Boilerplate reduction: Notebook template (#1204)

* Reduced notebook boilerplate

* Fixed lint issues

* Added unique suffix note

* Added unique string processor and moved tests to own folder

* Fixed broken link

* Added message about updating links

* Fixed typo

* Added missing import

* Added back useful instructions

* Addressed comments

* Removed matching engine

* Fixed comments
This commit is contained in:
Ivan Cheung
2022-11-08 14:10:50 -05:00
committed by GitHub
parent b7d98d6f9a
commit 35d71b410e
7 changed files with 239 additions and 462 deletions
@@ -38,7 +38,7 @@ from utils import NotebookProcessors, util
# A buffer so that workers finish before the orchestrating job
WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
PYTHON_VERSION = "3.9" # Set default python version
PYTHON_VERSION = "3.9" # Set default python version
def format_timedelta(delta: datetime.timedelta) -> str:
@@ -102,6 +102,7 @@ def _process_notebook(
"VPC_NETWORK": variable_vpc_network,
},
)
unique_strings_preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
# Use no-execute preprocessor
(
@@ -127,13 +128,15 @@ def _get_notebook_python_version(notebook_path: str) -> str:
src = file.read()
nb_json = json.loads(src)
#Iterate over the cells in the ipynb
for cell in nb_json['cells']:
if cell['cell_type'] == 'markdown':
markdown = str.join('', cell['source'])
# Iterate over the cells in the ipynb
for cell in nb_json["cells"]:
if cell["cell_type"] == "markdown":
markdown = str.join("", cell["source"])
# Look for the python version specification pattern
re_match = re.search('python version = (\d\.\d)', markdown, flags=re.IGNORECASE)
re_match = re.search(
"python version = (\d\.\d)", markdown, flags=re.IGNORECASE
)
if re_match:
# get the version number
python_version = re_match.group(1)
@@ -201,7 +204,9 @@ def process_and_execute_notebook(
operation = None
try:
# Get the python version for running the notebook if specified
notebook_exec_python_version = _get_notebook_python_version(notebook_path=notebook)
notebook_exec_python_version = _get_notebook_python_version(
notebook_path=notebook
)
print(f"Running notebook with python {notebook_exec_python_version}")
# Pre-process notebook by substituting variable names
@@ -230,7 +235,7 @@ def process_and_execute_notebook(
private_pool_id=private_pool_id,
private_pool_region=variable_region,
timeout_in_seconds=timeout_in_seconds,
python_version=notebook_exec_python_version
python_version=notebook_exec_python_version,
)
operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
@@ -443,7 +448,7 @@ def process_and_execute_notebooks(
result.log_url,
result.output_uri,
result.output_uri_web,
result.logs_bucket
result.logs_bucket,
]
for result in results_sorted
],
@@ -454,34 +459,34 @@ def process_and_execute_notebooks(
"log_url",
"output_uri",
"output_uri_web",
"logs_bucket"
"logs_bucket",
],
)
)
if len(notebooks) == 1:
print("="*100)
print("The notebook execution build log:\n")
print("="*100)
print("=" * 100)
print("The notebook execution build log:\n")
print("=" * 100)
build_id = results_sorted[0].build_id
logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
log_file_name = f"log-{build_id}.txt"
build_id = results_sorted[0].build_id
logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
log_file_name = f"log-{build_id}.txt"
log_contents = util.download_blob_into_memory(
bucket_name=logs_bucket_name,
blob_name=log_file_name,
download_as_text=True
log_contents = util.download_blob_into_memory(
bucket_name=logs_bucket_name,
blob_name=log_file_name,
download_as_text=True,
)
# Remove extra steps from the log
match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
# Remove extra steps from the log
match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
if match is not None:
match_index = match.span()[0]
print(log_contents[match_index:])
else:
print(log_contents)
if match is not None:
match_index = match.span()[0]
print(log_contents[match_index:])
else:
print(log_contents)
print("\n=== END RESULTS===\n")
-1
View File
@@ -2,5 +2,4 @@ notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb
notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb
notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb
notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
.cloud-build/tests/python_version_test.ipynb
+29
View File
@@ -14,6 +14,8 @@
# limitations under the License.
from typing import Dict
import random
import string
from nbconvert.preprocessors import Preprocessor
@@ -63,3 +65,30 @@ class UpdateVariablesPreprocessor(Preprocessor):
executable_cells.append(cell)
notebook.cells = executable_cells
return notebook, resources
