Commit Graph

283 Commits

Author SHA1 Message Date
Wagner Costa Santos
6845a5c6ea backtest_live_models - refactoring after PR review 2022-09-29 01:48:38 -03:00
robcaulk
83343dc2f1 control number of threads, update doc 2022-09-29 00:10:18 +02:00
th0rntwig
683b084323 Set train-test-split shuffle=False as default and remove stratification 2022-09-28 18:23:56 +02:00
Wagner Costa Santos
55ebbeec18 backtest_live models tests refactoring 2022-09-28 08:48:32 -03:00
Wagner Costa Santos
0be115de9c backtest_live_models - added new tests and refactoring 2022-09-27 10:26:57 -03:00
Wagner Costa Santos
72aa47fc51 backtest_live_models - fix issue with timerange BT and 2 trainings within same candle (no data) 2022-09-27 00:14:12 -03:00
Wagner Costa Santos
ec947ad65c remove commented code - backtest_live_models 2022-09-25 23:47:27 -03:00
Wagner Costa Santos
5880f7a638 backtest_live_models - params validation and get timerange from live models in BT 2022-09-25 23:14:00 -03:00
Wagner Costa Santos
f3f3917da3 Merge branch 'develop' into backtest_live_models 2022-09-25 20:05:26 -03:00
Wagner Costa Santos
0ed7b2bfc3 change start_backtesting to handle backtest_live_models 2022-09-25 10:35:55 -03:00
robcaulk
873d2a5069 no model save backtest, plot features backtest, ensure inlier plays nice, doc 2022-09-25 11:18:10 +02:00
Wagner Costa Santos
7f116db95e added generic function to get timerange from existent models 2022-09-24 13:01:53 -03:00
Wagner Costa Santos
d9c16d4888 Merge branch 'develop' into backtest_live_models 2022-09-24 12:30:55 -03:00
Wagner Costa Santos
3ee7eb63f7 starting backtest live models 2022-09-24 12:28:52 -03:00
Matthias
585342f193
Merge pull request #7454 from freqtrade/fix_backtesting_dfsize_freqai
Ensure the DF has the same size in backtesting FreqAI
2022-09-24 16:17:39 +02:00
th0rntwig
71e6c54ea4
Normalise distances before Weibull fit (#7432)
* Normalise distances before Weibull

