Skip to content

fix bug where the wrong param was passed into columnonehotencoder #165

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
nickotto merged 1 commit into from
Jan 6, 2025
Merged

fix bug where the wrong param was passed into columnonehotencoder #165

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
4 changes: 2 additions & 2 deletions tpot2/tpot_estimator/estimator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -581,15 +581,15 @@ def fit(self, X, y):
if self.categorical_features is not None: #if categorical features are specified, use those
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnSimpleImputer(self.categorical_features, strategy='most_frequent')))
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("numeric", strategy='mean')))
pipeline_steps.append(("ColumnOneHotEncoder", tpot2.builtin_modules.ColumnOneHotEncoder(self.categorical_features, strategy='most_frequent')))
pipeline_steps.append(("ColumnOneHotEncoder", tpot2.builtin_modules.ColumnOneHotEncoder(self.categorical_features, min_frequency=0.0001)))

else:
if isinstance(X, pd.DataFrame):
categorical_columns = X.select_dtypes(include=['object']).columns
if len(categorical_columns) > 0:
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnSimpleImputer("categorical", strategy='most_frequent')))
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("numeric", strategy='mean')))
pipeline_steps.append(("ColumnOneHotEncoder", tpot2.builtin_modules.ColumnOneHotEncoder("categorical", strategy='most_frequent')))
pipeline_steps.append(("ColumnOneHotEncoder", tpot2.builtin_modules.ColumnOneHotEncoder("categorical", min_frequency=0.0001)))
else:
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("all", strategy='mean')))
else:
Expand Down
4 changes: 2 additions & 2 deletions tpot2/tpot_estimator/steady_state_estimator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -624,15 +624,15 @@ def fit(self, X, y):
if self.categorical_features is not None: #if categorical features are specified, use those
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnSimpleImputer(self.categorical_features, strategy='most_frequent')))
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("numeric", strategy='mean')))
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnOneHotEncoder(self.categorical_features, strategy='most_frequent')))
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnOneHotEncoder(self.categorical_features, min_frequency=0.0001)))

else:
if isinstance(X, pd.DataFrame):
categorical_columns = X.select_dtypes(include=['object']).columns
if len(categorical_columns) > 0:
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnSimpleImputer("categorical", strategy='most_frequent')))
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("numeric", strategy='mean')))
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnOneHotEncoder("categorical", strategy='most_frequent')))
pipeline_steps.append(("impute_categorical", tpot2.builtin_modules.ColumnOneHotEncoder("categorical", min_frequency=0.0001)))
else:
pipeline_steps.append(("impute_numeric", tpot2.builtin_modules.ColumnSimpleImputer("all", strategy='mean')))
else:
Expand Down