---
title: "Dashboard Debangsu"
output: 
  flexdashboard::flex_dashboard:
    orientation: columns
    vertical_layout: fill
    social: menu
    source_code: embed

---

```{r setup, include=FALSE}
#install.packages("treemapify")
#install.packages("gganimate")

library(flexdashboard)
library(tidyverse)
library(plotly)
library(treemapify)
library(gganimate)
library(gifski)
library(png)
data<-read.csv("athlete_events.csv") 
region<-read.csv("noc_regions.csv")
```
Overall {data-icon="fab fa-r-project"}
===================================== 


Column {data-width=500}
-----------------------------------------------------------------------

### Sport and Events per year

```{r}
#rmarkdown::render("C:\\Users\\Debuw\\OneDrive\\Desktop\\Sem6\\DV\\R Proj\\Demo\\usingR.Rmd")

# sport event numbers per year 

fig_dat1<-data %>% filter(Year!=1906) %>% 
  group_by(Year,Season) %>% 
  summarise(sports=n_distinct(Sport),Sport_events=n_distinct(Event))%>%
  mutate(Sport=Season, Event=Season)
  
fig_dat1 %>% ggplot(aes(x=Year,y=Sport_events)) + 
  geom_line(aes(color=Event)) +
  geom_point(aes(color=Event)) +
  geom_bar(aes(x=Year, y=sports*1.5, fill=Sport),stat = "identity") +
  scale_fill_manual(values=c("orange","darkturquoise")) +
  scale_colour_manual(values = c("orange","darkturquoise")) +
  facet_grid(Sport~., scale="free_y") +
  labs(x="Year ") +
  scale_x_continuous(breaks = seq(1890 , 2016, 12)) +
  scale_y_continuous(name = "Number of Events",
                     sec.axis = sec_axis(~./1.5, name = "Number of Sports"))

```

Column {.tabset data-width=500}
-------       
### 2016 Rio Olympic Summer Games

```{r}
fig_dat2<-data %>% filter(Year==2016 & Season=="Summer") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat2 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12,
                    reflow = TRUE) +
  theme(legend.position = "none") +
  labs(title="Events number under 34 sports for 2016 Rio Summer Olympic Games")
```

### 2014 Sochi Olympic Winter Games

```{r}
fig_dat3<-data %>% filter(Year==2014 & Season=="Winter") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat3 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12) +
  theme(legend.position = "none") +
  labs(title="Events number under 15 sports for 2014 Sochi Winter Olympic Games")
```

### 2012 London Summer Games

```{r}
fig_dat3<-data %>% filter(Year==2012 & Season=="Summer") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat3 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12) +
  theme(legend.position = "none") +
  labs(title="Events number under 30 sports for 2012 London Summer Olympic Games")
```

### 2008 Beijing Summer Games

```{r}
fig_dat3<-data %>% filter(Year==2008 & Season=="Summer") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat3 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12) +
  theme(legend.position = "none") +
  labs(title="Events number under 32 sports for 2008 Beijing Summer Olympic Games")
```

### 2004 Athens Summer Games

```{r}
fig_dat3<-data %>% filter(Year==2004 & Season=="Summer") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat3 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12) +
  theme(legend.position = "none") +
  labs(title="Events number under 32 sports for 2004 Athens Summer Olympic Games")
```

### 2000 Sydney Summer Games

```{r}
fig_dat3<-data %>% filter(Year==2000 & Season=="Summer") %>% group_by(Sport) %>% summarise(Sport_events=n_distinct(Event))
fig_dat3 %>% ggplot(aes(area=Sport_events, fill=Sport, label=paste(Sport, Sport_events))) +
  geom_treemap() +
  geom_treemap_text(colour = "white",
                    place = "centre",
                    size = 12) +
  theme(legend.position = "none") +
  labs(title="Events number under 32 sports for 2000 Sydney Summer Olympic Games")
```

Athletes {data-icon="fa-swimmer"}
===================================== 

Column {.tabset data-width=500}
-------

### Summer Olympic Games number of Athletes
    
```{r}
# show the number of athlete
fig_dat4<-data %>% 
  filter(Season=="Summer" & Year!=1906) %>% 
  group_by(Year,Sex) %>% 
  summarise(Athletes=n_distinct(ID))
fig4<-fig_dat4 %>% ggplot(aes(x=Year,y=Athletes, fill=Sex)) + 
  geom_bar(stat="identity",position = "stack",color="black") +
  labs(x="Year", y="Number of Athletes Stacked") +
  scale_x_continuous(breaks = seq(1896 , 2016, 20))+
  scale_fill_manual(values = c("#c437bd", "#2656bd"))
ggplotly(fig4)
```

