Upload dataset before training model auto-sklearn. Fail early if there are issues with the dataset

Author: gustavocidornelas

examples/tabular-classification/sklearn/churn-classifier/churn-classifier-sklearn.ipynb

@@ -430,7 +430,7 @@
  "name": "python",
  "nbconvert_exporter": "python",
  "pygments_lexer": "ipython3",
- "version": "3.7.13"
+ "version": "3.8.13"
  }
  },
  "nbformat": 4,

unboxapi/__init__.py

@@ -1332,6 +1332,19 @@ def add_baseline(
  col_names = qb.column_names
  categorical_feature_names = qb.get_categorical_feature_names(train_features_df)
 
+ # Upload the validation set -- if there are issues, it's better to fail prior to model training
+ 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,
+ )
+
  # Train model
  print(
  f"Training model for approximately {round(0.0166 * timeout, 2)} minute(s)."
@@ -1347,22 +1360,10 @@ def add_baseline(
 
  # Create requirements file
  filename = "auto-requirements.txt"
- with open("auto-requirements.txt", "w") as f:
+ with open(filename, "w") as f:
  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,