[FAQ]TypeError while creating OneHotEncoder Object

[RevathyRamalingam]

Course

machine-learning-zoomcamp

Question

Why I am getting typeError while creating OneHotEncoder Object?

Answer

If you get Type Error when categorical values are oneHotEncoded using sparse as parameter, as below then here is the reason

TypeError Traceback (most recent call last)
Cell In[60], line 4
2 scaler = StandardScaler()
3 X_train_num = scaler.fit_transform(X_train_num)
----> 4 ohe = OneHotEncoder(sparse=False)
5 X_train_cat = ohe.fit_transform(df_train[categorical_columns].values)
6 X_train_cat

This error happens because in scikit-learn ≥1.2, the OneHotEncoder no longer uses the sparse parameter. Instead, it now uses sparse_output.
So create OneHotEncoder class using spare_output as argument like below,
ohe = OneHotEncoder(sparse_output=False)

Checklist

• I have searched existing FAQs and this question is not already answered
• The answer provides accurate, helpful information
• I have included any relevant code examples or links

[alexeygrigorev]

Resolved in #23. Thank you