CTYPTO/freqtrade
1
0
Fork 0
mirror of https://github.com/freqtrade/freqtrade.git synced 2026-01-19 21:40:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into maint/python_3.14

Browse Source
This commit is contained in:
Matthias
2025-12-23 06:37:51 +01:00
parent 025707d9ad 9baa6eebbe
commit c21ce5ef94
36 changed files with 1887 additions and 2159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.github/dependabot.yml vendored
View File

@@ -56,3 +56,8 @@ updates:
interval: "weekly"
open-pull-requests-limit: 10
target-branch: develop
groups:
actions:
patterns:
# Combine updates for github provided actions
- "actions/*"

2
.github/workflows/binance-lev-tier-update.yml vendored
View File

@@ -34,7 +34,7 @@ jobs:
run: python build_helpers/binance_update_lev_tiers.py
- uses: peter-evans/create-pull-request@84ae59a2cdc2258d6fa0732dd66352dddae2a412 # v7.0.9
- uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
token: ${{ secrets.REPO_SCOPED_TOKEN }}
add-paths: freqtrade/exchange/binance_leverage_tiers.json

14
.github/workflows/ci.yml vendored
View File

@@ -38,7 +38,7 @@ jobs:
python-version: ${{ matrix.python-version }}
- name: Install uv
uses: astral-sh/setup-uv@1e862dfacbd1d6d858c55d9b792c756523627244 # v7.1.4
uses: astral-sh/setup-uv@681c641aba71e4a1c380be3ab5e12ad51f415867 # v7.1.6
with:
activate-environment: true
enable-cache: true
@@ -74,7 +74,7 @@ jobs:
run: |
pytest --random-order --cov=freqtrade --cov=freqtrade_client --cov-config=.coveragerc
- uses: codecov/codecov-action@5a1091511ad55cbe89839c7260b706298ca349f7 # v5.5.1
- uses: codecov/codecov-action@671740ac38dd9b0130fbe1cec585b89eea48d3de # v5.5.2
if: (runner.os == 'Linux' && matrix.python-version == '3.12' && matrix.os == 'ubuntu-24.04')
with:
fail_ci_if_error: true
@@ -250,7 +250,7 @@ jobs:
python-version: "3.12"
- name: Install uv
uses: astral-sh/setup-uv@1e862dfacbd1d6d858c55d9b792c756523627244 # v7.1.4
uses: astral-sh/setup-uv@681c641aba71e4a1c380be3ab5e12ad51f415867 # v7.1.6
with:
activate-environment: true
enable-cache: true
@@ -335,7 +335,7 @@ jobs:
python -m build --sdist --wheel
- name: Upload artifacts 📦
uses: actions/upload-artifact@v5
uses: actions/upload-artifact@v6
with:
name: freqtrade-build
path: |
@@ -348,7 +348,7 @@ jobs:
python -m build --sdist --wheel ft_client
- name: Upload artifacts 📦
uses: actions/upload-artifact@v5
uses: actions/upload-artifact@v6
with:
name: freqtrade-client-build
path: |
@@ -372,7 +372,7 @@ jobs:
persist-credentials: false
- name: Download artifact 📦
uses: actions/download-artifact@v6
uses: actions/download-artifact@v7
with:
pattern: freqtrade*-build
path: dist
@@ -401,7 +401,7 @@ jobs:
persist-credentials: false
- name: Download artifact 📦
uses: actions/download-artifact@v6
uses: actions/download-artifact@v7
with:
pattern: freqtrade*-build
path: dist

14
.github/workflows/docker-build.yml vendored
View File

@@ -37,6 +37,17 @@ jobs:
with:
persist-credentials: false
- name: Visualize disk usage before build
run: df -h
- name: Cleanup some disk space
run: |
docker system prune -a --force || true
docker builder prune -af || true
- name: Visualize disk usage after cleanup
run: df -h
- name: Set docker tag names
id: tags
uses: ./.github/actions/docker-tags
@@ -142,6 +153,9 @@ jobs:
run: |
docker images
- name: Visualize disk usage after build
run: df -h
deploy-arm:
name: "Deploy Docker ARM64"
permissions:

2
.github/workflows/pre-commit-update.yml vendored
View File

@@ -28,7 +28,7 @@ jobs:
- name: Run auto-update
run: pre-commit autoupdate
- uses: peter-evans/create-pull-request@84ae59a2cdc2258d6fa0732dd66352dddae2a412 # v7.0.9
- uses: peter-evans/create-pull-request@98357b18bf14b5342f975ff684046ec3b2a07725 # v8.0.0
with:
token: ${{ secrets.REPO_SCOPED_TOKEN }}
add-paths: .pre-commit-config.yaml

8
.pre-commit-config.yaml
View File

@@ -31,8 +31,8 @@ repos:
- types-requests==2.32.4.20250913
- types-tabulate==0.9.0.20241207
- types-python-dateutil==2.9.0.20251115
- scipy-stubs==1.16.3.2
- SQLAlchemy==2.0.44
- scipy-stubs==1.16.3.3
- SQLAlchemy==2.0.45
# stages: [push]
- repo: https://github.com/pycqa/isort
@@ -44,7 +44,7 @@ repos:
- repo: https://github.com/charliermarsh/ruff-pre-commit
# Ruff version.
rev: 'v0.14.9'
rev: 'v0.14.10'
hooks:
- id: ruff
- id: ruff-format
@@ -83,6 +83,6 @@ repos:
# Ensure github actions remain safe
- repo: https://github.com/woodruffw/zizmor-pre-commit
rev: v1.18.0
rev: v1.19.0
hooks:
- id: zizmor

