def do(payload, config, plugin_config, inputs):
if payload["funtastic"] == "engines":
client = dataiku.api_client()
project = client.get_project(dataiku.default_project_key())
engines = project.get_settings().get_raw(
)['metrics']['engineConfig'].keys()
return {'engines': engines}
if payload["funtastic"] == "connections":
client = dataiku.api_client()
connections = client.list_connections().keys()
return {'connections': connections}
def get_dataset_flow():
client = dataiku.api_client()
project_key = dataiku.default_project_key()
project = client.get_project(project_key)
datasets = project.list_datasets()
dataset_names = [datasets[i]["name"] for i in range(len(datasets))]
return json.jsonify({"dataset_names": dataset_names})
def run(self, progress_callback):
# You should really comment your code better
# get remote key and url
remote_url = self.config.get('remote_url')
remote_key = self.config.get('remote_api')
project_key = self.project_key
# get local and remote wikis for current project
rp = dataikuapi.DSSClient(remote_url,
api_key=remote_key).get_project(project_key)
cp = dataiku.api_client().get_project(project_key)
local_wiki = cp.get_wiki()
remote_wiki = rp.get_wiki()
# replace or create new articles in the project wikis
for l_article in local_wiki.list_articles():
for r_article in remote_wiki.list_articles():
if l_article.article_id == r_article.article_id:
r_article.delete()
remote_wiki.create_article(l_article.article_id,
content=l_article.get_data().get_body())
return '<body>Wiki Updated on instance running at: ' + remote_url + '</body>'
def count_records(dataset: dataiku.Dataset) -> int:
"""
Count the number of records of a dataset using the Dataiku dataset metrics API
"""
metric_id = "records:COUNT_RECORDS"
dataset_name = dataset.name.split(".")[1]
partitions = dataset.read_partitions
client = dataiku.api_client()
project = client.get_project(dataiku.default_project_key())
logging.info("Counting records of dataset: {}".format(dataset_name))
if partitions is None or len(partitions) == 0:
project.get_dataset(dataset_name).compute_metrics(metric_ids=[metric_id])
metric = dataset.get_last_metric_values()
record_count = dataiku.ComputedMetrics.get_value_from_data(metric.get_global_data(metric_id=metric_id))
logging.info("Dataset contains {:d} records and is not partitioned".format(record_count))
else:
record_count = 0
for partition in partitions:
project.get_dataset(dataset_name).compute_metrics(partition=partition, metric_ids=[metric_id])
metric = dataset.get_last_metric_values()
record_count += dataiku.ComputedMetrics.get_value_from_data(
metric.get_partition_data(partition=partition, metric_id=metric_id)
)
logging.info("Dataset contains {:d} records in partition(s) {}".format(record_count, partitions))
return record_count
def get_token():
# Read in the existing conf
dss = dataiku.api_client()
project = dss.get_project(dataiku.default_project_key())
variables = project.get_variables()["standard"]
conf = variables.get("powerbi-settings", None)
# Decrypt
key = request.args.get("api-key")
pbi = {}
pbi["username"] = conf["username"]
pbi["password"] = decrypt_string(conf["password"], key)
pbi["client_id"] = conf["client_id"]
pbi["client_secret"] = decrypt_string(conf["client_secret"], key)
pbi["resource"] = conf["resource"]
pbi["grant_type"] = conf["grant_type"]
pbi["scope"] = conf["scope"]
# Get the token
response = requests.post(
'https://login.microsoftonline.com/common/oauth2/token', data=pbi)
o = {}
o["token"] = response.json().get("access_token")
return json.dumps(o)
def __init__(self, project_key, config, plugin_config):
"""
:param project_key: the project in which the runnable executes
:param config: the dict of the configuration of the object
:param plugin_config: contains the plugin settings
"""
self.project_key = project_key
self.config = config
self.plugin_config = plugin_config
self.Helm = Helm()
self.client = dataiku.api_client()
cluster = self.client.get_cluster(self.config.get('cluster'))
self.kubeconfig = cluster.get_settings().get_raw(
)['data']['kube_config_path']
cluster_endpoint = cluster.get_settings().get_raw(
)['data']['cluster']['Endpoint']
self.cluster_region = re.findall(r'((?:\w+-)+\w+)',
cluster_endpoint)[0]
kubernetes.config.load_kube_config(config_file=self.kubeconfig)
def get_snowflake_datasets():
project_key = default_project_key()
project = api_client().get_project(project_key)
return [
dataset for dataset in project.list_datasets()
if dataset.type == 'Snowflake'
]
def __init__(self, gds_name, devops_team):
#client object for this class to use
self.__client = dataiku.api_client()
#Validate user is allowed to do this
