Python3入门机器学习经典算法与应用——手写knn模块

心已赠人 2022-12-20 11:26 120阅读 0赞

### 文章目录 ###

*  手写knn模块
 *   *  kNN.py
     *  metrics.py
     *  model\_selection.py

# 手写knn模块 #

`-- playML
        |-- __init__.py
        |-- kNN.py
        |-- metrics.py
        `-- model_selection.py

其中`__init__.py`是一个空文件,

## kNN.py ##

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 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 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

## 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 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)

## model\_selection.py ##

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], \
            "the size of X must be equal to the size of y"
        assert 0.0 <= test_ratio <= 1.0, \
            "test_ration must be valid"
    
        if seed:
            np.random.seed(seed)
    
        shuffled_indexes = np.random.permutation(len(X))
    
        test_size = int(len(X) * test_ratio)
        test_indexes = shuffled_indexes[:test_size]
        train_indexes = shuffled_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

**参考**  
[git 支持tree命令][git _tree]

[git _tree]: https://www.cnblogs.com/mmzuo-798/p/10954515.html