本文整理汇总了Python中Utils.Utils.get_seed方法的典型用法代码示例。如果您正苦于以下问题：Python Utils.get_seed方法的具体用法？Python Utils.get_seed怎么用？Python Utils.get_seed使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Utils.Utils的用法示例。
在下文中一共展示了Utils.get_seed方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _objective
# 需要导入模块: from Utils import Utils [as 别名]
# 或者: from Utils.Utils import get_seed [as 别名]
def _objective(self, classifier):
self._iteration += 1
if self._n_folds > 1:
x = np.concatenate((self._x_test, self._x_train), axis=0)
y = np.concatenate((self._y_test, self._y_train), axis=0)
shuffle(x, y, random_state=Utils.get_seed())
score_arr = cross_val_score(classifier, x, y, cv=self._n_folds, n_jobs=-1)
score = np.mean(score_arr)
else:
classifier.fit(self._x_train, self._y_train)
score = classifier.score(self._x_test, self._y_test)
return -score示例2: calculate
# 需要导入模块: from Utils import Utils [as 别名]
# 或者: from Utils.Utils import get_seed [as 别名]
def calculate(x_all, y_all):
logging.warning('calculate')
x_all, x_val, y_all, y_val = train_test_split(x_all, y_all, test_size=40, random_state=Utils.get_seed())
# calculate for different train data size
for train_data_size in Configuration.SAMPLES_N:
logging.warning('calculate for data amount:{}'.format(train_data_size))
if train_data_size < x_all.shape[0]:
# get n_samples from dataset
tmp, x, tmp, y = train_test_split(x_all, y_all, test_size=train_data_size, random_state=Utils.get_seed())
else:
x, y = x_all, y_all
test_data_set(x, y, x_val, y_val)示例3: test_given_extraction_method
# 需要导入模块: from Utils import Utils [as 别名]
# 或者: from Utils.Utils import get_seed [as 别名]
def test_given_extraction_method(x, y, x_val, y_val, reduction_object):
logging.warning(
"Testing extraction method:{0} for x shape:{1}".format(reduction_object.__class__.__name__, x.shape))
svm_scores = list()
ann_scores = list()
decision_tree_scores = list()
random_forest_scores = list()
x, y, x_val, y_val = reduce_dimensions(x, y, x_val, y_val, reduction_object)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=Utils.get_seed())
suffix = str(len(x))
file_prefix = 'digits_' + suffix
for i in range(1, 10):
suffix = str(len(x))
file_prefix = 'digits_' + suffix
config = determine_parameters_all(x_train, y_train, x_test, y_test)
logging.warning(
'I:{0} \t Method:{1} Components_n:{2} result_file_prefix:{3}'.format(i, type(reduction_object).__name__,
reduction_object.n_components,
file_prefix))
svm_score = fit_and_score_svm(x_train, y_train, x_val, y_val, config)
ann_score = fit_and_score_ann(x_train, y_train, x_val, y_val, config)
decision_tree_score = fit_and_score_decision_tree(x_train, y_train, x_val, y_val, config)
random_forest_score = fit_and_score_random_forest(x_train, y_train, x_val, y_val, config)
svm_scores.append(svm_score)
ann_scores.append(ann_score)
decision_tree_scores.append(decision_tree_score)
random_forest_scores.append(random_forest_score)
save_results(file_prefix, 'svm', reduction_object, svm_scores)
save_results(file_prefix, 'ann', reduction_object, ann_scores)
save_results(file_prefix, 'forest', reduction_object, random_forest_scores)
save_results(file_prefix, 'tree', reduction_object, decision_tree_scores)