self.gds_name = gds_name
self.devops_team = devops_team
def do(payload, config, plugin_config, inputs):
if "method" not in payload:
return {}
client = dataiku.api_client()
if payload["method"] == "get-valid-csv-filenames":
required_columns = ["id", "className"]
sep = ","
# Retrieving model folder
model_folder_full_name = [
inp for inp in inputs if inp["role"] == "modelFolder"
][0]["fullName"]
model_folder = dataiku.Folder(model_folder_full_name).get_path()
csv_files_root_mf = glob.glob(model_folder + "/*.csv")
# Filtering out files without required columns
csv_valid_filenames = []
for f in csv_files_root_mf:
schema = retrieve_schema_from_pandas_compatible_csv_file(f, sep)
if len([col for col in required_columns
if col not in schema]) == 0:
valid_file = {"path": f, "name": os.path.basename(f)}
csv_valid_filenames.append(valid_file)
return {"csv_valid_filenames": csv_valid_filenames}
def get_folder_partition_root(folder, is_input=False):
"""Retrieve the partition root path using a dataiku.Folder.
Args:
folder (dataiku.Folder): Input or output folder of the recipe used to retrieve the partition path pattern.
is_input: True if the folder must be considered as a input, False if output
Returns:
Partition path or None if folder is not partitioned.
"""
folder_id = folder.get_id()
input_id = folder_id if is_input else None
dku_flow_variables = dataiku.get_flow_variables()
client = dataiku.api_client()
project = client.get_project(dataiku.default_project_key())
folder = project.get_managed_folder(folder_id)
folder_config = folder.get_definition()
partitioning_config = folder_config.get("partitioning")
if not partitioning_config:
return ""
file_path_pattern = partitioning_config.get("filePathPattern", None)
dimensions, types = get_dimensions(partitioning_config)
partitions = get_partitions(dku_flow_variables,
dimensions,
input_id=input_id)
file_path = complete_file_path_pattern(file_path_pattern, partitions,
dimensions, types)
file_path = complete_file_path_time_pattern(dku_flow_variables,
file_path,
input_id=input_id)
return file_path
def build_scenario(build_plan,
filter_on='ready',
connection='dataiku_workspace',
ref_table='referentialclient',
ref_project='DIReferential',
add_ecrm_context=True,
finish_on_client=None,
single_client=None):
scenario = Scenario()
if not isinstance(filter_on, list):
filter_on = [filter_on]
project_name = dataiku.default_project_key()
project_key = dataiku.api_client().get_project(project_name)
local_variables = project_key.get_variables()['local']
env = local_variables['env']
kut.display_message('reading client context referential')
executor = SQLExecutor2(connection=connection)
sql_query_referential_client = "SELECT * FROM " + '_'.join(
[env, ref_project, ref_table])
client_ref = executor.query_to_df(sql_query_referential_client)
filter_query = ' & '.join(filter_on)
client_ref = client_ref.query(filter_query) if filter_query else client_ref
kut.display_message('Client ready for automation : ' +
client_ref.clientName.unique())
kut.display_message('run configuration')
print(build_plan)
if not pd.isnull(finish_on_client):
finish_client = client_ref[client_ref.clientName == finish_on_client]
if len(finish_client) == 0:
kut.display_message(
'finish client not found in plan ' + finish_on_client +
' is the client name valid ?'
) # Example: load a DSS dataset as a Pandas dataframe
other_clients = client_ref[client_ref.clientName != finish_on_client]
client_ref = pd.concat([other_clients, finish_client],
ignore_index=True)
success = []
if single_client is not None:
requested_client = client_ref[client_ref.clientName == single_client]
if not len(single_client):
kut.display_message(
'requested single client is not found,building all allowed clients'
)
else:
client_ref = requested_client
for index, client_row in client_ref.iterrows():
variables = set_client_context(client_row=client_row,
add_ecrm_context=add_ecrm_context,
connection=connection)
client_name = variables['local']['clientName']
kut.display_message('starting builds on ' + client_name)
run_scenario(table_plan=build_plan, scenario=scenario)
success.append(client_name)
scenario.set_global_variables(successfullRun=success)
print('done_________________' + client_name)
return success
def __init__(self, project_key, config):
self.project_key = project_key
self.azure_ad_connection = config.get("azure_ad_connection", {})
self.flag_simulate = config.get("flag_simulate")
self.auth_method = self.azure_ad_connection.get("auth_method")
# Read the group configuration data from DSS
self.groups_dataset = config.get("groups_dataset", None)
if not self.groups_dataset:
raise Exception("No groups dataset has been selected.")
