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
Show Stats 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`

194
docs/freqai-feature-engineering.md
View File

@ -2,96 +2,132 @@
## Defining the features
Low level feature engineering is performed in the user strategy within a function called `populate_any_indicators()`. That function sets the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. One important syntax rule is that all `base features` string names are prepended with `%-{pair}`, while labels/targets are prepended with `&`.
Low level feature engineering is performed in the user strategy within a set of functions called `feature_engineering_*`. These function set the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. One important syntax rule is that all `base features` string names defined within `feature_engineering_*` functions must be prepended with `%-{pair}`. FreqAI is equipped with a set of functions to simplify rapid large-scale feature engineering:
| Function | Description |
|---------------|-------------|
| `feature_engineering__expand_all()` | This optional function will automatically expand the defined features on the config defined `indicator_periods_candles`, `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`.
| `feature_engineering__expand_basic()` | This optional function will automatically expand the defined features on the config defined `include_timeframes`, `include_shifted_candles`, and `include_corr_pairs`. Note: this function does *not* expand across `include_periods_candles`.
| `feature_engineering_standard()` | 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 `feature_engineering_expand` functions. This function is a good place to do custom exotic feature extractions (e.g. tsfresh). This function is also a good place for any feature that should not be auto-expanded upon (e.g. day of the week).
| `set_freqai_targets()` | Required function to set the targets for the model. All targets must be prepended with `&` to be recognized by the FreqAI internals.
!!! Note
Adding the full pair string, e.g. XYZ/USD, in the feature name enables improved performance for dataframe caching on the backend. If you decide *not* to add the full pair string in the feature string, FreqAI will operate in a reduced performance mode.
Meanwhile, high level feature engineering is handled within `"feature_parameters":{}` in the FreqAI config. Within this file, it is possible to decide large scale feature expansions on top of the `base_features` such as "including correlated pairs" or "including informative timeframes" or even "including recent candles."
It is advisable to start from the template `populate_any_indicators()` in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy:
It is advisable to start from the template `feature_engineering_*` functions in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy:
```python
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. The user controls the indicators
passed to the training/prediction by prepending indicators with `'%-' + pair `
(see convention below). I.e., the 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)
bollinger = qtpylib.bollinger_bands(
qtpylib.typical_price(dataframe), window=period, stds=2.2
)
dataframe["bb_lowerband-period"] = bollinger["lower"]
dataframe["bb_middleband-period"] = bollinger["mid"]
dataframe["bb_upperband-period"] = bollinger["upper"]
bollinger = qtpylib.bollinger_bands(
qtpylib.typical_price(informative), window=t, stds=2.2
dataframe["%-bb_width-period"] = (
dataframe["bb_upperband-period"]
- dataframe["bb_lowerband-period"]
) / dataframe["bb_middleband-period"]
dataframe["%-close-bb_lower-period"] = (
dataframe["close"] / dataframe["bb_lowerband-period"]
)
dataframe["%-roc-period"] = ta.ROC(dataframe, timeperiod=period)
dataframe["%-relative_volume-period"] = (
dataframe["volume"] / dataframe["volume"].rolling(period).mean()
)
return dataframe
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.
Features defined here will *not* be automatically duplicated on user defined
`indicator_periods_candles`
All features must be prepended with `%` to be recognized by FreqAI internals.
: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
)
informative[f"{pair}bb_lowerband-period_{t}"] = bollinger["lower"]
informative[f"{pair}bb_middleband-period_{t}"] = bollinger["mid"]
informative[f"{pair}bb_upperband-period_{t}"] = bollinger["upper"]
informative[f"%-{pair}bb_width-period_{t}"] = (
informative[f"{pair}bb_upperband-period_{t}"]
- informative[f"{pair}bb_lowerband-period_{t}"]
) / informative[f"{pair}bb_middleband-period_{t}"]
informative[f"%-{pair}close-bb_lower-period_{t}"] = (
informative["close"] / informative[f"{pair}bb_lowerband-period_{t}"]
)
informative[f"%-{pair}relative_volume-period_{t}"] = (
informative["volume"] / informative["volume"].rolling(t).mean()
)
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)
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)
# 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:
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
)
return df
```
In the presented example, the user does not wish to pass the `bb_lowerband` as a feature to the model,
@ -118,13 +154,13 @@ After having defined the `base features`, the next step is to expand upon them u
}
```
The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `populate_any_indicators()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `feature_engineering_expand_*()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `populate_any_indicators` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example).
You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `feature_engineering_expand_*()` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example).
`include_shifted_candles` indicates the number of previous candles to include in the feature set. For example, `include_shifted_candles: 2` tells FreqAI to include the past 2 candles for each of the features in the feature set.
In total, the number of features the user of the presented example strat has created is: length of `include_timeframes` * no. features in `populate_any_indicators()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
In total, the number of features the user of the presented example strat has created is: length of `include_timeframes` * no. features in `feature_engineering_expand_*()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
$= 3 * 3 * 3 * 2 * 2 = 108$.
### Returning additional info from training

8
docs/freqai-parameter-table.md
View File

@ -29,12 +29,12 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