### Winter Olympic Games number of Athletes
    
```{r}
# show the number of athlete
fig_dat5<-data %>% 
  filter(Season=="Winter") %>% 
  group_by(Year,Sex) %>% 
  summarise(Athletes=n_distinct(ID))
fig5<-fig_dat5 %>% ggplot(aes(x=Year,y=Athletes, group=Sex, fill=Sex)) + 
  geom_bar(stat="identity",position = "stack",color="black") +
  labs(x="Year", y="Number of Athletes Stacked") +
  scale_x_continuous(breaks = seq(1896 , 2016, 20)) +
  scale_fill_manual(values = c("#c437bd", "#2656bd"))
ggplotly(fig5)
```

Athletes Vs Winners{data-icon="fa-trophy"}
===================================== 

Column {.tabset data-width=500}
-------       
### Summer Olympic Games - GOLD

```{r}
sub_data1<-data %>% filter(Medal=='Gold' & Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(Gold_Medal_count=n_distinct(Event)) 
sub_data2<-data %>% filter(Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(athletes_count=n_distinct(ID))
fig_dat6<-merge(sub_data2,sub_data1, by=c("Year","Season","NOC"))
fig_dat6  %>% filter(Season=="Summer") %>% 
  ggplot(aes(x=athletes_count, y=Gold_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of gold medal") + 
  facet_wrap(Year~.)
```

### Winter Olympic Games - GOLD

```{r}
fig_dat6  %>% filter(Season=="Winter") %>% 
  ggplot(aes(x=athletes_count, y=Gold_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of gold medal") + 
  facet_wrap(Year~.)
```

Column {.tabset data-width=500}
-------       
### Summer Olympic Games - SILVER

```{r}
sub_data1<-data %>% filter(Medal=='Silver' & Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(Silver_Medal_count=n_distinct(Event)) 
sub_data2<-data %>% filter(Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(athletes_count=n_distinct(ID))
fig_dat6<-merge(sub_data2,sub_data1, by=c("Year","Season","NOC"))
fig_dat6  %>% filter(Season=="Summer") %>% 
  ggplot(aes(x=athletes_count, y=Silver_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of silver medal") + 
  facet_wrap(Year~.)
```

### Winter Olympic Games - SILVER

```{r}
fig_dat6  %>% filter(Season=="Winter") %>% 
  ggplot(aes(x=athletes_count, y=Silver_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of silver medal") + 
  facet_wrap(Year~.)
```

Column {.tabset data-width=500}
-------       
### Summer Olympic Games - BRONZE

```{r}
sub_data1<-data %>% filter(Medal=='Bronze' & Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(Bronze_Medal_count=n_distinct(Event)) 
sub_data2<-data %>% filter(Year!=1906) %>% 
  group_by(Year,Season, NOC) %>% 
  summarise(athletes_count=n_distinct(ID))
fig_dat6<-merge(sub_data2,sub_data1, by=c("Year","Season","NOC"))
fig_dat6  %>% filter(Season=="Summer") %>% 
  ggplot(aes(x=athletes_count, y=Bronze_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of bronze medal") + 
  facet_wrap(Year~.)
```

### Winter Olympic Games - BRONZE

```{r}
fig_dat6  %>% filter(Season=="Winter") %>% 
  ggplot(aes(x=athletes_count, y=Bronze_Medal_count)) + 
  geom_point() +
  labs(x="Number of athletes", y="Number of bronze medal") + 
  facet_wrap(Year~.)
```