groups_dataset_handle = dataiku.Dataset(self.groups_dataset, self.project_key)
self.groups_df = groups_dataset_handle.get_dataframe()
self.client = dataiku.api_client()
self.run_user = self.client.get_auth_info()["authIdentifier"]
self.session = requests.Session()
# Initialize a dataframe that will contain log data
self.log_df = pd.DataFrame(columns=["date", "user", "type", "message"])
# Configure auth method
self.required_credentials = self.get_required_credentials(
self.azure_ad_connection.get("auth_method")
)
# Read credentials
if self.azure_ad_connection.get("flag_user_credentials"):
self.credentials = self.get_credentials("user")
else:
self.credentials = self.get_credentials("parameters")
# Connect to Graph API
self.set_session_headers()
def asterDo():
# Recipe inputs
main_input_name = get_input_names_for_role('main')[0]
input_dataset = dataiku.Dataset(main_input_name)
# Recipe outputs
main_output_name = get_output_names_for_role('main')[0]
output_dataset = dataiku.Dataset(main_output_name)
# Recipe function param
dss_function = get_recipe_config().get('function', None)
# Daitaiku DSS params
client = dataiku.api_client()
projectkey = main_input_name.split('.')[0]
project = client.get_project(projectkey)
try:
# output dataset
outputTable = outputtableinfo(
output_dataset.get_location_info()['info'], main_output_name,
get_recipe_config() or {})
except Exception as error:
raise RuntimeError(
"""Error obtaining connection settings for output table."""
""" Make sure connection setting is set to 'Read a database table'."""
""" This plugin only supports Aster tables.""")
# input datasets
try:
main_input_names = get_input_names_for_role('main')
inputTables = []
for inputname in main_input_names:
inconnectioninfo = dataiku.Dataset(
inputname).get_location_info()['info']
inTable = inputtableinfo(inconnectioninfo, inputname, dss_function)
inputTables.append(inTable)
except Exception as error:
raise RuntimeError(
"""Error obtaining connection settings from one of the input tables."""
""" Make sure connection setting is set to 'Read a database table'."""
""" This plugin only supports Aster tables.""")
# actual query
query = getFunctionsQuery(dss_function, inputTables, outputTable)
print('\n'.join(query))
executor = SQLExecutor2(dataset=input_dataset)
if dss_function.get('dropIfExists', False):
dropAllQuery = getDropOutputTableArgumentsStatements(
dss_function.get('arguments', []))
executor.query_to_df('END TRANSACTION;', dropAllQuery)
executor.query_to_df("END TRANSACTION;", pre_queries=query)
# write table schema
nQuery = '''SELECT * FROM {} LIMIT (1);'''.format(outputTable.tablename)
selectResult = executor.query_to_df(nQuery)
output_schema = []
for column in selectResult.columns:
output_schema.append({"name": column, "type": "string"})
output_dataset.write_schema(output_schema)
def create_sync_recipe_from_dataset(project_key, recipe_name, inp_dataset_name,
out_dataset_name, connection):
client = dataiku.api_client()
prj = dataikuapi.dss.project.DSSProject(client, project_key)
#r = SyncRecipeCreator(recipe_name, prj).with_input(inp_dataset_name).\
r = dataikuapi.dss.recipe.SingleOutputRecipeCreator( 'shaker', recipe_name, prj ).with_input(inp_dataset_name).\
with_new_output(out_dataset_name, connection, format_option_id='PARQUET_HIVE').build()
def get_cluster_from_dss_cluster(dss_cluster_id):
# get the public API client
client = dataiku.api_client()
# get the cluster object in DSS
found = False
for c in client.list_clusters():
if c['name'] == dss_cluster_id:
found = True
if not found:
raise Exception("DSS cluster %s doesn't exist" % dss_cluster_id)
dss_cluster = client.get_cluster(dss_cluster_id)
# get the settings in it
dss_cluster_settings = dss_cluster.get_settings()
dss_cluster_config = dss_cluster_settings.get_raw()['params']['config']
# resolve since we get the config with the raw preset setup
dss_cluster_config = backend_json_call(
