python-knn

说明：  利用python进行数据分析，英文书籍，从pandas库的数据分析工具开始利用高性能工具对数据进行加载、清理、转换、合并以及重塑；利用matpIotlib创建散点图以及静态或交互式的可视化结果；利用pandas的groupby功能对数据集进行切片、切块和汇总操作；处理各种各样的时间序列数据。(Starting from the data analysis tools of pandas database, high performance tools are used to load, clean, transform, merge and remodel data; scatter plots and static or interactive visualization results are created by matpIotlib; data sets are sliced, sliced and aggregated by pandas group by function; and various operations are processed. Time series data.)

说明：  基于股票数据的神经网络，关于结算的预测，通过遗传算法加以改进(Based on the neural network of stock data, the prediction of settlement is improved by genetic algorithm)

生成随机数的算法,原书带的并不能直接使用,这是本人改的直接可用的()

Clustering the data with Density-Based Scan Algorithm with Noise (DBSCAN)

这是一本经典数值算法书,包含多种算法的理论,为编程者具有一定参考意义()

数据挖掘，推荐系统，堆叠降噪自编码器，逻辑回归(Data mining, recommender systems, stack noise reduction, self coder, logic regression)

本问题是计算最长有序子序列的一个动态规划算法,效率为31MS()

一种特征提取方法：结合主元分析(PCA)和核主元分析（KPCA）的前馈神经网络（FNN）(A feature extraction method: the feedforward neural network (FNN) combined with principal component analysis (PCA) and kernel principal component analysis (KPCA))

google搜索的核心技术,VC++源码实现,包含测试数据库()

说明：  多种基本分类训练，包括支持向量机，偏最小二乘，主成分分析和线性分析(A variety of basic classification training, including support vector machine, partial least squares, principal component analysis and linear analysis)