c905a86
merge develop into RL
2022-11-17 21:59:07 +01:00
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
91df79ff44
merge dev into backtest-live-predictions
2022-11-17 21:20:47 +01:00
cd6f87be17
Merge pull request #7728 from freqtrade/improve_timerange
...
Simplify timerange handling
2022-11-17 19:57:48 +01:00
3903b04d3f
save_live_data_backtest - added docs and tests
2022-11-17 15:20:07 -03:00
99bff9cbfa
backtesting_from_live_saved_files - code refactoring
2022-11-17 10:30:51 -03:00
913749c81b
backtesting_from_live_saved_files - code refactoring
2022-11-17 10:30:16 -03:00
b01e4e3dbf
change default value - save_live_data_backtest as false
2022-11-17 10:14:30 -03:00
1a19d90e2e
Merge branch 'develop' into backtest_fitlivepredictions
2022-11-17 10:13:11 -03:00
bf4d5b432a
ensure model_type is defined
2022-11-13 18:50:25 +01:00
6394ef4558
fix docstrings
2022-11-13 17:43:52 +01:00
96fafb7f56
remove limit_ram_use
2022-11-13 17:14:47 +01:00
b421521be3
help default ReinforcementLearner users by assigning the model_type automatically
2022-11-13 17:12:17 +01:00
90f168d1ff
remove more user references. cleanup dataprovider
2022-11-13 17:06:06 +01:00
388ca21200
update docs, fix bug in environment
2022-11-13 16:56:31 +01:00
af9e400562
add test coverage, fix bug in base environment. Ensure proper fee is used.
2022-11-13 15:31:37 +01:00
942840da2d
Improve setting wording to keep future possibilities open
2022-11-13 15:22:44 +01:00
81f800a79b
switch to using FT calc_profi_pct, reverse entry/exit fees
2022-11-13 13:41:17 +01:00
e71a8b8ac1
add ability to integrate state info or not, and prevent state info integration during backtesting
2022-11-12 18:46:48 +01:00
27fa9f1f4e
backtest saved dataframe from live
2022-11-12 14:37:23 -03:00
f9c6c538be
Merge branch 'develop' into backtest_fitlivepredictions
2022-11-12 09:37:45 -03:00
9c6b97c678
ensure normalization acceleration methods are employed in RL
2022-11-12 12:01:59 +01:00
6746868ea7
store dataprovider to self instead of strategy
2022-11-12 11:33:03 +01:00
7a4bb040a5
merge develop into feat/freqai-rl-dev
2022-11-12 10:54:34 +01:00
214c622475
move dataframe converter to converter.py
2022-11-12 10:38:25 +01:00
9617d8143d
Merge remote-tracking branch 'origin/develop' into add-single-precision-freqai
2022-11-12 10:21:38 +01:00
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
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
790ff2a84b
merge develop into add-single-prec
2022-11-11 18:08:51 +01:00
e46a57bbd0
move mem logs to debug
2022-11-11 18:05:32 +01:00
66514e84e4
add LightGBMClassifierMultiTarget. add test
2022-11-11 17:45:53 +01:00
054133955b
fix loading of metric tracker from disk
2022-11-11 17:24:09 +01:00
0f9c5f8d41
Simplify timerange handling
2022-11-10 18:28:18 +01:00
57313dd961
Update some usages of timerange to new, simplified method
2022-11-10 18:11:39 +01:00
4f0f3e5b64
removed unnecessary code
2022-11-09 10:07:24 -03:00
8ee95db927
refactoring backtesting_fit_live_predictions function
2022-11-09 09:51:42 -03:00
3e57c18ac6
add fix_live_predictions function to backtesting
2022-11-08 18:20:39 -03:00
8d9988a942
enforce date column in backtesting freqai predictions files
2022-11-08 11:06:23 -03:00
9c5ba0732a
save predictions with date and merge by date
2022-11-08 10:32:18 -03:00
884014a4b9
Fix some minor typos
2022-11-07 18:35:28 +00:00
6559384286
Merge branch 'develop' into backtest_live_models
2022-11-07 15:14:10 -03:00
43bdd34964
Optimize reduce_dataframe_footprint function
2022-11-05 19:13:02 +03:00
53df607067
avoid duplicating features with okx/gateio, ensure inference timer gets logged
2022-11-05 15:42:19 +01:00
257c833831
add doc for single precision, dont allow half precision, add test
2022-11-04 18:10:04 +01:00
3ccc120f92
add option to force single precision
2022-11-04 17:42:10 +01:00
8bdc99a3d6
fix self-imposed bug
2022-11-04 16:41:38 +01:00