10
docs/deprecated.md
View File

@@ -135,3 +135,13 @@ you can verify this with `freqtrade list-data --exchange <yourexchange> --show`.
Additional arguments to the above commands may be necessary, like configuration files or explicit user_data if they deviate from the default.
**Hyperliquid** is a special case now - which will no longer require 1h mark data - but will use regular candles instead (this data never existed and is identical to 1h futures candles). As we don't support download-data for hyperliquid (they don't provide historic data) - there won't be actions necessary for hyperliquid users.
## Catboost models in freqAI
CatBoost models have been removed with version 2025.12 and are no longer actively supported.
If you have existing bots using CatBoost models, you can still use them in your custom models by copy/pasting them from the git history (as linked below) and installing the Catboost library manually.
We do however recommend switching to other supported model libraries like LightGBM or XGBoost for better support and future compatibility.
* [CatboostRegressor](https://github.com/freqtrade/freqtrade/blob/c6f3b0081927e161a16b116cc47fb663f7831d30/freqtrade/freqai/prediction_models/CatboostRegressor.py)
* [CatboostClassifier](https://github.com/freqtrade/freqtrade/blob/c6f3b0081927e161a16b116cc47fb663f7831d30/freqtrade/freqai/prediction_models/CatboostClassifier.py)
* [CatboostClassifierMultiTarget](https://github.com/freqtrade/freqtrade/blob/c6f3b0081927e161a16b116cc47fb663f7831d30/freqtrade/freqai/prediction_models/CatboostClassifierMultiTarget.py)

12
docs/freqai-configuration.md
View File

@@ -200,15 +200,15 @@ If this value is set, FreqAI will initially use the predictions from the trainin
## Using different prediction models
FreqAI has multiple example prediction model libraries that are ready to be used as is via the flag `--freqaimodel`. These libraries include `CatBoost`, `LightGBM`, and `XGBoost` regression, classification, and multi-target models, and can be found in `freqai/prediction_models/`.
FreqAI has multiple example prediction model libraries that are ready to be used as is via the flag `--freqaimodel`. These libraries include `LightGBM`, and `XGBoost` regression, classification, and multi-target models, and can be found in `freqai/prediction_models/`.
Regression and classification models differ in what targets they predict - a regression model will predict a target of continuous values, for example what price BTC will be at tomorrow, whilst a classifier will predict a target of discrete values, for example if the price of BTC will go up tomorrow or not. This means that you have to specify your targets differently depending on which model type you are using (see details [below](#setting-model-targets)).
All of the aforementioned model libraries implement gradient boosted decision tree algorithms. They all work on the principle of ensemble learning, where predictions from multiple simple learners are combined to get a final prediction that is more stable and generalized. The simple learners in this case are decision trees. Gradient boosting refers to the method of learning, where each simple learner is built in sequence - the subsequent learner is used to improve on the error from the previous learner. If you want to learn more about the different model libraries you can find the information in their respective docs:
* CatBoost: https://catboost.ai/en/docs/
* LightGBM: https://lightgbm.readthedocs.io/en/v3.3.2/#
* XGBoost: https://xgboost.readthedocs.io/en/stable/#
* LightGBM: <https://lightgbm.readthedocs.io/en/v3.3.2/#>
* XGBoost: <https://xgboost.readthedocs.io/en/stable/#>
* CatBoost: <https://catboost.ai/en/docs/> (No longer actively supported since 2025.12)
There are also numerous online articles describing and comparing the algorithms. Some relatively lightweight examples would be [CatBoost vs. LightGBM vs. XGBoost — Which is the best algorithm?](https://towardsdatascience.com/catboost-vs-lightgbm-vs-xgboost-c80f40662924#:~:text=In%20CatBoost%2C%20symmetric%20trees%2C%20or,the%20same%20depth%20can%20differ.) and [XGBoost, LightGBM or CatBoost — which boosting algorithm should I use?](https://medium.com/riskified-technology/xgboost-lightgbm-or-catboost-which-boosting-algorithm-should-i-use-e7fda7bb36bc). Keep in mind that the performance of each model is highly dependent on the application and so any reported metrics might not be true for your particular use of the model.
@@ -219,7 +219,7 @@ Make sure to use unique names to avoid overriding built-in models.
#### Regressors
If you are using a regressor, you need to specify a target that has continuous values. FreqAI includes a variety of regressors, such as the `CatboostRegressor`via the flag `--freqaimodel CatboostRegressor`. An example of how you could set a regression target for predicting the price 100 candles into the future would be
If you are using a regressor, you need to specify a target that has continuous values. FreqAI includes a variety of regressors, such as the `LightGBMRegressor`via the flag `--freqaimodel LightGBMRegressor`. An example of how you could set a regression target for predicting the price 100 candles into the future would be
```python
df['&s-close_price'] = df['close'].shift(-100)
@@ -229,7 +229,7 @@ If you want to predict multiple targets, you need to define multiple labels usin
#### Classifiers
If you are using a classifier, you need to specify a target that has discrete values. FreqAI includes a variety of classifiers, such as the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example, if you want to predict if the price 100 candles into the future goes up or down you would set
If you are using a classifier, you need to specify a target that has discrete values. FreqAI includes a variety of classifiers, such as the `LightGBMClassifier` via the flag `--freqaimodel LightGBMClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example, if you want to predict if the price 100 candles into the future goes up or down you would set
```python
df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down')

