Initial Analysis.Rmd

---
title: "R Notebook"
output: html_notebook
---

This is an [R Markdown](http://rmarkdown.rstudio.com) Notebook. When you execute code within the notebook, the results appear beneath the code. 

Try executing this chunk by clicking the *Run* button within the chunk or by placing your cursor inside it and pressing *Ctrl+Shift+Enter*. 

```{r}
setwd("C:\\Users\\MascarenhasNeil\\Documents\\MPS Analytics\\Sem 2\\ALY6070 - Communication and Visualization for Data Analytics SEC Spring 2021 CPS\\Diplomacy Lab's Data Sets")
setwd("C:\\Users\\MascarenhasNeil\\Documents")
```


```{r}
df=read.csv("CommiteesDataCleaned.csv")
df2=read.csv("Committees_NonVoteV1.csv")
CommiteesData=read.csv("CommiteesData.csv")


```


```{r}
library(naniar)

library(ggplot2)
```


```{r}
vis_miss(df) + labs(x = "Look at all the missing ones", y = "Count", title = "For CommiteesData Dataset")
vis_miss(df2) + labs(x = "Look at all the missing ones", y = "Count", title = "For Committees_NonVoteV1 Dataset")

n_distinct(df$Agenda.short.form.title)
```


```{r}
gg_miss_var(df, show_pct = TRUE) + labs(y = "Look at all the missing ones")
gg_miss_var(df2) + labs(y = "Look at all the missing ones")
```


```{r}
names(df)
str(df,1)
names(df2)

str(CommiteesData)
```


```{r}
names(CommiteesData)


CommiteesData[CommiteesData$ï..Keywords!="",]


```


```{r}
names(CommiteesData)[1] <- c("Keywords")
names(CommiteesData)[2] <- c("Committee.Name")
KeyData = data.frame()
comD =  CommiteesData[CommiteesData$Keywords!="",]
    
    

# select(CommiteesData, c(1,8)) %>% filter(CommiteesData, ï..Keywords!="")


#i = 2
##nrow(comD)

for (i in 1:nrow(comD))
{

Keys = strsplit(as.character(comD[i,1]), split = "; ", fixed=T)
tempDF = data.frame()

for (key in 1:length(Keys[[1]])-1)
{
    tempDF = rbind(comD[i,-1],tempDF)
}

tempDF = cbind(Keys,tempDF )

names(tempDF) = names(CommiteesData)

KeyData = rbind(KeyData, tempDF)
## del tempDF = sample(data, size = length(Keys[[1]]), replace = T)

}

```



```{r}

```


```{r}

names(CommiteesData)[1] <- c("Keywords")
names(KeyData) <- names(CommiteesData)


nrow(KeyData)

head(KeyData,10)

write.csv(KeyData, 
          file="CommiteesDataPreProcessed.csv", append=TRUE, eol="\n",col.names=TRUE,sep=",",dec=".",na="NA", row.names = FALSE)


```


```{r}


Animals <- c("giraffes", "orangutans", "monkeys")
SF_Zoo <- c(20, 14, 23)
LA_Zoo <- c(12, 18, 29)
data <- data.frame(Animals, SF_Zoo, LA_Zoo)

plot_ly(data, x = ~Animals, y = ~SF_Zoo, type = 'bar', name = 'SF Zoo', text = SF_Zoo ) %>% 
    add_trace(y = ~LA_Zoo, name = 'LA Zoo') %>% 
    layout(yaxis = list(title = 'Count'), barmode = 'stack')






C_data %>%       # Applying group_by & summarise
            dplyr::filter(Keywords %in% input$selectKeys & CommiteeName %in% input$selectComm) %>%
            group_by(CommiteeName,Keywords) %>%
            summarise(count = count(Keywords)$freq) %>%
            ggplot(aes(x = count, y=reorder(Keywords, +count), fill=CommiteeName)) + 
            geom_bar(position="stack", stat="identity") +
            scale_x_continuous(breaks=seq(0,800,100)) +
            geom_text(aes(label = count),hjust = 1, colour = "white") +
            xlab("Count of Issues in each Commitee") + 
            ylab("Keywords") +
            theme_classic() + 
            theme(plot.title = element_text(hjust = 0.5, size = 15, face = "bold"))


```