{"id":13594528,"url":"https://github.com/ljpzzz/machinelearning","last_synced_at":"2025-05-14T01:09:47.363Z","repository":{"id":37335365,"uuid":"58616850","full_name":"ljpzzz/machinelearning","owner":"ljpzzz","description":"My blogs and code for machine learning. http://cnblogs.com/pinard","archived":false,"fork":false,"pushed_at":"2024-02-16T15:26:27.000Z","size":6617,"stargazers_count":8486,"open_issues_count":17,"forks_count":3749,"subscribers_count":303,"default_branch":"master","last_synced_at":"2025-04-03T01:43:42.916Z","etag":null,"topics":["algorithms","machinelearning","reinforcementlearning","scikit-learn"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ljpzzz.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-05-12T07:06:34.000Z","updated_at":"2025-04-02T15:30:48.000Z","dependencies_parsed_at":"2024-09-22T06:30:34.476Z","dependency_job_id":"4a5c79ad-0f44-46ee-970a-f00bd8a4efe4","html_url":"https://github.com/ljpzzz/machinelearning","commit_stats":{"total_commits":88,"total_committers":3,"mean_commits":"29.333333333333332","dds":0.2272727272727273,"last_synced_commit":"17302f708146ad46838b3782bf735364fa3cf16d"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ljpzzz%2Fmachinelearning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ljpzzz%2Fmachinelearning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ljpzzz%2Fmachinelearning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ljpzzz%2Fmachinelearning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ljpzzz","download_url":"https://codeload.github.com/ljpzzz/machinelearning/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248154634,"owners_count":21056541,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["algorithms","machinelearning","reinforcementlearning","scikit-learn"],"created_at":"2024-08-01T16:01:35.027Z","updated_at":"2025-04-10T03:40:02.241Z","avatar_url":"https://github.com/ljpzzz.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","📚 Project Purpose"],"sub_categories":["Machine Learning (Intermediate-Level"],"readme":"# 刘建平Pinard的博客配套代码\n\nhttp://www.cnblogs.com/pinard 刘建平Pinard\n\n之前不少朋友反应我博客中的代码都是连续的片段，不好学习，因此这里把文章和代码做一个整理。\n代码有部分来源于网络，已加上相关方版权信息。部分为自己原创，已加上我的版权信息。\n\n## 目录\n\n* [机器学习基础与回归算法](#2)\n\n* [机器学习分类算法](#3)\n\n* [机器学习聚类算法](#4)\n\n* [机器学习降维算法](#5)\n\n* [机器学习集成学习算法](#6)\n\n* [数学统计学](#7)\n\n* [机器学习关联算法](#8)\n\n* [机器学习推荐算法](#9)\n\n* [深度学习算法](#10)\n\n* [自然语言处理算法](#11)\n\n* [强化学习算法](#1)\n\n* [特征工程与算法落地](#12)\n\n## 注意\n\n2016-2017年写的博客使用的python版本是2.7， 2018年因为TensorFlow对Python3的一些要求，所以写博客使用的Python版本是3.6。少部分2016，2017年的博客代码无法找到，重新用Python3.6跑过上传，因此可能会出现和博客中代码稍有不一致的地方，主要涉及到print的语法和range的用法，若遇到问题，稍微修改即可跑通。\n\n## [赞助我](#13)\n\n\u003ch3 id=\"1\"\u003e强化学习文章与代码：:\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[强化学习（一）模型基础](https://www.cnblogs.com/pinard/p/9385570.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/introduction.py)\n[强化学习（二）马尔科夫决策过程(MDP)](https://www.cnblogs.com/pinard/p/9426283.html) | 无\n[强化学习（三）用动态规划（DP）求解](https://www.cnblogs.com/pinard/p/9463815.html) | 无\n[强化学习（四）用蒙特卡罗法（MC）求解](https://www.cnblogs.com/pinard/p/9492980.html) | 无\n[强化学习（五）用时序差分法（TD）求解](https://www.cnblogs.com/pinard/p/9529828.html) | 无\n[强化学习（六）时序差分在线控制算法SARSA](https://www.cnblogs.com/pinard/p/9614290.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/sarsa_windy_world.py)\n[强化学习（七）时序差分离线控制算法Q-Learning](https://www.cnblogs.com/pinard/p/9669263.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/q_learning_windy_world.py)\n[强化学习（八）价值函数的近似表示与Deep Q-Learning](https://www.cnblogs.com/pinard/p/9714655.