Medals {data-icon="fa-medal"}
===================================== 

Column {.tabset data-width=500}
-------

### Summer Olympic Games Gold Medal Leader Board
```{r}
# show the country with most gold Medal for each Summer Olympic Games
fig_dat6<-data %>% filter(Medal=='Gold') %>% 
  filter(Season=="Summer" & Year!=1906) %>%
  group_by(Year,NOC) %>% 
  summarise(Gold_Medal_count=n_distinct(Event)) %>% 
  top_n(1, Gold_Medal_count) %>% arrange(desc(Gold_Medal_count)) %>%
  merge(region,by="NOC")
fig_dat6 %>% ggplot(aes(x=factor(Year), y=Gold_Medal_count, fill=region)) + 
  geom_bar(stat='identity',position =   position_dodge()) + 
  geom_text(aes(x=factor(Year), y=Gold_Medal_count/2,label=NOC),size=2, position =position_dodge(width=1)) +
  geom_text(aes(x=factor(Year), y=Gold_Medal_count*1.05,label=Gold_Medal_count),size=2, position =position_dodge(width=1)) +
  coord_flip() +
  labs(x="Year",y="Gold Medals")
```

### Winter Olympic Games Gold Medal Leader Board
```{r}
# show the country with most gold Medal for each Summer Olympic Games
fig_dat7<-data %>% filter(Medal=='Gold') %>% 
  filter(Season=="Winter") %>%
  group_by(Year,NOC) %>% 
  summarise(Gold_Medal_count=n_distinct(Event)) %>% 
  top_n(1, Gold_Medal_count) %>% arrange(desc(Gold_Medal_count)) %>%
  merge(region,by="NOC")
fig_dat7 %>% ggplot(aes(x=factor(Year), y=Gold_Medal_count, fill=region)) + 
  geom_bar(stat='identity',position =   position_dodge()) + 
  geom_text(aes(x=factor(Year), y=Gold_Medal_count/2,label=NOC),size=2, position =position_dodge(width=1)) +
  geom_text(aes(x=factor(Year), y=Gold_Medal_count*1.05,label=Gold_Medal_count),size=2, position =position_dodge(width=1)) +
  coord_flip() +
  labs(x="Year",y="Gold Medals")
```

Column {.tabset data-width=500}
-------

### 2016 Rio Olympic Summer Leaderboard
```{r}
fig_dat8<-data %>% filter(Year==2016 & Season=="Summer" & Medal!="NA") %>% 
  group_by(NOC,Medal) %>% 
  summarise(Medal_count=n_distinct(Event)) %>%
  mutate(total_medal=sum(Medal_count)) %>%
  spread(Medal, Medal_count) %>% 
  arrange(desc(Gold),desc(total_medal)) %>%
  head(10) %>%
  ungroup() %>%
  mutate(gold_rank=1:10) %>%
  gather("Medal","count",-c(NOC,gold_rank,total_medal)) %>%
  mutate(Medal=factor(Medal, levels=c("Gold","Silver","Bronze"))) %>%
  merge(region,by="NOC")
fig_dat8 %>% ggplot(aes(x= reorder(region,-gold_rank),y=count, fill=Medal)) +
  geom_bar(stat = "identity", position = position_stack(reverse = T)) +
  scale_fill_manual(values=c("#FFCC33","#D7D7D7","#CC6600"))+
  labs(x="", y="") +
  coord_flip() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.background = element_blank()) 
  
```

### 2014 Sochi Olympic Winter Leaderboard
```{r}
fig_dat9<-data %>% filter(Year==2014 & Season=="Winter" & Medal!="NA") %>% 
  group_by(NOC,Medal) %>% 
  summarise(Medal_count=n_distinct(Event)) %>%
  mutate(total_medal=sum(Medal_count)) %>%
  spread(Medal, Medal_count) %>% 
  arrange(desc(Gold),desc(total_medal)) %>%
  head(10) %>%
  ungroup() %>%
  mutate(gold_rank=1:10) %>%
  gather("Medal","count",-c(NOC,gold_rank,total_medal)) %>%
  mutate(Medal=factor(Medal, levels=c("Gold","Silver","Bronze"))) %>%
  merge(region,by="NOC")
fig_dat9 %>% ggplot(aes(x= reorder(region,-gold_rank),y=count, fill=Medal)) +
  geom_bar(stat = "identity", position = position_stack(reverse = T)) +
  scale_fill_manual(values=c("#FFCC33","#D7D7D7","#CC6600"))+
  labs(x="", y="") +
  coord_flip() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.background = element_blank())
  
