python-scikit-learnHow to get best estimator from grid search CV
from sklearn import svm, datasets, model_selection
iris = datasets.load_iris()
parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}
clf = model_selection.GridSearchCV(svm.SVC(), parameters)
clf.fit(iris.data, iris.target)
estimator = clf.best_estimator_ctrl + cfrom sklearn importimport module from scikit-learn | load_irisloads Iris dataset |
parametersparameters dictionary to run grid search accross | .GridSearchCV(creates GridSearchCV model |
svm.SVC()use SVC model as an estimator | .fit(train transformation model |
.best_estimator_returns estimator which gave highest score | |
Usage example
from sklearn import svm, datasets, model_selection
iris = datasets.load_iris()
parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}
clf = model_selection.GridSearchCV(svm.SVC(), parameters)
clf.fit(iris.data, iris.target)
print(clf.best_estimator_)output
SVC(C=1, kernel='linear')
Related
More of Python Scikit Learn
- How to get best parameters from grid search CV
- Feature importance example
- Get linear regression model coefficients
- Using OneClassSVM for outliers detection example
- Using quantile regression
- Random forest example
- Using QDA classifier example
- Linear model feature importance calculation
- Using Ridge regression model example
- Grid search CV example
See more codes...