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

flake8 passing, use pathlib in lieu of os.path to accommodate windows/mac OS

Browse Source
This commit is contained in:
robcaulk
2022-05-04 17:42:34 +02:00
parent 93cf4cc262
commit 2a3347bc12
7 changed files with 593 additions and 439 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
freqtrade/templates/ExamplePredictionModel.py
View File

@@ -1,15 +1,17 @@
import numpy as np
from typing import Any, Dict, Tuple
import pandas as pd
from catboost import CatBoostRegressor, Pool
from pandas import DataFrame
from typing import Any, Dict, Tuple
from freqtrade.freqai.freqai_interface import IFreqaiModel
class ExamplePredictionModel(IFreqaiModel):
"""
User created prediction model. The class needs to override three necessary
functions, predict(), train(), fit(). The class inherits ModelHandler which
has its own DataHandler where data is held, saved, loaded, and managed.
has its own DataHandler where data is held, saved, loaded, and managed.
"""
def make_labels(self, dataframe: DataFrame) -> DataFrame:
@@ -19,15 +21,20 @@ class ExamplePredictionModel(IFreqaiModel):
:dataframe: the full dataframe for the present training period
"""
dataframe['s'] = (dataframe['close'].shift(-self.feature_parameters['period']).rolling(
self.feature_parameters['period']).max() / dataframe['close'] - 1)
self.dh.data['s_mean'] = dataframe['s'].mean()
self.dh.data['s_std'] = dataframe['s'].std()
dataframe["s"] = (
dataframe["close"]
.shift(-self.feature_parameters["period"])
.rolling(self.feature_parameters["period"])
.max()
/ dataframe["close"]
- 1
)
self.dh.data["s_mean"] = dataframe["s"].mean()
self.dh.data["s_std"] = dataframe["s"].std()
print('label mean',self.dh.data['s_mean'],'label std',self.dh.data['s_std'])
return dataframe['s']
print("label mean", self.dh.data["s_mean"], "label std", self.dh.data["s_std"])
return dataframe["s"]
def train(self, unfiltered_dataframe: DataFrame, metadata: dict) -> Tuple[DataFrame, DataFrame]:
"""
@@ -35,7 +42,7 @@ class ExamplePredictionModel(IFreqaiModel):
for storing, saving, loading, and managed.
:params:
:unfiltered_dataframe: Full dataframe for the current training period
:metadata: pair metadata from strategy.
:metadata: pair metadata from strategy.
:returns:
:model: Trained model which can be used to inference (self.predict)
"""
@@ -46,8 +53,12 @@ class ExamplePredictionModel(IFreqaiModel):
unfiltered_labels = self.make_labels(unfiltered_dataframe)
# filter the features requested by user in the configuration file and elegantly handle NaNs
features_filtered, labels_filtered = self.dh.filter_features(unfiltered_dataframe,
self.dh.training_features_list, unfiltered_labels, training_filter=True)
features_filtered, labels_filtered = self.dh.filter_features(
unfiltered_dataframe,
self.dh.training_features_list,
unfiltered_labels,
training_filter=True,
)
# split data into train/test data.
data_dictionary = self.dh.make_train_test_datasets(features_filtered, labels_filtered)
@@ -55,46 +66,47 @@ class ExamplePredictionModel(IFreqaiModel):
data_dictionary = self.dh.standardize_data(data_dictionary)
# optional additional data cleaning
if self.feature_parameters['principal_component_analysis']:
if self.feature_parameters["principal_component_analysis"]:
self.dh.principal_component_analysis()
if self.feature_parameters["remove_outliers"]:
self.dh.remove_outliers(predict=False)
if self.feature_parameters['DI_threshold']:
self.dh.data['avg_mean_dist'] = self.dh.compute_distances()
if self.feature_parameters["DI_threshold"]:
self.dh.data["avg_mean_dist"] = self.dh.compute_distances()
print("length of train data", len(data_dictionary['train_features']))
print("length of train data", len(data_dictionary["train_features"]))
model = self.fit(data_dictionary)
print('Finished training')
print("Finished training")