'plugins/get-resolved-settings',
data={
'elementConfig': json.dumps(dss_cluster_config),
'elementType': dss_cluster_settings.get_raw()['type']
})
logging.info("Resolved cluster config : %s" %
json.dumps(dss_cluster_config))
# build the helper class from the cluster settings (the macro doesn't have the params)
clusters = get_cluster_from_connection_info(
dss_cluster_config['config']['connectionInfo'],
dss_cluster_config['pluginConfig']['connectionInfo'])
cluster_data = dss_cluster_settings.get_plugin_data()
return cluster_data, clusters, dss_cluster_settings, dss_cluster_config
def list_datasets():
project_key = dataiku.default_project_key()
client = dataiku.api_client()
project = client.get_project(project_key)
dataset_list = [{
"name": dataset_dict['name']
} for dataset_dict in project.list_datasets()]
return json.dumps({'dataset_list': dataset_list})
def __init__(self, project_key, config, plugin_config):
self.project_key = project_key
self.config = config
self.plugin_config = plugin_config
self.client = dataiku.api_client()
if self.config.get('all_projects'):
self.projects = self.client.list_project_keys()
else:
self.projects = [self.project_key]
def test_recipe(spark_session, scenario, src_project_key, src_recipe_key,
testbench_project_key, test_params):
# Trigger dataiku, not parquet
context.set("BIRGITTA_DATASET_STORAGE", "DATAIKU")
# Trigger dataiku, not parquet
context.set("BIRGITTA_S3_BUCKET", "birgitta_s3_bucket")
print('####################################################')
print('Test recipe: %s (in project %s)' %
(src_recipe_key, src_project_key))
if src_project_key == testbench_project_key:
raise ValueError('Cannot clone recipe to same project as src project')
print('Clone dataset schemas')
schemas = test_params['schemas']
client = dataiku.api_client()
cloned_input_datasets = schemas['inputs'].keys()
cloned_input_datasets = clone_schemas(client, src_project_key,
testbench_project_key,
cloned_input_datasets, 'Inline')
cloned_output_datasets = schemas['outputs'].keys()
cloned_output_datasets = clone_schemas(client, src_project_key,
testbench_project_key,
cloned_output_datasets, 'HDFS')
expected_output_datasets = create_expected_output_schemas(
client, src_project_key, testbench_project_key, cloned_output_datasets)
print('Clone recipe')
recipe_manage.clone(client, src_project_key,
src_recipe_key, testbench_project_key,
test_name(src_recipe_key), cloned_input_datasets,
cloned_output_datasets)
test_cases = test_params['test_cases']
for test_case in test_cases:
print('Setup test case: ' + test_case['name'])
print('Empty and fill datasets with fixtures')
empty_and_fill_datasets(testbench_project_key, cloned_input_datasets,
schemas['inputs'], test_case['inputs'])
empty_and_fill_datasets(testbench_project_key, cloned_output_datasets,
schemas['outputs'], False) # empty dataset
empty_and_fill_datasets(testbench_project_key,
expected_output_datasets,
expected_params(schemas['outputs']),
expected_params(test_case['outputs']))
print('Run recipe')
testbench_output_dataset_key = test_params['principal_output_dataset']
scenario.build_dataset(dataset_name=testbench_output_dataset_key,
project_key=testbench_project_key)
print('Validate output')
for dataset_name in test_case['outputs']:
print('Validate output dataset: %s' % (dataset_name))
validate.datasets(spark_session, dataset_name,
expected_name(dataset_name),
testbench_project_key)
print('Successfully validated output dataset: %s' % (dataset_name))
print('Delete testbench recipe TODO')
print('Delete datasets TODO')
print('Tests successful')
def set_schema(self, dataset_name, dku_dataset, schema, project_key):
dataiku_schema = dkuschema.to_dataiku(schema)
client = dataiku.api_client()
if not project_key:
project_key = dku_dataset.get_config()['projectKey']
project = dataikuapi.dss.project.DSSProject(client, project_key)
