/
1_intro_empty.R
209 lines (145 loc) Β· 3.56 KB
/
1_intro_empty.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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
### -- Introduction and refreshers for R
### -- https://github.com/aurielfournier/AOS19AK
#######################################
### -- Necessary packages
#######################################
library(dplyr)
library(tidyr)
library(ggplot2)
# if these do not load, run the matching one of these below
# install.packages("dplyr")
# install.packages("tidyr")
# install.packages("ggplot2")
###################
### -- Loading In The Data
####################
# set working directory!!
# discuss eBird data
ebird <- read.csv("eBird_workshop.csv")
# Explain how to leave comments
#########################
### -- Filtering
#########################
ebird %>%
filter( ,
)
# Explain What Pipes are %>%
# explain assignment operators
a = 100
a <- 100
# filter is for rows
# select is for columns
## With pipes
ebird %>%
filter( ,
) %>%
select( , , )
## Without pipes
ebird_filter <- filter( , ,)
select( , , , )
# the "|" means 'or' in R
ebird %>%
filter() %>%
# comments here
distinct()
# the "&" means "and" in R
ebird %>%
filter() %>%
distinct()
#########################
### -- Match %in%
#########################
a_states <- c( , , , )
ebird %>%
filter( %in% ) %>%
distinct()
#########################
### -- GROUPING
#########################
ebird %>%
group_by() %>%
summarize(mean = ,
median = )
ebird %>%
group_by(, ) %>%
summarize(mean=)
#########################################
### -- CHALLENGE
#########################################
# What is the median samplesize for
# Arizona, Alaska, Arkansas and Alabama after 2014?
new_data <- ebird %>%
filter( %in% ,
) %>%
group_by() %>%
summarise(medianS = )
#note to self talk about Kiwi vs Us spelling
#########################
## MUTATE
#########################
colors <- c()
mebird <- ebird %>%
mutate(a_state = ,
state_year = )
mebird %>%
tail()
########################
## Separate
########################
mebird %>%
separate(,
sep=,
into=c(,
),
remove= ) %>%
head()
# or
mebird %>%
separate(year, sep=c( ),
into=c( , ),
remove=) %>%
head()
########################
## Joins
########################
cool_birds <- c( , , )
ebird1 <- ebird %>%
filter( %in% ,
%in% ) %>%
select(, , , ) %>%
filter()
# point out that you can use multiple filter statements if you want, or you can put them all in one statement, same result.
years_to_keep <- c(2008:2012, 2015)
ebird2 <- ebird %>%
filter( %in% ,
%in% ) %>%
select(, , , ) %>%
filter( %in% )
unique(ebird1$ )
unique(ebird2$ )
#
full_join(, , by=c(,,)) %>% distinct()
full_join(, , by=c(,,)) %>% head()
#
right_join(, , by=c(,,)) %>% distinct()
right_join(, , by=c(,,)) %>% head()
#
left_join(, , by=c(,,)) %>% distinct()
left_join(, , by=c(,,)) %>% head()
#
inner_join(, , by=c(,,)) %>% distinct()
inner_join(, , by=c(,,)) %>% head()
#####################################
## CHALLENGE
#####################################
# Calculate the mean presence in 2010
# of 2 randomly selected a_states
# Hint: Use the dplyr functions sample_n(),
# they have similar syntax to other dplyr functions.
# ?sample_n for help
ebird %>%
filter( ,
%in% ) %>%
group_by() %>%
sample_n() %>%
summarize(mean= )