def association_rule(table, group_by=None, **params):
check_required_parameters(_association_rule, params, ['table'])
params = get_default_from_parameters_if_required(params, _association_rule)
param_validation_check = [from_to(params, 0, 1, 'min_support'),
from_to(params, 0, 1, 'min_confidence')]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_association_rule, table, group_by=group_by, **params)
else:
return _association_rule(table, **params)
def decision_tree_classification_train(table, group_by=None, **params):
check_required_parameters(_decision_tree_classification_train, params,
['table'])
params = get_default_from_parameters_if_required(
params, _decision_tree_classification_train)
param_validation_check = [
greater_than_or_equal_to(params, 2, 'min_samples_split'),
greater_than_or_equal_to(params, 1, 'min_samples_leaf'),
from_to(params, 0.0, 0.5, 'min_weight_fraction_leaf'),
greater_than_or_equal_to(params, 0.0, 'min_impurity_decrease'),
greater_than_or_equal_to(params, 1, 'max_depth'),
greater_than_or_equal_to(params, 1, 'max_features'),
greater_than(params, 1, 'max_leaf_nodes')
]
validate(*param_validation_check)
if group_by is not None:
grouped_model = _function_by_group(_decision_tree_classification_train,
table,
group_by=group_by,
**params)
return grouped_model
else:
return _decision_tree_classification_train(table, **params)
def ngram(table, **params): # to be deprecated
check_required_parameters(_ngram, params, ['table'])
params = get_default_from_parameters_if_required(params, _ngram)
max_len = np.max(np.vectorize(len)(table[params["input_col"]])).item()
param_validation_check = [from_to(params, 1, max_len, 'n')]
validate(*param_validation_check)
return _ngram(table, **params)
def paired_ttest(table, group_by=None, **params):
check_required_parameters(_paired_ttest, params, ['table'])
params = get_default_from_parameters_if_required(params, _paired_ttest)
param_validation_check = [from_to(params, 0, 1, 'confidence_level')]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_paired_ttest, table, group_by=group_by, **params)
else:
return _paired_ttest(table, **params)
def two_sample_ttest_for_stacked_data(table, group_by=None, **params):
params = get_default_from_parameters_if_required(params, _two_sample_ttest_for_stacked_data)
param_validation_check = [from_to(params, 0, 1, 'confi_level')]
validate(*param_validation_check)
check_required_parameters(_two_sample_ttest_for_stacked_data, params, ['table'])
if group_by is not None:
return _function_by_group(_two_sample_ttest_for_stacked_data, table, group_by=group_by, **params)
else:
return _two_sample_ttest_for_stacked_data(table, **params)
def tsne(table, group_by=None, **params):
check_required_parameters(_tsne, params, ['table'])
params = get_default_from_parameters_if_required(params, _tsne)
param_validation_check = [from_to(params, 1, len(params['input_cols']), 'n_components')]
validate(*param_validation_check)
if group_by is not None:
grouped_model = _function_by_group(_tsne, table, group_by=group_by, **params)
return grouped_model
else:
return _tsne(table, **params)
def ewma(table, group_by=None, **params):
check_required_parameters(_ewma, params, ['table'])
params = get_default_from_parameters_if_required(params,_ewma)
param_validation_check = [greater_than_or_equal_to(params, 1, 'period_number'),
from_to(params, 0, 1, 'custom_ratio')]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_ewma, table, group_by=group_by, **params)
else:
return _ewma(table, **params)
def lda(table, group_by=None, **params):
check_required_parameters(_lda, params, ['table'])
params = get_default_from_parameters_if_required(params, _lda)
param_validation_check = [greater_than_or_equal_to(params, 2, 'num_voca'),
greater_than_or_equal_to(params, 2, 'num_topic'),
from_to(params, 2, params['num_voca'], 'num_topic_word'),
greater_than_or_equal_to(params, 1, 'max_iter'),
greater_than(params, 1.0, 'learning_offset')]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_lda, table, group_by=group_by, **params)
else:
return _lda(table, **params)
def holt_winters_train(table, group_by=None, **params):
len_table = len(table)
check_required_parameters(_holt_winters_train, params, ['table'])
params = get_default_from_parameters_if_required(params,
_holt_winters_train)
param_validation_check = [from_to(params, 2, (len_table) // 2, 'period')]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_holt_winters_train,
table,
group_by=group_by,
**params)
else:
return _holt_winters_train(table, **params)
def arima_train(table, group_by=None, **params):
check_required_parameters(_arima_train, params, ['table'])
params = get_default_from_parameters_if_required(params, _arima_train)
param_validation_check = [
greater_than_or_equal_to(params, 0, 'p'),
from_to(params, 0, 2, 'd'),
greater_than_or_equal_to(params, 0, 'q')
]
validate(*param_validation_check)
if group_by is not None:
return _function_by_group(_arima_train,
table,
group_by=group_by,
**params)
else:
return _arima_train(table, **params)
def split_data(table, group_by=None, **params):
params = get_default_from_parameters_if_required(params, _split_data)
param_validation_check = [
greater_than(params, 0.0, 'train_ratio'),
greater_than(params, 0.0, 'test_ratio'),
from_to(params, 0, 2**30, 'random_state')
]
validate(*param_validation_check)
check_required_parameters(_split_data, params, ['table'])
if group_by is not None:
return _function_by_group(_split_data,
table,
group_by=group_by,
**params)
else:
return _split_data(table, **params)
def penalized_linear_regression_train(table, group_by=None, **params):
check_required_parameters(_penalized_linear_regression_train, params,
['table'])
params = get_default_from_parameters_if_required(
params, _penalized_linear_regression_train)
param_validation_check = [
greater_than_or_equal_to(params, 0.0, 'alpha'),
from_to(params, 0.0, 1.0, 'l1_ratio'),
greater_than_or_equal_to(params, 1, 'max_iter'),
greater_than(params, 0.0, 'tol')
]
validate(*param_validation_check)
if group_by is not None:
grouped_model = _function_by_group(_penalized_linear_regression_train,
table,
group_by=group_by,
**params)
return grouped_model
else:
return _penalized_linear_regression_train(table, **params)
