Grid search with scikit-learn

At the beginning of the model selection and cross-validation chapter we tried to select the best nearest-neighbor model for the two last features of the iris dataset. We will refocus on that now with GridSearchCV in scikit-learn.

Getting ready

First, load the last two features of the iris dataset. Split the data into training and testing sets:

from sklearn import datasets

iris = datasets.load_iris()
X = iris.data[:,2:]
y = iris.target

from sklearn.model_selection import train_test_split, cross_val_score

X_train, X_test, y_train, y_test = train_test_split(X, y, stratify = y,random_state = 7)

How to do it...

1. Instantiate a nearest neighbors classifier:

from sklearn.neighbors import KNeighborsClassifier

knn_clf = KNeighborsClassifier()

2. Prepare a parameter grid, which is necessary for a grid search. A parameter grid is a dictionary with the parameter setting you would like to try:

param_grid = {'n_neighbors': list(range(3,9,1))}

3. Instantiate a grid search passing the following...