hw1.Rmd

---
title: "Hw1"
author: "Kacie Kang"
date: "2/20/2018"
output: html_document
runtime: shiny
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

Winter Olympics Medals over Time

1. Medal Counts over Time

replace the old country names with new names.
```{r}
library(tidyverse)
library(plyr)
winter <- read.csv("data/winter.csv")

winter$Country<- revalue(winter$Country, c("EUN"="RUS","URS"="RUS"))
winter$Country<- revalue(winter$Country, c("EUA"="GER","FRG"="GER","GDR"="GER"))
winter$Country<- revalue(winter$Country, c("YUG"="SCG"))
winter$Country<- revalue(winter$Country, c("TCH"="SVK"))
winter$Country<- revalue(winter$Country, c("ROU"="ROM"))


winter

```

 bonus point
 count team medals as single one By deleting the same names

```{r}

winter2=winter [!duplicated(winter[c("Year", "City", "Sport", "Discipline", "Country", "Gender", "Event", "Medal" )]),]
winter2
```
library(magrittr)  
  # this is for the chain operator %>%
  # also contained in the tidyverse package
 Merge two spreadsheets, Calculate a summary of how many winter games each country competed in medaled in  and how many medals of each type the country won. 
```{r}
dictionary <- read.csv("data/dictionary.csv")

mydata <- merge(x=dictionary,y= winter, by.x=c('Code'), by.y=c('Country'))

alldata <- mydata  %>% 
     group_by(Country,Medal)  %>% 
     dplyr::summarise(Number = n())

Total <- mydata  %>%
  group_by(Country)  %>%
  dplyr::summarise(Total = n())  %>%
  arrange(desc(Total))  %>%
  dplyr::mutate(rank=row_number()) 

medalsum <-ggplot(Total, aes(x=Country, y=Total)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity")  + ylab("Medal Sum") 

gsbsum <-ggplot(alldata, aes(x=Country, y=Number, fill=Medal)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity") + coord_flip() + ylab("Medal sum by gsb") 

alldata
mydata
medalsum
gsbsum
```

top10 countries
and #6, I used label here
 
```{r}

top10 <- Total  %>%
  filter(rank<=10) 


ptop10 <- merge(alldata, top10, by="Country")
  
plottop10 <-ggplot(top10 , aes(x=reorder(Country,Total), y=Total)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity",fill = 'steelblue', colour = 'darkred') + ylab("Medal Sum") +geom_text(mapping = aes(label = Total))

set.seed(1)
plotbygsb <-ggplot(data_plot_top10, aes(x=Country, y=Number, fill=Medal))  + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity")   + ylab("Medal sum by gsb")+scale_fill_brewer(palette = 'Accent')+geom_text(mapping = aes(label = Number))

top10 
ptop10
plottop10
plotbygsb
```
show the trend of total numbers of medals over time of top 10 countries.
and compare
this one in more easier to see through and find the differences
```{r}
library("ggthemes")

pyear <- mydata  %>% 
     group_by(Country,Year)  %>% 
     dplyr::summarise(Number = n())

ptop10year <- merge(data_plot_time, top10, by="Country")


pptop10year <- ggplot(ptop10year, aes(Year, Number)) +
  geom_line(aes(color=Country, group=Country)) + ylab("Medal Sum") +
  theme_tufte()

pyear 
ptop10year
pptop10year
```

2. Medal Counts adjusted by Population  GDP
Just consider gold medals.
```{r}

dbyPopulationGDP <- merge(Total, dictionary, by="Country") %>%
  dplyr::mutate(dividedbyPopulation=Total/Population*1000000) %>%
  dplyr::arrange(desc(dividedbyPopulation)) %>%
  dplyr::mutate(rankbyPopulation=row_number()) %>%
  dplyr::mutate(dividedbyGDP=Total/GDP.per.Capita*1000000) %>%
  dplyr::arrange(desc(dividedbyGDP)) %>%
  dplyr::mutate(rankbyGDP=row_number()) 

dbyPopulationGDP

top10bypop <- dbyPopulationGDP %>% filter(rankbyPopulation<=10)  %>%
  arrange(desc(dividedbyPopulation))
top10bypop

set.seed(1234)
ptop10bypop <-ggplot(top10bypop, aes(x=reorder(Country,dividedbyPopulation), y=dividedbyPopulation)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity",fill = 'steelblue', colour = 'darkred') +
 ylab("byPopulation") 
ptop10bypop

top10bydpg <- dbyPopulationGDP %>% filter(rankbyGDP<=10)  %>%
  arrange(desc(dividedbyPopulation))
top10bydpg

ptop10bygdp <-ggplot(top10bydpg, aes(x=reorder(Country,dividedbyGDP), y=dividedbyGDP)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity",fill = 'steelblue', colour = 'darkred') +
 ylab("byGDP") 
ptop10bygdp


