knn算法分类准确度（五）

分类准确度

    准确度用accuracy表示:

    代码实现准确率计算:

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn import datasets

#加载手写数字集图片数据
digits = datasets.load_digits()

#查看该数据集的描述信息
digits.DESCR

#查看数据集的shape
X = digits.data
X.shape

y = digits.target
y.shape

    取出某个数据集绘制图像：

some_digit = X[666]
y[666]

#将数据集变为(8,8)的二维数据
some_digit_image = some_digit.reshape(8,8)
#绘制二维图片
plt.imshow(some_digit_image,cmap=matplotlib.cm.binary)
plt.show()

    利用knn算法进行分类预测：

from knn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,test_ratio=0.2)

from knn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y)

from knn.kNN import KNNClassifier
knn_clf = KNNClassifier(k=6)
knn_clf.fit(X_train,y_train)
y_predict = knn_clf.predict(X_test)

    计算准确率：

sum(y_predict==y_test)/y_test.shape[0]

    封装为代码metrics.py：

import numpy as np

def accuracy_score(y_true, y_predict):
    """计算y_true和y_predict之间的准确率"""
    assert len(y_true) == len(y_predict), \
        "the size of y_true must be equal to the size of y_predict"

    return np.sum(y_true == y_predict) / y_test.shape[0]

    应用算法进行计算：

from knn.metrics import accuracy_score
accuracy_score(y_test,y_predict)

    将准确率代码整合封装到kNN.py中

    上述计算准确率的方式，必须用到y_predict，也就是必须进行预测

    在实际开发的某些情况下，开发者可能不想去进行预测，直接得到准确率

    修改kNN.py，代码如下：

import numpy as np
from math import sqrt
from collections import Counter
#新添加的代码
from .metrics import accuracy_score

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]

    #新添加的代码
    def score(self, X_test, y_test):
        """根据测试数据集 X_test 和 y_test 确定当前模型的准确度"""

        y_predict = self.predict(X_test)
        return accuracy_score(y_test, y_predict)

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

    测试使用：

knn_clf.score(X_test,y_test)

    sklearn中的accuracy_score

    代码：

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

#划分数据集
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2)

#训练knn模型
knn_classifier = KNeighborsClassifier(n_neighbors=6)
knn_classifier.fit(X_train,y_train)

#预测测试集
y_predict = knn_classifier.predict(X_test)

#计算准确率
from sklearn.metrics import accuracy_score
#方式1：
accuracy_score(y_test,y_predict)

#方式2：
knn_classifier.score(X_test,y_test)