fit a xgboost regressor with gridsearch over parameters in python

To fit an XGBoost regressor with grid search over parameters in Python, you can use the GridSearchCV class from the sklearn library. Here's an example of how you can do it:

First, import the necessary libraries:

main.py
import xgboost as xgb
from sklearn.model_selection import GridSearchCV
71 chars
3 lines

Next, define the XGBoost regressor and the parameter grid:

main.py
xgb_regressor = xgb.XGBRegressor()

param_grid = {
    'max_depth': [3, 5, 7],
    'learning_rate': [0.1, 0.01, 0.001],
    'n_estimators': [100, 500, 1000]
}
159 chars
8 lines

Then, create the GridSearchCV object and fit it to your data:

main.py
grid_search = GridSearchCV(estimator=xgb_regressor, param_grid=param_grid, cv=3, scoring='neg_mean_squared_error')
grid_search.fit(X_train, y_train)
149 chars
3 lines

In the code above, X_train and y_train are your input features and target variables, respectively. The cv parameter specifies the number of cross-validation folds, and scoring indicates the evaluation metric you want to use.

Finally, you can access the best estimator and its parameters:

main.py
best_estimator = grid_search.best_estimator_
best_params = grid_search.best_params_
84 chars
3 lines

The best_estimator variable holds the trained XGBoost regressor with the best combination of parameters found during grid search, and best_params contains the best parameters selected by the grid search.

Note: Make sure you have the xgboost library installed in your Python environment before running this code. You can install it using pip install xgboost.

I hope this helps! Let me know if you have any further questions.