|------------|-------------|
| | **Feature parameters within the `freqai.feature_parameters` sub dictionary**
| `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](freqai-feature-engineering.md). <br> **Datatype:** Dictionary.
| `include_timeframes` | A list of timeframes that all indicators in `populate_any_indicators` will be created for. The list is added as features to the base indicators dataset. <br> **Datatype:** List of timeframes (strings).
| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `populate_any_indicators` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset. <br> **Datatype:** List of assets (strings).
| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `populate_any_indicators` (see `templates/FreqaiExampleStrategy.py` for detailed usage). You can create custom labels and choose whether to make use of this parameter or not. <br> **Datatype:** Positive integer.
| `include_timeframes` | A list of timeframes that all indicators in `feature_engineering_expand_*()` will be created for. The list is added as features to the base indicators dataset. <br> **Datatype:** List of timeframes (strings).
| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `feature_engineering_expand_*()` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset. <br> **Datatype:** List of assets (strings).
| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `feature_engineering_expand_all()` (see `templates/FreqaiExampleStrategy.py` for detailed usage). You can create custom labels and choose whether to make use of this parameter or not. <br> **Datatype:** Positive integer.
| `include_shifted_candles` | Add features from previous candles to subsequent candles with the intent of adding historical information. If used, FreqAI will duplicate and shift all features from the `include_shifted_candles` previous candles so that the information is available for the subsequent candle. <br> **Datatype:** Positive integer.
| `weight_factor` | Weight training data points according to their recency (see details [here](freqai-feature-engineering.md#weighting-features-for-temporal-importance)). <br> **Datatype:** Positive float (typically < 1).
| `indicator_max_period_candles` | **No longer used (#7325)**. Replaced by `startup_candle_count` which is set in the [strategy](freqai-configuration.md#building-a-freqai-strategy). `startup_candle_count` is timeframe independent and defines the maximum *period* used in `populate_any_indicators()` for indicator creation. FreqAI uses this parameter together with the maximum timeframe in `include_time_frames` to calculate how many data points to download such that the first data point does not include a NaN. <br> **Datatype:** Positive integer.
| `indicator_max_period_candles` | **No longer used (#7325)**. Replaced by `startup_candle_count` which is set in the [strategy](freqai-configuration.md#building-a-freqai-strategy). `startup_candle_count` is timeframe independent and defines the maximum *period* used in `feature_engineering_*()` for indicator creation. FreqAI uses this parameter together with the maximum timeframe in `include_time_frames` to calculate how many data points to download such that the first data point does not include a NaN. <br> **Datatype:** Positive integer.
| `indicator_periods_candles` | Time periods to calculate indicators for. The indicators are added to the base indicator dataset. <br> **Datatype:** List of positive integers.
| `principal_component_analysis` | Automatically reduce the dimensionality of the data set using Principal Component Analysis. See details about how it works [here](#reducing-data-dimensionality-with-principal-component-analysis) <br> **Datatype:** Boolean. <br> Default: `False`.
| `plot_feature_importances` | Create a feature importance plot for each model for the top/bottom `plot_feature_importances` number of features. Plot is stored in `user_data/models/<identifier>/sub-train-<COIN>_<timestamp>.html`. <br> **Datatype:** Integer. <br> Default: `0`.

58
docs/freqai-reinforcement-learning.md
View File

@ -34,55 +34,25 @@ Setting up and running a Reinforcement Learning model is the same as running a R
freqtrade trade --freqaimodel ReinforcementLearner --strategy MyRLStrategy --config config.json
```
where `ReinforcementLearner` will use the templated `ReinforcementLearner` from `freqai/prediction_models/ReinforcementLearner` (or a custom user defined one located in `user_data/freqaimodels`). The strategy, on the other hand, follows the same base [feature engineering](freqai-feature-engineering.md) with `populate_any_indicators` as a typical Regressor:
where `ReinforcementLearner` will use the templated `ReinforcementLearner` from `freqai/prediction_models/ReinforcementLearner` (or a custom user defined one located in `user_data/freqaimodels`). The strategy, on the other hand, follows the same base [feature engineering](freqai-feature-engineering.md) with `feature_engineering_*` as a typical Regressor. The difference lies in the creation of the targets, Reinforcement Learning doesnt require them. However, FreqAI requires a default (neutral) value to be set in the action column:
```python
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
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.
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
More details about feature engineering available:
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
https://www.freqtrade.io/en/latest/freqai-feature-engineering
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)
# The following raw price values are necessary for RL models
informative[f"%-{pair}raw_close"] = informative["close"]
informative[f"%-{pair}raw_open"] = informative["open"]
informative[f"%-{pair}raw_high"] = informative["high"]
informative[f"%-{pair}raw_low"] = informative["low"]
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)
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)
# 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:
# For RL, there are no direct targets to set. This is filler (neutral)
# until the agent sends an action.
df["&-action"] = 0
return df
:param df: strategy dataframe which will receive the targets
usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
"""
# For RL, there are no direct targets to set. This is filler (neutral)
# until the agent sends an action.
df["&-action"] = 0
```
Most of the function remains the same as for typical Regressors, however, the function above shows how the strategy must pass the raw price data to the agent so that it has access to raw OHLCV in the training environment:

