def connect(self):
self._connected = True
try:
if client.base.Client.REST_ENDPOINT not in os.environ:
if os.path.exists("/dbfs/"):
# databricks
client.init(
"external",
self._host,
self._port,
self._project,
self._region_name,
self._secrets_store,
self._hostname_verification,
os.path.join("/dbfs", self._trust_store_path)
if self._trust_store_path is not None else None,
os.path.join("/dbfs", self._cert_folder),
os.path.join("/dbfs", self._api_key_file)
if self._api_key_file is not None else None,
self._api_key_value,
)
engine.init("spark")
else:
# aws
client.init(
"external",
self._host,
self._port,
self._project,
self._region_name,
self._secrets_store,
self._hostname_verification,
self._trust_store_path,
self._cert_folder,
self._api_key_file,
self._api_key_value,
)
engine.init(
"hive",
self._host,
self._cert_folder,
self._project,
client.get_instance()._cert_key,
)
else:
client.init("hopsworks")
engine.init("spark")
self._feature_store_api = feature_store_api.FeatureStoreApi()
self._project_api = project_api.ProjectApi()
self._hosts_api = hosts_api.HostsApi()
self._services_api = services_api.ServicesApi()
except (TypeError, ConnectionError):
self._connected = False
raise
print("Connected. Call `.close()` to terminate connection gracefully.")
def connect(self):
"""Instantiate the connection.
Creating a `Connection` object implicitly calls this method for you to
instantiate the connection. However, it is possible to close the connection
gracefully with the `close()` method, in order to clean up materialized
certificates. This might be desired when working on external environments such
as AWS SageMaker. Subsequently you can call `connect()` again to reopen the
connection.
!!! example
```python
import hsfs
conn = hsfs.connection()
conn.close()
conn.connect()
```
"""
self._connected = True
try:
# determine engine, needed to init client
if (self._engine is not None and self._engine.lower() == "spark") or (
self._engine is None and importlib.util.find_spec("pyspark")
):
self._engine = "spark"
elif (self._engine is not None and self._engine.lower() == "hive") or (
self._engine is None and not importlib.util.find_spec("pyspark")
):
self._engine = "hive"
else:
raise ConnectionError(
"Engine you are trying to initialize is unknown. "
"Supported engines are `'spark'` and `'hive'`."
)
# init client
if client.base.Client.REST_ENDPOINT not in os.environ:
client.init(
"external",
self._host,
self._port,
self._project,
self._engine,
self._region_name,
self._secrets_store,
self._hostname_verification,
self._trust_store_path,
self._cert_folder,
self._api_key_file,
self._api_key_value,
)
else:
client.init("hopsworks")
# init engine
engine.init(self._engine)
self._feature_store_api = feature_store_api.FeatureStoreApi()
self._project_api = project_api.ProjectApi()
self._hosts_api = hosts_api.HostsApi()
self._services_api = services_api.ServicesApi()
except (TypeError, ConnectionError):
self._connected = False
raise
print("Connected. Call `.close()` to terminate connection gracefully.")
def connect(self):
"""Instantiate the connection.
Creating a `Connection` object implicitly calls this method for you to
instantiate the connection. However, it is possible to close the connection
gracefully with the `close()` method, in order to clean up materialized
certificates. This might be desired when working on external environments such
as AWS SageMaker. Subsequently you can call `connect()` again to reopen the
connection.
!!! example
```python
import hsfs
conn = hsfs.connection()
conn.close()
conn.connect()
```
"""
self._connected = True
try:
if client.base.Client.REST_ENDPOINT not in os.environ:
if os.path.exists("/dbfs/"):
# databricks
client.init(
"external",
self._host,
self._port,
self._project,
self._region_name,
self._secrets_store,
self._hostname_verification,
os.path.join("/dbfs", self._trust_store_path)
if self._trust_store_path is not None else None,
os.path.join("/dbfs", self._cert_folder),
os.path.join("/dbfs", self._api_key_file)
if self._api_key_file is not None else None,
self._api_key_value,
)
engine.init("spark")
else:
# aws
client.init(
"external",
self._host,
self._port,
self._project,
self._region_name,
self._secrets_store,
self._hostname_verification,
self._trust_store_path,
self._cert_folder,
self._api_key_file,
self._api_key_value,
)
engine.init(
"hive",
self._host,
self._cert_folder,
self._project,
client.get_instance()._cert_key,
)
else:
client.init("hopsworks")
engine.init("spark")
self._feature_store_api = feature_store_api.FeatureStoreApi()
self._project_api = project_api.ProjectApi()
self._hosts_api = hosts_api.HostsApi()
self._services_api = services_api.ServicesApi()
except (TypeError, ConnectionError):
self._connected = False
raise
print("Connected. Call `.close()` to terminate connection gracefully.")