def test_replace_true_rerun(self):
with testing.postgresql.Postgresql() as postgresql:
# create an engine and generate a table with fake feature data
engine = create_engine(postgresql.url())
ensure_db(engine)
create_schemas(
engine=engine,
features_tables=features_tables,
labels=labels,
states=states,
)
matrix_metadata = matrix_metadata_creator(state="active",
test_duration="1month",
label_name="booking")
dates = [
datetime.datetime(2016, 1, 1, 0, 0),
datetime.datetime(2016, 2, 1, 0, 0),
datetime.datetime(2016, 3, 1, 0, 0),
]
feature_dictionary = {
"features0": ["f1", "f2"],
"features1": ["f3", "f4"]
}
uuid = filename_friendly_hash(matrix_metadata)
build_args = dict(
as_of_times=dates,
label_name="booking",
label_type="binary",
feature_dictionary=feature_dictionary,
matrix_metadata=matrix_metadata,
matrix_uuid=uuid,
matrix_type="test",
)
with get_matrix_storage_engine() as matrix_storage_engine:
builder = MatrixBuilder(
db_config=db_config,
matrix_storage_engine=matrix_storage_engine,
experiment_hash=experiment_hash,
engine=engine,
replace=True,
)
builder.build_matrix(**build_args)
assert len(
matrix_storage_engine.get_store(uuid).design_matrix) == 5
assert builder.sessionmaker().query(Matrix).get(uuid)
# rerun
builder.build_matrix(**build_args)
assert len(
matrix_storage_engine.get_store(uuid).design_matrix) == 5
assert builder.sessionmaker().query(Matrix).get(uuid)
def test_train_matrix(self):
with testing.postgresql.Postgresql() as postgresql:
# create an engine and generate a table with fake feature data
engine = create_engine(postgresql.url())
ensure_db(engine)
create_schemas(
engine=engine,
features_tables=features_tables,
labels=labels,
states=states,
)
with get_matrix_storage_engine() as matrix_storage_engine:
builder = MatrixBuilder(
db_config=db_config,
matrix_storage_engine=matrix_storage_engine,
experiment_hash=experiment_hash,
engine=engine,
)
uuid = filename_friendly_hash(self.good_metadata)
builder.build_matrix(
as_of_times=self.good_dates,
label_name="booking",
label_type="binary",
feature_dictionary=self.good_feature_dictionary,
matrix_metadata=self.good_metadata,
matrix_uuid=uuid,
matrix_type="train",
)
assert len(matrix_storage_engine.get_store(uuid).design_matrix) == 5
assert builder.sessionmaker().query(Matrix).get(uuid).feature_dictionary ==self.good_feature_dictionary
def test_replace_true_rerun(self):
with testing.postgresql.Postgresql() as postgresql:
# create an engine and generate a table with fake feature data
engine = create_engine(postgresql.url())
ensure_db(engine)
create_schemas(engine=engine,
features_tables=features_tables,
labels=labels,
states=states)
matrix_metadata = matrix_metadata_creator(
state='state_one and state_two', test_duration='1month')
dates = [
datetime.datetime(2016, 1, 1, 0, 0),
datetime.datetime(2016, 2, 1, 0, 0),
datetime.datetime(2016, 3, 1, 0, 0)
]
feature_dictionary = {
'features0': ['f1', 'f2'],
'features1': ['f3', 'f4'],
}
uuid = metta.generate_uuid(matrix_metadata)
build_args = dict(as_of_times=dates,
label_name='booking',
label_type='binary',
feature_dictionary=feature_dictionary,
matrix_metadata=matrix_metadata,
matrix_uuid=uuid,
matrix_type='test')
with get_matrix_storage_engine() as matrix_storage_engine:
builder = MatrixBuilder(
db_config=db_config,
matrix_storage_engine=matrix_storage_engine,
engine=engine,
replace=True)
builder.build_matrix(**build_args)
assert len(matrix_storage_engine.get_store(uuid).matrix) == 5
assert builder.sessionmaker().query(Matrix).get(uuid)
# rerun
builder.build_matrix(**build_args)
assert len(matrix_storage_engine.get_store(uuid).matrix) == 5
assert builder.sessionmaker().query(Matrix).get(uuid)
