tensorflow股票LSTM预测

利用mnist数据集做深度学习小实例

说明：  这是一个基于gensim的倒排表，同时也含有手动实现的部分(This is an inverted table based on gensim, and also contains manual implementation.)

构建了无向加权网，并对网络的度分布、集聚系数、最短路径、度匹配度、度中心性等重要参数进行了计算，在此基础上构建了社区挖掘算法用于网络的社区发现，并采用链路预测算法构建推荐系统(An undirected weighted network is constructed, and some important parameters, such as degree distribution, aggregation coefficient, shortest path, degree matching degree and degree centrality, are calculated. On this basis, a community discovery algorithm is built for the network, and a link prediction algorithm is used to construct a recommendation system.)

利用高德API爬取行政区域边界，生成csv文件。利用高德API爬取行政区域边界，生成csv文件。利用高德API爬取行政区域边界，生成csv文件。利用高德API爬取行政区域边界，生成csv文件。

WIn10+Anaconda环境下安装PyTorch(避坑指南)

说明：  segmentation image whit kmeans

Python是一种面向对象、解释型计算机程序设计语言，其应用领域非常广泛，包括数据分析、自然语言处理、机器学习、科学计算以及推荐系统构建等。 本书用Python语言来讲解算法的分析和设计。本书主要关注经典的算法，但同时会为读者理解基本算法问题和解决问题打下很好的基础。(Python is an object-oriented, interpretive computer programming language. It has a wide range of applications, including data analysis, natural language processing, machine learning, scientific computing and recommendation system construction. This book uses Python language to explain the analysis and design of algorithms. This book focuses on classical algorithms, but at the same time it will lay a good foundation for readers to understand basic algorithms and solve problems. The book consists of 11 chapters. The tree, graph, counting problem, inductive recursion, traversal, decomposition and merging, greedy algorithm, complex dependency, Dijkstra algorithm, matching and cutting problem, difficult problem and its dilution are introduced. The book has exercises and reference materials at the end of each chapter, which provides readers with more convenience for self-examination and further stu)

说明：  利用Pytorch实现的一个简单的神经网络，实现了异或门。(Using a simple neural network implemented by Pytorch, XOR gates are realized.)

该程序利用python提供的libsvm库实现支持向量机的单分类，程序中通过生成数据进行算法的训练，并生成数据进行预测，结果表明算法对于已成点的排除效果非常好，对数据集的弹性非常棒。

说明：  隐马尔科夫模型进行中文分词 模型训练 python HMM_train.py RenMinData.txt_utf8 RenMinData.RenMinData_utf8 为人民日报已经人工分词的预料。 生成三个文件 * prob_start.py 为模型的初始概率 * prob_trans.py 为模型状态转移概率 * prob_emit.py 为发射概率 测试模型效果 python HMM.py reference 维特比算法：(python HMM_train.py RenMinData.txt_utf8 RenMinData.RenMinData_utf8 prob_start.py prob_trans.py prob_semit.py)