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/dqn.py)\n[强化学习（九）Deep Q-Learning进阶之Nature DQN](https://www.cnblogs.com/pinard/p/9756075.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/nature_dqn.py)\n[强化学习（十）Double DQN (DDQN)](https://www.cnblogs.com/pinard/p/9778063.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/ddqn.py)\n[强化学习(十一) Prioritized Replay DQN](https://www.cnblogs.com/pinard/p/9797695.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/ddqn_prioritised_replay.py)\n[强化学习(十二) Dueling DQN](https://www.cnblogs.com/pinard/p/9923859.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/duel_dqn.py)\n[强化学习(十三) 策略梯度(Policy Gradient)](https://www.cnblogs.com/pinard/p/10137696.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/policy_gradient.py)\n[强化学习(十四) Actor-Critic](https://www.cnblogs.com/pinard/p/10272023.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/actor_critic.py)\n[强化学习(十五) A3C](https://www.cnblogs.com/pinard/p/10334127.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/a3c.py)\n[强化学习(十六) 深度确定性策略梯度(DDPG)](https://www.cnblogs.com/pinard/p/10345762.html)  | [代码](https://github.com/ljpzzz/machinelearning/blob/master/reinforcement-learning/ddpg.py)\n[强化学习(十七) 基于模型的强化学习与Dyna算法框架](https://www.cnblogs.com/pinard/p/10384424.html) | 无\n[强化学习(十八) 基于模拟的搜索与蒙特卡罗树搜索(MCTS)](https://www.cnblogs.com/pinard/p/10470571.html) | 无\n[强化学习(十九) AlphaGo Zero强化学习原理](https://www.cnblogs.com/pinard/p/10609228.html) | 无\n\n\n\u003ch3 id=\"2\"\u003e机器学习基础与回归算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[梯度下降（Gradient Descent）小结](https://www.cnblogs.com/pinard/p/5970503.html) | 无\n[最小二乘法小结](https://www.cnblogs.com/pinard/p/5976811.html) |无\n[交叉验证(Cross Validation)原理小结](https://www.cnblogs.com/pinard/p/5992719.html) | 无\n[精确率与召回率，RoC曲线与PR曲线](https://www.cnblogs.com/pinard/p/5993450.html) |无\n[线性回归原理小结](https://www.cnblogs.com/pinard/p/6004041.html) |无\n[机器学习研究与开发平台的选择](https://www.cnblogs.com/pinard/p/6007200.html) | 无\n[scikit-learn 和pandas 基于windows单机机器学习环境的搭建](https://www.cnblogs.com/pinard/p/6013484.html) |无\n[用scikit-learn和pandas学习线性回归](https://www.cnblogs.com/pinard/p/6016029.html) |[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/linear-regression.ipynb)\n[Lasso回归算法： 坐标轴下降法与最小角回归法小结](https://www.cnblogs.com/pinard/p/6018889.html) | 无\n[用scikit-learn和pandas学习Ridge回归](https://www.cnblogs.com/pinard/p/6023000.html) | [代码1](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/ridge_regression_1.ipynb) [代码2](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/ridge_regression.ipynb)\n[scikit-learn 线性回归算法库小结](https://www.cnblogs.com/pinard/p/6026343.html)|无\n[异常点检测算法小结](https://www.cnblogs.com/pinard/p/9314198.html)|无\n\n\u003ch3 id=\"3\"\u003e机器学习分类算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[逻辑回归原理小结](https://www.cnblogs.com/pinard/p/6029432.html) |无\n[scikit-learn 逻辑回归类库使用小结](https://www.cnblogs.com/pinard/p/6035872.html) |无\n[感知机原理小结](https://www.cnblogs.com/pinard/p/6042320.html) |无\n[决策树算法原理(上)](https://www.cnblogs.com/pinard/p/6050306.html) |无\n[决策树算法原理(下)](https://www.cnblogs.com/pinard/p/6053344.html)|无\n[scikit-learn决策树算法类库使用小结](https://www.cnblogs.com/pinard/p/6056319.html) |[代码1](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/decision_tree_classifier.ipynb) [代码2](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/decision_tree_classifier_1.ipynb)\n[K近邻法(KNN)原理小结](https://www.cnblogs.com/pinard/p/6061661.html) |无\n[scikit-learn K近邻法类库使用小结](https://www.cnblogs.com/pinard/p/6065607.html) |[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/knn_classifier.ipynb)\n[朴素贝叶斯算法原理小结](https://www.cnblogs.com/pinard/p/6069267.html) |无\n[scikit-learn 朴素贝叶斯类库使用小结](https://www.cnblogs.com/pinard/p/6074222.