4
freqtrade/freqai/RL/BaseReinforcementLearningModel.py
View File

@ -290,8 +290,8 @@ class BaseReinforcementLearningModel(IFreqaiModel):
prices_train = train_df.filter(ohlc_list, axis=1)
if prices_train.empty:
raise OperationalException('Reinforcement learning module didnt find the raw prices '
'assigned in populate_any_indicators. Please assign them '
'with:\n'
'assigned in feature_engineering_standard(). '
'Please assign them with:\n'
'informative[f"%-{pair}raw_close"] = informative["close"]\n'
'informative[f"%-{pair}raw_open"] = informative["open"]\n'
'informative[f"%-{pair}raw_high"] = informative["high"]\n'

8
freqtrade/freqai/data_kitchen.py
View File

@ -1252,12 +1252,12 @@ class FreqaiDataKitchen:
informative_copy = informative_df.copy()
for t in self.freqai_config["feature_parameters"]["indicator_periods_candles"]:
df_features = strategy.freqai_feature_engineering_indicator_periods(
df_features = strategy.feature_engineering_expand_all(
informative_copy.copy(), t)
suffix = f"{t}"
informative_df = self.merge_features(informative_df, df_features, tf, tf, suffix)
generic_df = strategy.freqai_feature_engineering_generic(informative_copy.copy())
generic_df = strategy.feature_engineering_expand_basic(informative_copy.copy())
suffix = "gen"
informative_df = self.merge_features(informative_df, generic_df, tf, tf, suffix)
@ -1332,8 +1332,8 @@ class FreqaiDataKitchen:
dataframe = self.populate_features(dataframe.copy(), corr_pair, strategy,
corr_dataframes, base_dataframes, True)
dataframe = strategy.freqai_feature_engineering_generalized_indicators(dataframe.copy())
dataframe = strategy.freqai_set_targets(dataframe.copy())
dataframe = strategy.feature_engineering_standard(dataframe.copy())
dataframe = strategy.set_freqai_targets(dataframe.copy())
self.get_unique_classes_from_labels(dataframe)

