4.4 分类准确度accuracy

from sklearn import datasets

from playML.model_selection import train_test_split
from playML.kNN2 import KNNClassfier

# 加载手写数字数据集
digits = datasets.load_digits()
print(digits.keys())
print(digits.DESCR)

X = digits.data
y = digits.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_ratio=0.2)
my_knn_clf = KNNClassfier(k=3)
my_knn_clf.fit(X_train, y_train)
y_predict = my_knn_clf.predict(X_test)

# 比对精确度
sum(y_predict == y_test)/len(y_test)

下面我们对对比精确度这个方法进行封装，新建文件metrics.py

def accuracy_score(y_true, y_predict):
    # 计算y_true和y_predict之间的准确率
    assert y_true.shape[0] == y_predict.shape[0],\
        "the size of y_true must be equal to the size of y_predict"

    return sum(y_true == y_predict)/len(y_true)

然后我们调用自己封装的度量函数

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

有些时候可能用户只想知道预测的准确率而不关心预测的具体结果，因此我们把前面的kNN文件中将度量函数引入。

import numpy as np
from math import sqrt
from collections import Counter
from .metrics import accuracy_score

class KNNClassfier:
    def __init__(self, k):
        # 初始化kNN分类器
        assert k >= 1, "k must be valid"
        self.k = k
        # _表示私有
        self._X_train = None
        self._y_train = None

    def fit(self, X_train, y_train):
        # 根据训练集训练KNN分类器
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must 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 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

下面我们来进行测试一下,在此之前将前面的运行程序要重新启动一下。

my_knn_clf.score(X_test, y_test)

scikit-learn中的accuracy_score

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)

from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(X_train, y_train)
y_predict = knn_clf.predict(X_test)

from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_predict)
# 对比我们的度量函数
knn_clf.score(X_test, y_test)