2
docs/freqai-parameter-table.md
View File

@@ -107,7 +107,6 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `n_steps` | An alternative way of setting `n_epochs` - the number of training iterations to run. Iteration here refer to the number of times we call `optimizer.step()`. Ignored if `n_epochs` is set. A simplified version of the function: <br><br> n_epochs = n_steps / (n_obs / batch_size) <br><br> The motivation here is that `n_steps` is easier to optimize and keep stable across different n_obs - the number of data points. <br> <br> **Datatype:** int. optional. <br> Default: `None`.
| `batch_size` | The size of the batches to use during training. <br><br> **Datatype:** int. <br> Default: `64`.
### Additional parameters
| Parameter | Description |
@@ -116,3 +115,4 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `freqai.keras` | If the selected model makes use of Keras (typical for TensorFlow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. <br> Default: `False`.
| `freqai.conv_width` | The width of a neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: `2`.
| `freqai.reduce_df_footprint` | Recast all numeric columns to float32/int32, with the objective of reducing ram/disk usage and decreasing train/inference timing. This parameter is set in the main level of the Freqtrade configuration file (not inside FreqAI). <br> **Datatype:** Boolean. <br> Default: `False`.
| `freqai.override_exchange_check` | Override the exchange check to force FreqAI to use exchanges that may not have enough historic data. Turn this to True if you know your FreqAI model and strategy do not require historical data. <br> **Datatype:** Boolean. <br> Default: `False`.

2
docs/requirements-docs.txt
View File

@@ -2,6 +2,6 @@ markdown==3.10
mkdocs==1.6.1
mkdocs-material==9.7.0
mdx_truly_sane_lists==1.3
pymdown-extensions==10.18
pymdown-extensions==10.19.1
jinja2==3.1.6
mike==2.1.3

18
freqtrade/exchange/binance.py
View File

@@ -17,7 +17,7 @@ from freqtrade.exchange.binance_public_data import (
download_archive_trades,
)
from freqtrade.exchange.common import retrier
from freqtrade.exchange.exchange_types import CcxtOrder, FtHas, Tickers
from freqtrade.exchange.exchange_types import FtHas, Tickers
from freqtrade.exchange.exchange_utils_timeframe import timeframe_to_msecs
from freqtrade.misc import deep_merge_dicts, json_load
from freqtrade.util import FtTTLCache
@@ -51,6 +51,8 @@ class Binance(Exchange):
"funding_fee_candle_limit": 1000,
"stoploss_order_types": {"limit": "stop", "market": "stop_market"},
"stoploss_blocks_assets": False, # Stoploss orders do not block assets
"stoploss_query_requires_stop_flag": True,
"stoploss_algo_order_info_id": "actualOrderId",
"tickers_have_price": False,
"floor_leverage": True,
"fetch_orders_limit_minutes": 7 * 1440, # "fetch_orders" is limited to 7 days
@@ -145,20 +147,6 @@ class Binance(Exchange):
except ccxt.BaseError as e:
raise OperationalException(e) from e
def fetch_stoploss_order(
self, order_id: str, pair: str, params: dict | None = None
) -> CcxtOrder:
if self.trading_mode == TradingMode.FUTURES:
params = params or {}
params.update({"stop": True})
return self.fetch_order(order_id, pair, params)
def cancel_stoploss_order(self, order_id: str, pair: str, params: dict | None = None) -> dict:
if self.trading_mode == TradingMode.FUTURES:
params = params or {}
params.update({"stop": True})
return self.cancel_order(order_id=order_id, pair=pair, params=params)
def get_historic_ohlcv(
self,
pair: str,

3520
freqtrade/exchange/binance_leverage_tiers.json
View File

File diff suppressed because it is too large Load Diff

4
freqtrade/exchange/bitget.py
View File

@@ -31,6 +31,7 @@ class Bitget(Exchange):
"stop_price_prop": "stopPrice",
"stoploss_blocks_assets": False, # Stoploss orders do not block assets
"stoploss_order_types": {"limit": "limit", "market": "market"},
"stoploss_query_requires_stop_flag": True,
"ohlcv_candle_limit": 200, # 200 for historical candles, 1000 for recent ones.
"order_time_in_force": ["GTC", "FOK", "IOC", "PO"],
}
@@ -128,9 +129,6 @@ class Bitget(Exchange):
return self._fetch_stop_order_fallback(order_id, pair)
def cancel_stoploss_order(self, order_id: str, pair: str, params: dict | None = None) -> dict:
return self.cancel_order(order_id=order_id, pair=pair, params={"stop": True})
@retrier
def additional_exchange_init(self) -> None:
"""