79
freqtrade/strategy/interface.py
View File

@ -611,40 +611,93 @@ class IStrategy(ABC, HyperStrategyMixin):
"""
return df
def freqai_feature_engineering_indicator_periods(self, dataframe: DataFrame,
period: int, **kwargs):
def feature_engineering_expand_all(self, dataframe: DataFrame,
period: int, **kwargs):
"""
This function will be called for all include_timeframes in each indicator_periods_candles
(including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
*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.
More details on how these config defined parameters accelerate feature engineering
in the documentation at:
https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
: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)
"""
return dataframe
def freqai_feature_engineering_generic(self, dataframe: DataFrame, **kwargs):
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
"""
This optional function will be called for all include_timeframes (including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
*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.
Features defined here will *not* be automatically duplicated on user defined
`indicator_periods_candles`
All features must be prepended with `%` to be recognized by FreqAI internals.
More details on how these config defined parameters accelerate feature engineering
in the documentation at:
https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
:param df: strategy dataframe which will receive the features
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-ema-200"] = ta.EMA(dataframe, timeperiod=200)
"""
return dataframe
def freqai_feature_engineering_generalized_indicators(self, dataframe: DataFrame, **kwargs):
def feature_engineering_standard(self, dataframe: DataFrame, **kwargs):
"""
This optional function will be called once with the dataframe of the main timeframe.
*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.
More details about feature engineering available:
https://www.freqtrade.io/en/latest/freqai-feature-engineering
:param df: strategy dataframe which will receive the features
usage example: dataframe["%-day_of_week"] = (dataframe["date"].dt.dayofweek + 1) / 7
"""
return dataframe
def freqai_set_targets(self, dataframe, **kwargs):
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.
More details about feature engineering available:
https://www.freqtrade.io/en/latest/freqai-feature-engineering
:param df: strategy dataframe which will receive the targets
usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
"""

