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

Merge branch 'develop' into add-xgboostclassifier

Browse Source
This commit is contained in:
Emre
2022-09-10 23:59:11 +03:00
committed by GitHub
parent 60eb02bb62 075748b21a
commit 330d7068ab
24 changed files with 254 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py
View File

@@ -36,9 +36,6 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
y = self._validate_data(X="no_validation", y=y, multi_output=True)
# if is_classifier(self):
# check_classification_targets(y)
if y.ndim == 1:
raise ValueError(
"y must have at least two dimensions for "
@@ -50,19 +47,12 @@ class FreqaiMultiOutputRegressor(MultiOutputRegressor):
):
raise ValueError("Underlying estimator does not support sample weights.")
# fit_params_validated = _check_fit_params(X, fit_params)
if not fit_params:
fit_params = [None] * y.shape[1]
# if not init_models:
# init_models = [None] * y.shape[1]
self.estimators_ = Parallel(n_jobs=self.n_jobs)(
delayed(_fit_estimator)(
self.estimator, X, y[:, i], sample_weight, **fit_params[i]
# init_model=init_models[i], eval_set=eval_sets[i],
# **fit_params_validated
)
for i in range(y.shape[1])
)

51
freqtrade/freqai/data_kitchen.py
View File

@@ -184,7 +184,7 @@ class FreqaiDataKitchen:
def filter_features(
self,
unfiltered_dataframe: DataFrame,
unfiltered_df: DataFrame,
training_feature_list: List,
label_list: List = list(),
training_filter: bool = True,
@@ -195,31 +195,35 @@ class FreqaiDataKitchen:
0s in the prediction dataset. However, prediction dataset do_predict will reflect any
row that had a NaN and will shield user from that prediction.
:params:
:unfiltered_dataframe: the full dataframe for the present training period
:unfiltered_df: the full dataframe for the present training period
:training_feature_list: list, the training feature list constructed by
self.build_feature_list() according to user specified parameters in the configuration file.
:labels: the labels for the dataset
:training_filter: boolean which lets the function know if it is training data or
prediction data to be filtered.
:returns:
:filtered_dataframe: dataframe cleaned of NaNs and only containing the user
:filtered_df: dataframe cleaned of NaNs and only containing the user
requested feature set.
:labels: labels cleaned of NaNs.
"""
filtered_dataframe = unfiltered_dataframe.filter(training_feature_list, axis=1)
filtered_dataframe = filtered_dataframe.replace([np.inf, -np.inf], np.nan)
filtered_df = unfiltered_df.filter(training_feature_list, axis=1)
filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan)
drop_index = pd.isnull(filtered_dataframe).any(1) # get the rows that have NaNs,
drop_index = pd.isnull(filtered_df).any(1) # get the rows that have NaNs,
drop_index = drop_index.replace(True, 1).replace(False, 0) # pep8 requirement.
if (training_filter):
const_cols = list((filtered_df.nunique() == 1).loc[lambda x: x].index)
if const_cols:
filtered_df = filtered_df.filter(filtered_df.columns.difference(const_cols))
logger.warning(f"Removed features {const_cols} with constant values.")
# we don't care about total row number (total no. datapoints) in training, we only care
# about removing any row with NaNs
# if labels has multiple columns (user wants to train multiple modelEs), we detect here
labels = unfiltered_dataframe.filter(label_list, axis=1)
labels = unfiltered_df.filter(label_list, axis=1)
drop_index_labels = pd.isnull(labels).any(1)
drop_index_labels = drop_index_labels.replace(True, 1).replace(False, 0)
dates = unfiltered_dataframe['date']
filtered_dataframe = filtered_dataframe[
dates = unfiltered_df['date']
filtered_df = filtered_df[
(drop_index == 0) & (drop_index_labels == 0)
] # dropping values
labels = labels[
@@ -229,13 +233,13 @@ class FreqaiDataKitchen:
(drop_index == 0) & (drop_index_labels == 0)
]
logger.info(
f"dropped {len(unfiltered_dataframe) - len(filtered_dataframe)} training points"
f" due to NaNs in populated dataset {len(unfiltered_dataframe)}."
f"dropped {len(unfiltered_df) - len(filtered_df)} training points"
f" due to NaNs in populated dataset {len(unfiltered_df)}."
)
if (1 - len(filtered_dataframe) / len(unfiltered_dataframe)) > 0.1 and self.live:
worst_indicator = str(unfiltered_dataframe.count().idxmin())
if (1 - len(filtered_df) / len(unfiltered_df)) > 0.1 and self.live:
worst_indicator = str(unfiltered_df.count().idxmin())
logger.warning(
f" {(1 - len(filtered_dataframe)/len(unfiltered_dataframe)) * 100:.0f} percent "
f" {(1 - len(filtered_df)/len(unfiltered_df)) * 100:.0f} percent "
" of training data dropped due to NaNs, model may perform inconsistent "
f"with expectations. Verify {worst_indicator}"
)
@@ -244,9 +248,9 @@ class FreqaiDataKitchen:
else:
# we are backtesting so we need to preserve row number to send back to strategy,
# so now we use do_predict to avoid any prediction based on a NaN
drop_index = pd.isnull(filtered_dataframe).any(1)
drop_index = pd.isnull(filtered_df).any(1)
self.data["filter_drop_index_prediction"] = drop_index
filtered_dataframe.fillna(0, inplace=True)
filtered_df.fillna(0, inplace=True)
# replacing all NaNs with zeros to avoid issues in 'prediction', but any prediction
# that was based on a single NaN is ultimately protected from buys with do_predict
drop_index = ~drop_index
@@ -255,11 +259,11 @@ class FreqaiDataKitchen:
logger.info(
"dropped %s of %s prediction data points due to NaNs.",
len(self.do_predict) - self.do_predict.sum(),
len(filtered_dataframe),
len(filtered_df),
)
labels = []
return filtered_dataframe, labels
return filtered_df, labels
def build_data_dictionary(
self,
@@ -466,10 +470,17 @@ class FreqaiDataKitchen:
) -> DataFrame:
"""
Function which takes the backtesting time range and
remove training data from dataframe
remove training data from dataframe, keeping only the
startup_candle_count candles
"""
startup_candle_count = self.config.get('startup_candle_count', 0)
tf = self.config['timeframe']
tr = self.config["timerange"]
backtesting_timerange = TimeRange.parse_timerange(tr)
if startup_candle_count > 0 and backtesting_timerange:
backtesting_timerange.subtract_start(timeframe_to_seconds(tf) * startup_candle_count)
start = datetime.fromtimestamp(backtesting_timerange.startts, tz=timezone.utc)
df = self.return_dataframe
df = df.loc[df["date"] >= start, :]
@@ -1215,7 +1226,6 @@ class FreqaiDataKitchen:
def save_backtesting_prediction(
self, append_df: DataFrame
) -> None:
"""
Save prediction dataframe from backtesting to h5 file format
:param append_df: dataframe for backtesting period
@@ -1229,7 +1239,6 @@ class FreqaiDataKitchen:
def get_backtesting_prediction(
self
) -> DataFrame:
"""
Get prediction dataframe from h5 file format
"""

