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

improve doc, update test strats, change function names

Browse Source
This commit is contained in:
robcaulk
2022-12-28 13:25:40 +01:00
parent 8227b4aafe
commit c2936d551b
14 changed files with 515 additions and 594 deletions
Download Patch File Download Diff File Expand all files Collapse all files

175
docs/freqai-configuration.md
View File

@@ -43,116 +43,113 @@ The FreqAI strategy requires including the following lines of code in the standa
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# the model will return all labels created by user in `populate_any_indicators`
# the model will return all labels created by user in `set_freqai_labels()`
# (& appended targets), an indication of whether or not the prediction should be accepted,
# the target mean/std values for each of the labels created by user in
# `populate_any_indicators()` for each training period.
# `feature_engineering_*` for each training period.
dataframe = self.freqai.start(dataframe, metadata, self)
return dataframe
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
"""
Function designed to automatically generate, name and merge features
from user indicated timeframes in the configuration file. User controls the indicators
passed to the training/prediction by prepending indicators with `'%-' + pair `
(see convention below). I.e. user should not prepend any supporting metrics
(e.g. bb_lowerband below) with % unless they explicitly want to pass that metric to the
model.
:param pair: pair to be used as informative
:param df: strategy dataframe which will receive merges from informatives
:param tf: timeframe of the dataframe which will modify the feature names
:param informative: the dataframe associated with the informative pair
*Only functional with FreqAI enabled strategies*
This function will automatically expand the defined features on the config defined
`indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and
`include_corr_pairs`. In other words, a single feature defined in this function
will automatically expand to a total of
`indicator_periods_candles` * `include_timeframes` * `include_shifted_candles` *
`include_corr_pairs` numbers of features added to the model.
All features must be prepended with `%` to be recognized by FreqAI internals.
:param df: strategy dataframe which will receive the features
:param period: period of the indicator - usage example:
dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
"""
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
dataframe["%-sma-period"] = ta.SMA(dataframe, timeperiod=period)
dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
t = int(t)
informative[f"%-{pair}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{pair}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{pair}adx-period_{t}"] = ta.ADX(informative, window=t)
return dataframe
indicators = [col for col in informative if col.startswith("%")]
# This loop duplicates and shifts all indicators to add a sense of recency to data
for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
if n == 0:
continue
informative_shift = informative[indicators].shift(n)
informative_shift = informative_shift.add_suffix("_shift-" + str(n))
informative = pd.concat((informative, informative_shift), axis=1)
def feature_engineering_expand_basic(self, dataframe, **kwargs):
"""
*Only functional with FreqAI enabled strategies*
This function will automatically expand the defined features on the config defined
`include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
In other words, a single feature defined in this function
will automatically expand to a total of
`include_timeframes` * `include_shifted_candles` * `include_corr_pairs`
numbers of features added to the model.
df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
skip_columns = [
(s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
]
df = df.drop(columns=skip_columns)
Features defined here will *not* be automatically duplicated on user defined
`indicator_periods_candles`
# Add generalized indicators here (because in live, it will call this
# function to populate indicators during training). Notice how we ensure not to
# add them multiple times
if set_generalized_indicators:
All features must be prepended with `%` to be recognized by FreqAI internals.
# user adds targets here by prepending them with &- (see convention below)
# If user wishes to use multiple targets, a multioutput prediction model
# needs to be used such as templates/CatboostPredictionMultiModel.py
df["&-s_close"] = (
df["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.mean()
/ df["close"]
- 1
:param df: strategy dataframe which will receive the features
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200)
"""
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
return dataframe
def feature_engineering_standard(self, dataframe, **kwargs):
"""
*Only functional with FreqAI enabled strategies*
This optional function will be called once with the dataframe of the base timeframe.
This is the final function to be called, which means that the dataframe entering this
function will contain all the features and columns created by all other
freqai_feature_engineering_* functions.
This function is a good place to do custom exotic feature extractions (e.g. tsfresh).
This function is a good place for any feature that should not be auto-expanded upon
(e.g. day of the week).
All features must be prepended with `%` to be recognized by FreqAI internals.