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/native_bayes.ipynb)\n[最大熵模型原理小结](https://www.cnblogs.com/pinard/p/6093948.html)|无\n[支持向量机原理(一) 线性支持向量机](https://www.cnblogs.com/pinard/p/6097604.html)|无\n[支持向量机原理(二) 线性支持向量机的软间隔最大化模型](https://www.cnblogs.com/pinard/p/6100722.html)|无\n[支持向量机原理(三)线性不可分支持向量机与核函数](https://www.cnblogs.com/pinard/p/6103615.html)|无\n[支持向量机原理(四)SMO算法原理](https://www.cnblogs.com/pinard/p/6111471.html)|无\n[支持向量机原理(五)线性支持回归](https://www.cnblogs.com/pinard/p/6113120.html)|无\n[scikit-learn 支持向量机算法库使用小结](https://www.cnblogs.com/pinard/p/6117515.html)|无\n[支持向量机高斯核调参小结](https://www.cnblogs.com/pinard/p/6126077.html) | [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/svm_classifier.ipynb)\n\n\u003ch3 id=\"7\"\u003e数学统计学文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[机器学习算法的随机数据生成](https://www.cnblogs.com/pinard/p/6047802.html) | [代码](https://github.com/ljpzzz/machinelearning/blob/master/mathematics/random_data_generation.ipynb)\n[MCMC(一)蒙特卡罗方法](https://www.cnblogs.com/pinard/p/6625739.html)|无\n[MCMC(二)马尔科夫链](https://www.cnblogs.com/pinard/p/6632399.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/mathematics/mcmc_2.ipynb)\n[MCMC(三)MCMC采样和M-H采样](https://www.cnblogs.com/pinard/p/6638955.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/mathematics/mcmc_3_4.ipynb)\n[MCMC(四)Gibbs采样](https://www.cnblogs.com/pinard/p/6645766.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/mathematics/mcmc_3_4.ipynb)\n[机器学习中的矩阵向量求导(一) 求导定义与求导布局](https://www.cnblogs.com/pinard/p/10750718.html)|无\n[机器学习中的矩阵向量求导(二) 矩阵向量求导之定义法](https://www.cnblogs.com/pinard/p/10773942.html)|无\n[机器学习中的矩阵向量求导(三) 矩阵向量求导之微分法](https://www.cnblogs.com/pinard/p/10791506.html)|无\n[机器学习中的矩阵向量求导(四) 矩阵向量求导链式法则](https://www.cnblogs.com/pinard/p/10825264.html)|无\n[机器学习中的矩阵向量求导(五) 矩阵对矩阵的求导](https://www.cnblogs.com/pinard/p/10930902.html)|无\n\n\n\u003ch3 id=\"6\"\u003e机器学习集成学习文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[集成学习原理小结](https://www.cnblogs.com/pinard/p/6131423.html) | 无\n[集成学习之Adaboost算法原理小结](https://www.cnblogs.com/pinard/p/6133937.html) | 无\n[scikit-learn Adaboost类库使用小结](https://www.cnblogs.com/pinard/p/6136914.html) | [代码](https://github.com/ljpzzz/machinelearning/blob/master/ensemble-learning/adaboost-classifier.ipynb)\n[梯度提升树(GBDT)原理小结](https://www.cnblogs.com/pinard/p/6140514.html) | 无\n[scikit-learn 梯度提升树(GBDT)调参小结](https://www.cnblogs.com/pinard/p/6143927.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/ensemble-learning/gbdt_classifier.ipynb)\n[Bagging与随机森林算法原理小结](https://www.cnblogs.com/pinard/p/6156009.html) | 无\n[scikit-learn随机森林调参小结](https://www.cnblogs.com/pinard/p/6160412.html) |  [代码](https://github.com/ljpzzz/machinelearning/blob/master/ensemble-learning/random_forest_classifier.ipynb)\n[XGBoost算法原理小结](https://www.cnblogs.com/pinard/p/10979808.html) | 无\n[XGBoost类库使用小结](https://www.cnblogs.com/pinard/p/11114748.html) |  [代码](https://github.com/ljpzzz/machinelearning/blob/master/ensemble-learning/xgboost-example.ipynb)\n\n\n\u003ch3 id=\"4\"\u003e机器学习聚类算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[K-Means聚类算法原理](https://www.cnblogs.com/pinard/p/6164214.html)|无\n[用scikit-learn学习K-Means聚类](https://www.cnblogs.com/pinard/p/6169370.html) | [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/kmeans_cluster.ipynb)\n[BIRCH聚类算法原理](https://www.cnblogs.com/pinard/p/6179132.html)|无\n[用scikit-learn学习BIRCH聚类](https://www.cnblogs.com/pinard/p/6200579.html) | [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/birch_cluster.ipynb)\n[DBSCAN密度聚类算法](https://www.cnblogs.com/pinard/p/6208966.html)|无\n[用scikit-learn学习DBSCAN聚类](https://www.cnblogs.com/pinard/p/6217852.