dapi_dataset = project.get_dataset(dataset_name)
ret = dapi_dataset.set_schema(dataiku_schema)
print(f"dataset.set_schema() for {dataset_name}", repr(ret))
def __init__(self, project_key, config, plugin_config):
"""
:param project_key: the project in which the runnable executes
:param config: the dict of the configuration of the object
:param plugin_config: contains the plugin settings
"""
self.project_key = project_key
self.config = config
self.plugin_config = plugin_config
self.client = dataiku.api_client()
def do(payload, config, plugin_config, inputs):
if 'method' not in payload:
return {}
client = dataiku.api_client()
if payload['method'] == 'get-fetching-functions':
return get_fetching_functions()
return {}
def run(self, progress_callback):
dss_cluster = dataiku.api_client().get_cluster(
self.config["dss_cluster_id"])
settings = dss_cluster.get_settings()
(client, cluster_id) = dku_dataproc.get_client_and_wait(settings)
client.scaleCluster(
cluster_id,
self.config["regular_worker_instances"],
numberOfSecondaryInstance=self.config["spot_worker_instances"])
return "Done"
def get_sensitive_data():
headers = dict(request.headers)
# Get the auth info of the user performing the request
auth_info = dataiku.api_client().get_auth_info_from_browser_headers(
headers)
print("User doing the query is %s" % auth_info["authIdentifier"])
# If the user's group is not TRUSTED_GROUP, raise an exception
if TRUSTED_GROUP not in auth_info["groups"]:
raise Exception("You do not belong here, go away")
else:
data = {"status": "ok", "you_are": auth_info["authIdentifier"]}
return json.dumps(data)
def do(payload, config, plugin_config, inputs):
"""
Create list of options of projects in instance.
"""
projects = dataiku.api_client().list_projects()
choices = []
for project in projects:
choices.append({
"value": project.get('projectKey'),
"label": project.get('projectKey')
})
return {"choices": choices}
def run(self, progress_callback):
dss_cluster = dataiku.api_client().get_cluster(
self.config["dss_cluster_id"])
settings = dss_cluster.get_settings()
(client, emr_cluster_id) = dku_emr.get_client_and_wait(settings)
logging.info("retrieving instance groups")
instance_groups = client.list_instance_groups(ClusterId=emr_cluster_id)
logging.info("retrieving master instance")
master_instances = client.list_instances(ClusterId=emr_cluster_id,
InstanceGroupTypes=['MASTER'],
InstanceStates=[
'AWAITING_FULFILLMENT',
'PROVISIONING',
'BOOTSTRAPPING', 'RUNNING'
])
master_instance_info = {
"privateIpAddress":
master_instances['Instances'][0]["PrivateIpAddress"]
}
logging.info("retrieving slave instances")
slave_instances = client.list_instances(
ClusterId=emr_cluster_id,
InstanceGroupTypes=['CORE', 'TASK'],
InstanceStates=[
'AWAITING_FULFILLMENT', 'PROVISIONING', 'BOOTSTRAPPING',
'RUNNING'
])
slave_instances_info = [{
"privateIpAddress": inst["PrivateIpAddress"]
} for inst in slave_instances["Instances"]]
return {
"masterInstance":
master_instance_info,
"slaveInstances":
slave_instances_info,
'instanceGroups': [{
"instanceGroupId":
x["Id"],
"runningInstanceCount":
x["RunningInstanceCount"],
"instanceType":
x["InstanceType"],
"instanceGroupType":
x["InstanceGroupType"],
"status":
x["Status"]["State"]
} for x in instance_groups["InstanceGroups"]]
}
def __init__(self, gds_name, base_ad_group):
#client object for this class to use
self.__client = dataiku.api_client()
#Validate user is allowed to do this
self.gds_name = AdminValidator(self.__client, gds_name)
assert (base_ad_group in self.__client.get_general_settings(
).settings['ldapSettings']['authorizedGroups']
), 'Whitelist the AD group first / check for ad group typos.'
self.base_ad_group = base_ad_group
self.devops_team = base_ad_group.replace('GEN-ZZ-APP-GG-ai-',
'').replace('-', '_')
def get_emr_cluster_info(dss_cluster_id):
"""Returns dictionary containing info about the EMR cluster used by a project."""