23
freqtrade/exchange/exchange.py
View File

@@ -132,6 +132,7 @@ class Exchange:
"stop_price_prop": "stopLossPrice", # Used for stoploss_on_exchange response parsing
"stoploss_order_types": {},
"stoploss_blocks_assets": True, # By default stoploss orders block assets
"stoploss_query_requires_stop_flag": False, # Require "stop": True" to fetch stop orders
"order_time_in_force": ["GTC"],
"ohlcv_params": {},
"ohlcv_has_history": True, # Some exchanges (Kraken) don't provide history via ohlcv
@@ -1687,7 +1688,24 @@ class Exchange:
def fetch_stoploss_order(
self, order_id: str, pair: str, params: dict | None = None
) -> CcxtOrder:
return self.fetch_order(order_id, pair, params)
if self.get_option("stoploss_query_requires_stop_flag"):
params = params or {}
params["stop"] = True
order = self.fetch_order(order_id, pair, params)
val = self.get_option("stoploss_algo_order_info_id")
if val and order.get("status", "open") == "closed":
if new_orderid := order.get("info", {}).get(val):
# Fetch real order, which was placed by the algo order.
actual_order = self.fetch_order(order_id=new_orderid, pair=pair, params=None)
actual_order["id_stop"] = actual_order["id"]
actual_order["id"] = order_id
actual_order["type"] = "stoploss"
actual_order["stopPrice"] = order.get("stopPrice")
actual_order["status_stop"] = "triggered"
return actual_order
return order
def fetch_order_or_stoploss_order(
self, order_id: str, pair: str, stoploss_order: bool = False
@@ -1741,6 +1759,9 @@ class Exchange:
raise OperationalException(e) from e
def cancel_stoploss_order(self, order_id: str, pair: str, params: dict | None = None) -> dict:
if self.get_option("stoploss_query_requires_stop_flag"):
params = params or {}
params["stop"] = True
return self.cancel_order(order_id, pair, params)
def is_cancel_order_result_suitable(self, corder) -> TypeGuard[CcxtOrder]:

2
freqtrade/exchange/exchange_types.py
View File

@@ -19,6 +19,8 @@ class FtHas(TypedDict, total=False):
stop_price_type_value_mapping: dict
stoploss_order_types: dict[str, str]
stoploss_blocks_assets: bool
stoploss_query_requires_stop_flag: bool
stoploss_algo_order_info_id: str
# ohlcv
ohlcv_params: dict
ohlcv_candle_limit: int

25
freqtrade/exchange/gate.py
View File

@@ -30,6 +30,8 @@ class Gate(Exchange):
"stoploss_order_types": {"limit": "limit"},
"stop_price_param": "stopPrice",
"stop_price_prop": "stopPrice",
"stoploss_query_requires_stop_flag": True,
"stoploss_algo_order_info_id": "fired_order_id",
"l2_limit_upper": 1000,
"marketOrderRequiresPrice": True,
"trades_has_history": False, # Endpoint would support this - but ccxt doesn't.
@@ -42,6 +44,7 @@ class Gate(Exchange):
"stop_price_type_field": "price_type",
"l2_limit_upper": 300,
"stoploss_blocks_assets": False,
"stoploss_algo_order_info_id": "trade_id",
"stop_price_type_value_mapping": {
PriceType.LAST: 0,
PriceType.MARK: 1,
@@ -132,25 +135,3 @@ class Gate(Exchange):
def get_order_id_conditional(self, order: CcxtOrder) -> str:
return safe_value_fallback2(order, order, "id_stop", "id")
def fetch_stoploss_order(
self, order_id: str, pair: str, params: dict | None = None
) -> CcxtOrder:
order = self.fetch_order(order_id=order_id, pair=pair, params={"stop": True})
if order.get("status", "open") == "closed":
# Places a real order - which we need to fetch explicitly.
val = "trade_id" if self.trading_mode == TradingMode.FUTURES else "fired_order_id"
if new_orderid := order.get("info", {}).get(val):
order1 = self.fetch_order(order_id=new_orderid, pair=pair, params=params)
order1["id_stop"] = order1["id"]
order1["id"] = order_id
order1["type"] = "stoploss"
order1["stopPrice"] = order.get("stopPrice")
order1["status_stop"] = "triggered"
return order1
return order
def cancel_stoploss_order(self, order_id: str, pair: str, params: dict | None = None) -> dict:
return self.cancel_order(order_id=order_id, pair=pair, params={"stop": True})

4
freqtrade/exchange/okx.py
View File

@@ -31,6 +31,7 @@ class Okx(Exchange):
"ohlcv_candle_limit": 100, # Warning, special case with data prior to X months
"stoploss_order_types": {"limit": "limit"},
"stoploss_on_exchange": True,
"stoploss_query_requires_stop_flag": True,
"trades_has_history": False, # Endpoint doesn't have a "since" parameter
"ws_enabled": True,
}
@@ -263,9 +264,6 @@ class Okx(Exchange):
return safe_value_fallback2(order, order, "id_stop", "id")
return order["id"]
def cancel_stoploss_order(self, order_id: str, pair: str, params: dict | None = None) -> dict:
return self.cancel_order(order_id=order_id, pair=pair, params={"stop": True})
def _fetch_orders_emulate(self, pair: str, since_ms: int) -> list[CcxtOrder]:
orders = []