```

### 2012 London Olympic Summer Leaderboard
```{r}
fig_dat9<-data %>% filter(Year==2012 & Season=="Summer" & Medal!="NA") %>% 
  group_by(NOC,Medal) %>% 
  summarise(Medal_count=n_distinct(Event)) %>%
  mutate(total_medal=sum(Medal_count)) %>%
  spread(Medal, Medal_count) %>% 
  arrange(desc(Gold),desc(total_medal)) %>%
  head(10) %>%
  ungroup() %>%
  mutate(gold_rank=1:10) %>%
  gather("Medal","count",-c(NOC,gold_rank,total_medal)) %>%
  mutate(Medal=factor(Medal, levels=c("Gold","Silver","Bronze"))) %>%
  merge(region,by="NOC")
fig_dat9 %>% ggplot(aes(x= reorder(region,-gold_rank),y=count, fill=Medal)) +
  geom_bar(stat = "identity", position = position_stack(reverse = T)) +
  scale_fill_manual(values=c("#FFCC33","#D7D7D7","#CC6600"))+
  labs(x="", y="") +
  coord_flip() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.background = element_blank())
  
```

### 2008 Beijing Olympic Summer Leaderboard
```{r}
fig_dat9<-data %>% filter(Year==2008 & Season=="Summer" & Medal!="NA") %>% 
  group_by(NOC,Medal) %>% 
  summarise(Medal_count=n_distinct(Event)) %>%
  mutate(total_medal=sum(Medal_count)) %>%
  spread(Medal, Medal_count) %>% 
  arrange(desc(Gold),desc(total_medal)) %>%
  head(10) %>%
  ungroup() %>%
  mutate(gold_rank=1:10) %>%
  gather("Medal","count",-c(NOC,gold_rank,total_medal)) %>%
  mutate(Medal=factor(Medal, levels=c("Gold","Silver","Bronze"))) %>%
  merge(region,by="NOC")
fig_dat9 %>% ggplot(aes(x= reorder(region,-gold_rank),y=count, fill=Medal)) +
  geom_bar(stat = "identity", position = position_stack(reverse = T)) +
  scale_fill_manual(values=c("#FFCC33","#D7D7D7","#CC6600"))+
  labs(x="", y="") +
  coord_flip() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.background = element_blank())
  
```

### 2004 Athens Olympic Summer Leaderboard

```{r}
fig_dat9<-data %>% filter(Year==2004 & Season=="Summer" & Medal!="NA") %>% 
  group_by(NOC,Medal) %>% 
  summarise(Medal_count=n_distinct(Event)) %>%
  mutate(total_medal=sum(Medal_count)) %>%
  spread(Medal, Medal_count) %>% 
  arrange(desc(Gold),desc(total_medal)) %>%
  head(10) %>%
  ungroup() %>%
  mutate(gold_rank=1:10) %>%
  gather("Medal","count",-c(NOC,gold_rank,total_medal)) %>%
  mutate(Medal=factor(Medal, levels=c("Gold","Silver","Bronze"))) %>%
  merge(region,by="NOC")
fig_dat9 %>% ggplot(aes(x= reorder(region,-gold_rank),y=count, fill=Medal)) +
  geom_bar(stat = "identity", position = position_stack(reverse = T)) +
  scale_fill_manual(values=c("#FFCC33","#D7D7D7","#CC6600"))+
  labs(x="", y="") +
  coord_flip() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(),
        panel.background = element_blank())
  
```

Animated Medals {data-icon="fa-medal"}
===================================== 

```{r}
medalCounts <- data %>% filter(!is.na(Medal))%>% 
  group_by(NOC, Medal, Event, Games, Year) %>%
  summarize(isMedal=1)
medalCounts <-  medalCounts %>% 
  group_by(NOC, Medal, Year) %>%
  summarize(Count= sum(isMedal))
medalCounts <- left_join(medalCounts, region, by= "NOC" )
medalCounts <- medalCounts %>% 
  mutate (Team = region)
medalCounts <- medalCounts %>% select( Medal, Team, Count, Year)
levelsTeam <- medalCounts %>%
  group_by(Team) %>%
  summarize(Total=sum(Count)) %>%
  arrange(desc(Total)) %>%
  select(Team) %>%
  slice(10:1)
medalCounts$Team <- factor(medalCounts$Team, levels=levelsTeam$Team)
medalCounts <- medalCounts %>% filter(Team != "NA")
plotMedalsAnim<- ggplot(medalCounts, aes(x=Team, y=Count, fill=Medal)) +
  labs(x = "Nations", y = "Count", 
       title='Top 10 - Comparison over time, nations with the most medals', 
       subtitle = 'Olympic Games from 1896 to 2016 - Year: {frame_time}')  +
  transition_time(Year)+
  geom_col() +
  coord_flip() +
  scale_fill_manual(values=c("#CC6600","#FFCC33","#D7D7D7"))

animate(plotMedalsAnim,fps=2)


