-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.Rhistory
165 lines (165 loc) · 11.2 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
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
setwd("/Users/administrator/Desktop/doping olympische spiele")
library(dplyr)
library(ggplot2)
cases <- read.csv("IAAF-doping-cases-clean-deutsch.csv", stringsAsFactors = F, encoding="utf-8")
View(cases)
setwd("/Users/administrator/Desktop/doping olympische spiele")
library(dplyr)
library(ggplot2)
cases <- read.csv("IAAF-doping-cases-clean-deutsch.csv", stringsAsFactors = F, encoding="utf-8")
#athl <- read.csv("participants-by-event.csv", quote="", encoding="utf-8", sep=";")
#names(athl) = c("Jahr","Ort","Name","Land","Geschlecht","Sport","Disziplin","Medal")
library(tidyr)
read.csv("iaaf-teilnehmer.csv",stringsAsFactors = F)
athl <- read.csv("iaaf-teilnehmer.csv",stringsAsFactors = F)
View(athl)
names(athl)[1] = "Land"
write.csv(athl, "iaaf-teilnehmer.csv", row.names = F)
#fälle pro jahr
cpy <- cases %>% group_by(Jahr) %>% summarize(count=length(unique(Name)))# %>%
group_by(Jahr) %>% summarize(count=sum(count))# %>% arrange(-count)
tmp <- athl %>% group_by(Jahr) %>% summarize(sum = sum(count))
cpy <- left_join(cpy, tmp, by=c("Jahr")) %>% mutate(norm = count/sum)
write.csv(cpy, "fälleprojahr.csv", row.names = F)
#fälle pro land
cpc <- cases %>% group_by(COUNTRY, Land, Jahr) %>% filter(Jahr >= 1996) %>%
summarize(count=length(unique(Name))) %>%
group_by(COUNTRY, Land) %>% summarize(count=sum(count)) %>% arrange(-count)
tmp <- athl %>% filter(Jahr >= 1996) %>% group_by(Land) %>% summarize(sum = sum(count))
cpc <- left_join(cpc, tmp, by=c("COUNTRY" = "Land")) %>% mutate(norm = count/sum)
write.csv(cpc, "fälleproland.csv", row.names = F)
fälle nach geschlecht
cpg <- cases %>% group_by(Geschlecht, Jahr) %>% summarize(count=length(unique(Name))) %>% filter(Jahr >= 1996) %>%
group_by(Geschlecht) %>% summarize(count=sum(count)) %>%arrange(-count)
tmp <- athl %>% filter(Jahr >= 1996) %>% group_by(Geschlecht) %>% summarize(sum=sum(count))
#spread(Geschlecht, count) %>% mutate(wshare = Women/(Women+Men))
cpg <- left_join(cpg, tmp, by="Geschlecht") %>% mutate(norm = count/sum)
write.csv(cpg, "fällenachgeschlecht.csv", row.names = F)
cpg <- cpg %>% ungroup
ggplot(cpg, aes(x=Geschlecht, y=count, fill=Geschlecht)) + theme_minimal() + #scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anzahl überführter Leichtathleten nach Geschlecht seit 1996") +
theme(legend.position="none", axis.text.x = element_text(angle=45,hjust=1), panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=0.9), aes(x=Geschlecht, label=paste0(count,"/",sum)), vjust=-0.5)
pdf("results/doping-results.pdf", width=14)
#fälle pro jahr
ggplot(cpy, aes(x=Jahr, y=count)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +
ggtitle("Doping Violations in Athletics at Olympic Games") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(count)), vjust=-1)
'
#fälle pro jahr normiert
ggplot(cpy, aes(x=Jahr, y=norm)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +
ggtitle("Anteil überführter Athleten über die Jahre") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(round(norm*100, 2),"%")), vjust=-1) + scale_y_continuous(labels=scales::percent)
#tests pro jahr
ggplot(tests, aes(x=Year, y=Number.of.tests)) + theme_light() + scale_x_continuous(breaks = rev(unique(tests$Year))) +
ggtitle("Gesamtzahl an Doping-Tests bei den olympischen Spielen") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Year, label=paste0(Number.of.tests)), vjust=-1)
'
#fälle pro land
#sonstiges kategorie einrichten
cpc <- cpc %>% ungroup %>% arrange(-count)
