Stat 20代做、代写R编程设计、代做Rmd file、代写R

日期：2019-05-12 09:52

2019/5/10 Lab2.utf8

https://ccle.ucla.edu/pluginfile.php/2840089/mod_resource/content/1/Lab2.html 1/3

Lab 2

Stat 20 Spring 2019

Due May 17th by 6:00am

General Instructions

1. The lab should be written as a .Rmd file and knitted to a .html file. An upload link can be found in Week

3 of CCLE. Please upload an .Rmd and the knitted .html (and also a photograph or scan of your hand

drawn image – more on this later).

2. You may work in groups. In fact, Jake and I would encourage that you collaborate together, decide on

what to do together, work through constructing whatever additional variables together, and generating a

graph together. BUT you are individually responsible for generating a lab for submission and you are

responsible for writing your own answers to the questions (as indicated below).

Individually means that your individual lab submission should not closely match another student’s lab

submission. If your match scoring with another submitted lab is too high (too high is determined by the typical

match score and the variation around it) there will be deductions taken or extra work assigned to correct the

issue.

Lab Overview

Your job is to download the dataset called simpsons_episodes.csv from week 3 of CCLE and use it to create a

single static (i.e., not interactive) visualization that you believe effectively communicates this dataset and also

provide a brief write-up (no more than 2-3 paragraphs) describing your visualization. Lastly, answer a few

open-ended questions (i.e., there is no one correct answer) related to working with this data.

Analysis Guidance

2019/5/10 Lab2.utf8

https://ccle.ucla.edu/pluginfile.php/2840089/mod_resource/content/1/Lab2.html 2/3

The given data set must be used and must be the main element of your graphic, HOWEVER you may (not

required) filter, transform, and augment (e.g., create new variables from old, locate external data and join) it to

highlight the things that you think are most important in the data.

Assignment

1. The visualization (one, needs to fit on the screen, group or

individual)

A. We just want one, if you are working with a group, your group may come up with several, choose the one

you like best and use it. This visualization/graphic should appear in your knitted .html file and the code which

created it should be clearly visible in your .Rmd file.

B. Please size your image so that it fits on a single screen of a computer at most (we want to be able to see all

of it when it’s time to view). Please make certain that any text appearing on the graphic is readable.

2. The Brief Write-Up (2-3 paragraphs at most, individual only)

A. Because different graphics can highlight different aspects of a data set, your brief write-up should clearly

state what part of the data you are attempting to most effectively communicate. In other words, which story in

the data are you trying to tell us (i.e., there are many stories in any data set, this part is a description of your

visualization)?

B. Which part of the data did it involve? To keep this lab from becoming overwhelming, it is also important to

have an awareness of which aspects of the data are not being addressed due to your choices. For example,

your data may have a natural grouping that you chose to ignore because it was not interesting. Do not try to

visualize every dimension of the data, just be brave and keep it simple (but do try to make it interesting).

C. Somewhere in your brief write-up document your (or your group’s) choices and tell us why these choices

were appropriate for the data.

Your choices include the visualization type, size, color, scaling, among other visual elements, as well as the

use of data filtering, feature construction, or other data transformations. Consider this - how did your decisions

help communicate your ideas?

3. The Open-Ended Questions (one paragraph per please,

individual only)

These are “thought” questions and should be yours alone, not a group decision. While you might discuss this

within the context of a group, our hope is that you are the owner/creator of the answers.

A. If you could add any additional information you wanted just by snapping your fingers, what three columns

would you add? Give us a column name, what kind of data would we find in this column, and what would some

of its values (e.g., a range of values, a set of labels) be? Please also indicate where do you think we might find

2019/5/10 Lab2.utf8

https://ccle.ucla.edu/pluginfile.php/2840089/mod_resource/content/1/Lab2.html 3/3

this data?

B. Given that you have these three additional columns of data, what questions would you be able to answer

with this new data which you could not answer with the original data? Please give us at minimum two

additional questions.

C. (LAST ONE) Imagine you have all the additional data you want, on a clean sheet of paper (if you need one,

stop by my office and I’ll give you some) please sketch what visualization you believe you would be able to

create with your new data. Your sketch doesn’t need to be colored, nor does it need to be accurate, nor does it

need to be good, it is simply a mental exercise to generate what you would visualize using software if you

knew how to do it.

This does not need to be a standard, textbook visualization, you are free to use your imagination (think - Da

Vinci, Van Gogh, Picasso…). And please upload either a photograph or scan of your sketch.

(Extra Credit - thank Jake, not me) Include pseudocode or a rough approximation of the R code you believe

would create or be progress towards creating the imagined visualization in part 3.

This Lab is due May 17th no later than 6am (just in

case Jake wants to discuss it in the morning)