def setUp(self):
"""
Loads train dataset config, train Dataset and test dataset config.
"""
self.config = dataset.load_config(os.path.join(
'.', 'data', 'train_dataset2'))
self.data = dataset.Dataset(self.config["filepath"],
self.config["key attrib index"],
self.config["class attrib index"],
self.config["split char"],
self.config["missing value string"],
load_numeric=True)
self.test_config = dataset.load_config(os.path.join(
'.', 'data', 'test_dataset2'))
def setUp(self):
"""
Loads dataset config and Dataset without numeric attributes.
"""
self.config = dataset.load_config(os.path.join(
'.', 'data', 'train_dataset1'))
self.data = dataset.Dataset(self.config["filepath"],
self.config["key attrib index"],
self.config["class attrib index"],
self.config["split char"],
self.config["missing value string"],
load_numeric=False)
def setUp(self):
"""
Loads dataset config.
"""
self.criterion = criteria.GiniGain
self.config = dataset.load_config(
os.path.join('.', 'data', 'train_dataset2'))
self.data = dataset.Dataset(self.config["filepath"],
self.config["key attrib index"],
self.config["class attrib index"],
self.config["split char"],
self.config["missing value string"],
load_numeric=True)
self.decision_tree = decision_tree.DecisionTree(self.criterion)
def setUp(self):
"""
Loads dataset config and Dataset without numeric attributes.
"""
self.config = dataset.load_config(
os.path.join('.', 'data', 'train_dataset1'))
self.data = dataset.Dataset(self.config["filepath"],
self.config["key attrib index"],
self.config["class attrib index"],
self.config["split char"],
self.config["missing value string"],
load_numeric=True)
self.tree_node = decision_tree.TreeNode(
self.data,
list(range(self.data.num_samples)),
self.data.valid_nominal_attribute,
self.data.valid_numeric_attribute,
max_depth_remaining=0,
min_samples_per_node=1,
use_stop_conditions=False,
max_p_value_chi_sq=None)
def setUp(self):
"""
Loads dataset config and Dataset without numeric attributes, trains the tree.
"""
import criteria
self.criterion = criteria.GiniGain
self.config = dataset.load_config(
os.path.join('.', 'data', 'train_dataset1'))
self.data = dataset.Dataset(self.config["filepath"],
self.config["key attrib index"],
self.config["class attrib index"],
self.config["split char"],
self.config["missing value string"],
load_numeric=False)
self.decision_tree = decision_tree.DecisionTree(self.criterion)
self.decision_tree.train(self.data,
list(range(self.data.num_samples)),
max_depth=1,
min_samples_per_node=1,
use_stop_conditions=False,
max_p_value_chi_sq=None)
def test_test_from_csv(self):
"""
Tests DecisionTree's test_from_csv().
"""
test_config = dataset.load_config(
os.path.join('.', 'data', 'train_dataset1'))
(classifications, num_correct_classifications,
num_correct_classifications_wo_unkown, total_cost,
total_cost_wo_unkown, classified_with_unkown_value_array, num_unkown,
unkown_value_attrib_index_array) = self.decision_tree.test_from_csv(
test_config["filepath"], test_config["key attrib index"],
test_config["class attrib index"], test_config["split char"],
test_config["missing value string"])
self.assertEqual(classifications, [0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0])
self.assertEqual(num_correct_classifications, 11)
self.assertEqual(num_correct_classifications_wo_unkown, 11)
self.assertEqual(total_cost, 1.0)
self.assertEqual(total_cost_wo_unkown, 1.0)
self.assertEqual(classified_with_unkown_value_array, [False] * 12)
self.assertEqual(num_unkown, 0)
self.assertEqual(unkown_value_attrib_index_array, [None] * 12)
def main(experiment_config):
"""Sets the configurations according to `experiment_config` and runs them.