* Track inlier-metric params
2022-09-22 18:11:50 +02:00
Wagner Costa Santos
b1dbc3a65f remove function remove_training_from_backtesting and ensure BT period is correct with startup_candle_count 2022-09-22 12:13:51 -03:00
Matthias
667853c504 Use Alias to type config objects 2022-09-18 13:20:55 +02:00
Robert Caulk
73e122ad10
Merge pull request #7391 from wagnercosta/fixBTfreqaiV2
Fix FreaqAI backtesting - startup_candle_count bug
2022-09-10 21:53:00 +02:00
Wagner Costa Santos
311ae8bf1f freqai backtesting - add startup_candle_count at function description 2022-09-10 14:45:42 -03:00
Robert Caulk
4a47c63f71
Merge pull request #7374 from th0rntwig/filter-constant-features 2022-09-10 16:58:58 +02:00
Wagner Costa Santos
79985fda01 fix backtesting freqai startup candles bug 2022-09-10 10:27:17 -03:00
robcaulk
05581db4e3 ensure columns are only dropped in training 2022-09-09 20:37:21 +02:00
Wagner Costa Santos
d38cc06139 Fix freqai backtesting time range issue 2022-09-09 19:27:05 +02:00
Wagner Costa Santos
f4f2884a66 Fix freqai backtesting time range issue 2022-09-07 18:52:58 -03:00
th0rntwig
cdc72bf8ca Correct indexing 2022-09-07 18:14:13 +02:00
th0rntwig
047ded1baa Check for constant columns 2022-09-07 17:47:27 +02:00
Robert Caulk
d7585161b2
Merge branch 'develop' into add-inlier-metric 2022-09-06 20:40:21 +02:00
robcaulk
d44296783e isort datakitchen 2022-09-06 20:10:12 +02:00
robcaulk
e83c9b276d fix whitespace 2022-09-06 19:56:52 +02:00
robcaulk
4b28d0495f fix timestamping, move imports, add words to doc 2022-09-06 19:46:58 +02:00
robcaulk
78d01810ed reduce code redundancy, ensure live always gets the latest data 2022-09-05 00:12:00 +02:00
Wagner Costa Santos
d43ed186fc fix issue with freqai backtesting at slice dataframe 2022-09-05 00:12:00 +02:00
Robert Caulk
8545d74378
Merge pull request #7331 from th0rntwig/pca
Normalise PCA space
2022-09-03 21:49:54 +02:00
robcaulk
5cfb4154eb revert all changes in normalize_data() 2022-09-03 19:48:30 +02:00
robcaulk
c21808ff98 remove metadata redundancy, fix pca bug 2022-09-03 16:54:30 +02:00
robcaulk
c9be66b5b6 increase test coverage for dk, improve function naming, extra cleaning 2022-09-03 15:52:29 +02:00
robcaulk
599c1c79fb reorganized backtest utilities, test new functionality, improve/update doc 2022-09-03 14:00:01 +02:00
th0rntwig
11b2bc269e Added missing s 2022-09-01 22:37:32 +02:00
th0rntwig
3f8400df10 Normalise PCA space 2022-09-01 21:51:33 +02:00
Wagner Costa Santos
d6e115178a refactoring freqai backtesting - remove duplicate code 2022-09-01 07:09:23 -03:00
Wagner Costa Santos
44d3a9140d Merge branch 'develop' of https://github.com/wagnercosta/freqtrade into develop 2022-08-31 15:37:06 -03:00
Wagner Costa Santos
7bed0450d2 pr review - refactoring backtesting freqai 2022-08-31 15:36:29 -03:00
wagnercosta
3d4497467c
Merge branch 'freqtrade:develop' into develop 2022-08-31 14:47:06 -03:00
Wagner Costa Santos
df51da22ee refactoring freqai backtesting 2022-08-31 11:23:48 -03:00
Matthias
a88ffd2c9d Merge branch 'develop' into move_datadownload 2022-08-31 10:23:45 +00:00
robcaulk
7e8e29e42d use continuous value for inlier_metric 2022-08-30 20:41:37 +02:00
robcaulk
a58dd0bbf9 add noise feature, improve docstrings 2022-08-30 18:26:24 +02:00
robcaulk
b11742a4c5 integrate inlier metric function 2022-08-30 18:26:24 +02:00
th0rntwig
d3cb211283 Add inlier metric computation 2022-08-30 18:26:24 +02:00
th0rntwig
50e2808667
Fix bug in DI (#7321) 2022-08-30 12:54:39 +02:00
robcaulk
62c0a174c8 allow users to properly reverse train-test data ordering 2022-08-29 11:04:58 +02:00
robcaulk
dd628eb525 add tests for outlier detection and removal functions 2022-08-28 12:56:39 +02:00
robcaulk
1e41c773a0 fix outlier protection 2022-08-28 12:11:29 +02:00
th0rntwig
71f7d68783 Fixed mypy error 2022-08-27 12:44:55 +02:00
elintornquist
86c5ac44e4 Add outlier percentage check 2022-08-26 23:05:07 +02:00
elintornquist
b2d664c63c Change MinPts calculation 2022-08-26 18:57:27 +02:00
robcaulk
65b552e310 make docs reflect reality, move download_all_data to new utils.py file, automatic startup_candle detection 2022-08-26 15:30:01 +02:00
robcaulk
4b7e640f31 reduce code duplication, optimize auto data download per tf 2022-08-26 13:56:44 +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
006b11e5d5 fix leftover bug in indicator population 2022-08-14 21:42:55 +02:00
robcaulk
ad846cdb76 fix lock bug, update docstring 2022-08-14 20:24:29 +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
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
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
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
robcaulk
29b7b014e5 fix bug in DB path initialization 2022-08-05 18:19:26 +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
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
c84d54b35e Fix typing issue, avoid using .get() when unnecessary, convert to fstrings 2022-07-29 08:12:50 +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
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
robcaulk
c91e23dc50 let user avoid normalizing labels 2022-07-23 16:14:13 +02:00
robcaulk
a1cff377ec add record of contribution to data_kitchen.py 2022-07-23 13:32:04 +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
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
183dec866a remove ability to backtest open ended timeranges (safer) 2022-07-21 13:02:52 +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
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
robcaulk
ef409dd345 Add ground work for TensorFlow models, add protections from common mistakes 2022-07-12 18:09:17 +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
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
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
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
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
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
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
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
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
4b26b6aaec add lock to any historic data access 2022-06-07 00:54:18 +02:00
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
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
7523ed825e automatically detect maximum required data based on user fed indicators (to avoid NaNs in dataset for rolling indicators), add new config parameter for backtesting to let users increase their startup_candles to accommodate high timeframe indicators, add docs to explain all. Add new feature for automatic indicator duplication according to user defined intervals (exhibited in example strat and configs now). 2022-05-31 18:42:27 +02:00
robcaulk
70adf55643 Automatically detect and change follower data_path to accommodate remote systems 2022-05-31 12:35:09 +02:00
robcaulk
0306f5ca13 Add autopurge feature so that FreqAI cleans up after itself when it no longer needs old models on disk 2022-05-31 11:58:21 +02:00
robcaulk
29d2f59f12 fix PCA bug 2022-05-31 00:40:45 +02:00
robcaulk
a20651efd8 Increase performance by only predicting on most recent candle instead of full strat provided dataframe. Collect predictions and store them so that we can feed true predictions back to strategy (so that frequi isnt updating historic predictions based on newly trained models). 2022-05-30 11:37:05 +02:00
robcaulk
2f1a2c1cd7 allow users to store data in custom formats, update spot config to reflect better target horizon to training period ratio 2022-05-30 02:12:31 +02:00
robcaulk
4eb4753e20 allow subdaily retraining for backtesting 2022-05-29 17:44:35 +02:00
robcaulk
83dd453723 catch errors occuring on background thread, and make sure to keep the ball rolling. Improve pair retraining queue. 2022-05-28 18:26:19 +02:00