```
medal by country
```{r}
pbymedal <- ggplot(alldata, aes(x=Country, y=Number, fill=Country,label=Medal)) +
  geom_bar(width = 1,stat="identity") +
  coord_polar(theta = "y") +
  theme_bw() +
  guides(fill=guide_legend(title = "Country")) +
  theme(axis.text.y= element_blank(),
        axis.ticks = element_blank(),
        axis.text.x= element_blank(),
        axis.title.y= element_blank(),
)
pbymedal
```

```{r}
a<- merge(top10bypop, ptop10year, by="Country")
a [!duplicated(a[c(0:10 )]),]



ggplot(a)+geom_density(aes(x=Country, colour=Population))
ggplot(a)+geom_density(aes(x=Country, colour=GDP.per.Capita))

```

3. Host Country Advantage
it shows the host country has advantages
```{r}
library(tidyr)
library(rvest)
library(stringr)
library(plyr)
library("ggthemes")

wiki_hosts <- read_html("https://en.wikipedia.org/wiki/Winter_Olympic_Games")
hosts <- html_table(html_nodes(wiki_hosts, "table")[[5]], fill=TRUE)
hosts <- hosts[-1,1:3]
hosts$city <- str_split_fixed(hosts$Host, n=2, ",")[,1]
hosts$country <- str_split_fixed(hosts$Host, n=2, ",")[,2]


hosts$city<- revalue(hosts$city, c("St. Moritz" ="St.Moritz","Garmisch-Partenkirchen"= "Garmisch Partenkirchen"))

data_plot_average <- data_plot_time %>% 
  group_by(Country) %>% 
  mutate(Number_average_by_Year=sum(Number)/19) 
data_plot_average <- unite(data_plot_average, "Country_Year", Country, Year,remove = FALSE)


data_plot_average$host <-data_plot_average$Country_Year %in% c("France_1924","Switzerland_1928","United States_1932","Germany_1936","Switzerland_1948","Norway_1952","Italy_1956","United States_1960","Austria_1964","France_1968","Japan_1972","Austria_1976","United States_1980","Yugoslavia_1984","Canada_1988","France_1992","Norway_1994","Japan_1998","United States_2002","Italy_2006","Canada_2010","Russia_2014")

data_plot_average

ggplot(data_plot_average, aes(Year, Number))  +
  geom_line(aes(color=Country, group=Country)) + ylab("Medal Sum") +
  theme_tufte()


ggplot(data_plot_average, aes(x=Year, y=Country)) + geom_point(alpha = 0.5, size = 1,aes(fill = host, colour=host)) 
```




 4. Country success by sport / discipline / event
 I play Snowboard too. so I chose Snowboard to show the data
 I count the medal won by countries and present by pie pic
```{r}
dSnowboard <- mydata  %>%
  filter(Discipline == "Snowboard") %>% 
  group_by(Country)  %>%
  dplyr::summarise(SnowboardMedalbyCountry = n()) %>%
  dplyr::mutate(Snowboardmedalsum=sum(SnowboardMedalbyCountry))  %>%
  dplyr::mutate(SnowboardMedalratio=SnowboardMedalbyCountry/Snowboardmedalsum)  %>%
  arrange(desc(SnowboardMedalratio))  
  
pSnowboard <-ggplot(dSnowboard, aes(x=Country, y=SnowboardMedalratio)) + geom_point(alpha = 1, size = 2)+ ylab("Ratio") 


ggplot(dSnowboard, aes(x = "", y = SnowboardMedalratio, fill = Country)) + 
  geom_bar(stat = "identity") + 
  coord_polar(theta = "y")

dSnowboard
pSnowboard