x <- cpc %>% mutate(Land = c(cpc$Land[1:5], rep("Sonstige",length(cpc$Land)-5)))
x <- mutate(x, Land = factor(x$Land, levels=c("Türkei","Belarus","Ukraine","Russland","USA","Sonstige"))) %>%
group_by(Land) %>% summarize(count=sum(count), sum=sum(sum), norm=count/sum)
x$Land <- factor(c("Turkey","Belarus","Ukraine","Russia","USA","Others"), levels=c("Turkey","Belarus","Ukraine","Russia","USA","Others"))
#sonstiges summe und norm
tmp <- athl %>% filter(Jahr >= 1996) %>% group_by(Land) %>% summarize(sum = sum(count))
tmp2 = filter(tmp, Land != "TUR" & Land != "RUS" & Land != "BLR" & Land != "UKR" & Land != "USA")
x$sum[6] <- sum(tmp2$sum); x$norm[6] <- x$count[6] / x$sum[6]
#gesamtdurchschnitt
cmean = sum(cpc$count)/sum(tmp$sum) #0.00514601
ggplot(x, aes(x=Land, y=norm, fill=Land)) + theme_minimal() + scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Share of Athletes with Annulled olympic performances due to Doping since incl. 1996") +
geom_hline(yintercept = cmean) + theme(legend.position="none") +
geom_text(aes(x=1, y=cmean, label=paste("Total mean =", paste0(round(cmean*100,2),"%"))), hjust=0,vjust=-0.5)+
geom_text(position= position_dodge(width=0.9), aes(x=Land, label=paste0(count,"/",sum)), vjust=-0.5)
#fälle nach geschlecht
cpg <- cpg %>% ungroup
ggplot(cpg, aes(x=Geschlecht, y=count, fill=Geschlecht)) + theme_minimal() + #scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anzahl überführter Leichtathleten nach Geschlecht seit 1996") +
theme(legend.position="none", axis.text.x = element_text(angle=45,hjust=1), panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=0.9), aes(x=Geschlecht, label=paste0(count,"/",sum)), vjust=-0.5)
'
#fälle nach geschlecht und jahr
cpgy <- cpgy %>% ungroup %>% arrange(-norm)
ggplot(cpgy, aes(x=Jahr, y=norm, fill=Geschlecht)) + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +theme_minimal() +
geom_bar(stat="identity",position="dodge") + ggtitle("Doping-Fälle nach Geschlecht und Jahr") +
theme(legend.position="bottom", panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=3.5), aes(x=Jahr, label=paste0(count,"/",sum)), vjust=-0.5)
'
dev.off()
ggplot(cpy, aes(x=Jahr, y=count)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +
ggtitle("Doping Violations in Athletics at Olympic Games") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(count)), vjust=-1)
ggplot(cpy, aes(x=Jahr, y=count)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpy$Jahr))) +
ggtitle("Doping Violations in Athletics at Olympic Games") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(count)), vjust=-1)
cpc <- cpc %>% ungroup %>% arrange(-count)
x <- cpc %>% mutate(Land = c(cpc$Land[1:5], rep("Sonstige",length(cpc$Land)-5)))
x <- mutate(x, Land = factor(x$Land, levels=c("Türkei","Belarus","Ukraine","Russland","USA","Sonstige"))) %>%
group_by(Land) %>% summarize(count=sum(count), sum=sum(sum), norm=count/sum)
#x$Land <- factor(c("Turkey","Belarus","Ukraine","Russia","USA","Others"), levels=c("Turkey","Belarus","Ukraine","Russia","USA","Others"))
#sonstiges summe und norm
tmp <- athl %>% filter(Jahr >= 1996) %>% group_by(Land) %>% summarize(sum = sum(count))
tmp2 = filter(tmp, Land != "TUR" & Land != "RUS" & Land != "BLR" & Land != "UKR" & Land != "USA")
x$sum[6] <- sum(tmp2$sum); x$norm[6] <- x$count[6] / x$sum[6]
#gesamtdurchschnitt
cmean = sum(cpc$count)/sum(tmp$sum) #0.00514601
ggplot(x, aes(x=Land, y=norm, fill=Land)) + theme_minimal() + scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anteil überführter Leichtathleten seit 1996") +
geom_hline(yintercept = cmean) + theme(legend.position="none") +
geom_text(aes(x=1, y=cmean, label=paste("Total mean =", paste0(round(cmean*100,2),"%"))), hjust=0,vjust=-0.5)+
