数据挖掘复习笔记VIP专享VIP免费

学习必备欢迎下载Course Review 1Introduction to data mining, some definition (Ch1,Ch3) 2 Data preprocessing Ch2 ( Han,data mining book) Why preprocess the data? Data cleaning 清理Data integration 集成Data transformation 变换Data reduction 约简Data discretization 离散化3 Data Warehouse and OLAP Technology: An Overview Ch2 What is warehouse? Difference between warehouse and database 4 Classification and Prediction Ch4 Distance based algorithm: KNN (K- Nearest Neighbors) Classification by Decision Tree Induction : ID3 strategy Classification by Bayesian Prediction by linear regression 5 Cluster Analysis （Ch5）Distance measure: Euclidean distance, Manhattan distance Hierarchical Methods: Agglomerative, Divisive Partitioning Methods: k-Means, k-Medoid / PAM (Partition Around Medoids) Clustering Cluster based on attribute: ROCK Clustering in large database: BIRCH,DBSCAN,CURE6 Association Rules （Ch6）Basic concept: Support , confidence, correlation Efficient and Scalable Frequent Itemset Mining Methods: Apriori algorithm Improving the Efficiency of Apriori: partitioning ,sampling, FP-growth without candidate generation Mining Various Kinds of Association Rules:Multi-level, Multidimensional, Quantitative From Association Mining to Correlation Analysis: Strong Rules Are Not Necessarily Interesting 学习必备欢迎下载Introduction to data mining, some definition (Ch1,Ch3) 1 Data mining (knowledge discovery from data) （数据挖掘的定义）Extraction of interesting (non-trivial, implicit, previously unknown and potentially useful) patterns or knowledge from huge amount of data 1+ 数据挖掘与只是发现的异同从大量的数据中提取非平凡的，先前不知道的，潜在有用的模式的过程。Expert systems or small ML/statistical programs 专家系统是数据处理小程序2 数据挖掘的应用Market analysis and management（...