Plus proches voisins | K-nearest neighbours

K-nearest neighbours (KNN) is a machine learning algorithm that is good a classifying moderately-sized datasets. It does so by looking at the n-dimensional space, where n is the number of features, and looking at nearby points to the data point you want to classify. It is a fairly simple technique but it can be very effective for data with low noise levels where the data points are nicely grouped together. Creating the model is almost instantaneously however classifying depends on the size of the training data.
The notebook in this tutorial will show you how to apply this technique to classifying penguins, diabetes patients, and books to display its strength and weaknesses.

K近邻（K-nearest neighbours, KNN）是一种适用于中等规模数据集分类任务的机器学习算法。其核心逻辑为：在以特征数量为维度的n维空间中，分析待分类数据点的邻近数据点，以此完成分类工作。该算法原理相对简洁，但在低噪声且数据点聚类规整的场景中往往可取得优异的分类效果。模型构建几乎可瞬时完成，但分类效率则取决于训练数据集的规模。

本教程配套的Notebook将演示如何将该算法应用于企鹅、糖尿病患者与图书的分类任务，以全面展现其优势与局限性。