def test_using_deleted_database(self):
err_raised = False
print("Running the test using a stale connection... ")
self.delete_arangopipe_db()
new_admin = ArangoPipeAdmin(reuse_connection=True)
ap_config = new_admin.get_config()
try:
ap = ArangoPipe(config=ap_config)
except Exception:
print("Stale connection identified...")
print("Using a new connection...")
mscp = ManagedServiceConnParam()
conn_config = ArangoPipeConfig()
conn_params = { mscp.DB_SERVICE_HOST : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_HOST], \
mscp.DB_SERVICE_END_POINT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_END_POINT],\
mscp.DB_SERVICE_NAME : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_NAME],\
mscp.DB_SERVICE_PORT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_PORT],\
mscp.DB_CONN_PROTOCOL : self.test_cfg['arangodb'][self.mscp.DB_CONN_PROTOCOL]}
conn_config = conn_config.create_connection_config(conn_params)
admin = ArangoPipeAdmin(reuse_connection=False, config=conn_config)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
print("Using new connection to look up a non existent dataset...")
ap.lookup_dataset("non existent dataset")
self.assertFalse(err_raised)
return
def verify_install():
#mshost: "5366b66b7d19.arangodb.cloud"
config = ArangoPipeConfig()
msc = ManagedServiceConnParam()
conn_params = { msc.DB_SERVICE_HOST : "d874fc3f1fa5.arangodb.cloud", \
msc.DB_SERVICE_END_POINT : "apmdb",\
msc.DB_SERVICE_NAME : "createDB",\
msc.DB_SERVICE_PORT : 8529,\
msc.DB_CONN_PROTOCOL : 'https',\
msc.DB_NOTIFICATION_EMAIL : 'somebody@some_company.com'}
config = config.create_connection_config(conn_params)
admin = ArangoPipeAdmin(reuse_connection=False, config=config)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
ap.lookup_dataset("non existent dataset")
try:
proj_info = {"name": "Wine-Quality-Regression-Modelling"}
proj_reg = admin.register_project(proj_info)
except:
print('-' * 60)
traceback.print_exc(file=sys.stdout)
print('-' * 60)
print("Installation of Arangopipe API verified !")
return
def setUp(self):
#mshost: "5366b66b7d19.arangodb.cloud"
self.delete_users()
self.delete_arangopipe_db()
conn_config = ArangoPipeConfig()
self.test_cfg = self.get_test_config()
conn_params = { self.mscp.DB_SERVICE_HOST : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_HOST], \
self.mscp.DB_USER_NAME : self.test_cfg['arangodb'][self.mscp.DB_USER_NAME],\
self.mscp.DB_PASSWORD : self.test_cfg['arangodb'][self.mscp.DB_PASSWORD],\
self.mscp.DB_NAME : self.test_cfg['arangodb'][self.mscp.DB_NAME], \
self.mscp.DB_ROOT_USER : self.test_cfg['arangodb'][self.mscp.DB_ROOT_USER],\
self.mscp.DB_ROOT_USER_PASSWORD : self.test_cfg['arangodb'][self.mscp.DB_ROOT_USER_PASSWORD],\
self.mscp.DB_SERVICE_END_POINT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_END_POINT],\
self.mscp.DB_SERVICE_NAME : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_NAME],\
self.mscp.DB_SERVICE_PORT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_PORT],\
self.mscp.DB_CONN_PROTOCOL : self.test_cfg['arangodb'][self.mscp.DB_CONN_PROTOCOL]}
conn_config = conn_config.create_connection_config(conn_params)
self.admin = ArangoPipeAdmin(reuse_connection = False,\
config = conn_config, persist_conn= False)
return
def arango_pipe_connections(conn_params, reuse_prev_connection=True):
mdb_config = ArangoPipeConfig()
mdb_config = mdb_config.create_connection_config(conn_params)
admin = ArangoPipeAdmin(reuse_connection=reuse_prev_connection,
config=mdb_config)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
yield admin, ap
def setUp(self):
conn_config = ArangoPipeConfig()
conn_params = { self.mscp.DB_SERVICE_HOST : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_HOST], \