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/dbscan_cluster.ipynb)\n[谱聚类（spectral clustering）原理总结](https://www.cnblogs.com/pinard/p/6221564.html) |无\n[用scikit-learn学习谱聚类](https://www.cnblogs.com/pinard/p/6235920.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/spectral_cluster.ipynb)\n\n\u003ch3 id=\"5\"\u003e机器学习降维算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[主成分分析（PCA）原理总结](https://www.cnblogs.com/pinard/p/6239403.html)|无\n[用scikit-learn学习主成分分析(PCA)](https://www.cnblogs.com/pinard/p/6243025.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/pca.ipynb)\n[线性判别分析LDA原理总结](https://www.cnblogs.com/pinard/p/6244265.html)|无\n[用scikit-learn进行LDA降维](https://www.cnblogs.com/pinard/p/6249328.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/lda.ipynb)\n[奇异值分解(SVD)原理与在降维中的应用](https://www.cnblogs.com/pinard/p/6251584.html)|无\n[局部线性嵌入(LLE)原理总结](https://www.cnblogs.com/pinard/p/6266408.html)|无\n[用scikit-learn研究局部线性嵌入(LLE)](https://www.cnblogs.com/pinard/p/6273377.html) |[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/lle.ipynb)\n\n\u003ch3 id=\"8\"\u003e机器学习关联算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[典型关联分析(CCA)原理总结](https://www.cnblogs.com/pinard/p/6288716.html)|无\n[Apriori算法原理总结](https://www.cnblogs.com/pinard/p/6293298.html)|无\n[FP Tree算法原理总结](https://www.cnblogs.com/pinard/p/6307064.html)|无\n[PrefixSpan算法原理总结](https://www.cnblogs.com/pinard/p/6323182.html)|无\n[用Spark学习FP Tree算法和PrefixSpan算法](https://www.cnblogs.com/pinard/p/6340162.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/fp_tree_prefixspan.ipynb)\n[日志和告警数据挖掘经验谈](https://www.cnblogs.com/pinard/p/6039099.html) | 无\n\n\u003ch3 id=\"9\"\u003e机器学习推荐算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[协同过滤推荐算法总结](https://www.cnblogs.com/pinard/p/6349233.html)|无\n[矩阵分解在协同过滤推荐算法中的应用](https://www.cnblogs.com/pinard/p/6351319.html)|无\n[SimRank协同过滤推荐算法](https://www.cnblogs.com/pinard/p/6362647.html)|无\n[用Spark学习矩阵分解推荐算法](https://www.cnblogs.com/pinard/p/6364932.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/matrix_factorization.ipynb)\n[分解机(Factorization Machines)推荐算法原理](https://www.cnblogs.com/pinard/p/6370127.html)|无\n[贝叶斯个性化排序(BPR)算法小结](https://www.cnblogs.com/pinard/p/9128682.html)|无\n[用tensorflow学习贝叶斯个性化排序(BPR)](https://www.cnblogs.com/pinard/p/9163481.html)| [代码](https://github.com/ljpzzz/machinelearning/blob/master/classic-machine-learning/bpr.ipynb)\n\n\u003ch3 id=\"10\"\u003e深度学习算法文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[深度神经网络（DNN）模型与前向传播算法](https://www.cnblogs.com/pinard/p/6418668.html)|无\n[深度神经网络（DNN）反向传播算法(BP)](https://www.cnblogs.com/pinard/p/6422831.html)|无\n[深度神经网络（DNN）损失函数和激活函数的选择](https://www.cnblogs.com/pinard/p/6437495.html)|无\n[深度神经网络（DNN）的正则化](https://www.cnblogs.com/pinard/p/6472666.html)|无\n[卷积神经网络(CNN)模型结构](https://www.cnblogs.com/pinard/p/6483207.html)|无\n[卷积神经网络(CNN)前向传播算法](https://www.cnblogs.com/pinard/p/6489633.html)|无\n[卷积神经网络(CNN)反向传播算法](https://www.cnblogs.com/pinard/p/6494810.html)|无\n[循环神经网络(RNN)模型与前向反向传播算法](https://www.cnblogs.com/pinard/p/6509630.html)|无\n[LSTM模型与前向反向传播算法](https://www.cnblogs.com/pinard/p/6519110.html)|无\n[受限玻尔兹曼机（RBM）原理总结](https://www.cnblogs.com/pinard/p/6530523.html)|无\n\n\u003ch3 id=\"11\"\u003e自然语言处理文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[文本挖掘的分词原理](https://www.cnblogs.com/pinard/p/6677078.html)|无\n[文本挖掘预处理之向量化与Hash Trick](https://www.cnblogs.com/pinard/p/6688348.