19d90b813a
improve readibility in start_backtesting()
2022-11-04 16:10:46 +01:00
8008c63319
Merge branch 'develop' into backtest_live_models
2022-11-04 09:09:39 -03:00
a7acfb7ab7
fix dict key error
2022-11-04 09:02:28 -03:00
90c5bfb4b5
add default conv_width
2022-11-03 21:35:12 +01:00
05b309caf2
ensure colon replaced for cached attach
2022-11-03 21:17:48 +01:00
6938ed6584
change default conv_width to 1
2022-11-03 21:11:26 +01:00
444a068481
merge develop into track-current-candle
2022-11-03 21:09:08 +01:00
db942321ad
fix bug with lightgbm and colons
2022-11-03 21:03:48 +01:00
d721b50230
flake8
2022-11-03 19:13:24 +01:00
3ba1e221eb
fix typo
2022-11-03 19:08:33 +01:00
6c4bdb8f67
remove special characters from feature names
2022-11-03 18:49:39 +01:00
17798b3397
Merge branch 'develop' into backtest_live_models
2022-11-03 13:29:25 -03:00
356d79b38a
verify mean and std exists in model metadata
2022-11-03 13:27:56 -03:00
ce92731132
ensure backwards compatitibility
2022-11-02 20:20:35 +01:00
23b6915dde
fix issue with different backtesting prediction size
2022-11-02 15:49:51 -03:00
1a38c10fc6
remove old code
2022-11-02 19:37:47 +01:00
255eb71270
start tracking the current candle in FreqAI, add robustness to corr_df caching and inference timer, add test for cache corr_df
2022-11-02 19:32:22 +01:00
97df232ac6
add a warning to __init__ for get_corr_dataframes
2022-10-31 18:18:00 +01:00
66d8ed6c0b
Merge remote-tracking branch 'origin/develop' into reduce-indicator-population
2022-10-31 09:42:01 +01:00
d59a7fa2f9
remove analysis_lock and realign example hybrid strat
2022-10-30 17:07:33 +01:00
391c3f56f7
Add typehint to corr_pairlist
2022-10-30 13:28:01 +01:00
7053f81fa8
simplified predict and predict_proba using super(). Added duplicate class label check.
2022-10-30 09:48:30 +00:00
cf4af2175c
Merge pull request #7662 from markdregan/backtest_extra_returns_fix
...
Fix missing f-string from PR #7611
2022-10-30 10:47:06 +01:00
a2843165e1
fix leftovers from merge
2022-10-30 10:31:38 +01:00
52e15b2070
Merge remote-tracking branch 'origin/develop' into feat/freqai-rl-dev
2022-10-30 10:16:39 +01:00
d1a0874683
merge develop into feat/freqai-rl-dev
2022-10-30 10:13:03 +01:00
fc53054d43
leverage list length knowledge, f-string change
2022-10-30 10:12:14 +01:00
f98c7a2423
Remove loop of normalization from metadata
2022-10-30 10:12:14 +01:00
c26fda282f
fix missing f-string from PR #7611
2022-10-30 08:19:59 +00:00
650bb8b7d7
ensure full pair string is used for caching dataframes. If not, revert to old behavior. Update docs.
2022-10-29 22:26:49 +02:00
801e91c39e
Merge pull request #7618 from wizrds/fix/docker-config-record
...
Update function in FreqAI interface to record FreqAI config params
2022-10-29 08:56:20 +02:00
6ef82dd8b6
minor change to return
2022-10-27 12:41:12 +01:00
b9bf9edb02
update rapidjson opts
2022-10-25 14:12:13 -06:00
217add70bd
add strat and config for testing on PR
2022-10-25 20:07:39 +01:00
47056eded3
multi target classifier working but not for parallel
2022-10-25 18:24:27 +01:00
1ef38f137d
Fix XGBoost regressor "used before assignment"
2022-10-25 13:37:04 +02:00
51be45547f
remove np object, make default str
2022-10-24 12:23:54 -06:00
6669714a73
Update mal-formatted docstrings
2022-10-24 18:12:17 +02:00
137aa1756b
Merge pull request #7593 from th0rntwig/prediction-shape
...
Fix constant PCA
2022-10-24 08:33:36 +02:00
4d2b7a74f1
move record params to utils, use rapidjson
2022-10-23 20:51:32 +02:00
07e813dfa0
change param record to only get certain params
2022-10-23 12:09:07 -06:00
49ff51f11f
Change storage loc and fix test fail
2022-10-23 16:24:02 +02:00
4464e91256
use self.identifier in full path
2022-10-21 19:53:33 -06:00
5ee3b8cbbb
update config recording to use all configs, fix tests
2022-10-21 19:48:26 -06:00
a85826bf24
Merge pull request #7611 from markdregan/backtest_extra_returns
...
