import pickle
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score
from sklearn import metrics
iris = datasets.load_iris()
X_train,X_test,y_train,y_test = train_test_split(iris.data, iris.target, test_size=0.3)
k_range = range(1,31)
k_score = []
for k in k_range:
knn = KNeighborsClassifier(n_neighbors=k)
scores = cross_val_score(knn, X_train, y_train, cv=10, scoring='accuracy')
k_score.append(scores.mean())
plt.figure()
plt.plot(k_range, k_score)
plt.xlabel('Value of k for KNN')
plt.ylabel('CrossValidation accuracy')
plt.show()
max_score = max(k_score)
print("max score:", max_score)
best_k = k_range[k_score.index(max_score)]
knn = KNeighborsClassifier(n_neighbors=best_k)
knn.fit(X_train, y_train)
y_predict = knn.predict(X_test)
print("test data accuracy:", metrics.accuracy_score(y_test, y_predict))
print("classification report:\n”, metrics.classification_report(y_test, y_predict))
with open("knn.pkl", "wb") as f:
pickle.dump(knn, f)