228
freqtrade/templates/FreqaiExampleStrategy.py
View File

@ -1,12 +1,11 @@
import logging
from functools import reduce
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from technical import qtpylib
from freqtrade.strategy import CategoricalParameter, IStrategy, merge_informative_pair
from freqtrade.strategy import CategoricalParameter, IStrategy
logger = logging.getLogger(__name__)
@ -18,8 +17,8 @@ class FreqaiExampleStrategy(IStrategy):
IFreqaiModel to the strategy. Namely, the user uses:
self.freqai.start(dataframe, metadata)
to make predictions on their data. populate_any_indicators() automatically
generates the variety of features indicated by the user in the
to make predictions on their data. feature_engineering_*() automatically
generate the variety of features indicated by the user in the
canonical freqtrade configuration file under config['freqai'].
"""
@ -47,16 +46,30 @@ class FreqaiExampleStrategy(IStrategy):
std_dev_multiplier_sell = CategoricalParameter(
[0.75, 1, 1.25, 1.5, 1.75], space="sell", default=1.25, optimize=True)
def freqai_feature_engineering_indicator_periods(self, dataframe, period, **kwargs):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
"""
This function will be called for all include_timeframes in each indicator_periods_candles
(including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
*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.
More details on how these config defined parameters accelerate feature engineering
in the documentation at:
https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
: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)
"""
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
@ -86,32 +99,72 @@ class FreqaiExampleStrategy(IStrategy):
return dataframe
def freqai_feature_engineering_generic(self, dataframe, **kwargs):
def feature_engineering_expand_basic(self, dataframe, **kwargs):
"""
This optional function will be called for all include_timeframes (including corr_pairs).
After that, the features will be shifted by the number of candles in the
include_shifted_candles.
*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.
Features defined here will *not* be automatically duplicated on user defined
`indicator_periods_candles`
All features must be prepended with `%` to be recognized by FreqAI internals.
More details on how these config defined parameters accelerate feature engineering
in the documentation at:
https://www.freqtrade.io/en/latest/freqai-parameter-table/#feature-parameters
https://www.freqtrade.io/en/latest/freqai-feature-engineering/#defining-the-features
: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 freqai_feature_engineering_generalized_indicators(self, dataframe, **kwargs):
def feature_engineering_standard(self, dataframe, **kwargs):
"""
This optional function will be called once with the dataframe of the main timeframe.
*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.
More details about feature engineering available:
https://www.freqtrade.io/en/latest/freqai-feature-engineering
: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
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
return dataframe
def freqai_set_targets(self, dataframe, **kwargs):
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.
More details about feature engineering available:
https://www.freqtrade.io/en/latest/freqai-feature-engineering
:param df: strategy dataframe which will receive the targets
usage example: dataframe["&-target"] = dataframe["close"].shift(-1) / dataframe["close"]
"""
@ -123,128 +176,41 @@ class FreqaiExampleStrategy(IStrategy):
/ dataframe["close"]
- 1
)
# Classifiers are typically set up with strings as targets:
# df['&s-up_or_down'] = np.where( df["close"].shift(-100) >
# df["close"], 'up', 'down')
# If user wishes to use multiple targets, they can add more by
# appending more columns with '&'. User should keep in mind that multi targets
# requires a multioutput prediction model such as
# templates/CatboostPredictionMultiModel.py,
# df["&-s_range"] = (
# df["close"]
# .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
# .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
# .max()
# -
# df["close"]
# .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
# .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
# .min()
# )
return dataframe
def populate_any_indicators_old(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
"""
DEPRECATED - USE FEATURE ENGINEERING FUNCTIONS INSTEAD
Function designed to automatically generate, name and merge features
from user indicated timeframes in the configuration file. User can add
additional features here, but must follow the naming convention.
This method is *only* used in FreqaiDataKitchen class and therefore
it is only called if FreqAI is active.
: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
"""
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
# 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, timeperiod=t)
informative[f"%-{pair}sma-period_{t}"] = ta.SMA(informative, timeperiod=t)
informative[f"%-{pair}ema-period_{t}"] = ta.EMA(informative, timeperiod=t)
bollinger = qtpylib.bollinger_bands(
qtpylib.typical_price(informative), window=t, stds=2.2
)
informative[f"{pair}bb_lowerband-period_{t}"] = bollinger["lower"]
informative[f"{pair}bb_middleband-period_{t}"] = bollinger["mid"]
informative[f"{pair}bb_upperband-period_{t}"] = bollinger["upper"]
informative[f"%-{pair}bb_width-period_{t}"] = (
informative[f"{pair}bb_upperband-period_{t}"]
- informative[f"{pair}bb_lowerband-period_{t}"]
) / informative[f"{pair}bb_middleband-period_{t}"]
informative[f"%-{pair}close-bb_lower-period_{t}"] = (
informative["close"] / informative[f"{pair}bb_lowerband-period_{t}"]
)
informative[f"%-{pair}roc-period_{t}"] = ta.ROC(informative, timeperiod=t)
informative[f"%-{pair}relative_volume-period_{t}"] = (
informative["volume"] / informative["volume"].rolling(t).mean()
)
informative[f"%-{pair}pct-change"] = informative["close"].pct_change()
informative[f"%-{pair}raw_volume"] = informative["volume"]
informative[f"%-{pair}raw_price"] = informative["close"]
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)
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)
# 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:
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)
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
)
# Classifiers are typically set up with strings as targets:
# df['&s-up_or_down'] = np.where( df["close"].shift(-100) >
# df["close"], 'up', 'down')
# If user wishes to use multiple targets, they can add more by
# appending more columns with '&'. User should keep in mind that multi targets
# requires a multioutput prediction model such as
# templates/CatboostPredictionMultiModel.py,
# df["&-s_range"] = (
# df["close"]
# .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
# .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
# .max()
# -
# df["close"]
# .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
# .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
# .min()
# )
return df
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
# All indicators must be populated by populate_any_indicators() for live functionality
# to work correctly.
# All indicators must be populated by feature_engineering_*() functions
# the model will return all labels created by user in `populate_any_indicators`
# the model will return all labels created by user in `feature_engineering_*`
# (& 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.
# `set_freqai_targets()` for each training period.
dataframe = self.freqai.start(dataframe, metadata, self)
for val in self.std_dev_multiplier_buy.range:
dataframe[f'target_roi_{val}'] = (
dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * val

