Skip to content

Adding support for Baseline Model #58

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

Closed
wants to merge 7 commits into from
Closed

Adding support for Baseline Model #58

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
da6d7bb
add support for baseline model
gbayomi Sep 13, 2022
2c1b3ea
WIP - Update quick baseline according to PR reviews
gustavocidornelas Sep 14, 2022
d306d5e
adding back validation df and fixing minor bugs
gbayomi Sep 14, 2022
1a60542
Add missing docstrings, update API reference, and update changelog
gustavocidornelas Sep 14, 2022
e597790
Upload dataset before training model auto-sklearn. Fail early if ther…
gustavocidornelas Sep 15, 2022
2f84830
Update Unbox -> Openlayer references for the quick baseline
gustavocidornelas Sep 28, 2022
a06a98a
Fix black formatting issues
gustavocidornelas Sep 30, 2022
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
adding back validation df and fixing minor bugs
  • Loading branch information
@gbayomi @gustavocidornelas
gbayomi authored and gustavocidornelas committed Sep 28, 2022
commit d306d5e69435b304e46263c29d75e504682780b0
24 changes: 19 additions & 5 deletions openlayer/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1213,12 +1213,13 @@ def add_baseline(
task_type: TaskType,
class_names: List[str],
label_column_name: str,
commit_message: str,
train_df: pd.DataFrame = None,
val_df: pd.DataFrame = None,
ensemble_size: int = 10,
random_seed: int = 0,
timeout: int = 60,
per_run_limit: int = None,
commit_message: Optional[str] = None,
project_id: str = None,
) -> Model:
"""Add a baseline model to the Unbox platform. You only need to specify a training set
Expand All @@ -1236,6 +1237,8 @@ def add_baseline(
E.g. `['positive', 'negative']`.
label_column_name : str
Column containing dataset labels
commit_message : str
Commit message for the model version.
train_df : pd.DataFrame, default None
Training set dataframe.
ensemble_size : int, default 10
Expand All @@ -1246,8 +1249,6 @@ def add_baseline(
Maximum time to train all the models.
per_run_limit : int, default None
Maximum time to train each model.
commit_message : str, default None
Commit message for the model version.

Returns
-------
Expand Down Expand Up @@ -1331,7 +1332,7 @@ def add_baseline(
categorical_feature_names = qb.get_categorical_feature_names(train_features_df)

# Train model
print(f"Training model for approximately {round(0.0166 * timeout, 2)} minutes")
print(f"Training model for approximately {round(0.0166 * timeout, 2)} minute(s).")
model = qb.train_auto_classifiers(
timeout=timeout,
per_run_limit=per_run_limit,
Expand All @@ -1347,6 +1348,19 @@ def add_baseline(
f.write("Automunge==8.30\n")
f.write("scikit-learn== 0.24.1")

if val_df is not None:
self.add_dataframe(
df=val_df,
task_type=task_type,
project_id=project_id,
class_names=class_names,
label_column_name=label_column_name,
commit_message=commit_message,
feature_names=col_names,
categorical_feature_names=categorical_feature_names,
)


# Upload model
model_info = self.add_model(
function=predict_proba,
Expand All @@ -1358,7 +1372,7 @@ def add_baseline(
name=f"Baseline model",
commit_message=commit_message,
feature_names=col_names,
train_sample_df=pd.sample(train_df, n=3000, random_state=random_seed),
train_sample_df=train_df.sample(n=3000, random_state=random_seed),
train_sample_label_column_name=label_column_name,
categorical_feature_names=categorical_feature_names,
requirements_txt_file="auto-requirements.txt",
Expand Down