:param df: strategy dataframe which will receive the features
usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
"""
dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
dataframe["%-hour_of_day"] = (dataframe["date"].dt.hour + 1) / 25
return dataframe
def set_freqai_targets(self, dataframe, **kwargs):
"""
*Only functional with FreqAI enabled strategies*
Required function to set the targets for the model.
All targets must be prepended with `&` to be recognized by the FreqAI internals.
:param df: strategy dataframe which will receive the targets
usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
"""
dataframe["&-s_close"] = (
dataframe["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.mean()
/ dataframe["close"]
- 1
)
return df
```
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`.
Notice how the `feature_engineering_*()` is where [features](freqai-feature-engineering.md#feature-engineering) are added. Meanwhile `set_freqai_targets()` adds the labels/targets. A full example strategy is available in `templates/FreqaiExampleStrategy.py`.
!!! Note
The `self.freqai.start()` function cannot be called outside the `populate_indicators()`.
!!! Note
Features **must** be defined in `populate_any_indicators()`. Defining FreqAI features in `populate_indicators()`
will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, the following structure inside `populate_any_indicators()` should be used
(as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`):
```python
def populate_any_indicators(self, pair, df, tf, informative=None, set_generalized_indicators=False):
...
# Add generalized indicators here (because in live, it will call only this function to populate
# indicators for retraining). Notice how we ensure not to add them multiple times by associating
# these generalized indicators to the basepair/timeframe
if set_generalized_indicators:
df['%-day_of_week'] = (df["date"].dt.dayofweek + 1) / 7
df['%-hour_of_day'] = (df['date'].dt.hour + 1) / 25
# user adds targets here by prepending them with &- (see convention below)
# If user wishes to use multiple targets, a multioutput prediction model
# needs to be used such as templates/CatboostPredictionMultiModel.py
df["&-s_close"] = (
df["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.mean()
/ df["close"]
- 1
)
```
Please see the example script located in `freqtrade/templates/FreqaiExampleStrategy.py` for a full example of `populate_any_indicators()`.
Features **must** be defined in `feature_engineering_*()`. Defining FreqAI features in `populate_indicators()`
will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, you should use `feature_engineering_standard()`
(as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`).
## Important dataframe key patterns
@@ -160,11 +157,11 @@ Below are the values you can expect to include/use inside a typical strategy dat
| DataFrame Key | Description |
|------------|-------------|
| `df['&*']` | Any dataframe column prepended with `&` in `populate_any_indicators()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
| `df['&*']` | Any dataframe column prepended with `&` in `set_freqai_targets()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
| `df['&*_std/mean']` | Standard deviation and mean values of the defined labels during training (or live tracking with `fit_live_predictions_candles`). Commonly used to understand the rarity of a prediction (use the z-score as shown in `templates/FreqaiExampleStrategy.py` and explained [here](#creating-a-dynamic-target-threshold) to evaluate how often a particular prediction was observed during training or historically with `fit_live_predictions_candles`). <br> **Datatype:** Float.
| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -2 and 2, which lets you know if the prediction is trustworthy or not. `do_predict==1` means that the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di)) of the input data point is above the threshold defined in the config, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers()` is active, the Support Vector Machine (SVM, see details [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm)) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, or vice versa, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. As with the SVM, if `use_DBSCAN_to_remove_outliers` is active, DBSCAN (see details [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan)) may also detect outliers and subtract 1 from `do_predict`. Hence, if both the SVM and DBSCAN are active and identify a datapoint that was above the DI threshold as an outlier, the result will be `do_predict==-2`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`. <br> **Datatype:** Integer between -2 and 2.
| `df['DI_values']` | Dissimilarity Index (DI) values are proxies for the level of confidence FreqAI has in the prediction. A lower DI means the prediction is close to the training data, i.e., higher prediction confidence. See details about the DI [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di). <br> **Datatype:** Float.
| `df['%*']` | Any dataframe column prepended with `%` in `populate_any_indicators()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md). <br> **Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
| `df['%*']` | Any dataframe column prepended with `%` in `feature_engineering_*()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md). <br> **Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
## Setting the `startup_candle_count`