adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #7860 from freqtrade/update-freqai-tf-handling

Browse Source 
Ensure base tf to be include_timeframes
This commit is contained in:
Robert Caulk 2022-12-11 12:50:07 +01:00 committed by GitHub
commit 0f75ec9c97
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
config_examples/config_freqai.example.json
View File

@ -79,9 +79,7 @@
"test_size": 0.33,
"random_state": 1
},
"model_training_parameters": {
"n_estimators": 1000
}
"model_training_parameters": {}
},
"bot_name": "",
"force_entry_enable": true,

11
docs/freqai-configuration.md
View File

@ -26,10 +26,7 @@ FreqAI is configured through the typical [Freqtrade config file](configuration.m
},
"data_split_parameters" : {
"test_size": 0.25
},
"model_training_parameters" : {
"n_estimators": 100
},
}
}
```
@ -118,7 +115,7 @@ The FreqAI strategy requires including the following lines of code in the standa
```
Notice how the `populate_any_indicators()` is where [features](freqai-feature-engineering.md#feature-engineering) and labels/targets are added. A full example strategy is available in `templates/FreqaiExampleStrategy.py`.
Notice how the `populate_any_indicators()` is where [features](freqai-feature-engineering.md#feature-engineering) and labels/targets are added. A full example strategy is available in `templates/FreqaiExampleStrategy.py`.
Notice also the location of the labels under `if set_generalized_indicators:` at the bottom of the example. This is where single features and labels/targets should be added to the feature set to avoid duplication of them from various configuration parameters that multiply the feature set, such as `include_timeframes`.
@ -182,7 +179,7 @@ The `startup_candle_count` in the FreqAI strategy needs to be set up in the same
## Creating a dynamic target threshold
Deciding when to enter or exit a trade can be done in a dynamic way to reflect current market conditions. FreqAI allows you to return additional information from the training of a model (more info [here](freqai-feature-engineering.md#returning-additional-info-from-training)). For example, the `&*_std/mean` return values describe the statistical distribution of the target/label *during the most recent training*. Comparing a given prediction to these values allows you to know the rarity of the prediction. In `templates/FreqaiExampleStrategy.py`, the `target_roi` and `sell_roi` are defined to be 1.25 z-scores away from the mean which causes predictions that are closer to the mean to be filtered out.
Deciding when to enter or exit a trade can be done in a dynamic way to reflect current market conditions. FreqAI allows you to return additional information from the training of a model (more info [here](freqai-feature-engineering.md#returning-additional-info-from-training)). For example, the `&*_std/mean` return values describe the statistical distribution of the target/label *during the most recent training*. Comparing a given prediction to these values allows you to know the rarity of the prediction. In `templates/FreqaiExampleStrategy.py`, the `target_roi` and `sell_roi` are defined to be 1.25 z-scores away from the mean which causes predictions that are closer to the mean to be filtered out.
```python
dataframe["target_roi"] = dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * 1.25
@ -230,7 +227,7 @@ If you want to predict multiple targets, you need to define multiple labels usin
#### Classifiers
If you are using a classifier, you need to specify a target that has discrete values. FreqAI includes a variety of classifiers, such as the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example, if you want to predict if the price 100 candles into the future goes up or down you would set
If you are using a classifier, you need to specify a target that has discrete values. FreqAI includes a variety of classifiers, such as the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example, if you want to predict if the price 100 candles into the future goes up or down you would set
```python
df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down')

7
freqtrade/configuration/config_validation.py
View File

@ -355,6 +355,13 @@ def _validate_freqai_include_timeframes(conf: Dict[str, Any]) -> None:
f"Main timeframe of {main_tf} must be smaller or equal to FreqAI "
f"`include_timeframes`.Offending include-timeframes: {', '.join(offending_lines)}")
# Ensure that the base timeframe is included in the include_timeframes list
if main_tf not in freqai_include_timeframes:
feature_parameters = conf.get('freqai', {}).get('feature_parameters', {})
include_timeframes = [main_tf] + freqai_include_timeframes
conf.get('freqai', {}).get('feature_parameters', {}) \
.update({**feature_parameters, 'include_timeframes': include_timeframes})
def _validate_freqai_backtest(conf: Dict[str, Any]) -> None:
if conf.get('runmode', RunMode.OTHER) == RunMode.BACKTEST:

5
freqtrade/constants.py
View File

@ -608,9 +608,8 @@ CONF_SCHEMA = {
"backtest_period_days",
"identifier",
"feature_parameters",
"data_split_parameters",
"model_training_parameters"
]
"data_split_parameters"
]
},
},
}

2
freqtrade/freqai/prediction_models/ReinforcementLearner.py
View File

@ -61,7 +61,7 @@ class ReinforcementLearner(BaseReinforcementLearningModel):
model = self.MODELCLASS(self.policy_type, self.train_env, policy_kwargs=policy_kwargs,
tensorboard_log=Path(
dk.full_path / "tensorboard" / dk.pair.split('/')[0]),
**self.freqai_info['model_training_parameters']
**self.freqai_info.get('model_training_parameters', {})
)
else:
logger.info('Continual training activated - starting training from previously '

7
tests/test_configuration.py
View File

@ -1046,8 +1046,13 @@ def test__validate_freqai_include_timeframes(default_conf, caplog) -> None:
# Validation pass
conf.update({'timeframe': '1m'})
validate_config_consistency(conf)
conf.update({'analyze_per_epoch': True})
# Ensure base timeframe is in include_timeframes
conf['freqai']['feature_parameters']['include_timeframes'] = ["5m", "15m"]
validate_config_consistency(conf)
assert conf['freqai']['feature_parameters']['include_timeframes'] == ["1m", "5m", "15m"]
conf.update({'analyze_per_epoch': True})
with pytest.raises(OperationalException,
match=r"Using analyze-per-epoch .* not supported with a FreqAI strategy."):
validate_config_consistency(conf)