Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

fix: model.fit metric not collected issue. #1085

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Oct 15, 2024
Merged

fix: model.fit metric not collected issue. #1085

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
126f1a7
fix: model.fit metric not collected issue.
Genesis929 Oct 15, 2024
f343e9e
update
Genesis929 Oct 15, 2024
f97974b
Merge branch 'main' into model_fit_metric_fix
Genesis929 Oct 15, 2024
f64eba2
fix unit test
Genesis929 Oct 15, 2024
a10a547
update code and test
Genesis929 Oct 15, 2024
8e7937b
update code
Genesis929 Oct 15, 2024
70f96b0
update comment
Genesis929 Oct 15, 2024
0a40d19
update test
Genesis929 Oct 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion 4 bigframes/session/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1373,7 +1373,9 @@ def _start_query_ml_ddl(
# https://cloud.google.com/bigquery/docs/customer-managed-encryption#encrypt-model
job_config.destination_encryption_configuration = None

return bf_io_bigquery.start_query_with_client(self.bqclient, sql, job_config)
return bf_io_bigquery.start_query_with_client(
self.bqclient, sql, job_config, metrics=self._metrics
)

def _export(
self,
Expand Down
13 changes: 13 additions & 0 deletions 13 tests/system/large/ml/test_linear_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,10 +128,20 @@ def test_unordered_mode_linear_regression_configure_fit_score_predict(
]
]
y_train = df[["body_mass_g"]]

start_execution_count = df._block._expr.session._metrics.execution_count
model.fit(X_train, y_train)
end_execution_count = df._block._expr.session._metrics.execution_count
# The fit function initiates two queries: the first generates and caches
# the training data, while the second creates and fits the model.
assert end_execution_count - start_execution_count == 2

# Check score to ensure the model was fitted
start_execution_count = end_execution_count
result = model.score(X_train, y_train).to_pandas()
end_execution_count = df._block._expr.session._metrics.execution_count
assert end_execution_count - start_execution_count == 1

utils.check_pandas_df_schema_and_index(
result, columns=utils.ML_REGRESSION_METRICS, index=1
)
Expand All @@ -154,7 +164,10 @@ def test_unordered_mode_linear_regression_configure_fit_score_predict(
assert reloaded_model.max_iterations == 20
assert reloaded_model.tol == 0.01

start_execution_count = df._block._expr.session._metrics.execution_count
pred = reloaded_model.predict(df)
end_execution_count = df._block._expr.session._metrics.execution_count
assert end_execution_count - start_execution_count == 1
utils.check_pandas_df_schema_and_index(
pred,
columns=("predicted_body_mass_g",),
Expand Down
6 changes: 6 additions & 0 deletions 6 tests/system/small/ml/test_core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -383,8 +383,14 @@ def test_model_forecast(time_series_bqml_arima_plus_model: core.BqmlModel):

def test_model_register(ephemera_penguins_bqml_linear_model: core.BqmlModel):
model = ephemera_penguins_bqml_linear_model

start_execution_count = model.session._metrics.execution_count

model.register()

end_execution_count = model.session._metrics.execution_count
assert end_execution_count - start_execution_count == 1

assert model.model.model_id is not None
model_name = "bigframes_" + model.model.model_id
# Only registered model contains the field, and the field includes project/dataset. Here only check model_id.
Expand Down
1 change: 1 addition & 0 deletions 1 tests/unit/ml/test_golden_sql.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ def mock_session():
TEMP_MODEL_ID.project, TEMP_MODEL_ID.dataset_id
)
mock_session._bq_kms_key_name = None
mock_session._metrics = None

query_job = mock.create_autospec(bigquery.QueryJob)
type(query_job).destination = mock.PropertyMock(
Expand Down
Morty Proxy This is a proxified and sanitized view of the page, visit original site.