1. 加载数据集
import numpy as np
from sklearn import datasets
iris = datasets.load_iris()
iris.keys()
dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])
X = iris.data
X.shape
(150, 4)
iris.feature_names
['sepal length (cm)','sepal width (cm)','petal length (cm)','petal width (cm)']
y = iris.target
y.shape
(150,)
iris.target_names
array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
2.拆分数据集
shuffle_index = np.random.permutation(len(y))
shuffle_index.shape
(150,)
train_ratio = 0.8
train_size = int(len(X) * train_ratio)
train_size
120
train_index = shuffle_index[ :train_size]
test_index = shuffle_index[train_size: ]X_train = X[train_index]
y_train = y[train_index]X_test = X[test_index]
y_test = y[test_index]X_train.shape, y_train.shape, X_test.shape, y_test.shape
((120, 4), (120,), (30, 4), (30,))
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=train_ratio, random_state=666)
X_train.shape, X_test.shape, y_train.shape, y_test.shape
((120, 4), (30, 4), (120,), (30,))
3.预测
from sklearn.neighbors import KNeighborsClassifier
knn_classifier = KNeighborsClassifier(n_neighbors=5)
knn_classifier.fit(X_train, y_train)
y_predict = knn_classifier.predict(X_test)
4.评价
np.sum(y_predict==y_test)
30
accutacy = np.sum(y_predict==y_test) / len(y_test)
accutacy
1.0
from sklearn.metrics import accuracy_score
accuracy_score(y_predict, y_test)
1.0
)
)