#self.mscp.DB_ROOT_USER : self.test_cfg['arangodb'][self.mscp.DB_ROOT_USER],\
#self.mscp.DB_ROOT_USER_PASSWORD : self.test_cfg['arangodb'][self.mscp.DB_ROOT_USER_PASSWORD],\
self.mscp.DB_SERVICE_END_POINT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_END_POINT],\
self.mscp.DB_SERVICE_NAME : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_NAME],\
self.mscp.DB_SERVICE_PORT : self.test_cfg['arangodb'][self.mscp.DB_SERVICE_PORT],\
self.mscp.DB_CONN_PROTOCOL : self.test_cfg['arangodb'][self.mscp.DB_CONN_PROTOCOL]}
conn_config = conn_config.create_connection_config(conn_params)
self.admin = ArangoPipeAdmin(reuse_connection=False,
config=conn_config)
the_config = self.admin.get_config()
self.ap = ArangoPipe(config=the_config)
self.provision_project()
return
def setUp(self):
#mshost: "5366b66b7d19.arangodb.cloud"
config = ArangoPipeConfig()
msc = ManagedServiceConnParam()
conn_params = { msc.DB_SERVICE_HOST : self.test_cfg['arangodb'][msc.DB_SERVICE_HOST], \
msc.DB_SERVICE_END_POINT : self.test_cfg['arangodb'][msc.DB_SERVICE_END_POINT],\
msc.DB_SERVICE_NAME : self.test_cfg['arangodb'][msc.DB_SERVICE_NAME],\
msc.DB_SERVICE_PORT : self.test_cfg['arangodb'][msc.DB_SERVICE_PORT],\
msc.DB_CONN_PROTOCOL : self.test_cfg['arangodb'][msc.DB_CONN_PROTOCOL],\
msc.DB_NOTIFICATION_EMAIL : 'somebody@some_company.com'}
config = config.create_connection_config(conn_params)
self.config = config
self.admin = ArangoPipeAdmin(reuse_connection = False,\
config= self.config, persist_conn= False)
ap_config = self.admin.get_config()
self.ap = ArangoPipe(config = ap_config)
self.provision_project()
return
import datetime
from arangopipe.arangopipe_storage.arangopipe_admin_api import ArangoPipeAdmin
from arangopipe.arangopipe_storage.arangopipe_config import ArangoPipeConfig
def eval_metrics(actual, pred):
rmse = np.sqrt(mean_squared_error(actual, pred))
mae = mean_absolute_error(actual, pred)
r2 = r2_score(actual, pred)
return rmse, mae, r2
if __name__ == "__main__":
warnings.filterwarnings("ignore")
np.random.seed(40)
admin = ArangoPipeAdmin(reuse_connection=True)
the_config = admin.get_config()
ap = ArangoPipe(config=the_config)
# Read the wine-quality csv file (make sure you're running this from the root of MLflow!)
wine_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"wine-quality.csv")
data = pd.read_csv(wine_path)
ds_reg = ap.lookup_dataset("wine dataset")
fs_reg = ap.lookup_featureset("wine_no_transformations")
# Split the data into training and test sets. (0.75, 0.25) split.
train, test = train_test_split(data)
# The predicted column is "quality" which is a scalar from [3, 9]
train_x = train.drop(["quality"], axis=1)
def generate_runs(clean=False):
cfg = read_data()
mscp = ManagedServiceConnParam()
#delete_users()
#delete_arangopipe_db()
conn_config = ArangoPipeConfig()
conn_params = { mscp.DB_SERVICE_HOST : cfg['arangodb'][mscp.DB_SERVICE_HOST], \
mscp.DB_USER_NAME : cfg['arangodb'][mscp.DB_USER_NAME],\
mscp.DB_PASSWORD : cfg['arangodb'][mscp.DB_PASSWORD],\
mscp.DB_NAME : cfg['arangodb'][mscp.DB_NAME], \
mscp.DB_ROOT_USER : cfg['arangodb'][mscp.DB_ROOT_USER],\
mscp.DB_ROOT_USER_PASSWORD : cfg['arangodb'][mscp.DB_ROOT_USER_PASSWORD],\
mscp.DB_SERVICE_END_POINT : cfg['arangodb'][mscp.DB_SERVICE_END_POINT],\
mscp.DB_SERVICE_NAME : cfg['arangodb'][mscp.DB_SERVICE_NAME],\
mscp.DB_SERVICE_PORT : cfg['arangodb'][mscp.DB_SERVICE_PORT],\
mscp.DB_CONN_PROTOCOL : cfg['arangodb'][mscp.DB_CONN_PROTOCOL]}
conn_config = conn_config.create_connection_config(conn_params)
admin = ArangoPipeAdmin(reuse_connection=False, config=conn_config)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
if clean:
admin.delete_arangomldb()
admin.create_db()
admin.create_enterprise_ml_graph()