"""
raw_output_filepath = os.path.join(experiment_config["output folder"],
'raw_output.csv')
with open(raw_output_filepath, 'w') as fout:
init_raw_output_csv(fout, output_split_char=',')
criteria_list = get_criteria(experiment_config["criteria"])
if "starting seed index" not in experiment_config:
starting_seed = 1
else:
starting_seed = experiment_config["starting seed index"]
if experiment_config["prunning parameters"]["use chi-sq test"]:
max_p_value_chi_sq = experiment_config["prunning parameters"][
"max chi-sq p-value"]
decision_tree.MIN_SAMPLES_IN_SECOND_MOST_FREQUENT_VALUE = experiment_config[
"prunning parameters"]["second most freq value min samples"]
else:
max_p_value_chi_sq = None
decision_tree.MIN_SAMPLES_IN_SECOND_MOST_FREQUENT_VALUE = None
decision_tree.USE_MIN_SAMPLES_SECOND_LARGEST_CLASS = experiment_config[
"prunning parameters"]["use second most freq class min samples"]
if decision_tree.USE_MIN_SAMPLES_SECOND_LARGEST_CLASS:
decision_tree.MIN_SAMPLES_SECOND_LARGEST_CLASS = experiment_config[
"prunning parameters"]["second most freq class min samples"]
else:
decision_tree.MIN_SAMPLES_SECOND_LARGEST_CLASS = None
if experiment_config["use all datasets"]:
datasets_configs = dataset.load_all_configs(
experiment_config["datasets basepath"])
datasets_configs.sort(key=lambda config: config["dataset name"])
else:
datasets_folders = [
os.path.join(experiment_config["datasets basepath"],
folderpath)
for folderpath in experiment_config["datasets folders"]
]
datasets_configs = [
dataset.load_config(folderpath)
for folderpath in datasets_folders
]
if experiment_config["load one dataset at a time"]:
datasets = dataset.load_all_datasets(
datasets_configs, experiment_config["use numeric attributes"])
for ((dataset_name, curr_dataset),
min_num_samples_allowed) in itertools.product(
datasets, experiment_config["prunning parameters"]
["min num samples allowed"]):
for criterion in criteria_list:
print('-' * 100)
print(criterion.name)
print()
run(dataset_name,
curr_dataset,
experiment_config["num training samples"],
criterion,
min_num_samples_allowed=min_num_samples_allowed,
max_depth=experiment_config["max depth"],
num_trials=experiment_config["num trials"],
starting_seed=starting_seed,
use_numeric_attributes=experiment_config[
"use numeric attributes"],
use_chi_sq_test=experiment_config[
"prunning parameters"]["use chi-sq test"],
max_p_value_chi_sq=max_p_value_chi_sq,
output_file_descriptor=fout,
output_split_char=',')
else:
for (dataset_config, min_num_samples_allowed) in itertools.product(
datasets_configs, experiment_config["prunning parameters"]
["min num samples allowed"]):
curr_dataset = dataset.Dataset(
dataset_config["filepath"],
dataset_config["key attrib index"],
dataset_config["class attrib index"],
dataset_config["split char"],
dataset_config["missing value string"],
experiment_config["use numeric attributes"])
for criterion in criteria_list:
print('-' * 100)
print(criterion.name)
print()
run(dataset_config["dataset name"],
curr_dataset,
experiment_config["num training samples"],
criterion,
min_num_samples_allowed=min_num_samples_allowed,
max_depth=experiment_config["max depth"],
num_trials=experiment_config["num trials"],
starting_seed=starting_seed,
use_numeric_attributes=experiment_config[
"use numeric attributes"],
use_chi_sq_test=experiment_config[
"prunning parameters"]["use chi-sq test"],
max_p_value_chi_sq=max_p_value_chi_sq,
output_file_descriptor=fout,
output_split_char=',')
def setUp(self):
"""
Loads dataset config.
"""
self.config = dataset.load_config(os.path.join(
'.', 'data', 'dataset_without_valid_attributes'))
def test_loading_correct_config(self):
"""
Correct config.
"""
self.assertIsInstance(dataset.load_config(os.path.join('.', 'data', 'train_dataset1')),
dict)
def test_missing_missing_value_str(self):
"""
Config without missing_value_str.
"""
self.assertIsNone(
dataset.load_config(os.path.join('.', 'data', 'wrong_configs', 'config_5')))
def test_missing_split_char(self):
"""
Config without split_char.
"""
self.assertIsNone(
dataset.load_config(os.path.join('.', 'data', 'wrong_configs', 'config_4')))
def test_missing_class_index(self):
"""
Config without class_attrib_index.
"""
self.assertIsNone(
dataset.load_config(os.path.join('.', 'data', 'wrong_configs', 'config_3')))
def test_missing_name(self):
"""
Config without dataset_name.
"""
self.assertIsNone(
dataset.load_config(os.path.join('.', 'data', 'wrong_configs', 'config_1')))
def test_nonexistent_file(self):
"""
Config pointing to non-existent file.
"""
self.assertIsNone(dataset.load_config('.'))
def setUp(self):
"""
Loads dataset config.
"""
self.config = dataset.load_config(os.path.join(
'.', 'data', 'train_dataset2'))