2
tests/freqai/test_freqai_datakitchen.py
View File

@ -82,7 +82,7 @@ def test_compute_distances(mocker, freqai_conf):
freqai = make_data_dictionary(mocker, freqai_conf)
freqai_conf['freqai']['feature_parameters'].update({"DI_threshold": 1})
avg_mean_dist = freqai.dk.compute_distances()
assert round(avg_mean_dist, 2) == 1.99
assert round(avg_mean_dist, 2) == 1.98
def test_use_SVM_to_remove_outliers_and_outlier_protection(mocker, freqai_conf, caplog):

60
tests/strategy/strats/freqai_rl_test_strat.py
View File

@ -1,11 +1,10 @@
import logging
from functools import reduce
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from freqtrade.strategy import IStrategy, merge_informative_pair
from freqtrade.strategy import IStrategy
logger = logging.getLogger(__name__)
@ -25,49 +24,36 @@ class freqai_rl_test_strat(IStrategy):
startup_candle_count: int = 30
can_short = False
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
return dataframe
t = int(t)
informative[f"%-{pair}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
# The following columns are necessary for RL models.
informative[f"%-{pair}raw_close"] = informative["close"]
informative[f"%-{pair}raw_open"] = informative["open"]
informative[f"%-{pair}raw_high"] = informative["high"]
informative[f"%-{pair}raw_low"] = informative["low"]
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
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)
dataframe["%-raw_close"] = dataframe["close"]
dataframe["%-raw_open"] = dataframe["open"]
dataframe["%-raw_high"] = dataframe["high"]
dataframe["%-raw_low"] = dataframe["low"]
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)
return dataframe
# 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:
# For RL, there are no direct targets to set. This is filler (neutral)
# until the agent sends an action.
df["&-action"] = 0
def feature_engineering_standard(self, dataframe, **kwargs):
return df
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
return dataframe
def set_freqai_targets(self, dataframe, **kwargs):
dataframe["&-action"] = 0
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

61
tests/strategy/strats/freqai_test_classifier.py
View File

@ -2,11 +2,10 @@ import logging
from functools import reduce
import numpy as np
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy, merge_informative_pair
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy
logger = logging.getLogger(__name__)
@ -57,55 +56,35 @@ class freqai_test_classifier(IStrategy):
informative_pairs.append((pair, tf))
return informative_pairs
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
coin = pair.split('/')[0]
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
return dataframe
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
informative[f"%-{coin}pct-change"] = informative["close"].pct_change()
informative[f"%-{coin}raw_volume"] = informative["volume"]
informative[f"%-{coin}raw_price"] = informative["close"]
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_standard(self, dataframe, **kwargs):
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)
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
# 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:
df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
return dataframe
# 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-up_or_down'] = np.where(df["close"].shift(-100) > df["close"], 'up', 'down')
def set_freqai_targets(self, dataframe, **kwargs):
return df
dataframe['&s-up_or_down'] = np.where(dataframe["close"].shift(-100) >
dataframe["close"], 'up', 'down')
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

