Passing categorical data to Sklearn Decision Tree

by

(This is just a reformat of my comment above from 2016…it still holds true.)

The accepted answer for this question is misleading.

As it stands, sklearn decision trees do not handle categorical data – see issue #5442.

The recommended approach of using Label Encoding converts to integers which the DecisionTreeClassifier() will treat as numeric. If your categorical data is not ordinal, this is not good – you’ll end up with splits that do not make sense.

Using a OneHotEncoder is the only current valid way, allowing arbitrary splits not dependent on the label ordering, but is computationally expensive.

More Related Contents:

  1. How to extract the decision rules from scikit-learn decision-tree?
  2. Why is Random Forest with a single tree much better than a Decision Tree classifier?
  3. confused about random_state in decision tree of scikit learn
  4. sklearn error ValueError: Input contains NaN, infinity or a value too large for dtype(‘float64’)
  5. ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject
  6. Save classifier to disk in scikit-learn
  7. Accuracy Score ValueError: Can’t Handle mix of binary and continuous target
  8. where to put freeze_support() in a Python script?
  9. How to normalize a NumPy array to a unit vector?
  10. How to do n-D distance and nearest neighbor calculations on numpy arrays
  11. Is there a library function for Root mean square error (RMSE) in python?
  12. How to get precision, recall and f-measure from confusion matrix in Python [duplicate]
  13. How to convert a Scikit-learn dataset to a Pandas dataset
  14. Custom transformer for sklearn Pipeline that alters both X and y
  15. Scikit Learn SVC decision_function and predict
  16. RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility
  17. Save MinMaxScaler model in sklearn
  18. sklearn plot confusion matrix with labels
  19. confusion matrix error “Classification metrics can’t handle a mix of multilabel-indicator and multiclass targets”
  20. Using explicit (predefined) validation set for grid search with sklearn
  21. LabelEncoder: TypeError: ‘>’ not supported between instances of ‘float’ and ‘str’
  22. What are the pros and cons between get_dummies (Pandas) and OneHotEncoder (Scikit-learn)?
  23. Run an OLS regression with Pandas Data Frame
  24. How to upgrade scikit-learn package in anaconda
  25. sklearn pipeline – how to apply different transformations on different columns
  26. How to compute precision, recall, accuracy and f1-score for the multiclass case with scikit learn?
  27. What are the different use cases of joblib versus pickle?
  28. Using Smote with Gridsearchcv in Scikit-learn
  29. Does GridSearchCV perform cross-validation?
  30. Python import error: cannot import name ‘six’ from ‘sklearn.externals’

Leave a Comment