print(f'--------------------done training {metadata["pair"]}--------------------')
return model
def fit(self, data_dictionary: Dict) -> Any:
"""
Most regressors use the same function names and arguments e.g. user
Most regressors use the same function names and arguments e.g. user
can drop in LGBMRegressor in place of CatBoostRegressor and all data
management will be properly handled by Freqai.
:params:
:data_dictionary: the dictionary constructed by DataHandler to hold
:data_dictionary: the dictionary constructed by DataHandler to hold
all the training and test data/labels.
"""
train_data = Pool(
data=data_dictionary['train_features'],
label=data_dictionary['train_labels'],
weight=data_dictionary['train_weights']
data=data_dictionary["train_features"],
label=data_dictionary["train_labels"],
weight=data_dictionary["train_weights"],
)
test_data = Pool(
data=data_dictionary['test_features'],
label=data_dictionary['test_labels'],
weight=data_dictionary['test_weights']
data=data_dictionary["test_features"],
label=data_dictionary["test_labels"],
weight=data_dictionary["test_weights"],
)
model = CatBoostRegressor(verbose=100, early_stopping_rounds=400,
**self.model_training_parameters)
model = CatBoostRegressor(
verbose=100, early_stopping_rounds=400, **self.model_training_parameters
)
model.fit(X=train_data, eval_set=test_data)
return model
@@ -103,7 +115,7 @@ class ExamplePredictionModel(IFreqaiModel):
"""
Filter the prediction features data and predict with it.
:param: unfiltered_dataframe: Full dataframe for the current backtest period.
:return:
:return:
:predictions: np.array of predictions
:do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
data (NaNs) or felt uncertain about data (PCA and DI index)
@@ -112,27 +124,31 @@ class ExamplePredictionModel(IFreqaiModel):
print("--------------------Starting prediction--------------------")
original_feature_list = self.dh.build_feature_list(self.config)
filtered_dataframe, _ = self.dh.filter_features(unfiltered_dataframe, original_feature_list, training_filter=False)
filtered_dataframe, _ = self.dh.filter_features(
unfiltered_dataframe, original_feature_list, training_filter=False
)
filtered_dataframe = self.dh.standardize_data_from_metadata(filtered_dataframe)
self.dh.data_dictionary['prediction_features'] = filtered_dataframe
self.dh.data_dictionary["prediction_features"] = filtered_dataframe
# optional additional data cleaning
if self.feature_parameters['principal_component_analysis']:
# optional additional data cleaning
if self.feature_parameters["principal_component_analysis"]:
pca_components = self.dh.pca.transform(filtered_dataframe)
self.dh.data_dictionary['prediction_features'] = pd.DataFrame(data=pca_components,
columns = ['PC'+str(i) for i in range(0,self.dh.data['n_kept_components'])],
index = filtered_dataframe.index)
self.dh.data_dictionary["prediction_features"] = pd.DataFrame(
data=pca_components,
columns=["PC" + str(i) for i in range(0, self.dh.data["n_kept_components"])],
index=filtered_dataframe.index,
)
if self.feature_parameters["remove_outliers"]:
self.dh.remove_outliers(predict=True) # creates dropped index
self.dh.remove_outliers(predict=True) # creates dropped index
if self.feature_parameters['DI_threshold']:
self.dh.check_if_pred_in_training_spaces() # sets do_predict
if self.feature_parameters["DI_threshold"]:
self.dh.check_if_pred_in_training_spaces() # sets do_predict
predictions = self.model.predict(self.dh.data_dictionary['prediction_features'])
predictions = self.model.predict(self.dh.data_dictionary["prediction_features"])
# compute the non-standardized predictions
predictions = predictions * self.dh.data['labels_std'] + self.dh.data['labels_mean']
predictions = predictions * self.dh.data["labels_std"] + self.dh.data["labels_mean"]
print("--------------------Finished prediction--------------------")