11
freqtrade/freqai/freqai_interface.py
View File

@@ -14,6 +14,7 @@ from numpy.typing import NDArray
from pandas import DataFrame
from freqtrade.configuration import TimeRange
from freqtrade.constants import DATETIME_PRINT_FORMAT
from freqtrade.enums import RunMode
from freqtrade.exceptions import OperationalException
from freqtrade.exchange import timeframe_to_seconds
@@ -92,6 +93,12 @@ class IFreqaiModel(ABC):
self._threads: List[threading.Thread] = []
self._stop_event = threading.Event()
def __getstate__(self):
"""
Return an empty state to be pickled in hyperopt
"""
return ({})
def assert_config(self, config: Dict[str, Any]) -> None:
if not config.get("freqai", {}):
@@ -233,10 +240,10 @@ class IFreqaiModel(ABC):
trained_timestamp = tr_train
tr_train_startts_str = datetime.fromtimestamp(
tr_train.startts,
tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT)
tr_train_stopts_str = datetime.fromtimestamp(
tr_train.stopts,
tz=timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT)
logger.info(
f"Training {metadata['pair']}, {self.pair_it}/{self.total_pairs} pairs"
f" from {tr_train_startts_str} to {tr_train_stopts_str}, {train_it}/{total_trains} "

3
freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py
View File

@@ -60,6 +60,9 @@ class CatboostRegressorMultiTarget(BaseRegressionModel):
{'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

6
freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py
View File

@@ -56,9 +56,9 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel):
'init_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=lgb)
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)
# model = FreqaiMultiOutputRegressor(estimator=lgb)
# model.fit(X=X, y=y, sample_weight=sample_weight, init_models=init_models,
# eval_sets=eval_sets, eval_sample_weight=eval_weights)
return model

3
freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py
View File

@@ -55,6 +55,9 @@ class XGBoostRegressorMultiTarget(BaseRegressionModel):
'xgb_model': init_models[i]})
model = FreqaiMultiOutputRegressor(estimator=xgb)
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