2
freqtrade/freqai/base_models/BaseClassifierModel.py
View File

@@ -18,7 +18,7 @@ class BaseClassifierModel(IFreqaiModel):
"""
Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
User *must* inherit from this class and set fit(). See example scripts
such as prediction_models/CatboostClassifier.py for guidance.
such as prediction_models/XGBoostClassifier.py for guidance.
"""
def train(self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs) -> Any:

2
freqtrade/freqai/base_models/BaseRegressionModel.py
View File

@@ -18,7 +18,7 @@ class BaseRegressionModel(IFreqaiModel):
"""
Base class for regression type models (e.g. Catboost, LightGBM, XGboost etc.).
User *must* inherit from this class and set fit(). See example scripts
such as prediction_models/CatboostRegressor.py for guidance.
such as prediction_models/XGBoostRegressor.py for guidance.
"""
def train(self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs) -> Any:

4
freqtrade/freqai/freqai_interface.py
View File

@@ -948,7 +948,7 @@ class IFreqaiModel(ABC):
return dk
# Following methods which are overridden by user made prediction models.
# See freqai/prediction_models/CatboostPredictionModel.py for an example.
# See freqai/prediction_models/XGBoostRegressor.py for an example.
@abstractmethod
def train(self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs) -> Any:
@@ -964,7 +964,7 @@ class IFreqaiModel(ABC):
def fit(self, data_dictionary: dict[str, Any], dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
Most regressors use the same function names and arguments e.g. user
can drop in LGBMRegressor in place of CatBoostRegressor and all data
can drop in LGBMRegressor in place of XGBoostRegressor and all data
management will be properly handled by Freqai.
:param data_dictionary: Dict = the dictionary constructed by DataHandler to hold
all the training and test data/labels.

61
freqtrade/freqai/prediction_models/CatboostClassifier.py
View File

@@ -1,61 +0,0 @@
import logging
from pathlib import Path
from typing import Any
from catboost import CatBoostClassifier, Pool
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
class CatboostClassifier(BaseClassifierModel):
"""
User created prediction model. The class inherits IFreqaiModel, which
means it has full access to all Frequency AI functionality. Typically,
users would use this to override the common `fit()`, `train()`, or
`predict()` methods to add their custom data handling tools or change
various aspects of the training that cannot be configured via the
top level config.json file.
"""
def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary holding all data for train, test,
labels, weights
:param dk: The datakitchen object for the current coin/model
"""
train_data = Pool(
data=data_dictionary["train_features"],
label=data_dictionary["train_labels"],
weight=data_dictionary["train_weights"],
)
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0:
test_data = None
else:
test_data = Pool(
data=data_dictionary["test_features"],
label=data_dictionary["test_labels"],
weight=data_dictionary["test_weights"],
)
cbr = CatBoostClassifier(
allow_writing_files=True,
loss_function="MultiClass",
train_dir=Path(dk.data_path),
**self.model_training_parameters,
)
init_model = self.get_init_model(dk.pair)
cbr.fit(
X=train_data,
eval_set=test_data,
init_model=init_model,
)
return cbr

79
freqtrade/freqai/prediction_models/CatboostClassifierMultiTarget.py
View File

@@ -1,79 +0,0 @@
import logging
from pathlib import Path
from typing import Any
from catboost import CatBoostClassifier, Pool
from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
from freqtrade.freqai.base_models.FreqaiMultiOutputClassifier import FreqaiMultiOutputClassifier
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
class CatboostClassifierMultiTarget(BaseClassifierModel):
"""
User created prediction model. The class inherits IFreqaiModel, which
means it has full access to all Frequency AI functionality. Typically,
users would use this to override the common `fit()`, `train()`, or
`predict()` methods to add their custom data handling tools or change
various aspects of the training that cannot be configured via the
top level config.json file.
"""
def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary holding all data for train, test,
labels, weights
:param dk: The datakitchen object for the current coin/model
"""
cbc = CatBoostClassifier(
allow_writing_files=True,
loss_function="MultiClass",
train_dir=Path(dk.data_path),
**self.model_training_parameters,
)
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
sample_weight = data_dictionary["train_weights"]
eval_sets = [None] * y.shape[1]
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) != 0:
eval_sets = [None] * data_dictionary["test_labels"].shape[1]
for i in range(data_dictionary["test_labels"].shape[1]):
eval_sets[i] = Pool(
data=data_dictionary["test_features"],
label=data_dictionary["test_labels"].iloc[:, i],
weight=data_dictionary["test_weights"],
)
init_model = self.get_init_model(dk.pair)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{
"eval_set": eval_sets[i],
"init_model": init_models[i],
}
)
model = FreqaiMultiOutputClassifier(estimator=cbc)
thread_training = self.freqai_info.get("multitarget_parallel_training", False)
if thread_training:
model.n_jobs = y.shape[1]
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
return model

