Skip to content

Allow to retrain the same project #8

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

Merged
merged 2 commits into from
Apr 16, 2022
Merged

Allow to retrain the same project #8

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5f69604
Allow to retrain the same project
levkk Apr 16, 2022
c24419e
rollbacks
levkk Apr 16, 2022
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
2 changes: 1 addition & 1 deletion pgml/pgml/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
def version():
return "0.3"
return "0.4"
32 changes: 26 additions & 6 deletions pgml/pgml/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,23 +420,43 @@ def train(
test_size (float or int, optional): If float, should be between 0.0 and 1.0 and represent the proportion of the dataset to include in the test split. If int, represents the absolute number of test samples. If None, the value is set to the complement of the train size. If train_size is also None, it will be set to 0.25.
test_sampling: (str, optional): How to sample to create the test data. Defaults to "random". Valid values are ["first", "last", "random"].
"""
project = Project.create(project_name, objective)
snapshot = Snapshot.create(relation_name, y_column_name, test_size, test_sampling)
best_model = None
best_error = None
if objective == "regression":
algorithms = ["linear", "random_forest"]
elif objective == "classification":
algorithms = ["random_forest"]
else:
raise PgMLException(
f"Unknown objective '{objective}', available options are: regression, classification"
f"Unknown objective `{objective}`, available options are: regression, classification."
)

try:
project = Project.find_by_name(project_name)
except PgMLException:
project = Project.create(project_name, objective)

if project.objective != objective:
raise PgMLException(
f"Project `{project_name}` already exists with a different objective: `{project.objective}`. Create a new project instead."
)

snapshot = Snapshot.create(relation_name, y_column_name, test_size, test_sampling)
deployed = Model.find_deployed(project.id)

# Let's assume that the deployed model is better for now.
best_model = deployed
best_error = best_model.mean_squared_error if best_model else None

for algorithm_name in algorithms:
model = Model.create(project, snapshot, algorithm_name)
model.fit(snapshot)

# Find the better model and deploy that.
if best_error is None or model.mean_squared_error < best_error:
best_error = model.mean_squared_error
best_model = model
best_model.deploy()

if deployed and deployed.id == best_model.id:
return "rolled back"
else:
best_model.deploy()
return "deployed"
4 changes: 2 additions & 2 deletions sql/install.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,9 +109,9 @@ RETURNS TABLE(project_name TEXT, objective TEXT, status TEXT)
AS $$
from pgml.model import train

train(project_name, objective, relation_name, y_column_name)
status = train(project_name, objective, relation_name, y_column_name)

return [(project_name, objective, "deployed")]
return [(project_name, objective, status)]
$$ LANGUAGE plpython3u;

---
Expand Down