```


Novel {data-icon="fa-exclamation"}
===================================== 


Column {data-width=500}
-------

### Density Plot

```{r}
ggplot(data, aes(x=Age, fill=Sex))+
  geom_density(alpha=0.4)+
  labs(x = "Age", title = "Age Distribution of Olympians - Gender and Awards")+
  theme_minimal()+
  facet_wrap(~Medal)
```


Column {data-width=500}
-------

### Boxplot Age

```{r}

plotbox <- plot_ly(data, x = ~Age, type="box", color = I("black"), name = 'All athletes') %>%
  add_trace(name="Athletics (m)",data=filter(data[data$Sport %in% "Athletics",],Sex=="M"),color=I("purple"),fillcolor="red") %>%
  add_trace(name="Athletics (f)",data=filter(data[data$Sport %in% "Athletics",],Sex=="F"),color=I("green"),fillcolor="red") %>%
  add_trace(name="Cycling (m)",data=filter(data[data$Sport %in% "Cycling",],Sex=="M"),color=I("purple"),fillcolor="orange") %>%
  add_trace(name="Cycling (f)",data=filter(data[data$Sport %in% "Cycling",],Sex=="F"),color=I("green"),fillcolor="orange") %>%
  add_trace(name="Fencing (m)",data=filter(data[data$Sport %in% "Fencing",],Sex=="M"),color=I("purple"),fillcolor="cyan") %>%
  add_trace(name="Fencing (f)",data=filter(data[data$Sport %in% "Fencing",],Sex=="F"),color=I("green"),fillcolor="cyan") %>%
  add_trace(name="Gymnastics (m)",data=filter(data[data$Sport %in% "Gymnastics",],Sex=="M"),color=I("purple"),fillcolor="blue") %>%
  add_trace(name="Gymnastics (f)",data=filter(data[data$Sport %in% "Gymnastics",],Sex=="F"),color=I("green"),fillcolor="blue") %>%
  add_trace(name="Swimming (m)",data=filter(data[data$Sport %in% "Swimming",],Sex=="M"),color=I("purple"),fillcolor="grey") %>%
  add_trace(name="Swimming (f)",data=filter(data[data$Sport %in% "Swimming",],Sex=="F"),color=I("green"),fillcolor="grey")
plotbox

```

Wordcloud {data-icon="fa-cloud"}
===================================== 

Column {data-width=500}
-------

### WordCloud
```{r}
library("wordcloud")
team_ordering <- data %>% 
  select(Team) %>% 
  count(Team, sort = TRUE) %>% 
  group_by(Team) %>%
  with(wordcloud(Team, n, max.words = 30, colors = brewer.pal(20, "Set1")))
```

Column {data-width=500}
-------
```{r}


```

Map {data-icon="fa-map-location-dot"}
===================================== 

```{r}
medalCounts <- data %>% filter(!is.na(Medal))%>% 
  group_by(NOC, Medal, Event, Games) %>%
  summarize(isMedal=1)
medalCounts <-  medalCounts %>% 
  group_by(NOC, Medal) %>%
  summarize(Count= sum(isMedal))
medalCounts <- left_join(medalCounts, region, by= "NOC" ) %>% 
  select(region, NOC, Medal, Count)
medalCounts <- medalCounts %>%
  group_by(region) %>%
  summarize(Total=sum(Count))
data_regions <- medalCounts %>% 
  left_join(region,by="region") %>%
  filter(!is.na(region))
earth <- map_data("world")
earth <- left_join(earth, data_regions, by="region")
# PLOT MAP
plotMapMedals <- ggplot(earth, aes(x = long, y = lat, group = group)) +
  geom_polygon(aes(fill = Total, label= region)) +
  labs(x = "", y = "", 
       title="Map of nations - Most medals won", 
       subtitle = "") +
  guides(fill=guide_colourbar(title="medals")) +
  scale_fill_gradient(low="white",high="gold3")
plotMapMedals
ggplotly(plotMapMedals)
```