60
freqtrade/freqai/prediction_models/CatboostRegressor.py
View File

@@ -1,60 +0,0 @@
import logging
from pathlib import Path
from typing import Any
from catboost import CatBoostRegressor, Pool
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
class CatboostRegressor(BaseRegressionModel):
"""
User created prediction model. The class inherits IFreqaiModel, which
means it has full access to all Frequency AI functionality. Typically,
users would use this to override the common `fit()`, `train()`, or
`predict()` methods to add their custom data handling tools or change
various aspects of the training that cannot be configured via the
top level config.json file.
"""
def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary holding all data for train, test,
labels, weights
:param dk: The datakitchen object for the current coin/model
"""
train_data = Pool(
data=data_dictionary["train_features"],
label=data_dictionary["train_labels"],
weight=data_dictionary["train_weights"],
)
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0:
test_data = None
else:
test_data = Pool(
data=data_dictionary["test_features"],
label=data_dictionary["test_labels"],
weight=data_dictionary["test_weights"],
)
init_model = self.get_init_model(dk.pair)
model = CatBoostRegressor(
allow_writing_files=True,
train_dir=Path(dk.data_path),
**self.model_training_parameters,
)
model.fit(
X=train_data,
eval_set=test_data,
init_model=init_model,
)
return model

78
freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py
View File

@@ -1,78 +0,0 @@
import logging
from pathlib import Path
from typing import Any
from catboost import CatBoostRegressor, Pool
from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
logger = logging.getLogger(__name__)
class CatboostRegressorMultiTarget(BaseRegressionModel):
"""
User created prediction model. The class inherits IFreqaiModel, which
means it has full access to all Frequency AI functionality. Typically,
users would use this to override the common `fit()`, `train()`, or
`predict()` methods to add their custom data handling tools or change
various aspects of the training that cannot be configured via the
top level config.json file.
"""
def fit(self, data_dictionary: dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
"""
User sets up the training and test data to fit their desired model here
:param data_dictionary: the dictionary holding all data for train, test,
labels, weights
:param dk: The datakitchen object for the current coin/model
"""
cbr = CatBoostRegressor(
allow_writing_files=True,
train_dir=Path(dk.data_path),
**self.model_training_parameters,
)
X = data_dictionary["train_features"]
y = data_dictionary["train_labels"]
sample_weight = data_dictionary["train_weights"]
eval_sets = [None] * y.shape[1]
if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) != 0:
eval_sets = [None] * data_dictionary["test_labels"].shape[1]
for i in range(data_dictionary["test_labels"].shape[1]):
eval_sets[i] = Pool(
data=data_dictionary["test_features"],
label=data_dictionary["test_labels"].iloc[:, i],
weight=data_dictionary["test_weights"],
)
init_model = self.get_init_model(dk.pair)
if init_model:
init_models = init_model.estimators_
else:
init_models = [None] * y.shape[1]
fit_params = []
for i in range(len(eval_sets)):
fit_params.append(
{
"eval_set": eval_sets[i],
"init_model": init_models[i],
}
)
model = FreqaiMultiOutputRegressor(estimator=cbr)
thread_training = self.freqai_info.get("multitarget_parallel_training", False)
if thread_training:
model.n_jobs = y.shape[1]
model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
return model

4
freqtrade/freqai/utils.py
View File

@@ -97,7 +97,7 @@ def plot_feature_importance(
"""
Plot Best and worst features by importance for a single sub-train.
:param model: Any = A model which was `fit` using a common library
such as catboost or lightgbm
such as XGBoost or lightgbm
:param pair: str = pair e.g. BTC/USD
:param dk: FreqaiDataKitchen = non-persistent data container for current coin/loop
:param count_max: int = the amount of features to be loaded per column
@@ -115,6 +115,8 @@ def plot_feature_importance(
for label in models:
mdl = models[label]
if "catboost.core" in str(mdl.__class__):
# CatBoost is no longer actively supported since 2025.12
# However users can still use it in their custom models
feature_importance = mdl.get_feature_importance()
elif "lightgbm.sklearn" in str(mdl.__class__):
feature_importance = mdl.feature_importances_

20
freqtrade/rpc/api_server/api_backtest.py
View File

@@ -52,29 +52,25 @@ def __run_backtest_bg(btconfig: Config):
lastconfig = ApiBG.bt["last_config"]
strat = StrategyResolver.load_strategy(btconfig)
validate_config_consistency(btconfig)
if (
not ApiBG.bt["bt"]
or lastconfig.get("timeframe") != strat.timeframe
time_settings_changed = (
lastconfig.get("timeframe") != strat.timeframe
or lastconfig.get("timeframe_detail") != btconfig.get("timeframe_detail")
or lastconfig.get("timerange") != btconfig["timerange"]
):
)
if not ApiBG.bt["bt"] or time_settings_changed:
from freqtrade.optimize.backtesting import Backtesting
ApiBG.bt["bt"] = Backtesting(btconfig)
else:
ApiBG.bt["bt"].config = deep_merge_dicts(btconfig, ApiBG.bt["bt"].config)
ApiBG.bt["bt"].init_backtest()
# Only reload data if timeframe changed.
if (
not ApiBG.bt["data"]
or not ApiBG.bt["timerange"]
or lastconfig.get("timeframe") != strat.timeframe
or lastconfig.get("timerange") != btconfig["timerange"]
):
# Only reload data if timerange is open or settings changed
if not ApiBG.bt["data"] or not ApiBG.bt["timerange"] or time_settings_changed:
ApiBG.bt["data"], ApiBG.bt["timerange"] = ApiBG.bt["bt"].load_bt_data()
lastconfig["timerange"] = btconfig["timerange"]
lastconfig["timeframe_detail"] = btconfig.get("timeframe_detail")
lastconfig["timeframe"] = strat.timeframe
lastconfig["enable_protections"] = btconfig.get("enable_protections")
lastconfig["dry_run_wallet"] = btconfig.get("dry_run_wallet")

