simple_knn_tunando_neighbors.py

# bibliotecas
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import numpy as np

# remove warnings
import warnings
warnings.filterwarnings("ignore")

# dataset
iris = load_iris()

# features e target
X = iris.data
y = iris.target

mean_scores = []
for k in range(1,51):
    scores = []
    for i in range(60):
        X_train, X_test, y_train, y_test = train_test_split(X,y)
        model = KNeighborsClassifier(n_neighbors=k)
        model.fit(X_train,y_train)
        accuracy = model.score(X_test,y_test)
        scores.append(accuracy)
    mean_scores.append(np.mean(scores))

import matplotlib.pyplot as plt
import seaborn as sns
plt.plot(np.arange(1,51),mean_scores)
plt.yticks([])
plt.title("Acurácias do k-NN por número de vizinhos")
plt.xlabel("Número de vizinhos")
plt.ylabel("Acurácia")
plt.show()