Skip to content
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’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Do Not Merge] - Test #1688

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[Do Not Merge] - Test #1688

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1,851 changes: 933 additions & 918 deletions ...tion-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

976 changes: 481 additions & 495 deletions ...-learning/classification-credit-card-fraud/auto-ml-classification-credit-card-fraud.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

1,177 changes: 589 additions & 588 deletions .../automated-machine-learning/classification-text-dnn/auto-ml-classification-text-dnn.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

77 changes: 45 additions & 32 deletions how-to-use-azureml/automated-machine-learning/classification-text-dnn/helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,52 +4,65 @@
from azureml.core.run import Run


def run_inference(test_experiment, compute_target, script_folder, train_run,
test_dataset, target_column_name, model_name):
def run_inference(
test_experiment,
compute_target,
script_folder,
train_run,
test_dataset,
target_column_name,
model_name,
):

inference_env = train_run.get_environment()

est = Estimator(source_directory=script_folder,
entry_script='infer.py',
script_params={
'--target_column_name': target_column_name,
'--model_name': model_name
},
inputs=[
test_dataset.as_named_input('test_data')
],
compute_target=compute_target,
environment_definition=inference_env)
est = Estimator(
source_directory=script_folder,
entry_script="infer.py",
script_params={
"--target_column_name": target_column_name,
"--model_name": model_name,
},
inputs=[test_dataset.as_named_input("test_data")],
compute_target=compute_target,
environment_definition=inference_env,
)

run = test_experiment.submit(
est, tags={
'training_run_id': train_run.id,
'run_algorithm': train_run.properties['run_algorithm'],
'valid_score': train_run.properties['score'],
'primary_metric': train_run.properties['primary_metric']
})

run.log("run_algorithm", run.tags['run_algorithm'])
est,
tags={
"training_run_id": train_run.id,
"run_algorithm": train_run.properties["run_algorithm"],
"valid_score": train_run.properties["score"],
"primary_metric": train_run.properties["primary_metric"],
},
)

run.log("run_algorithm", run.tags["run_algorithm"])
return run


def get_result_df(remote_run):

children = list(remote_run.get_children(recursive=True))
summary_df = pd.DataFrame(index=['run_id', 'run_algorithm',
'primary_metric', 'Score'])
summary_df = pd.DataFrame(
index=["run_id", "run_algorithm", "primary_metric", "Score"]
)
goal_minimize = False
for run in children:
if('run_algorithm' in run.properties and 'score' in run.properties):
summary_df[run.id] = [run.id, run.properties['run_algorithm'],
run.properties['primary_metric'],
float(run.properties['score'])]
if('goal' in run.properties):
goal_minimize = run.properties['goal'].split('_')[-1] == 'min'
if "run_algorithm" in run.properties and "score" in run.properties:
summary_df[run.id] = [
run.id,
run.properties["run_algorithm"],
run.properties["primary_metric"],
float(run.properties["score"]),
]
if "goal" in run.properties:
goal_minimize = run.properties["goal"].split("_")[-1] == "min"

summary_df = summary_df.T.sort_values(
'Score',
ascending=goal_minimize).drop_duplicates(['run_algorithm'])
summary_df = summary_df.set_index('run_algorithm')
"Score", ascending=goal_minimize
).drop_duplicates(["run_algorithm"])
summary_df = summary_df.set_index("run_algorithm")

return summary_df
42 changes: 25 additions & 17 deletions how-to-use-azureml/automated-machine-learning/classification-text-dnn/infer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,33 +12,39 @@

parser = argparse.ArgumentParser()
parser.add_argument(
'--target_column_name', type=str, dest='target_column_name',
help='Target Column Name')
"--target_column_name",
type=str,
dest="target_column_name",
help="Target Column Name",
)
parser.add_argument(
'--model_name', type=str, dest='model_name',
help='Name of registered model')
"--model_name", type=str, dest="model_name", help="Name of registered model"
)

args = parser.parse_args()
target_column_name = args.target_column_name
model_name = args.model_name

print('args passed are: ')
print('Target column name: ', target_column_name)
print('Name of registered model: ', model_name)
print("args passed are: ")
print("Target column name: ", target_column_name)
print("Name of registered model: ", model_name)

model_path = Model.get_model_path(model_name)
# deserialize the model file back into a sklearn model
model = joblib.load(model_path)

run = Run.get_context()
# get input dataset by name
test_dataset = run.input_datasets['test_data']
test_dataset = run.input_datasets["test_data"]

X_test_df = test_dataset.drop_columns(columns=[target_column_name]) \
.to_pandas_dataframe()
y_test_df = test_dataset.with_timestamp_columns(None) \
.keep_columns(columns=[target_column_name]) \
.to_pandas_dataframe()
X_test_df = test_dataset.drop_columns(
columns=[target_column_name]
).to_pandas_dataframe()
y_test_df = (
test_dataset.with_timestamp_columns(None)
.keep_columns(columns=[target_column_name])
.to_pandas_dataframe()
)

predicted = model.predict_proba(X_test_df)

Expand All @@ -47,11 +53,13 @@

# Use the AutoML scoring module
train_labels = model.classes_
class_labels = np.unique(np.concatenate((y_test_df.values, np.reshape(train_labels, (-1, 1)))))
class_labels = np.unique(
np.concatenate((y_test_df.values, np.reshape(train_labels, (-1, 1))))
)
classification_metrics = list(constants.CLASSIFICATION_SCALAR_SET)
scores = scoring.score_classification(y_test_df.values, predicted,
classification_metrics,
class_labels, train_labels)
scores = scoring.score_classification(
y_test_df.values, predicted, classification_metrics, class_labels, train_labels
)

print("scores:")
print(scores)
Expand Down
Loading