ai_start2.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from scipy.spatial import distance

def euc(a,b):
    return distance.euclidean(a,b)

class ScrappyKNN():
    def fit(self, X_train, y_train):
        self.X_train = X_train
        self.y_train = y_train
        
    def predict(self, X_test):
        predictions = []
        for row in X_test:
            label = self.closest(row)
            predictions.append(label)
        return predictions

    def closest(self, row):
        best_dist = euc(row, self.X_train[0])
        best_index = 0 
        for i in range(1,len(self.X_train)):
            dist = euc(row,self.X_train[i])
            if dist < best_dist:
                best_dist = dist
                best_index = i
        return self.y_train[best_index]
    
from sklearn.datasets import load_iris
iris = load_iris()

X = iris.data
y = iris.target

# 随机分出用于训练和测试的「data+target」
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .5)

my_clf = ScrappyKNN()

my_clf.fit(X_train, y_train)

predictions = my_clf.predict(X_test)

from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, predictions))