proj_info = {"name": "Home_Value_Assessor"}
proj_reg = admin.register_project(proj_info)
period = period_string_generator()
ds_info = {"description": "Housing Price Data"}
featureset = data.dtypes.to_dict()
featureset = {k: str(featureset[k]) for k in featureset}
count = 1
for data_tuple in dataset_generator():
logger.info("Processing Dataset:" + str(count))
count = count + 1
aperiod = next(period)
X_train = data_tuple[0]
X_test = data_tuple[1]
y_train = data_tuple[2]
y_test = data_tuple[3]
X_val = data_tuple[4]
y_val = data_tuple[5]
alpha_random = np.random.uniform(0.0005, 0.001)
lrm = linear_model.Lasso(alpha=alpha_random)
lrm.fit(X_train, y_train)
predicted_val = lrm.predict(X_val)
(rmse, mae, r2) = eval_metrics(y_val, predicted_val)
ruuid = uuid.uuid4()
model_perf = {"rmse": rmse, "r2": r2, "mae": mae, "run_id": str(ruuid), \
"timestamp": str(dt.datetime.now())}
serving_pred = lrm.predict(X_test)
(rmse, mae, r2) = eval_metrics(y_test, serving_pred)
ex_servingperf = {"rmse": rmse, "r2": r2, "mae": mae,\
"period" : aperiod}
deployment_tag = "Deployment_HPE_" + aperiod
dataset_tag = "Housing_Dataset_" + aperiod
pipeline_tag = "Pipeline_HPE" + aperiod
feature_pipeline_tag = "Feature Pipeline HPE" + aperiod
ds_info["name"] = dataset_tag
ds_info["tag"] = dataset_tag
ds_info["source"] = "Housing Price Operational Data Store"
featureset["generated_by"] = feature_pipeline_tag
featureset["name"] = "log_transformed_house_value_" + str(ruuid)
featureset["tag"] = dataset_tag
ds_reg = ap.register_dataset(ds_info)
fs_reg = ap.register_featureset(featureset, ds_reg["_key"])
model_tag = "model_period:" + aperiod
model_name = "Housing Regression Model_" + str(ruuid)
model_info = {"name": model_name,\
"type": "LASSO regression", "tag": model_tag}
model_reg = ap.register_model(model_info,
project="Home_Value_Assessor")
model_params = {"alpha": alpha_random, "run_id": str(ruuid)}
run_info = {"dataset" : ds_reg["_key"],\
"featureset": fs_reg["_key"],\
"run_id": str(ruuid),\
"model": model_reg["_key"],\
"model-params": model_params,\
"model-perf": model_perf,\
"pipeline" : pipeline_tag,\
"project": "Housing Price Assessor",
"tag_for_deployment": True,\
"deployment_tag": deployment_tag}
ap.log_run(run_info)
admin.register_deployment(deployment_tag)
user_id = "Arangopipe Test Data Generator"
ap.log_serving_perf(ex_servingperf, deployment_tag, user_id)
print("Done loading data into the test database!")
return
def run_driver():
params = {'batch_size': 128, 'shuffle': True, 'num_workers': 6}
trng_dataset = CH_Dataset()
test_dataset = CH_Dataset(train=False)
training_generator = data.DataLoader(trng_dataset, **params)
test_generator = data.DataLoader(test_dataset, **params)
input_size = trng_dataset.input_size
output_size = trng_dataset.output_size
m = CH_LinearRegression(inputSize=input_size, outputSize=output_size)
cost_func = nn.MSELoss()
learning_rate = 0.1
optimizer = torch.optim.Adam(m.parameters(), lr=learning_rate)
all_losses = []
test_pred_list = []
test_acts_list = []
num_epochs = 100
loss_sched = {}
for e in range(num_epochs):
batch_losses = []
for ix, (Xb, yb) in enumerate(training_generator):
_X = Variable(Xb).float()
_y = Variable(yb).float()
#==========Forward pass===============
preds = m(_X)
preds = torch.flatten(preds)
loss = cost_func(preds, _y)
#==========backward pass==============
optimizer.zero_grad()
loss.backward()
optimizer.step()
batch_losses.append(loss.item())
all_losses.append(loss.item())
mbl = sqrt(np.mean(batch_losses))
if e % 5 == 0:
print("training loss: " + str(mbl))
loss_sched[e] = mbl
# prepares model for inference when trained with a dropout layer
# print(m.training)
# m.eval()
# print(m.training)
test_batch_losses = []