geom_text(position= position_dodge(width=0.9), aes(x=Land, label=paste0(count,"/",sum)), vjust=-0.5)
cpg <- cpg %>% ungroup
ggplot(cpg, aes(x=Geschlecht, y=count, fill=Geschlecht)) + theme_minimal() + #scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anzahl überführter Leichtathleten nach Geschlecht seit 1996") +
theme(legend.position="none", axis.text.x = element_text(angle=45,hjust=1), panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=0.9), aes(x=Geschlecht, label=paste0(count,"/",sum)), vjust=-0.5)
pdf("results/alle-normiert.pdf", width=14)
#fälle pro jahr
ggplot(cpy, aes(x=Jahr, y=count)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpy$Jahr))) +
ggtitle("Doping Violations in Athletics at Olympic Games") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(count)), vjust=-1)
'
#fälle pro jahr normiert
ggplot(cpy, aes(x=Jahr, y=norm)) + theme_light() + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +
ggtitle("Anteil überführter Athleten über die Jahre") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Jahr, label=paste0(round(norm*100, 2),"%")), vjust=-1) + scale_y_continuous(labels=scales::percent)
#tests pro jahr
ggplot(tests, aes(x=Year, y=Number.of.tests)) + theme_light() + scale_x_continuous(breaks = rev(unique(tests$Year))) +
ggtitle("Gesamtzahl an Doping-Tests bei den olympischen Spielen") + geom_line(colour="orange") + geom_point() +
geom_text(aes(x=Year, label=paste0(Number.of.tests)), vjust=-1)
'
#fälle pro land
#sonstiges kategorie einrichten
cpc <- cpc %>% ungroup %>% arrange(-count)
x <- cpc %>% mutate(Land = c(cpc$Land[1:5], rep("Sonstige",length(cpc$Land)-5)))
x <- mutate(x, Land = factor(x$Land, levels=c("Türkei","Belarus","Ukraine","Russland","USA","Sonstige"))) %>%
group_by(Land) %>% summarize(count=sum(count), sum=sum(sum), norm=count/sum)
#x$Land <- factor(c("Turkey","Belarus","Ukraine","Russia","USA","Others"), levels=c("Turkey","Belarus","Ukraine","Russia","USA","Others"))
#sonstiges summe und norm
tmp <- athl %>% filter(Jahr >= 1996) %>% group_by(Land) %>% summarize(sum = sum(count))
tmp2 = filter(tmp, Land != "TUR" & Land != "RUS" & Land != "BLR" & Land != "UKR" & Land != "USA")
x$sum[6] <- sum(tmp2$sum); x$norm[6] <- x$count[6] / x$sum[6]
#gesamtdurchschnitt
cmean = sum(cpc$count)/sum(tmp$sum) #0.00514601
ggplot(x, aes(x=Land, y=norm, fill=Land)) + theme_minimal() + scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anteil überführter Leichtathleten seit 1996") +
geom_hline(yintercept = cmean) + theme(legend.position="none") +
geom_text(aes(x=1, y=cmean, label=paste("Total mean =", paste0(round(cmean*100,2),"%"))), hjust=0,vjust=-0.5)+
geom_text(position= position_dodge(width=0.9), aes(x=Land, label=paste0(count,"/",sum)), vjust=-0.5)
#fälle nach geschlecht
cpg <- cpg %>% ungroup
ggplot(cpg, aes(x=Geschlecht, y=count, fill=Geschlecht)) + theme_minimal() + #scale_y_continuous(labels=scales::percent) +
geom_bar(stat="identity") + ggtitle("Anzahl überführter Leichtathleten nach Geschlecht seit 1996") +
theme(legend.position="none", axis.text.x = element_text(angle=45,hjust=1), panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=0.9), aes(x=Geschlecht, label=paste0(count,"/",sum)), vjust=-0.5)
'
#fälle nach geschlecht und jahr
cpgy <- cpgy %>% ungroup %>% arrange(-norm)
ggplot(cpgy, aes(x=Jahr, y=norm, fill=Geschlecht)) + scale_x_continuous(breaks = rev(unique(cpgy$Jahr))) +theme_minimal() +
geom_bar(stat="identity",position="dodge") + ggtitle("Doping-Fälle nach Geschlecht und Jahr") +
theme(legend.position="bottom", panel.background = element_rect(fill="white")) +
geom_text(position= position_dodge(width=3.5), aes(x=Jahr, label=paste0(count,"/",sum)), vjust=-0.5)
'
dev.off()