def test_correlate_categories_builder(self):
builder = Wrangle.from_env('test', has_contract=False)
builder.set_persist_contract(
ConnectorContract(uri="eb://synthetic_members",
module_name='ds_engines.handlers.event_handlers',
handler='EventPersistHandler'))
df = pd.DataFrame()
df['pcp_tax_id'] = [
993406113, 133757370, 260089066, 448512481, 546434723
] * 2
correlations = [993406113, 133757370, 260089066, 448512481, 546434723]
actions = {
0: 'LABCORP OF AMERICA',
1: 'LPCH MEDICAL GROUP',
2: 'ST JOSEPH HERITAGE MEDICAL',
3: 'MONARCH HEALTHCARE',
4: 'PRIVIA MEICAL GROUP'
}
df['pcp_name'] = builder.tools.correlate_categories(
df,
header='pcp_tax_id',
correlations=correlations,
actions=actions,
column_name='pcp_name')
result = builder.tools.run_intent_pipeline(df)
self.assertEqual((10, 2), result.shape)
def setUp(self):
# clean out any old environments
for key in os.environ.keys():
if key.startswith('HADRON'):
del os.environ[key]
os.environ['HADRON_PM_PATH'] = os.path.join('work', 'config')
os.environ['HADRON_DEFAULT_PATH'] = os.path.join('work', 'data')
try:
os.makedirs(os.environ['HADRON_PM_PATH'])
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
except:
raise IOError('Unable to create directories')
PropertyManager._remove_all()
builder = SyntheticBuilder.from_env('task1', has_contract=False)
builder.set_persist()
builder.pm_persist()
tr = Transition.from_env('task2', has_contract=False)
tr.set_source_uri(builder.get_persist_contract().raw_uri)
tr.set_persist()
tr.pm_persist()
wr = Wrangle.from_env('task3', has_contract=False)
wr.set_source_uri(tr.get_persist_contract().raw_uri)
wr.set_persist()
wr.pm_persist()
def setUp(self):
# clean out any old environments
for key in os.environ.keys():
if key.startswith('HADRON'):
del os.environ[key]
# Local Domain Contract
os.environ['HADRON_PM_PATH'] = os.path.join('working', 'contracts')
os.environ['HADRON_PM_TYPE'] = 'json'
# Local Connectivity
os.environ['HADRON_DEFAULT_PATH'] = Path('working/data').as_posix()
# Specialist Component
try:
os.makedirs(os.environ['HADRON_PM_PATH'])
except:
pass
try:
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
except:
pass
PropertyManager._remove_all()
tr = Transition.from_env('task1', has_contract=False)
tr.set_source_uri(
"https://raw.githubusercontent.com/mwaskom/seaborn-data/master/titanic.csv"
)
tr.set_persist()
wr = Wrangle.from_env('task2', has_contract=False)
wr.set_source_uri(tr.get_persist_contract().raw_uri)
wr.set_persist()
controller = Controller.from_env(has_contract=False)
controller.intent_model.transition(canonical=pd.DataFrame(),
task_name='task1',
intent_level='transition')
controller.intent_model.wrangle(canonical=pd.DataFrame(),
task_name='task2',
intent_level='wrangle')
def test_repeat_iterations(self):
wr = Wrangle.from_env('task2')
wr.set_persist(
wr.pm.file_pattern(name='tester',
prefix='result1_',
file_type='parquet'))
controller = Controller.from_env()
controller.run_controller(repeat=1)
self.assertEqual(['result1_tester.parquet'], os.listdir('work/data/'))
shutil.rmtree('work/data')
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
wr.set_persist(
wr.pm.file_pattern(name='tester',
prefix='result1_',
file_type='parquet',
stamped='ns'))
controller.run_controller(repeat=3)
self.assertEqual(3, len(os.listdir('work/data/')))
shutil.rmtree('work/data')
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
controller.run_controller(repeat=2, sleep=1)
self.assertEqual(2, len(os.listdir('work/data/')))
shutil.rmtree('work/data')
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
controller.run_controller(repeat=2, sleep=1, run_time=4)
self.assertEqual(4, len(os.listdir('work/data/')))
def setUp(self):
# clean out any old environments
for key in os.environ.keys():
if key.startswith('HADRON'):
del os.environ[key]
os.environ['HADRON_PM_PATH'] = os.path.join('work', 'config')
os.environ['HADRON_DEFAULT_PATH'] = os.path.join('work', 'data')
try:
os.makedirs(os.environ['HADRON_PM_PATH'])
os.makedirs(os.environ['HADRON_DEFAULT_PATH'])
except:
pass
PropertyManager._remove_all()
tr = Transition.from_env('task1', has_contract=False)
tr.set_source_uri(
"https://raw.githubusercontent.com/mwaskom/seaborn-data/master/titanic.csv"
)
tr.set_persist()
wr = Wrangle.from_env('task2', has_contract=False)
wr.set_source_uri(tr.get_persist_contract().raw_uri)
wr.set_persist()
controller = Controller.from_env(has_contract=False)
controller.intent_model.transition(canonical=pd.DataFrame(),
task_name='task1',
intent_level='task1_tr')
controller.intent_model.wrangle(canonical=pd.DataFrame(),
task_name='task2',
intent_level='task2_wr')
def test_runs(self):
"""Basic smoke test"""
im = Wrangle.from_env('tester',
default_save=False,
default_save_intent=False,
reset_templates=False,
has_contract=False).intent_model
self.assertTrue(WrangleIntentModel, type(im))