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/hash_trick.ipynb)\n[文本挖掘预处理之TF-IDF](https://www.cnblogs.com/pinard/p/6693230.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/tf-idf.ipynb)\n[中文文本挖掘预处理流程总结](https://www.cnblogs.com/pinard/p/6744056.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/chinese_digging.ipynb)\n[英文文本挖掘预处理流程总结](https://www.cnblogs.com/pinard/p/6756534.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/english_digging.ipynb)\n[文本主题模型之潜在语义索引(LSI)](https://www.cnblogs.com/pinard/p/6805861.html)|无\n[文本主题模型之非负矩阵分解(NMF)](https://www.cnblogs.com/pinard/p/6812011.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/nmf.ipynb)\n[文本主题模型之LDA(一) LDA基础](https://www.cnblogs.com/pinard/p/6831308.html)|无\n[文本主题模型之LDA(二) LDA求解之Gibbs采样算法](https://www.cnblogs.com/pinard/p/6867828.html)|无\n[文本主题模型之LDA(三) LDA求解之变分推断EM算法](https://www.cnblogs.com/pinard/p/6873703.html)|无\n[用scikit-learn学习LDA主题模型](https://www.cnblogs.com/pinard/p/6908150.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/lda.ipynb)\n[EM算法原理总结](https://www.cnblogs.com/pinard/p/6912636.html)|无\n[隐马尔科夫模型HMM（一）HMM模型](https://www.cnblogs.com/pinard/p/6945257.html)|无\n[隐马尔科夫模型HMM（二）前向后向算法评估观察序列概率](https://www.cnblogs.com/pinard/p/6955871.html)|无\n[隐马尔科夫模型HMM（三）鲍姆-韦尔奇算法求解HMM参数](https://www.cnblogs.com/pinard/p/6972299.html)|无\n[隐马尔科夫模型HMM（四）维特比算法解码隐藏状态序列](https://www.cnblogs.com/pinard/p/6991852.html)|无\n[用hmmlearn学习隐马尔科夫模型HMM](https://www.cnblogs.com/pinard/p/7001397.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/hmm.ipynb)\n[条件随机场CRF(一)从随机场到线性链条件随机场](https://www.cnblogs.com/pinard/p/7048333.html)|无\n[条件随机场CRF(二) 前向后向算法评估标记序列概率](https://www.cnblogs.com/pinard/p/7055072.html)|无\n[条件随机场CRF(三) 模型学习与维特比算法解码](https://www.cnblogs.com/pinard/p/7068574.html)|无\n[word2vec原理(一) CBOW与Skip-Gram模型基础](https://www.cnblogs.com/pinard/p/7160330.html)|无\n[word2vec原理(二) 基于Hierarchical Softmax的模型](https://www.cnblogs.com/pinard/p/7243513.html)|无\n[word2vec原理(三) 基于Negative Sampling的模型](https://www.cnblogs.com/pinard/p/7249903.html)|无\n[用gensim学习word2vec](https://www.cnblogs.com/pinard/p/7278324.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/natural-language-processing/word2vec.ipynb)\n\n\u003ch3 id=\"12\"\u003e特征工程与算法落地文章与代码：\u003c/h3\u003e\n\n|文章 | 代码|\n---|---\n[特征工程之特征选择](https://www.cnblogs.com/pinard/p/9032759.html)|无\n[特征工程之特征表达](https://www.cnblogs.com/pinard/p/9061549.html)|无\n[特征工程之特征预处理](https://www.cnblogs.com/pinard/p/9093890.html)|无\n[用PMML实现机器学习模型的跨平台上线](https://www.cnblogs.com/pinard/p/9220199.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/model-in-product/sklearn-jpmml)\n[tensorflow机器学习模型的跨平台上线](https://www.cnblogs.com/pinard/p/9251296.html)|[代码](https://github.com/ljpzzz/machinelearning/blob/master/model-in-product/tensorflow-java)\n\n\u003ch3 id=\"13\"\u003e赞助我\u003c/h3\u003e\n\n你的支持是我写作的动力(1.微信/2.支付宝)：\n\n![微信赞助](./assert/invoice.bmp)\n\n\n![支付宝赞助](./assert/invoice_ali.bmp)\n\nLicense MIT.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fljpzzz%2Fmachinelearning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fljpzzz%2Fmachinelearning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fljpzzz%2Fmachinelearning/lists"}