def split_abt_buy(rnd: random.Random):
model = BootEA()
model.set_args(load_args("../OpenEA/run/args/bootea_args_15K.json"))
dataset = CsvDataset(
CsvType.products,
f"{base_path}/abt-buy/Abt.csv",
f"{base_path}/abt-buy/Buy.csv",
f"{base_path}/abt-buy/abt_buy_perfectMapping.csv",
model,
rnd,
)
print(f"abt-buy: {len(dataset.kg1.entities_set)}, {len(dataset.kg2.entities_set)}")
split_dataset(dataset, f"{base_path}/abt-buy")
def test_create(self):
"""Test Create
Args:
self: TestCsvDataset
Returns:
None
Raises:
None
"""
__location__ = os.path.realpath(
os.path.join(os.getcwd(), os.path.dirname(__file__)))
dataset_csv_file_path = os.path.join(__location__, 'sample_data.csv')
CsvDataset(dataset_csv_file_path, None, False)
# test with bad dataset_csv_file_path
with self.assertRaises(PreconditionException) as context:
CsvDataset(1)
self.assertTrue('Invalid dataset_csv_file_path' in str(context.exception))
def split_amazon_google(rnd: random.Random):
model = BootEA()
model.set_args(load_args("../OpenEA/run/args/bootea_args_15K.json"))
dataset = CsvDataset(
CsvType.products,
f"{base_path}/amazon-google/Amazon.csv",
f"{base_path}/amazon-google/GoogleProducts.csv",
f"{base_path}/amazon-google/Amzon_GoogleProducts_perfectMapping.csv",
model,
rnd,
)
print(
f"amazon-google: {len(dataset.kg1.entities_set)}, {len(dataset.kg2.entities_set)}"
)
split_dataset(dataset, f"{base_path}/amazon-google")
def split_dblp_scholar(rnd: random.Random):
model = BootEA()
model.set_args(load_args("../OpenEA/run/args/bootea_args_15K.json"))
dataset = CsvDataset(
CsvType.articles,
f"{base_path}/dblp-scholar/DBLP1.csv",
f"{base_path}/dblp-scholar/Scholar.csv",
f"{base_path}/dblp-scholar/DBLP-Scholar_perfectMapping.csv",
model,
rnd,
)
print(
f"dblp-scholar: {len(dataset.kg1.entities_set)}, {len(dataset.kg2.entities_set)}"
)
split_dataset(dataset, f"{base_path}/dblp-scholar")
def split_dblp_acm(rnd: random.Random):
model = BootEA()
model.set_args(load_args("../OpenEA/run/args/bootea_args_15K.json"))
dataset = CsvDataset(
CsvType.articles,
f"{base_path}/dblp-acm/DBLP2.csv",
f"{base_path}/dblp-acm/ACM.csv",
f"{base_path}/dblp-acm/DBLP-ACM_perfectMapping.csv",
model,
rnd,
)
print(
f"dblp2-acm: {len(dataset.kg1.entities_set)}, {len(dataset.kg2.entities_set)}"
)
split_dataset(dataset, f"{base_path}/dblp-acm")
def test_load(self):
"""Test Load
Args:
self: TestCsvDataset
Returns:
None
Raises:
None
"""
__location__ = os.path.realpath(
os.path.join(os.getcwd(), os.path.dirname(__file__)))
dataset_csv_file_path = os.path.join(__location__, 'sample_data.csv')
csv_dataset = CsvDataset(dataset_csv_file_path, None, False)
csv_dataset.load(dataset_csv_file_path)
self.assertEqual(len(csv_dataset.get_field_names()), 18)
policy_ids = csv_dataset.get_field('policyID', np.int)
self.assertEqual(len(policy_ids), 3)
self.assertEqual(policy_ids[0], 119736)
self.assertEqual(policy_ids[1], 448094)
self.assertEqual(policy_ids[2], 206893)
state_codes = csv_dataset.get_field('statecode')
self.assertEqual(len(state_codes), 3)
self.assertEqual(state_codes[0], 'FL')
self.assertEqual(state_codes[1], 'CA')
self.assertEqual(state_codes[2], 'FL')
# test with bad dataset_csv_file_path
with self.assertRaises(PreconditionException) as context:
CsvDataset(1)
self.assertTrue('Invalid dataset_csv_file_path' in str(context.exception))
def __init__(self,
dataset_csv_file_path,
output_folder_path,
log_file_path):
"""Test Analysis
Args:
dataset_csv_file_path: absolute path to the csv file
output_folder_path: output folder path
log_file_path: path to the log file
Returns:
None
Raises:
None
"""
super(__class__, self).__init__(self.ANALYSIS_NAME, log_file_path, output_folder_path)
self.dataset_csv_file_path = os.path.abspath(dataset_csv_file_path)
self.dataset = CsvDataset(dataset_csv_file_path, self.logger)
self.logger.trace('Finished Loading Test Analysis Dataset...')