2
freqtrade/templates/FreqaiExampleHybridStrategy.py
View File

@@ -20,7 +20,7 @@ class FreqaiExampleHybridStrategy(IStrategy):
Launching this strategy would be:
freqtrade trade --strategy FreqaiExampleHybridStrategy --strategy-path freqtrade/templates
--freqaimodel CatboostClassifier --config config_examples/config_freqai.example.json
--freqaimodel XGBoostClassifier --config config_examples/config_freqai.example.json
or the user simply adds this to their config:

4
freqtrade/templates/FreqaiExampleStrategy.py
View File

@@ -205,8 +205,8 @@ class FreqaiExampleStrategy(IStrategy):
# 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
# freqai/prediction_models/CatboostRegressorMultiTarget.py,
# freqtrade trade --freqaimodel CatboostRegressorMultiTarget
# freqai/prediction_models/LightGBMClassifierMultiTarget.py,
# freqtrade trade --freqaimodel LightGBMClassifierMultiTarget
# df["&-s_range"] = (
# df["close"]

1
pyproject.toml
View File

@@ -85,7 +85,6 @@ hyperopt = [
freqai = [
"scikit-learn",
"joblib",
"catboost; platform_machine != 'arm'",
"lightgbm",
"xgboost",
"tensorboard",

6
requirements-dev.txt
View File

@@ -6,8 +6,8 @@
-r requirements-freqai-rl.txt
-r docs/requirements-docs.txt
ruff==0.14.8
mypy==1.19.0
ruff==0.14.9
mypy==1.19.1
pre-commit==4.5.0
pytest==9.0.2
pytest-asyncio==1.3.0
@@ -24,7 +24,7 @@ time-machine==3.1.0
nbconvert==7.16.6
# mypy types
scipy-stubs==1.16.3.2 # keep in sync with `scipy` in `requirements-hyperopt.txt`
scipy-stubs==1.16.3.3 # keep in sync with `scipy` in `requirements-hyperopt.txt`
types-cachetools==6.2.0.20251022
types-filelock==3.2.7
types-requests==2.32.4.20250913

1
requirements-freqai.txt
View File

@@ -5,7 +5,6 @@
# Required for freqai
scikit-learn==1.7.2
joblib==1.5.3
catboost==1.2.8; 'arm' not in platform_machine and python_version < '3.14'
lightgbm==4.6.0
xgboost==3.1.2
tensorboard==2.20.0

2
requirements-hyperopt.txt
View File

@@ -4,6 +4,6 @@
# Required for hyperopt
scipy==1.16.3
scikit-learn==1.7.2
filelock==3.20.0
filelock==3.20.1
optuna==4.6.0
cmaes==0.12.0

10
requirements.txt
View File

@@ -7,17 +7,17 @@ ft-pandas-ta==0.3.16
ta-lib==0.6.8
technical==1.5.3
ccxt==4.5.27
ccxt==4.5.28
cryptography==46.0.3
aiohttp==3.13.2
SQLAlchemy==2.0.44
SQLAlchemy==2.0.45
python-telegram-bot==22.5
# can't be hard-pinned due to telegram-bot pinning httpx with ~
httpx>=0.24.1
humanize==4.14.0
cachetools==6.2.2
cachetools==6.2.3
requests==2.32.5
urllib3==2.6.0
urllib3==2.6.2
certifi==2025.11.12
jsonschema==4.25.1
tabulate==0.9.0
@@ -37,7 +37,7 @@ orjson==3.11.5
sdnotify==0.3.2
# API Server
fastapi==0.124.0
fastapi==0.124.4
pydantic==2.12.5
uvicorn==0.38.0
pyjwt==2.10.1

18
tests/exchange/test_gate.py
View File

@@ -16,9 +16,9 @@ def test_fetch_stoploss_order_gate(default_conf, mocker):
exchange.fetch_stoploss_order("1234", "ETH/BTC")
assert fetch_order_mock.call_count == 1
assert fetch_order_mock.call_args_list[0][1]["order_id"] == "1234"
assert fetch_order_mock.call_args_list[0][1]["pair"] == "ETH/BTC"
assert fetch_order_mock.call_args_list[0][1]["params"] == {"stop": True}
assert fetch_order_mock.call_args_list[0][0][0] == "1234"
assert fetch_order_mock.call_args_list[0][0][1] == "ETH/BTC"
assert fetch_order_mock.call_args_list[0][0][2] == {"stop": True}
default_conf["trading_mode"] = "futures"
default_conf["margin_mode"] = "isolated"
@@ -36,21 +36,19 @@ def test_fetch_stoploss_order_gate(default_conf, mocker):
exchange.fetch_stoploss_order("1234", "ETH/BTC")
assert exchange.fetch_order.call_count == 2
assert exchange.fetch_order.call_args_list[0][1]["order_id"] == "1234"
assert exchange.fetch_order.call_args_list[0][0][0] == "1234"
assert exchange.fetch_order.call_args_list[1][1]["order_id"] == "222555"
def test_cancel_stoploss_order_gate(default_conf, mocker):
exchange = get_patched_exchange(mocker, default_conf, exchange="gate")
cancel_order_mock = MagicMock()
exchange.cancel_order = cancel_order_mock
cancel_order_mock = mocker.patch.object(exchange, "cancel_order", autospec=True)
exchange.cancel_stoploss_order("1234", "ETH/BTC")
assert cancel_order_mock.call_count == 1
assert cancel_order_mock.call_args_list[0][1]["order_id"] == "1234"
assert cancel_order_mock.call_args_list[0][1]["pair"] == "ETH/BTC"
assert cancel_order_mock.call_args_list[0][1]["params"] == {"stop": True}
assert cancel_order_mock.call_args_list[0][0][0] == "1234"
assert cancel_order_mock.call_args_list[0][0][1] == "ETH/BTC"
assert cancel_order_mock.call_args_list[0][0][2] == {"stop": True}
@pytest.mark.parametrize(