test_pred_list = []
test_acts_list = []
for _X, _y in test_generator:
_X = Variable(_X).float()
_y = Variable(_y).float()
#apply model
test_preds = m(_X)
test_preds = torch.flatten(test_preds)
test_loss = cost_func(test_preds, _y)
test_pred_list.extend(test_preds.detach().numpy().ravel())
test_acts_list.extend(_y.numpy().ravel())
test_batch_losses.append(test_loss.item())
# print("Batch loss: {}".format(test_loss.item()))
tmbl = sqrt(np.mean(test_batch_losses))
print("test loss: " + str(tmbl))
# Store experiment results in Arangopipe
conn_config = ArangoPipeConfig()
msc = ManagedServiceConnParam()
test_cfg = get_test_config()
conn_params = { msc.DB_SERVICE_HOST : test_cfg['arangodb'][msc.DB_SERVICE_HOST], \
msc.DB_SERVICE_END_POINT : test_cfg['arangodb'][msc.DB_SERVICE_END_POINT],\
msc.DB_SERVICE_NAME : test_cfg['arangodb'][msc.DB_SERVICE_NAME],\
msc.DB_SERVICE_PORT : test_cfg['arangodb'][msc.DB_SERVICE_PORT],\
msc.DB_CONN_PROTOCOL : test_cfg['arangodb'][msc.DB_CONN_PROTOCOL]}
# conn_params = { msc.DB_SERVICE_HOST : "localhost", \
# msc.DB_SERVICE_END_POINT : "apmdb",\
# msc.DB_SERVICE_NAME : "createDB",\
# msc.DB_SERVICE_PORT : 8529,\
# msc.DB_CONN_PROTOCOL : 'http',\
# msc.DB_NOTIFICATION_EMAIL : 'somebody@some_company.com'}
conn_config = conn_config.create_connection_config(conn_params)
proj_info = {"name": "Housing_Price_Estimation_Project"}
admin = ArangoPipeAdmin(reuse_connection=False, config=conn_config)
proj_reg = admin.register_project(proj_info)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
ruuid = str(uuid.uuid4().int)
model_name = "pytorch-linear-reg" + "_dev_run_" + ruuid
model_info = {"name": model_name, "type": "model-development"}
model_reg = ap.register_model(model_info,
project="Housing_Price_Estimation_Project")
ds_info = trng_dataset.get_dataset()
ds_reg = ap.register_dataset(ds_info)
fs = trng_dataset.get_featureset()
fs_reg = ap.register_featureset(fs, ds_reg["_key"])
model_params = {"optimizer": "Adam", "training_epochs": 100,\
"batch_size": 128, "learning_rate": learning_rate,\
"run_id": ruuid}
model_perf = {"training_loss_schedule": jsonpickle.encode(loss_sched),\
"run_id": ruuid, "timestamp": str(datetime.datetime.now())}
run_tag = "Housing-Price-Pytorch-Experiment" + "_dev_run_" + ruuid
run_info = {"dataset" : ds_reg["_key"],\
"featureset": fs_reg["_key"],\
"run_id": ruuid,\
"model": model_reg["_key"],\
"model-params": model_params,\
"model-perf": model_perf,\
"tag": run_tag,\
"project": "Housing Price Estimation Project"}
ap.log_run(run_info)
mp = ap.lookup_modelperf(run_tag)
print(
"A look up of the loss schedule for this experiment in Arangopipe yields:"
)
print(str(mp["training_loss_schedule"]))
return
return rmse, mae, r2
if __name__ == "__main__":
proj_info = {"name": "Wine-Quality-Regression-Modelling"}
conn_config = ArangoPipeConfig()
msc = ManagedServiceConnParam()
conn_params = { msc.DB_SERVICE_HOST : "localhost", \
msc.DB_SERVICE_END_POINT : "apmdb",\
msc.DB_SERVICE_NAME : "createDB",\
msc.DB_SERVICE_PORT : 8529,
msc.DB_CONN_PROTOCOL : 'http'}
conn_config = conn_config.create_connection_config(conn_params)
admin = ArangoPipeAdmin(reuse_connection=False, config=conn_config)
proj_reg = admin.register_project(proj_info)
warnings.filterwarnings("ignore")
np.random.seed(40)
ap_config = admin.get_config()
ap = ArangoPipe(config=ap_config)
# Read the wine-quality csv file (make sure you're running this from the root of MLflow!)
wine_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"wine-quality.csv")
data = pd.read_csv(wine_path)
ds_info = {"name" : "wine dataset",\
"description": "Wine quality ratings","source": "UCI ML Repository" }
ds_reg = ap.register_dataset(ds_info)
featureset = data.dtypes.to_dict()