Python遇见机器学习 ---- k近邻（kNN）算法(五）

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 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"""
        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):
        """根据测试数据集确定当前准确度"""
        y_predict = self.predict(X_test)
        return accuracy_score(y_test, y_predict)
    def __repr__(self):
        return "KNN(k=%d)" % self.k

import numpy as np
def accuracy_score(y_true, y_predict):
    """计算y_true和y_predict之间的准确率"""
    # 保证预测对象的个数与正确对象个数相同，才能一一对比
    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_predict == y_true) / len(y_true)

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"""
    # 确保有多少个数据就有多少个标签
    assert X.shape[0] == y.shape[0], \
        "the size of X must be equal to the size of y"
    assert 0.0 <= test_ratio <= 1.0, \
        "test_ratio must be valid"
    if seed:
        np.random.seed(seed)
    shuffle_indexes = np.random.permutation(len(X)) # 打乱数据，形成150个索引的随机排列
    test_size = int(len(X) * test_ratio)
    test_indexes = shuffle_indexes[:test_size]  # 测试数据集索引
    train_indexes = shuffle_indexes[test_size:]  # 训练数据集
    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

import numpy as np
class StandardScaler:
    def __init__(self):
        self.mean_ = None
        self.scale_ = None
    def fit(self, X):
        """根据训练数据集X获得数据的均值和方差"""
        assert X.ndim == 2, "The dimension of X must be 2"
        self.mean_ = np.array([np.mean(X[:,i]) for i in range(X.shape[1])])
        self.scale_ = np.array([np.std(X[:, i]) for i in range(X.shape[1])])
        return self
    def transform(self, X):
        """将X根据这个StandardScaler进行均值方差归一化处理"""
        assert X.ndim == 2, "The dimension of X must be 2"
        assert self.mean_ is not None and self.scale_ is not None, \
            "must fit before transform!"
        assert X.shape[1] == len(self.mean_), \
            "the feature number of X must be equal to mean_ and std_"
        resX = np.empty(shape=X.shape, dtype=float)
        for col in range(X.shape[1]):
            resX[:,col] = (X[:,col] - self.mean_[col]) / self.scale_[col]
        return resX