scikit-learn中的机器学习算法封装

kＮＮ算法的封装

对于上文中的kNN的算法,将他封装成了一个函数.

import numpy as np
from math import sqrt
from collections import Counter

def kNN_classify(k, X_train, y_train, x):

    assert 1 <= k <=  X_train.shape[0], "k must be valid"
    assert X_train.shape[0] == y_train.shape[0],\
        "the size of X_train must equal to the size of y_train"
    assert X_train.shape[1] == x.shape[0],\
        "the feature number of x must be equal to X_train"

    distances = [sqrt(np.sum((x_train - x) ** 2)) for x_train in X_train]
    nearest = np.argsort(distances)

    topK_y = [y_train[i] for i in nearest[:k]]
    votes = Counter(topK_y)

    return votes.most_common(1)[0][0]

assert的解释:
1.为了保证k的数量在1和点的数量之间.
2.为了保证x中点的数量和y中类型的数量相一致.
3.为了保证新来的这个点与x中的点的类别是一样的.

使用scikit-learn中的kNN

from sklearn.neighbors import KNeighborsClassifier
kNN_classifier = KNeighbiorsClassifier(n_neighbors=6)
kNN_classifier.fit(X_train, y_train)
X_predict = x.reshape(1, -1)
kNN_classifier.predict(X_predict)

通过上述几行代码我们,就完成了一次新来的数据的预测.
接下来我们根据scikit-learn中的kNN对我们以前自己写的kNN进行重新的整理,得到如下代码:

import numpy as np
from math import sqrt
from collections import Counter

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):
        """根据训练数据据X_train和y_train训练kNN分类器"""
        self._X_train = X_train
        self._y_train = y_train
        return self

    def predict(self, X_predict):
        """给定预测数据集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 __pepr__(self):
        return "KNN(k=%d)" %self.k