-
Notifications
You must be signed in to change notification settings - Fork 1
/
review.R
87 lines (65 loc) · 2.52 KB
/
review.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
#core skills that you learned this unit
#we can access bundles of code that are already written with libaries
library(dplyr)
#we run each line and can look down in the console to see the effect
library(nycflights13)
#but flights is invisible until you assign it a name
flights<-flights
#arguments go left to right
#bigger to smaller; abstract to specific
#and pipes let you pass the RIGHT HAND SIDE of the line to the LEFT hand side of the next line
#we can check in our file environment for uploading or downloading files
readr::TV <- read_csv("TV.csv")
#we can look inside in a few ways
#wide
glimpse(TV)
#long
head(TV)
#wide and long are two very different ways that our brains work
#sometimes we need to transition between them
#wide data are especially important because their dual encoding (both axes have information)
#so they let us build rich stories, but are bad for analysis and visualization
#we can look around in things
TV %>%
filter(Network == "ABC")
#or arrange our data quickly (much faster than excel)
TV %>%
arrange(desc(Rating))
#we can query with multiple factors and arrange
TV %>%
filter(Network=="NBC" & Type == "Sitcom" & Rating > 20) %>%
arrange(desc(Rating))
#we can also rename things
#destructively
colnames(TV)[3]<-"Place"
#and mostly reverse it with tidy
TV<-TV %>% mutate("Rank" = Place)
#We can also quickly summarize too...
TV %>%
group_by(Year,Network) %>%
summarize(Rating=mean(Rating))
#which we can store
A<-TV %>%
group_by(Year,Network) %>%
summarize(Rating=mean(Rating))
#and make graphics of
ggplot(A, aes(Year,Rating,colour=Rating))+geom_jitter()
#call your DATASET
#establish your aesthetic bindings (X,Y,Colour,Size,Alpha)
#add your mark (geom)
#then facets (multiples)
#and styles
#there are MANY more geoms that can be used, our group wrote a package that uses PICTURES as geoms
#all done up...
ggplot(A, aes(Year,Rating,colour=Rating))+geom_jitter()+facet_grid(~Network)+
scale_color_gradient(low="purple", high="yellow")+theme(axis.text.x = element_text(angle = 90))
#we can also add a fun new data dimension...
#import joiner
#two columns with the SAME NAME, store that
B<-inner_join(A, joiner)
#joins are very useful and can be used to filter too
#the math on the BACK of the DPLYR cheatsheet is called 'set theory'
#make more graphs
ggplot(B, aes(Year,Rating,colour=Genre))+geom_jitter()+facet_grid(~Network)+
scale_color_discrete()+theme(axis.text.x = element_text(angle = 90))+labs(title="What Music Was Popular?")
#these skills allow you to make maps or almost anything...