一、判断机器算法的性能1基本使用

1.目的

判断机器算法的性能（train test split）目的是帮助我们找到一个更好的模型/测试时数据，训练数据；预测的准确率（越接近1越准确）:

2.使用pycharm函数封装

使用pycharm函数封装的形式运行train test split算法：

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分割成训练数据集和测试数据集"""
    assert x.shape[0]==y.shape[0],\
    "the size of x must be equal to the sze of y"
    assert 0.0<=test_ratio<=1.0,\
    "test_ration must be valid"
    if seed:
        np.random.seed(seed)
    shuffle_indexes = np.random.permutation(len(x))
    test_size = int(len(x) * test_ratio)
    test_indexes = shuffle_indexes[:test_size]  # 确定测试数据集对应的索引
    train_indexes = shuffle_indexes[test_size:]  # 训练数据集所对应的索引
    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

3.sklearn中的train test split：

4.完美调用：

二、判断机器算法的性能2分类的准确度（accuracy）

分类的准确度（accuracy）：

准确度初步计算：

完善KNNpy程序如下：

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