【Python 3.7】机器学习笔记：KNN算法预测鸢尾花数据集的准确性问题

【Python 3.7】机器学习：KNN算法预测鸢尾花数据集的准确性问题

在 KNN.py 文件中的 KNN：

import numpy as np
from math import sqrt
from collections import Counter


class KNNClassifier:

    def __init__(self, k):
        """初始化kNN分类器"""
        assert k >= 1, "k must be valid"
        self.k = k
        self._X_train = None
        self._y_train = None

    def fit(self, X_train, y_train):
        """根据训练数据集X_train和y_train训练kNN分类器"""
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must be equal to the size of y_train"
        assert self.k <= X_train.shape[0], \
            "the size of X_train must be at least k."

        self._X_train = X_train
        self._y_train = y_train
        return self

    def predict(self, X_predict):
        """给定待预测数据集X_predict，返回表示X_predict的结果向量"""
        assert self._X_train is not None and self._y_train is not None, \
                "must fit before predict!"
        assert X_predict.shape[1] == self._X_train.shape[1], \
                "the feature number of X_predict must be equal to X_train"

        y_predict = [self._predict(x) for x in X_predict]
        return np.array(y_predict)

    def _predict(self, x):
        """给定单个待预测数据x，返回x的预测结果值"""
        assert x.shape[0] == self._X_train.shape[1], \
            "the feature number of x must be equal to X_train"

        distances = [sqrt(np.sum((x_train - x) ** 2))
                     for x_train in self._X_train]
        nearest = np.argsort(distances)

        topK_y = [self._y_train[i] for i in nearest[:self.k]]
        votes = Counter(topK_y)

        return votes.most_common(1)[0][0]



    def __repr__(self):
        return "KNN(k=%d)" % self.k

建立测试的模型 model_selection.py 文件：

import numpy as np

def train_test_split(X,y,test_ratio=0.2,seed=None):
    """将数据 X 和 y 按照test_ratio分割成X_train, X_test, y_train, y_test"""
    assert X.shape[0]==y.shape[0]
    assert 0.0<=test_ratio<=1.0
    if seed:
        np.random.seed(seed)


    shuffle_indexes = np.random.permutation(len(X))


    test_size = int(len(X)*test_ratio)
    test_indexes = shuffle_indexes[:test_size]
    train_indexes = shuffle_indexes[test_size:]

    X_train = X[train_indexes]
    y_train = y[train_indexes]

    X_test = X[test_indexes]
    y_test = y[test_indexes]
    return X_train,X_test,y_train,y_test

调用KNN.py和model_selection.py中的函数来对鸢尾花数据集进行测试：

from sklearn.model_selection import train_test_split
from sklearn import datasets
'''载入鸢尾花数据集'''
iris=datasets.load_iris()
X=iris.data
y=iris.target

X_train, X_test, y_train, y_test = train_test_split(X,y)

from KNN import KNNClassifier
my_knn_clf=KNNClassifier(k=3)
my_knn_clf.fit(X_train,y_train)
y_predict=my_knn_clf.predict(X_test)

print(sum(y_predict==y_test))
"""预测准确率"""
print(sum(y_predict==y_test)/len(y_test))

运行一次的结果为：

37
0.9736842105263158