forked from pjournal/mef07g-sunforest
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.Rhistory
110 lines (110 loc) · 5.75 KB
/
.Rhistory
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
gdd <- read.csv("https://raw.githubusercontent.com/berkorbay/datasets/master/gdd/gdd_b12_levels.csv")
library(dplyr)
library(ggplot2)
#1.1) Gender
gdd_g <- gdd %>%
mutate(gender = case_when(female == 1 ~ 'female', female == 0 ~ 'male', female == 999 ~ 'all genders'))
gdd_g %>%
head(10)
#1.2) Urban / Rural
gdd_r <- gdd_g %>%
mutate(residence = case_when(urban == 1 ~ 'urban', urban == 0 ~ 'rural', urban == 999 ~ 'all residences'))
gdd_r %>%
head(10)
#1.3) Education Level
gdd_f <- gdd_r %>%
mutate(edu_level = case_when(edu == 1 ~ 'low', edu == 2 ~ 'medium', edu == 3 ~ 'high',edu == 999 ~ 'all levels'))
gdd_f %>%
head(10)
gdd_1 <- gdd %>%
filter(age== 999, female == 999, urban == 999, edu == 999) %>%
group_by(iso3, year) %>%
summarise(mean_values = (lowerci_95+upperci_95)/2, median) %>%
arrange(desc(median))
gdd_1
gdd_2 <- ggplot(gdd_1, aes(x = year, y = median, color = iso3)) + geom_line()
gdd_2
gdd_3 <- ggplot(gdd_1, aes(x = year, y = mean_values, color = iso3)) + geom_line()
gdd_3
gdd_4 <- gdd %>%
filter(age== 999, female == 999, urban == 999, edu == 999) %>%
group_by(iso3) %>%
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_4
#bar chart to compare country average intake:
gdd_5 <- ggplot(gdd_4, aes(x = iso3, y = mean_values, color = iso3)) + geom_col()
gdd_5
gdd_6 <- gdd %>%
filter(female == 999, urban == 999, edu == 999, age < 999, iso3 == "BGR" | iso3 == "ROU"| iso3 == "POL") %>%
group_by(age) %>%
#again to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_6
#visualise to see if there is any major change by different age group:
gdd_7 <- ggplot(gdd_6, aes(x = age, y = mean_values, fill = age)) + geom_col() + geom_text(aes(label = round(mean_values, 1)))
gdd_7
gdd_8 <- gdd %>%
filter(female == 999, urban == 999, edu == 999, age < 999) %>%
group_by(age) %>%
#again to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_8
gdd_9 <- ggplot(gdd_8, aes(x = age, y = mean_values, fill=age)) + geom_col() + geom_text(aes(label = round(mean_values, 1)))
gdd_9
gdd_10 <- gdd_f %>%
filter(age== 999, gender == "female" | gender == "male", residence == "urban" | residence == "rural", edu == 999) %>%
group_by(gender, residence) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_10
gdd_11 <- ggplot(gdd_10, aes(x=residence, y=mean_values, fill=gender)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_11
gdd_12 <- gdd_f %>%
filter(age== 999, gender == "female" | gender == "male", residence == "urban" | residence == "rural", edu == 999, iso3 == "BGR" | iso3 == "ROU"| iso3 == "POL") %>%
group_by(gender, residence) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_12
gdd_13 <- ggplot(gdd_12, aes(x=residence, y=mean_values, fill=gender)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_13
gdd_14 <- gdd_f %>%
filter(age== 999, gender == "female" | gender == "male", residence == "urban" | residence == "rural", edu == 999, iso3 == "EST") %>%
group_by(gender, residence) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_14
gdd_15 <- ggplot(gdd_14, aes(x=residence, y=mean_values, fill=gender)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_15
gdd_16 <- gdd_f %>%
filter(age== 999, urban == 999, edu_level == "low" | edu_level == "medium" | edu_level == "high", gender == "male" | gender == "female") %>%
group_by(edu_level, gender) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_16
gdd_17 <- ggplot(gdd_16, aes(x=gender, y=mean_values, fill=edu_level)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_17
gdd_18 <- gdd_f %>%
filter(age== 999, urban == 999, edu_level == "low" | edu_level == "medium" | edu_level == "high", gender == "male" | gender == "female", iso3 == "BGR" | iso3 == "ROU"| iso3 == "POL") %>%
group_by(edu_level, gender) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_18
gdd_19 <- ggplot(gdd_18, aes(x=gender, y=mean_values, fill=edu_level)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_19
gdd_20 <- gdd_f %>%
filter(age== 999, urban == 999, edu_level == "low" | edu_level == "medium" | edu_level == "high", gender == "male" | gender == "female", iso3 == "EST") %>%
group_by(edu_level, gender) %>%
#to ensure we take the average of seperate years rather than all the years:
summarise(mean_values = mean(lowerci_95+upperci_95)/2) %>%
arrange(desc(mean_values))
gdd_20
gdd_21 <- ggplot(gdd_20, aes(x=gender, y=mean_values, fill=edu_level)) + geom_bar(stat="identity") + expand_limits(x=0) + expand_limits(y=0) + geom_text(aes(label = round(mean_values, 1)), position = position_stack(vjust = 0.5))
gdd_21