Make extra_returns_per_train data available during backtest
2022-10-21 17:13:22 +02:00
6606a0113f
refactoring - remove unnecessary config file
2022-10-20 14:53:25 -03:00
589944055e
fix typos - live predictions candles
2022-10-20 12:15:41 -03:00
52b60c5cbb
Merge branch 'develop' into backtest_live_models
2022-10-20 11:59:37 -03:00
a9db668082
avoid redundant indicator population for corr_pair list
2022-10-20 16:30:32 +02:00
073ce1659e
remove un-used f-string
2022-10-20 14:26:10 +01:00
295ba21389
Make extra_returns_per_train values available during backtest
2022-10-20 12:05:37 +01:00
033c5bd441
Make check constant pred labels agnostic
2022-10-18 12:55:47 +02:00
880ddccaa8
Merge pull request #7590 from freqtrade/list-models
...
List models
2022-10-17 20:40:41 +02:00
441032be25
Fix sys.stdout bug for CatboostRegressorMultiTarget
2022-10-17 19:48:27 +02:00
6cb14148aa
Fix random test failure due to catboost bug
...
https://github.com/catboost/catboost/issues/2195
2022-10-17 07:00:44 +02:00
23a5a516f9
Merge pull request #7557 from freqtrade/add-metric-tracker
...
Add metric tracker to FreqAI
2022-10-16 18:20:07 +02:00
20fc521771
Fix constant PCA
2022-10-15 23:30:12 +02:00
62ca822597
Merge pull request #7569 from Silur/develop
...
Add XGBoost random forest predictors to freqai
2022-10-15 16:09:26 +02:00
3b4402aaab
Merge branch 'move-disk-writing-to-ram' into add-metric-tracker
2022-10-15 13:52:14 +02:00
99dbba6cad
avoid reading from disk to instantiate large objects
2022-10-15 13:50:55 +02:00
d81eef0b70
add timestamps to each metric, use rapidjson
2022-10-15 13:23:01 +02:00
b236e362ba
Merge remote-tracking branch 'origin/develop' into add-metric-tracker
2022-10-14 19:00:49 +02:00
7f05b44376
Add eval set to CatboostClassifier
2022-10-13 23:01:09 +03:00
6919f3aa75
Backtest live models - fix utc date convert issue
2022-10-13 15:03:27 -03:00
93fe2b6446
Merge branch 'develop' into backtest_live_models
2022-10-13 11:22:58 -03:00
1e31be562e
remove whitespace
2022-10-11 21:05:42 +02:00
dba1b573bc
remove tensorboard dir from other pred models
2022-10-11 19:49:24 +02:00
5b5bb8aab5
catboost tensorboard bugfix
2022-10-11 19:05:46 +02:00
2e34aa9f04
Merge pull request #7544 from th0rntwig/prediction-shape
...
Remove constant labels from prediction
2022-10-10 21:24:25 +02:00
7bcb7d9a1a
Merge pull request #7554 from initrv/add-catboost-tensorboard
...
Add tensorboard for catboost
2022-10-10 21:03:45 +02:00
3081e73f8a
Merge branch 'develop' into backtest_live_models
2022-10-10 14:53:45 -03:00
2ad086dd7a
add XGBoost random forest predictors to freqai
2022-10-10 14:38:43 +02:00
eaae9c9e03
Update docstring format
2022-10-10 12:19:29 +00:00
60de192d47
Update Classifier docstrings
2022-10-10 12:13:41 +00:00
a4aa1b972c
isolate and standardize location of tensorboard files, add doc, ensure backtesting functionality
2022-10-09 21:11:37 +02:00
76b33359a9
add an optional metric tracker to collect train timings, inference timings, and cpu load data
2022-10-09 20:22:42 +02:00
4daf0000c7
Move check and add log warning
2022-10-08 16:15:48 +02:00
8d7adfabe9
clean RL tests to avoid dir pollution and increase speed
2022-10-08 12:10:38 +02:00
e337d4b78a
Reset dataframe index after slice
2022-10-07 20:00:05 +02:00
d42fb15608
Improve generic exception handler
2022-10-07 16:05:41 +02:00
a9d5e04a43
Remove constant labels from prediction
2022-10-06 19:26:33 +02:00
Matthias
Emre
robcaulk
richardjozsa
stm
Wagner Costa
Mark Regan
Timothy Pogue
th0rntwig
rcaulk
silur