66
tests/strategy/strats/freqai_test_multimodel_classifier_strat.py
View File

@ -2,11 +2,10 @@ import logging
from functools import reduce
import numpy as np
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy, merge_informative_pair
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy
logger = logging.getLogger(__name__)
@ -44,59 +43,38 @@ class freqai_test_multimodel_classifier_strat(IStrategy):
)
max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=False, load=True)
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
coin = pair.split('/')[0]
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
return dataframe
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
informative[f"%-{coin}pct-change"] = informative["close"].pct_change()
informative[f"%-{coin}raw_volume"] = informative["volume"]
informative[f"%-{coin}raw_price"] = informative["close"]
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_standard(self, dataframe, **kwargs):
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)
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
# 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:
df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
return dataframe
# 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-up_or_down'] = np.where(df["close"].shift(-50) >
df["close"], 'up', 'down')
def set_freqai_targets(self, dataframe, **kwargs):
df['&s-up_or_down2'] = np.where(df["close"].shift(-50) >
df["close"], 'up2', 'down2')
dataframe['&s-up_or_down'] = np.where(dataframe["close"].shift(-50) >
dataframe["close"], 'up', 'down')
return df
dataframe['&s-up_or_down2'] = np.where(dataframe["close"].shift(-50) >
dataframe["close"], 'up2', 'down2')
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

94
tests/strategy/strats/freqai_test_multimodel_strat.py
View File

@ -1,11 +1,10 @@
import logging
from functools import reduce
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy, merge_informative_pair
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy
logger = logging.getLogger(__name__)
@ -43,74 +42,53 @@ class freqai_test_multimodel_strat(IStrategy):
)
max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=False, load=True)
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
coin = pair.split('/')[0]
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
return dataframe
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
informative[f"%-{coin}pct-change"] = informative["close"].pct_change()
informative[f"%-{coin}raw_volume"] = informative["volume"]
informative[f"%-{coin}raw_price"] = informative["close"]
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_standard(self, dataframe, **kwargs):
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)
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
# 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:
df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
return dataframe
# 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
def set_freqai_targets(self, dataframe, **kwargs):
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
)
df["&-s_range"] = (
df["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.max()
-
df["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.min()
)
dataframe["&-s_range"] = (
dataframe["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.max()
-
dataframe["close"]
.shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
.rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
.min()
)
return df
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:

72
tests/strategy/strats/freqai_test_strat.py
View File

@ -1,11 +1,10 @@
import logging
from functools import reduce
import pandas as pd
import talib.abstract as ta
from pandas import DataFrame
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy, merge_informative_pair
from freqtrade.strategy import DecimalParameter, IntParameter, IStrategy
logger = logging.getLogger(__name__)
@ -43,62 +42,41 @@ class freqai_test_strat(IStrategy):
)
max_roi_time_long = IntParameter(0, 800, default=400, space="sell", optimize=False, load=True)
def populate_any_indicators(
self, pair, df, tf, informative=None, set_generalized_indicators=False
):
def feature_engineering_expand_all(self, dataframe, period, **kwargs):
coin = pair.split('/')[0]
dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
dataframe["%-mfi-period"] = ta.MFI(dataframe, timeperiod=period)
dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf)
return dataframe
# first loop is automatically duplicating indicators for time periods
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
def feature_engineering_expand_basic(self, dataframe: DataFrame, **kwargs):
t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
dataframe["%-pct-change"] = dataframe["close"].pct_change()
dataframe["%-raw_volume"] = dataframe["volume"]
dataframe["%-raw_price"] = dataframe["close"]
informative[f"%-{coin}pct-change"] = informative["close"].pct_change()
informative[f"%-{coin}raw_volume"] = informative["volume"]
informative[f"%-{coin}raw_price"] = informative["close"]
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_standard(self, dataframe, **kwargs):
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)
dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
# 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:
df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
return dataframe
# 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
def set_freqai_targets(self, dataframe, **kwargs):
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
return dataframe
def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame: