def test_only_score_contains_sample_weight():
mlflow.sklearn.autolog()
from sklearn.gaussian_process import GaussianProcessRegressor
assert "sample_weight" not in _get_arg_names(GaussianProcessRegressor.fit)
assert "sample_weight" in _get_arg_names(GaussianProcessRegressor.score)
mock_obj = mock.Mock()
def mock_score(self, X, y, sample_weight=None): # pylint: disable=unused-argument
mock_obj(X, y, sample_weight)
return 0
assert inspect.signature(
GaussianProcessRegressor.score) == inspect.signature(mock_score)
GaussianProcessRegressor.score = mock_score
model = GaussianProcessRegressor()
X, y = get_iris()
with mlflow.start_run() as run:
model.fit(X, y)
mock_obj.assert_called_once_with(X, y, None)
run_id = run.info.run_id
params, metrics, tags, artifacts = get_run_data(run_id)
assert params == truncate_dict(
stringify_dict_values(model.get_params(deep=True)))
assert {TRAINING_SCORE: model.score(X, y)}.items() <= metrics.items()
assert tags == get_expected_class_tags(model)
assert MODEL_DIR in artifacts
assert_predict_equal(load_model_by_run_id(run_id), model, X)
def test_call_fit_with_arguments_score_does_not_accept():
mlflow.sklearn.autolog()
from sklearn.linear_model import SGDRegressor
assert "intercept_init" in _get_arg_names(SGDRegressor.fit)
assert "intercept_init" not in _get_arg_names(SGDRegressor.score)
mock_obj = mock.Mock()
def mock_score(self, X, y, sample_weight=None): # pylint: disable=unused-argument
mock_obj(X, y, sample_weight)
return 0
assert inspect.signature(
SGDRegressor.score) == inspect.signature(mock_score)
SGDRegressor.score = mock_score
model = SGDRegressor()
X, y = get_iris()
with mlflow.start_run() as run:
model.fit(X, y, intercept_init=0)
mock_obj.assert_called_once_with(X, y, None)
run_id = run._info.run_id
params, metrics, tags, artifacts = get_run_data(run_id)
assert params == truncate_dict(
stringify_dict_values(model.get_params(deep=True)))
assert metrics == {TRAINING_SCORE: model.score(X, y)}
assert tags == get_expected_class_tags(model)
assert MODEL_DIR in artifacts
assert_predict_equal(load_model_by_run_id(run_id), model, X)
def get_input_example():
# Fetch an input example using the first several rows of the array-like
# training data supplied to the training routine (e.g., `fit()`)
fit_arg_names = _get_arg_names(estimator.fit)
X_var_name, y_var_name = fit_arg_names[:2]
input_example = _get_Xy(args, kwargs, X_var_name,
y_var_name)[0][:INPUT_EXAMPLE_SAMPLE_ROWS]
return input_example
def test_both_fit_and_score_contain_sample_weight(sample_weight_passed_as):
mlflow.sklearn.autolog()
from sklearn.linear_model import SGDRegressor
# ensure that we use an appropriate model for this test
assert "sample_weight" in _get_arg_names(SGDRegressor.fit)
assert "sample_weight" in _get_arg_names(SGDRegressor.score)
mock_obj = mock.Mock()
def mock_score(self, X, y, sample_weight=None): # pylint: disable=unused-argument
mock_obj(X, y, sample_weight)
return 0
assert inspect.signature(
SGDRegressor.score) == inspect.signature(mock_score)
SGDRegressor.score = mock_score
model = SGDRegressor()
X, y = get_iris()
sample_weight = abs(np.random.randn(len(X)))
with mlflow.start_run() as run:
if sample_weight_passed_as == "positional":
model.fit(X, y, None, None, sample_weight)
elif sample_weight_passed_as == "keyword":
model.fit(X, y, sample_weight=sample_weight)
mock_obj.assert_called_once_with(X, y, sample_weight)
run_id = run.info.run_id
params, metrics, tags, artifacts = get_run_data(run_id)
assert params == truncate_dict(
stringify_dict_values(model.get_params(deep=True)))
assert {TRAINING_SCORE: model.score(X, y)}.items() <= metrics.items()
assert tags == get_expected_class_tags(model)
assert MODEL_DIR in artifacts
assert_predict_equal(load_model_by_run_id(run_id), model, X)
def _log_posttraining_metadata(estimator, *args, **kwargs):
"""
Records metadata for a scikit-learn estimator after training has completed.
This is intended to be invoked within a patched scikit-learn training routine
(e.g., `fit()`, `fit_transform()`, ...) and assumes the existence of an active
MLflow run that can be referenced via the fluent Tracking API.
:param estimator: The scikit-learn estimator for which to log metadata.
:param args: The arguments passed to the scikit-learn training routine (e.g.,
`fit()`, `fit_transform()`, ...).
:param kwargs: The keyword arguments passed to the scikit-learn training routine.
"""
if hasattr(estimator, "score"):
try:
score_args = _get_args_for_score(estimator.score,
estimator.fit, args, kwargs)
training_score = estimator.score(*score_args)
except Exception as e: # pylint: disable=broad-except
msg = (
estimator.score.__qualname__ +
" failed. The 'training_score' metric will not be recorded. Scoring error: "
+ str(e))
_logger.warning(msg)
else:
try_mlflow_log(mlflow.log_metric, "training_score",
training_score)
# log common metrics and artifacts for estimators (classifier, regressor)
_log_specialized_estimator_content(estimator,
mlflow.active_run().info.run_id,
args, kwargs)
input_example = None
signature = None
if hasattr(estimator, "predict"):
try:
# Fetch an input example using the first several rows of the array-like
# training data supplied to the training routine (e.g., `fit()`)
SAMPLE_ROWS = 5
fit_arg_names = _get_arg_names(estimator.fit)
X_var_name, y_var_name = fit_arg_names[:2]
input_example = _get_Xy(args, kwargs, X_var_name,
y_var_name)[0][:SAMPLE_ROWS]
model_output = estimator.predict(input_example)
signature = infer_signature(input_example, model_output)
except Exception as e: # pylint: disable=broad-except
input_example = None
msg = "Failed to infer an input example and model signature: " + str(
e)
_logger.warning(msg)
try_mlflow_log(
log_model,
estimator,
artifact_path="model",
signature=signature,
input_example=input_example,
)
if _is_parameter_search_estimator(estimator):
if hasattr(estimator, "best_estimator_"):
try_mlflow_log(
log_model,
estimator.best_estimator_,
artifact_path="best_estimator",
signature=signature,
input_example=input_example,
)
if hasattr(estimator, "best_params_"):
best_params = {
"best_{param_name}".format(param_name=param_name):
param_value
for param_name, param_value in
estimator.best_params_.items()
}
try_mlflow_log(mlflow.log_params, best_params)
if hasattr(estimator, "cv_results_"):
try:
# Fetch environment-specific tags (e.g., user and source) to ensure that lineage
# information is consistent with the parent run
environment_tags = context_registry.resolve_tags()
_create_child_runs_for_parameter_search(
cv_estimator=estimator,
parent_run=mlflow.active_run(),
child_tags=environment_tags,
)
except Exception as e: # pylint: disable=broad-except
msg = (
"Encountered exception during creation of child runs for parameter search."
" Child runs may be missing. Exception: {}".format(
str(e)))
_logger.warning(msg)
try:
cv_results_df = pd.DataFrame.from_dict(
estimator.cv_results_)
_log_parameter_search_results_as_artifact(
cv_results_df,
mlflow.active_run().info.run_id)
except Exception as e: # pylint: disable=broad-except
msg = (
"Failed to log parameter search results as an artifact."
" Exception: {}".format(str(e)))
_logger.warning(msg)
