th0rntwig
683b084323
Set train-test-split shuffle=False as default and remove stratification
2022-09-28 18:23:56 +02:00
robcaulk
48e89e68b9
fix typos
2022-09-25 20:22:19 +02:00
robcaulk
873d2a5069
no model save backtest, plot features backtest, ensure inlier plays nice, doc
2022-09-25 11:18:10 +02:00
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
paranoidandy
2cc00a1a2c
Allow use of --strategy-list with freqai, with warning ( #7455 )
...
* Allow use of --strategy-list with freqai, with warning
* ensure populate_any_indicators is identical for resused identifiers
* use pair instead of metadata["pair"]
Co-authored-by: robcaulk <rob.caulk@gmail.com>
2022-09-24 13:21:01 +02:00
Matthias
6643d90e64
simplify freqAI start_backtesting
2022-09-24 10:34:14 +02:00
Emre
a4eaff4da6
Add training elapsed time
2022-09-23 01:18:34 -07:00
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
robcaulk
b5fd11f91b
protect against unforeseen issues in scanning thread
2022-09-19 21:18:31 +02:00
robcaulk
42c75b4a7b
combine log messages
2022-09-19 19:16:32 +02:00
Robert Caulk
9b66297cc0
Fix append
2022-09-19 12:47:20 +02:00
Robert Caulk
995396c775
Add useful log info
2022-09-19 11:42:56 +02:00
Robert Caulk
ad652817ef
Ensure train ordering after restart
...
Ensure lowest timestamps get trained first after restart
2022-09-19 11:11:23 +02:00
Robert Caulk
f9460c80c2
Merge pull request #7434 from freqtrade/improve-train-queue
...
improve train queue system in FreqAI
2022-09-19 10:55:53 +02:00
Matthias
ea58c29ded
Add plot_feature_importance to schema definition
2022-09-19 08:13:54 +00:00
Matthias
225f7cd5f8
Merge pull request #7431 from initrv/add-plot-feature-importance
...
Add plot feature importance
2022-09-19 08:41:10 +02:00
Matthias
d930931000
Bring back sleep - it'll ensure we give up control over the thread.
2022-09-19 07:14:33 +02:00
robcaulk
470d5d8405
ensure full new pairlist is in the queue
2022-09-18 17:08:07 +02:00
robcaulk
eaa43337d2
improve train queue system, ensure crash resilience in train queue.
2022-09-18 17:00:55 +02:00
robcaulk
95457d23ca
escape freqai-specific characters from file naming
2022-09-18 13:59:30 +02:00
Matthias
667853c504
Use Alias to type config objects
2022-09-18 13:20:55 +02:00
robcaulk
188f75d8ec
set model in models dict
2022-09-18 12:50:44 +02:00
robcaulk
1ef875901a
maintian user privacy by keeping plotly offline
2022-09-18 00:01:42 +02:00
robcaulk
68f7a31504
ensure continued operation despite not being able to plot
2022-09-18 00:00:14 +02:00
robcaulk
2c23effbf2
allow plot to plot multitargets, add test
2022-09-17 19:17:44 +02:00
initrv
1c92734f39
simplify plot_feature_importance call
2022-09-17 18:53:43 +03:00
initrv
86aa875bc9
plot features as html instead of png
2022-09-16 21:47:12 +03:00
initrv
b707a6da35
Add ability to plot feature importance
2022-09-16 19:17:41 +03:00
initrv
37dd22c89e
Fixed a bug that prevents clearing old models
...
Corrects the error of clearing old models when the model directory contains directories with names that do not match a regular expression
2022-09-14 03:40:13 +03:00
Emre
330d7068ab
Merge branch 'develop' into add-xgboostclassifier
2022-09-10 23:59:11 +03:00
Robert Caulk
075748b21a
Merge pull request #7392 from freqtrade/improve_ai_tests
...
Improve freqai tests by utilizing parametrization
2022-09-10 22:37:21 +02:00
robcaulk
5a0cfee27e
allow user to multithread jobs (advanced users only)
2022-09-10 22:16:49 +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
Matthias
e4caccc353
Merge pull request #7367 from freqtrade/add-continual-learning
...
add continual learning to catboost and friends
2022-09-10 20:17:28 +02:00
Wagner Costa Santos
311ae8bf1f
freqai backtesting - add startup_candle_count at function description
2022-09-10 14:45:42 -03:00
Emre
60eb02bb62
Add XGBoostClassifier
2022-09-10 20:13:16 +03:00
Robert Caulk
2077f84f9b
Merge pull request #7363 from wagnercosta/fixHyperoptFreqai
...
Fix hyperopt - freqai
2022-09-10 17:02:01 +02:00
Robert Caulk
4a47c63f71
Merge pull request #7374 from th0rntwig/filter-constant-features
2022-09-10 16:58:58 +02:00
robcaulk
10b6aebc5f
enable continual learning and evaluation sets on multioutput models.
2022-09-10 16:54:13 +02:00
Wagner Costa Santos
a1f88cca80
merge develop
2022-09-10 10:35:16 -03:00
Wagner Costa Santos
79985fda01
fix backtesting freqai startup candles bug
2022-09-10 10:27:17 -03:00
Matthias
5705b8759b
Merge branch 'develop' into add-continual-learning
2022-09-10 08:24:04 +02:00
robcaulk
05581db4e3
ensure columns are only dropped in training
2022-09-09 20:37:21 +02:00
Matthias
97be3318f4
Use Datetime_format from constants
2022-09-09 20:31:02 +02:00
robcaulk
a826c0eb83
ensure signatures match, reduce verbosity
2022-09-09 19:30:53 +02:00
Emre
acb410a0de
Remove verbosity params
2022-09-09 19:30:53 +02:00
Emre
df6e43d2c5
Add XGBoostRegressorMultiTarget class
2022-09-09 19:30:53 +02:00
Emre
1b6410d7d1
Add XGBoostRegressor for freqAI, fix mypy errors
2022-09-09 19:30:53 +02:00
Wagner Costa Santos
d38cc06139
Fix freqai backtesting time range issue
2022-09-09 19:27:05 +02:00
