python

朴素贝叶斯是经典的机器学习算法之一，也是为数不多的基于概率论的分类算法。朴素贝叶斯原理简单，也很容易实现，多用于文本分类，比如垃圾邮件过滤。(Naive Bayes is one of the classical machine learning algorithms, and is also one of the few classification algorithms based on probability theory. Naive Bayesian principle is simple and easy to implement. It is mostly used for text categorization, such as spam filtering.)

Python密度聚类 最近在Science上的一篇基于密度的聚类算法《Clustering by fast search and find of density peaks》引起了大家的关注(在我的博文“论文中的机器学习算法——基于密度峰值的聚类算法”中也进行了中文的描述)。于是我就想了解下基于密度的聚类算法，熟悉下基于密度的聚类算法与基于距离的聚类算法，如K-Means算法之间的区别。 基于密度的聚类算法主要的目标是寻找被低密度区域分离的高密度区域。与基于距离的聚类算法不同的是，基于距离的聚类算法的聚类结果是球状的簇，而基于密度的聚类算法可以发现任意形状的聚类，这对于带有噪音点的数据起着重要的作用。(The main goal of the density based clustering algorithm is to find high density regions separated by low density regions. Different from distance based clustering algorithm, the clustering results based on distance clustering algorithm are spherical clusters, and density based clustering algorithm can detect clustering of arbitrary shapes, which plays an important role in data with noisy points.)

ocr,一个深度学习的ocr开源代码，非常不错的ocr。(ocr, this is a great ocr open source code by Python. Very nice project.)

用python语言实现二级希尔密码的加解密(Python implements two-level Hill encryption and decryption)

说明：  方向梯度直方图检测算子，能够提取图像的HOG特征，进行分类与识别(Directional gradient histogram detection operator can extract the hog features of the image for classification and recognition)

说明：  三维voronoi多面体混凝土土骨料网格划分(Mesh generation of 3D Voronoi polyhedral concrete soil aggregate)

说明：  Python程序调用jieba库与词云提取平凡的世界词云(Extracting ordinary world word cloud with Jieba library and word cloud)

textCNN文本分类

说明：  ACO优化BP模型，避免局部最优，从而进行预测(ACO optimizes BP model, avoids local optimization, and forecasts)

蒙特卡洛树搜索的demo，模拟一个tic tac toe游戏，可以做到不败。 python3编写，无依赖。 UCT可以替换，现在有变种叫PUCT，可能效果会更好。