12
tests/exchange/test_okx.py
View File

@@ -661,14 +661,14 @@ def test_stoploss_adjust_okx(mocker, default_conf, sl1, sl2, sl3, side):
def test_stoploss_cancel_okx(mocker, default_conf):
exchange = get_patched_exchange(mocker, default_conf, exchange="okx")
exchange.cancel_order = MagicMock()
co_mock = mocker.patch.object(exchange, "cancel_order", autospec=True)
exchange.cancel_stoploss_order("1234", "ETH/USDT")
assert exchange.cancel_order.call_count == 1
assert exchange.cancel_order.call_args_list[0][1]["order_id"] == "1234"
assert exchange.cancel_order.call_args_list[0][1]["pair"] == "ETH/USDT"
assert exchange.cancel_order.call_args_list[0][1]["params"] == {"stop": True}
assert co_mock.call_count == 1
args, _ = co_mock.call_args
assert args[0] == "1234"
assert args[1] == "ETH/USDT"
assert args[2] == {"stop": True}
def test__get_stop_params_okx(mocker, default_conf):

13
tests/freqai/test_freqai_interface.py
View File

@@ -1,6 +1,5 @@
import logging
import shutil
import sys
from pathlib import Path
from unittest.mock import MagicMock
@@ -32,12 +31,6 @@ from tests.freqai.conftest import (
def can_run_model(model: str) -> None:
is_pytorch_model = "Reinforcement" in model or "PyTorch" in model
if is_arm() and "Catboost" in model:
pytest.skip("CatBoost is not supported on ARM.")
if "Catboost" in model and sys.version_info >= (3, 14):
pytest.skip("CatBoost is not supported on Python 3.14+.")
if is_pytorch_model and is_mac():
pytest.skip("Reinforcement learning / PyTorch module not available on intel based Mac OS.")
@@ -48,7 +41,6 @@ def can_run_model(model: str) -> None:
("LightGBMRegressor", True, False, True, True, False, 0, 0),
("XGBoostRegressor", False, True, False, True, False, 10, 0.05),
("XGBoostRFRegressor", False, False, False, True, False, 0, 0),
("CatboostRegressor", False, False, False, True, True, 0, 0),
("PyTorchMLPRegressor", False, False, False, False, False, 0, 0),
("PyTorchTransformerRegressor", False, False, False, False, False, 0, 0),
("ReinforcementLearner", False, True, False, True, False, 0, 0),
@@ -142,9 +134,7 @@ def test_extract_data_and_train_model_Standard(
[
("LightGBMRegressorMultiTarget", "freqai_test_multimodel_strat"),
("XGBoostRegressorMultiTarget", "freqai_test_multimodel_strat"),
("CatboostRegressorMultiTarget", "freqai_test_multimodel_strat"),
("LightGBMClassifierMultiTarget", "freqai_test_multimodel_classifier_strat"),
("CatboostClassifierMultiTarget", "freqai_test_multimodel_classifier_strat"),
],
)
@pytest.mark.filterwarnings(r"ignore:.*__sklearn_tags__.*:DeprecationWarning")
@@ -188,7 +178,6 @@ def test_extract_data_and_train_model_MultiTargets(mocker, freqai_conf, model, s
"model",
[
"LightGBMClassifier",
"CatboostClassifier",
"XGBoostClassifier",
"XGBoostRFClassifier",
"SKLearnRandomForestClassifier",
@@ -250,13 +239,11 @@ def test_extract_data_and_train_model_Classifiers(mocker, freqai_conf, model):
[
("LightGBMRegressor", 2, "freqai_test_strat"),
("XGBoostRegressor", 2, "freqai_test_strat"),
("CatboostRegressor", 2, "freqai_test_strat"),
("PyTorchMLPRegressor", 2, "freqai_test_strat"),
("PyTorchTransformerRegressor", 2, "freqai_test_strat"),
("ReinforcementLearner", 3, "freqai_rl_test_strat"),
("XGBoostClassifier", 2, "freqai_test_classifier"),
("LightGBMClassifier", 2, "freqai_test_classifier"),
("CatboostClassifier", 2, "freqai_test_classifier"),
("PyTorchMLPClassifier", 2, "freqai_test_classifier"),
],
)