R关于绘图应该可以写很多, 不过这里只列举在compstat这门课里最经常用的几个函数. 关于R的绘图, 详细了解可以运行 demo(graphics)或者 example("plot").
R里面的绘图命令分为两类: 一类是"high-level"的"创建新图片"命令, 运行以后会新画一个图; 另一类则是"low-level"的命令, 不会创建新图片, 而只会在当前图片中修改添加(例如添加线条, 添加点等). 下面分别简单介绍, 最后再介绍其他一些绘图配置的命令.
介绍一下常用的参数意义, 以及画图的配置. 详细文档见?par. 这些参数可以放在绘图命令中.
par(mfrow=c(1,2)): 这个命令是设定画图的布局, 把放置图片的区域分为一行两列, 第一个plot的图片在左边, 第二个在右边. col: 设定画图(线段/点)的颜色, 可以用数字(col=1, 2 ...首先, R似乎默认所有的变量都为向量vector, 即使一个单独的数字也是长度为1的, 所以1等价于c(1).
> a <- 1
> a
[1] 1
> length(a)
[1] 1
> a[1]
[1] 1
> typeof(a)
[1] "double" # means "double vector" (I think)
> 1 == c(1)
[1] TRUE
R的vector/list/matrix支持类似numpy(稍有不同)的fancy indexing, 以下是例子:
> v <- 1:10
> v[1:3 ...这个"从入门到放弃"系列是为了应付eth的computational statistics这门课... 对R无爱...
首先在stat里面有一些叫法和以前不太一样:
predictor variable: 就是机器学习里面说的feature (Xi)design points: 是机器学习里的训练数据(X1...Xn)response variable: 要预测的变量(y)这个是用R编程的标配, 确实很方便, 不用可惜. 另外R markdown也不错, 可以边写markdown边运行代码, 建议编辑器窗口里新建rmd文件.
一些常用的快捷键:
alt+-: 用于输入赋值符号<-ctrl+enter: (在console里)执行光标所在的行, 等同于按钮"run"ctrl ...scala is pure OO: every value is an obj, every operation is a method of obj.
scala.Int scala.Boolean maps to JVM standard primitive types.
Implement Boolean withous primitive type in scala:
Then defin false and true as objects, give implementation for ifThenElse() funciton:
object ...This week, we'll cover traits, and we'll learn how to organize classes into hierarchies. We'll cover the hierarchy of standard Scala types, and see how to organize classes and traits into packages. Finally, we'll touch upon the different sorts of polymorphism in Scala.
This week, we'll learn about functions as first-class values, and higher order functions. We'll also learn about Scala's syntax and how it's formally defined. Finally, we'll learn about methods, classes, and data abstraction through the design of a data structure for rational numbers.
In this week, we'll learn the difference between functional imperative programming. We step through the basics of Scala; covering expressions, evaluation, conditionals, functions, and recursion
imperative programming:
~~~> Von Neumann computer:
conceptualize data ...
Get up and running with Scala on your computer. Complete an example assignment to familiarize yourself with our unique way of submitting assignments.
use worksheet as a better REPL
navigate to the directory of the assignment you are working on, then start sbt.
(when first running ...
problems with text:
→ need a lot of labeled data ⇒ not realistic.
⇒ unsupervised learning
similar words appear in similar context.
embedding: map words to small vectors
measure the closeness by cosine distance:
initial: random vector ...
statistical invariance → weight sharing
e.g. image colors, translation invariance...
is NNs that share their weights across space.
convolution: slide a small patch of NN over the image to produce a new "image"
convnet forms a pyramid, each "stack of pincake" get larger depth and smaller area.
