9394559170

Committed 26 Apr 2024 06:36AM UTC coverage: 94.656% (-0.02%) from 94.674%

Build # 9394559170

Build Type

push

github

Committed by

xmatthias

Commit Message

Loader should be passed as kwarg for clarity

Run Details

20280 of 21425 relevant lines covered (94.66%)

0.95 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

93.94

/freqtrade/freqai/prediction_models/LightGBMClassifierMultiTarget.py

import logging
from typing import Any, Dict

from lightgbm import LGBMClassifier

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 LightGBMClassifierMultiTarget(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
        """

        lgb = LGBMClassifier(**self.model_training_parameters)

        X = data_dictionary["train_features"]
        y = data_dictionary["train_labels"]
        sample_weight = data_dictionary["train_weights"]

        eval_weights = None
        eval_sets = [None] * y.shape[1]

        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
            eval_weights = [data_dictionary["test_weights"]]
            eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1]  # type: ignore
            for i in range(data_dictionary['test_labels'].shape[1]):
                eval_sets[i] = (  # type: ignore
                    data_dictionary["test_features"],
                    data_dictionary["test_labels"].iloc[:, i]
                )

        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], 'eval_sample_weight': eval_weights,
                 'init_model': init_models[i]})

        model = FreqaiMultiOutputClassifier(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)

        return model

1	import logging	1✔
2	from typing import Any, Dict	1✔
3
4	from lightgbm import LGBMClassifier	1✔
5
6	from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel	1✔
7	from freqtrade.freqai.base_models.FreqaiMultiOutputClassifier import FreqaiMultiOutputClassifier	1✔
8	from freqtrade.freqai.data_kitchen import FreqaiDataKitchen	1✔
9
10
11	logger = logging.getLogger(__name__)	1✔
12
13
14	class LightGBMClassifierMultiTarget(BaseClassifierModel):	1✔
15	"""
16	User created prediction model. The class inherits IFreqaiModel, which
17	means it has full access to all Frequency AI functionality. Typically,
18	users would use this to override the common `fit()`, `train()`, or
19	`predict()` methods to add their custom data handling tools or change
20	various aspects of the training that cannot be configured via the
21	top level config.json file.
22	"""
23
24	def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:	1✔
25	"""
26	User sets up the training and test data to fit their desired model here
27	:param data_dictionary: the dictionary holding all data for train, test,
28	labels, weights
29	:param dk: The datakitchen object for the current coin/model
30	"""
31
32	lgb = LGBMClassifier(**self.model_training_parameters)	1✔
33
34	X = data_dictionary["train_features"]	1✔
35	y = data_dictionary["train_labels"]	1✔
36	sample_weight = data_dictionary["train_weights"]	1✔
37
38	eval_weights = None	1✔
39	eval_sets = [None] * y.shape[1]	1✔
40
41	if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:	1✔
42	eval_weights = [data_dictionary["test_weights"]]	1✔
43	eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1] # type: ignore	1✔
44	for i in range(data_dictionary['test_labels'].shape[1]):	1✔
45	eval_sets[i] = ( # type: ignore	1✔
46	data_dictionary["test_features"],
47	data_dictionary["test_labels"].iloc[:, i]
48	)
49
50	init_model = self.get_init_model(dk.pair)	1✔
51	if init_model:	1✔
52	init_models = init_model.estimators_	×
53	else:
54	init_models = [None] * y.shape[1]	1✔
55
56	fit_params = []	1✔
57	for i in range(len(eval_sets)):	1✔
58	fit_params.append(	1✔
59	{'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights,
60	'init_model': init_models[i]})
61
62	model = FreqaiMultiOutputClassifier(estimator=lgb)	1✔
63	thread_training = self.freqai_info.get('multitarget_parallel_training', False)	1✔
64	if thread_training:	1✔
65	model.n_jobs = y.shape[1]	×
66	model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)	1✔
67
68	return model	1✔

freqtrade / freqtrade / 9394559170

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous