@Sarah
2016-01-12T05:36:41.000000Z
字数 618
阅读 1446
BI
Association analysis:同时买1 2 3 的也可能买4, car reatings ,to extract those
Missing data:
mir:missing at random
missing not at random:
why these data are missing
cluster analysis
type pf clustering:
guest lecture:after first exam 在三月29
selpf orgnizing map
unsupervised:
fuzzy clustering:衡量how stringly 两个cluster
crisp clustering:不知道两个custerz之间的距离
text analytics/mining:generly about ,to put similay txt together
model of behavior
4月4号 group check point :小组陈述15-25分钟
最后一周不考试/提前考
四月末考试
trainning data set:持续的traning ,应用到 test
test data set:
validation data set:
random forest:unsample learinig method
random Forest(随机森林)算法是通过训练多个决策树,生成模型,然后综合利用多个决策树进行分类。
测试概念
给例子:解释是什么
用一行就解释,别写得太长