Prediction of KNN Iris species after normalization and standardization

API

sklearn.neighbors.KNeighborsClassifier(n_neighbors=5,algorithm=‘auto’)
n_neighbors：
int, Optional （ Default = 5）,k_neighbors Query the number of neighbors used by default
algorithm：{‘auto’,‘ball_tree’,‘kd_tree’,‘brute’}
Fast k Nearest neighbor search algorithm , The default parameter is auto, It can be understood that the algorithm decides the appropriate search algorithm by itself . besides , Users can also specify their own search algorithm ball_tree、kd_tree、brute Method to search ,
brute It's brute force search , That's linear scanning , When the training set is large , Calculation is very time-consuming .
kd_tree, structure kd A tree data structure that stores data for quick retrieval ,kd Tree is the binary tree in data structure . Trees constructed by median segmentation , Each node is a hyperrectangle , In dimension less than 20 High aging rate .
ball tree To overcome kd The tree was invented due to high-dimensional failure , Its construction process is based on the center of mass C Sum radius r Split sample space , Each node is a hypersphere .

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier

# 1. Get data set 
iris = load_iris()

# 2. Basic data processing 
# x_train,x_test,y_train,y_test Is the eigenvalue of the training set 、 Test set eigenvalues 、 Training set target value 、 Test set target value 
x_train, x_test, y_train, y_test = train_test_split\
    (iris.data, iris.target, test_size=0.2, random_state=22)

# 3、 Feature Engineering ： Standardization 
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)

estimator = KNeighborsClassifier(n_neighbors=9)
estimator.fit(x_train, y_train)

y_predict = estimator.predict(x_test)
print(" The predicted result is :\n", y_predict)
print(" Compare the real value with the predicted value ：\n", y_predict == y_test)
#  Method 2： Direct calculation accuracy 
score = estimator.score(x_test, y_test)
print(" Accuracy rate is ：\n", score)

fit Represents the calculated mean , And variance
here transfer.fit_transform It means to extract the features of the training set after calculating the mean and variance ,
transfer.transform Represents using the previously instantiated transfer Get the mean and variance for eigenvalue extraction