iris dataset으로 지도학습(KNN) / 비지도학습(K-Means) 비교

 

iris 데이터로 지도학습(KNN) / 비지도학습(K-Means) 비교했다.

# iris dataset으로 지도학습(KNN) / 비지도학습(K-Means)

from sklearn.datasets import load_iris

iris_dataset = load_iris()

print(iris_dataset['data'][:3])
print(iris_dataset['feature_names'])

# train / test sprit
from sklearn.model_selection import train_test_split
# train / test split (7 : 3)
x_train, x_test, y_train, y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], test_size = 0.25, random_state = 42)
print(x_train.shape, x_test.shape, y_train.shape, y_test.shape) # (112, 4) (38, 4) (112,) (38,)

# 지도학습(KNN)
from sklearn.neighbors import KNeighborsClassifier
from sklearn import metrics

knnmodel = KNeighborsClassifier(n_neighbors=5)
knnmodel.fit(x_train, y_train) # feature, label

predict_label = knnmodel.predict(x_test)
print('예측값 :', predict_label)
print('실제값 :', y_test)
print('acc :', metrics.accuracy_score(y_test, predict_label))

print()
# 비지도학습(K-Means)
from sklearn.cluster import KMeans
kmeansModel = KMeans(n_clusters=3, init='k-means++', random_state = 0)
kmeansModel.fit(x_train)

print(kmeansModel.labels_)

print('o cluster :', y_train[kmeansModel.labels_ == 0])
print('o cluster :', y_train[kmeansModel.labels_ == 1])
print('o cluster :', y_train[kmeansModel.labels_ == 2])

pred_cluster = kmeansModel.predict(x_test)
print('pred_cluster :', pred_cluster)

import numpy as np
np_arr = np.array(pred_cluster)

pred_label = np_arr.tolist()
print(pred_label)
print('test acc : {:.2f}'.format(np.mean(pred_label == y_test)))


<console>
[[5.1 3.5 1.4 0.2]
 [4.9 3.  1.4 0.2]
 [4.7 3.2 1.3 0.2]]
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
(112, 4) (38, 4) (112,) (38,)
예측값 : [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
 0]
실제값 : [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
 0]
acc : 1.0

[0 0 1 1 1 0 0 1 1 2 1 2 1 2 1 0 2 1 0 0 0 1 1 0 0 0 1 0 1 2 0 1 1 0 1 1 1
 1 2 1 0 1 2 0 0 1 2 0 1 0 0 1 1 2 1 2 2 1 0 0 1 2 0 0 0 1 2 0 2 2 0 1 1 1
 2 2 0 2 1 2 1 1 1 0 1 1 0 1 2 2 0 1 2 2 0 2 0 2 2 2 1 2 1 1 1 1 0 1 1 0 1
 2]
o cluster : [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
o cluster : [2 1 1 1 2 1 1 1 1 1 2 1 1 1 2 2 2 1 1 1 1 1 2 1 1 1 1 2 1 1 1 2 1 1 1 1 1
 1 1 1 1 1 1 2 2 1 2 1]
o cluster : [2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 1 2 2 2 2]
pred_cluster : [1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 1 0 2 2 2 2 2 0 0 0 0 1 0 0 1 1
 0]
[1, 0, 2, 1, 1, 0, 1, 2, 1, 1, 2, 0, 0, 0, 0, 1, 2, 1, 1, 2, 0, 1, 0, 2, 2, 2, 2, 2, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0]
test acc : 0.95