# Generate a uuid of a specifed length
def generate_uuid(length: int = 8) -> str:
return "".join(random.choices(string.ascii_lowercase + string.digits, k=length))
class UniqueStringsPreprocessor(Preprocessor):
# A preprocessor that replaces strings that end with "-unique" with a uuid.
@staticmethod
def update_unique_strings(content: str):
# Replace strings that end with "-unique" with a uuid.
return content.replace('-unique"', f'-{generate_uuid()}"')
def preprocess(self, notebook, resources=None):
executable_cells = []
for cell in notebook.cells:
if cell.cell_type == "code":
cell.source = self.update_unique_strings(
content=cell.source,
)
executable_cells.append(cell)
notebook.cells = executable_cells
return notebook, resources
@@ -40,65 +40,3 @@ def get_updated_value(content: str, variable_name: str, variable_value: str) ->
content,
flags=re.M,
)
def test_update_value():
new_content = get_updated_value(
content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert (
new_content
== 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
)
def test_update_value_single_quotes():
new_content = get_updated_value(
content="PROJECT_ID = '[your-project-id]'",
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert new_content == "PROJECT_ID = 'sample-project'"
def test_update_value_avoidance():
new_content = get_updated_value(
content="PROJECT_ID = shell_output[0] ",
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert new_content == "PROJECT_ID = shell_output[0] "
def test_region():
new_content = get_updated_value(
content='REGION = "[your-region]" # @param {type:"string"}',
variable_name="REGION",
variable_value="us-central1",
)
assert new_content == 'REGION = "us-central1" # @param {type:"string"}'
def test_region_equal_equals_ignore():
# Tests that == is ignored
new_content = get_updated_value(
content='REGION == "[your-region]" # @param {type:"string"}',
variable_name="REGION",
variable_value="us-central1",
)
assert new_content == 'REGION == "[your-region]" # @param {type:"string"}'
def test_service_account():
# Tests that == is ignored
new_content = get_updated_value(
content='SERVICE_ACCOUNT = "[your-service-account]" # @param {type:"string"}',
variable_name="SERVICE_ACCOUNT",
variable_value="12345-compute@developer.gserviceaccount.com",
)
assert (
new_content
== 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com" # @param {type:"string"}'
)
@@ -0,0 +1,14 @@
from utils import NotebookProcessors
def test_update_value():
# Test that the content was updated
preprocessor = NotebookProcessors.UniqueStringsPreprocessor()
content = 'PROJECT_ID = "your-project-id-unique"'
new_content = preprocessor.update_unique_strings(content)
assert new_content != content
assert new_content.startswith('PROJECT_ID = "your-project-id-')
assert new_content.endswith('"')
@@ -0,0 +1,63 @@
from utils import UpdateNotebookVariables
def test_update_value():
new_content = UpdateNotebookVariables.get_updated_value(
content='asdf\nPROJECT_ID = "[your-project-id]" #@param {type:"string"} \nasdf',
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert (
new_content
== 'asdf\nPROJECT_ID = "sample-project" #@param {type:"string"} \nasdf'
)
def test_update_value_single_quotes():
new_content = UpdateNotebookVariables.get_updated_value(
content="PROJECT_ID = '[your-project-id]'",
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert new_content == "PROJECT_ID = 'sample-project'"
def test_update_value_avoidance():
new_content = UpdateNotebookVariables.get_updated_value(
content="PROJECT_ID = shell_output[0] ",
variable_name="PROJECT_ID",
variable_value="sample-project",
)
assert new_content == "PROJECT_ID = shell_output[0] "
def test_region():
new_content = UpdateNotebookVariables.get_updated_value(
content='REGION = "[your-region]" # @param {type:"string"}',
variable_name="REGION",
variable_value="us-central1",
)
assert new_content == 'REGION = "us-central1" # @param {type:"string"}'
def test_region_equal_equals_ignore():
# Tests that == is ignored
new_content = UpdateNotebookVariables.get_updated_value(
content='REGION == "[your-region]" # @param {type:"string"}',
variable_name="REGION",
variable_value="us-central1",
)
assert new_content == 'REGION == "[your-region]" # @param {type:"string"}'
def test_service_account():
# Tests that == is ignored
new_content = UpdateNotebookVariables.get_updated_value(
content='SERVICE_ACCOUNT = "[your-service-account]" # @param {type:"string"}',
variable_name="SERVICE_ACCOUNT",
variable_value="12345-compute@developer.gserviceaccount.com",
)
assert (
new_content
== 'SERVICE_ACCOUNT = "12345-compute@developer.gserviceaccount.com" # @param {type:"string"}'
)