# client = client or dataiku.api_client()
# cluster_info_macro = proj.get_macro("pyrunnable_emr-clusters_get-cluster-info")
# dss_cluster_info = {'dss_cluster_id': dss_cluster_id}
# response = cluster_info_macro.get_result(cluster_info_macro.run(params=dss_cluster_info))
cluster = dataiku.api_client().get_cluster(dss_cluster_id)
cluster_settings = cluster.get_settings().settings
emr_cluster_id = cluster_settings['data']['emrClusterId']
aws_region_id = cluster_settings['params']['config']['awsRegionId']
boto_client = boto3.client('emr', region_name=aws_region_id)
instance_groups = {
g['Id']: {}
for g in boto_client.list_instance_groups(ClusterId=emr_cluster_id)
}
for gid in instance_groups.keys():
pass
dss_cluster_info = {
'dss_cluster_id': dss_cluster_id,
'emr_cluster_id': emr_cluster_id,
'instance_groups': instance_groups
}
logging.info("retrieving master instance")
master_instances = boto_client.list_instances(
ClusterId=emr_cluster_id,
InstanceGroupTypes=['MASTER'],
InstanceStates=[
'AWAITING_FULFILLMENT', 'PROVISIONING', 'BOOTSTRAPPING', 'RUNNING'
])
master_instance_info = {
"privateIpAddress": master_instances['Instances'][0]["PublicIpAddress"]
}
# if cluster_mgr_project_key is not None:
# cluster_mgr_info = client.get_project(cluster_mgr_project_key).get_variables(
# )['standard']['emr']['clusters'].get(dss_cluster_id)
# if cluster_mgr_info is not None:
# instance_groups = cluster_mgr_info['instance_groups']
# for dss_grp_info in dss_cluster_info['instanceGroups']:
# grp_id = dss_grp_info['instanceGroupId']
# cluster_mgr_grp_info = instance_groups.get(grp_id)
# if cluster_mgr_grp_info:
# dss_grp_info.update(
# {'resizable': cluster_mgr_grp_info.get('resizable', False)}
# )
return dss_cluster_info
def create_parquet_dataset(project_key,
dataset_name,
connection_name,
hive_db='default',
hive_tbl='default',
dataset_path='default'):
client = dataiku.api_client()
prj = client.get_project(project_key)
ds_formatparams = {
'parquetBlockSizeMB': 128,
'parquetCompressionMethod': 'SNAPPY',
'parquetFlavor': 'HIVE',
'parquetLowerCaseIdentifiers': False,
'representsNullFields': False
}
if hive_db == 'default':
# We use the default settings, the database is stored in ${hive_db_<CONN>}
meta_sync = True
hive_database = '${hive_db_' + connection_name + '}'
if hive_tbl == 'default':
hive_table_name = '${projectKey}_' + dataset_name
else:
hive_table_name = hive_tbl
if hive_db is None:
hive_database = None
hive_table_name = None
meta_sync = False
if dataset_path == 'default':
path = '/${projectKey}/' + dataset_name
else:
path = dataset_path
ds_params = {
u'path': path,
u'connection': connection_name,
u'notReadyIfEmpty': False,
u'metastoreSynchronizationEnabled': meta_sync,
u'hiveDatabase': hive_database,
u'hiveTableName': hive_table_name,
u'filesSelectionRules': {
u'excludeRules': [],
u'explicitFiles': [],
u'mode': u'ALL',
u'includeRules': []
},
u'timeout': 10000
}
return prj.create_dataset(dataset_name,
'HDFS',
params=ds_params,
formatType='parquet',
formatParams=ds_formatparams)
def pytest_generate_tests(metafunc):
if "scenario_id" in metafunc.fixturenames:
p_host = metafunc.config.getoption('--host')
p_api = metafunc.config.getoption('--api')
p_project = metafunc.config.getoption('--project')
dataiku.set_remote_dss(p_host, p_api)
client = dataiku.api_client()
project = client.get_project(p_project)
list_scenarios = []
for scenario in project.list_scenarios():
if scenario["id"].startswith("TEST_"):
print("Adding scenario to test :", scenario["id"])
list_scenarios.append(scenario["id"])
metafunc.parametrize("scenario_id", list_scenarios)
def __init__(self, folder_name, host="127.0.0.1", verbosity=logging.WARN):
Thread.__init__(self)
self.project_key = os.environ["DKU_CURRENT_PROJECT_KEY"]
self.folder_name = folder_name
self.client = dataiku.api_client()
logging.set_verbosity(verbosity)
# Getting app
logs_path = self.__get_logs_path()
app = self.__get_tb_app(logs_path)
# Setting server
self.srv = make_server(host, 0, app)