def test_log_metadata_successfully(self):
ws1 = metadata.Workspace(backend_url_prefix="127.0.0.1:8080",
name="ws_1",
description="a workspace for testing",
labels={"n1": "v1"})
r = metadata.Run(
workspace=ws1,
name="first run",
description="first run in ws_1",
)
data_set = r.log(
metadata.DataSet(description="an example data",
name="mytable-dump",
owner="*****@*****.**",
uri="file://path/to/dataset",
version="v1.0.0",
query="SELECT * FROM mytable"))
assert data_set.id
metrics = r.log(
metadata.Metrics(
name="MNIST-evaluation",
description=
"validating the MNIST model to recognize handwritten digits",
owner="*****@*****.**",
uri="gcs://my-bucket/mnist-eval.csv",
data_set_id="123",
model_id="12345",
metrics_type=metadata.Metrics.VALIDATION,
values={"accuracy": 0.95},
labels={"mylabel": "l1"}))
assert metrics.id
model = r.log(
metadata.Model(name="MNIST",
description="model to recognize handwritten digits",
owner="*****@*****.**",
uri="gcs://my-bucket/mnist",
model_type="neural network",
training_framework={
"name": "tensorflow",
"version": "v1.0"
},
hyperparameters={
"learning_rate": 0.5,
"layers": [10, 3, 1],
"early_stop": True
},
version="v0.0.1",
labels={"mylabel": "l1"}))
assert model.id
self.assertTrue(len(ws1.list()) > 0)
self.assertTrue(len(ws1.list(metadata.Model.ARTIFACT_TYPE_NAME)) > 0)
self.assertTrue(len(ws1.list(metadata.Metrics.ARTIFACT_TYPE_NAME)) > 0)
self.assertTrue(len(ws1.list(metadata.DataSet.ARTIFACT_TYPE_NAME)) > 0)
def log_dataset_info(ws, ws_run, data_uri):
exec1 = metadata.Execution(
name="execution" + datetime.utcnow().isoformat("T"),
workspace=ws,
run=ws_run,
description="copy action",
)
_ = exec1.log_input(
metadata.DataSet(description="gh summarization data",
name="gh-summ-data",
owner="*****@*****.**",
uri=data_uri,
version="v1.0.0"))
def test_log_metadata_successfully_with_minimum_information(self):
ws1 = metadata.Workspace(backend_url_prefix="127.0.0.1:8080", name="ws_1")
r = metadata.Run(workspace=ws1, name="first run")
e = metadata.Execution(name="test execution", workspace=ws1, run=r)
self.assertIsNotNone(e.id)
data_set = e.log_input(
metadata.DataSet(name="mytable-dump", uri="file://path/to/dataset"))
self.assertIsNotNone(data_set.id)
metrics = e.log_output(
metadata.Metrics(name="MNIST-evaluation",
uri="gcs://my-bucket/mnist-eval.csv"))
self.assertIsNotNone(metrics.id)
model = e.log_output(
metadata.Model(name="MNIST", uri="gcs://my-bucket/mnist"))
self.assertIsNotNone(model.id)
minioClient = Minio(minio_endpoint,
access_key=minio_key,
secret_key=minio_secret,
secure=False)
minioClient.fget_object('data', 'recommender/users.csv', '/tmp/users.csv')
customers = pd.read_csv('/tmp/users.csv')
minioClient.fget_object('data', 'recommender/transactions.csv',
'/tmp/transactions.csv')
transactions = pd.read_csv('/tmp/transactions.csv')
#Log experiment data set
data_set = exec.log_input(
metadata.DataSet(
description="recommender current transactions and customers",
name="Current transactions and customers",
version=execTime,
uri="minio:/tmp/transactions.csv; minio:/tmp/users.csv"))
# In[6]:
print(customers.shape)
customers.head()
# In[7]:
print(transactions.shape)
transactions.head()
# # 3 Data preparation
#
def test_log_metadata_successfully(self):
ws1 = metadata.Workspace(
backend_url_prefix="127.0.0.1:8080",
name="ws_1",
description="a workspace for testing",
labels={"n1": "v1"})
r = metadata.Run(
workspace=ws1,
name="first run",
description="first run in ws_1",
)
e = metadata.Execution(
name="test execution",
workspace=ws1,
run=r,
description="an execution",
)
self.assertIsNotNone(e.id)
data_set = e.log_input(
metadata.DataSet(
description="an example data",
name="mytable-dump",
owner="*****@*****.**",
uri="file://path/to/dataset",
version="v1.0.0",
query="SELECT * FROM mytable"))
self.assertIsNotNone(data_set.id)
metrics = e.log_output(
metadata.Metrics(
name="MNIST-evaluation",
description="validating the MNIST model to recognize handwritten digits",
owner="*****@*****.**",
uri="gcs://my-bucket/mnist-eval.csv",
data_set_id="123",
model_id="12345",
metrics_type=metadata.Metrics.VALIDATION,
values={"accuracy": 0.95},
labels={"mylabel": "l1"}))
self.assertIsNotNone(metrics.id)
model = e.log_output(
metadata.Model(
name="MNIST",
description="model to recognize handwritten digits",
owner="*****@*****.**",
uri="gcs://my-bucket/mnist",
model_type="neural network",
training_framework={
"name": "tensorflow",
"version": "v1.0"
},
hyperparameters={
"learning_rate": 0.5,
"layers": [10, 3, 1],
"early_stop": True
},
version="v0.0.1",
labels={"mylabel": "l1"}))
self.assertIsNotNone(model.id)
# Test listing artifacts in a workspace
self.assertTrue(len(ws1.list()) > 0)
self.assertTrue(len(ws1.list(metadata.Model.ARTIFACT_TYPE_NAME)) > 0)
self.assertTrue(len(ws1.list(metadata.Metrics.ARTIFACT_TYPE_NAME)) > 0)
self.assertTrue(len(ws1.list(metadata.DataSet.ARTIFACT_TYPE_NAME)) > 0)
# Test lineage tracking.
output_events = ws1.client.list_events2(model.id).events
assert len(output_events) == 1
execution_id = output_events[0].execution_id
assert execution_id == e.id
all_events = ws1.client.list_events(execution_id).events
assert len(all_events) == 3
)
exec = metadata.Execution(
name="execution" + datetime.utcnow().isoformat("T"),
workspace=ws1,
run=r,
description="execution example",
)
# Log data set, model and its evaluation
# In[3]:
data_set = exec.log_input(
metadata.DataSet(description="an example data",
name="mytable-dump",
owner="*****@*****.**",
uri="file://path/to/dataset",
version="v1.0.0",
query="SELECT * FROM mytable"))
model = exec.log_output(
metadata.Model(name="MNIST",
description="model to recognize handwritten digits",
owner="*****@*****.**",
uri="gcs://my-bucket/mnist",
model_type="neural network",
training_framework={
"name": "tensorflow",
"version": "v1.0"
},
hyperparameters={
"learning_rate": 0.5,
"layers": [10, 3, 1],