4-4 分類準確度

分類準確度的計算方式:

分類正確的樣本數 / 總樣本數

自己封裝的類, 與sklearn同接口:

(新加了score(X_test, y_test)函數,不關心predict的具體值是多少(predict函數在score中調用),只關心模型的準確度)

# from sklearn.neighbors import KNeighborsClassifier
import numpy as np
from math import sqrt
from collections import Counter
from .metrics import accuracy_score

class KNNClassifier:

    def __init__(self, k):
        """初始化KNN分類器"""
        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):
        """根據訓練數據集X_train和y_train訓練KNN分類器"""
        print(X_train.shape[0])
        print(y_train.shape[0])
        assert X_train.shape[0] == y_train.shape[0]#, \ "the size of X_train must be equal to 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):
        """給定待預測數據集X_predict,返回表示X_predict的結果向量"""
        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):
        """給定單個待預測數據x,返回x的預測結果值"""
        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):
        """根據測試集X_test和y_test確定當前模型的準確度"""
        y_predit = self.predict(X_test)

        return accuracy_score(y_test, y_predit)

使用sklearn的KNN模塊進行模型準確度的計算:

from sklearn.model_selection import train_test_split
from sklearn import datasets

# 數據集加載
digits = datasets.load_digits()

X = digits.data
y = digits.target

print(X.shape)
print(y.shape)

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=666)

# KNN
from sklearn.neighbors import KNeighborsClassifier

KNN_classifier = KNeighborsClassifier(n_neighbors=3)
KNN_classifier.fit(X_train, y_train)

# KNN中自帶的準確度計算函數
print(KNN_classifier.score(X_test, y_test))