```



5. Most successful athletes 
he won the most medals in 15 years. 
```{r}

most_Successful_Athletes <- winter %>% 
   group_by(Athlete,Country,Gender)  %>%
    dplyr::summarise(Total_Medal_by_Athletes = n()) %>%
    dplyr::arrange(desc(Total_Medal_by_Athletes))  

most_Successful_Athletes[1,1]

mostevent <- winter %>% 
  filter(Athlete == "BJOERNDALEN, Ole Einar") %>%
  group_by(Year,Medal)  %>%
   dplyr::summarise(Totalmedal= n()) 

gmost<-ggplot(mostevent, aes(x=Year, y=Totalmedal)) + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity",fill = 'steelblue', colour = 'darkred') +
 ylab("Totalmedal") 

gmost
```


6. Make two plots interactive
which shows up how much medal(S) BJOERNDALEN, Ole Einar won in different table/every year
which is easier for reader to zoom in the see the exact number
```{r}
library(devtools)
library(plotly)

ggplot(mostevent, aes(x=Year, y=Totalmedal,color = Year)) +  
     geom_point() + theme(legend.position="none") +
     facet_wrap(~ Year) + 
     ggtitle("Medal(s)BJOERNDALEN, Ole Einar won through years ")

ggplotly(plotbygsb)
plotbygsb <-ggplot(data_plot_top10, aes(x=Country, y=Number, fill=Medal))  + scale_y_continuous(expand = c(0,0)) +geom_bar(position="dodge",stat="identity")   + ylab("Medal sum by gsb")+scale_fill_brewer(palette = 'Accent')+geom_text(mapping = aes(label = Number))

```


7. Data Table

this contains data about snowboard medals won by countries and a ratio of which country won the most of it
because I play snowboard and I am very interested in it.
we can do search among the countries, medals by country, and sort by the small errow.
```{r}
library(DT)
datatable(dSnowboard) %>%
    formatStyle('Country',  color = 'white', 
                backgroundColor = 'blue', fontWeight = 'bold')

dSnowboard %>%
  datatable(
    rownames = FALSE,
    colnames = "Data of Snowboard medals",
    filter = list(position = "top"),
    options = list(
      dom = "Bfrtip",
      buttons = I("colvis"),
      language = list(sSearch = "Filter:")
    ),
    extensions = c("Buttons", "Responsive")
  )
```








This R Markdown document is made interactive using Shiny. Unlike the more traditional workflow of creating static reports, you can now create documents that allow your readers to change the assumptions underlying your analysis and see the results immediately. 

To learn more, see [Interactive Documents](http://rmarkdown.rstudio.com/authoring_shiny.html).

## Inputs and Outputs

You can embed Shiny inputs and outputs in your document. Outputs are automatically updated whenever inputs change.  This demonstrates how a standard R plot can be made interactive by wrapping it in the Shiny `renderPlot` function. The `selectInput` and `sliderInput` functions create the input widgets used to drive the plot.

```{r eruptions, echo=FALSE}
inputPanel(
  selectInput("n_breaks", label = "Number of bins:",
              choices = c(10, 20, 35, 50), selected = 20),
  
  sliderInput("bw_adjust", label = "Bandwidth adjustment:",
              min = 0.2, max = 2, value = 1, step = 0.2)
)

renderPlot({
  hist(faithful$eruptions, probability = TRUE, breaks = as.numeric(input$n_breaks),
       xlab = "Duration (minutes)", main = "Geyser eruption duration")
  
  dens <- density(faithful$eruptions, adjust = input$bw_adjust)
  lines(dens, col = "blue")
})
```

## Embedded Application

It's also possible to embed an entire Shiny application within an R Markdown document using the `shinyAppDir` function. This example embeds a Shiny application located in another directory:

```{r tabsets, echo=FALSE}
shinyAppDir(
  system.file("examples/06_tabsets", package = "shiny"),
  options = list(
    width = "100%", height = 550
  )
)
```

Note the use of the `height` parameter to determine how much vertical space the embedded application should occupy.

You can also use the `shinyApp` function to define an application inline rather then in an external directory.

In all of R code chunks above the `echo = FALSE` attribute is used. This is to prevent the R code within the chunk from rendering in the document alongside the Shiny components.