Wolfram Language Paclet Repository
Community-contributed installable additions to the Wolfram Language
XGBPaclet Functionality
Here are the main functions in XGBPaclet and examples of them in action.
The function to perform XGBoost Training | |
The function to load and evaluate the XGBoost model on given data. |
More functions will be added or updated in the future versions.
Create a XGBoost Python session
A XGBoost python session is required before using XgbTrain[].
The following code shows how to create a XGBoost python session:
The following code shows how to create a XGBoost python session:
In[1]:=
[◼] | RegisterEnvironment |
Out[1]=
xgb
In[8]:=
session=
["xgb"];
[◼] | StartEnvironment |
Prepare dataset for the following examples
Create binary classification training set and validation set for the following examples
In[1]:=
binary`traindata=RandomReal[{-10,10},{100,3}];binary`testdata=RandomReal[{-10,10},{100,3}];binary`trainlabel=RandomChoice[{"a","b"},{100}];binary`testlabel=RandomChoice[{"a","b"},{100}];binary`trainset={binary`traindatabinary`trainlabel};binary`testset={binary`testdatabinary`testlabel};
How to use XgbTrain[] to train a model
Use to train a model with trainset and XGBoost python session, and store the trained model in the output session:
XgbTrain[]
In[18]:=
 | XgbTrain |
Starting the Python Prediction evaluation...
Classification task detected!
shap is not available
pandas is not available
matplotlib is imported
xgboost is imported
sklearn is imported
Auto-generated feature names : ['feat1', 'feat2', 'feat3']
Basic category parameters : {'max_depth': 3, 'eta': 1, 'objective': 'binary:logistic'} ,num_round = 5
Final parameters : {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic', 'eval_metric': ['logloss']} , num_round = 5
Start training xgb.train()
[0] train-logloss:0.63421
[1] train-logloss:0.59543
[2] train-logloss:0.55549
[3] train-logloss:0.52532
[4] train-logloss:0.50755
End of Training
How to use XgbModelPredict[] for the prediction.
XgbMeasurement[]
In[16]:=
result=
[session,binary`trainset];result["prediction"]
 | XgbMeasurement |
Classification task detected!
Starting the Python evaluation...
matplotlib is imported
xgboost is imported
sklearn is imported
Auto-generated feature names : ['feat1', 'feat2', 'feat3']
Out[17]=
{b,b,b,a,a,b,a,a,a,b,a,b,a,a,b,b,b,a,a,a,a,b,b,a,a,a,a,a,a,a,a,a,a,a,b,b,a,a,a,a,a,b,a,a,a,a,a,a,a,a,a,b,a,a,a,b,b,a,a,a,a,a,a,a,b,a,b,a,a,a,a,a,a,b,b,a,b,a,a,a,b,a,a,b,b,b,a,b,a,a,a,a,a,b,a,a,a,a,a,b}
 |
|
""