ExploritoryAnalysis.Rmd

---
title: "Data Exploration"
author: "Christina De Cesaris"
date: "3/8/2021"
output: html_document
---

```{r}
library(tidyverse)
library(AER)
library(ggplot2)
library(plotly)
library(lmerTest)
library(MASS)
library(grid)
library(gridExtra)
library(DT)
```

# Expolritiy Analysis

```{r}
data(Guns)

dim(Guns)
summary(Guns)
str(Guns)


which(is.na(Guns)) #data clean

head(Guns)
```







```{r warning=FALSE, include=FALSE}
av_st = Guns %>%
  group_by(state) %>% # average all state
  summarise_all(mean) %>%
  mutate_if(is.numeric,funs(round(.,2)))
av_st
#av_st


av_st_r = Guns %>%
  group_by(state) %>% # average all state
  summarise(mean(violent),median(violent), sd(violent), max(violent), min(violent))%>%
  mutate_if(is.numeric,funs(round(.,2)))
av_st_r


av_yr_r = Guns %>%
  group_by(year) %>% # average all state
  summarise(mean(violent),median(violent), sd(violent), max(violent), min(violent))%>%
  mutate_if(is.numeric,funs(round(.,2)))
av_yr_r

av_styr = Guns %>%   # average each year each state
  group_by(year,state) %>%
  summarise_all(mean)%>%
  mutate_if(is.numeric,funs(round(.,2)))
av_styr

av_yr = Guns %>% # average all states each years
  group_by(year)%>%
  summarise_all(mean)%>%
  mutate_if(is.numeric,funs(round(.,2)))
av_yr
#delete null cols
av_yr=dplyr::select(av_yr,-c(12,13))
av_st=dplyr::select(av_st,-c(2,7,8,13))
```




```{r Yearly Trends All States}



v=Guns %>%
  ggplot( 
    aes(x=year,
        y=violent,
        group=state,
        color=state)) +
    geom_line() +
    labs(
      title="Yearly Trends in Violent Crime by State",
      x="School ID",
      y = "Violent Crime Rate per 100K Poeple") +
    theme(
      text = element_text(
        size=8,
        face = 'bold'),
        axis.text.x = element_text(angle=75,hjust=1),
        axis.ticks.x = element_line(size=0.5)) +
     scale_x_discrete(
       guide = guide_axis(n.dodge =1),
                     expand=c(0, 0)) +
    scale_fill_discrete(name = "State")


ggplotly(v)

r = Guns %>%
  
  ggplot( 
    aes(x=year,
        y=robbery,
        group=state,
        color=state)) +
    geom_line() +
    labs(
      title="Yearly Trends in Robbery Crime by State",
      x="School ID",
      y = "Robbery Crime Rate per 100K People") +
    theme(
      text = element_text(
        size=8,
        face = 'bold'),
        axis.text.x = element_text(angle=75,hjust=1),
        axis.ticks.x = element_line(size=0.5)) +
     scale_x_discrete(
       guide = guide_axis(n.dodge =1),
                     expand=c(0, 0)) +
     scale_fill_discrete(name = "State")


ggplotly(r)


m = Guns %>%
  
  ggplot(
    aes(x=year,
        y=(violent),
        group=year,
        col=year)) +
    geom_boxplot()+
  labs(
      title="USA Violent Crime by Year",
      x="Year",
      y = "Violent Crime Rate per 100K People") +
    theme(
      text = element_text(
        size=8,
        face = 'bold'),
        axis.text.x = element_text(angle=75,hjust=1),
        axis.ticks.x = element_line(size=0.5)) +
     scale_x_discrete(
       guide = guide_axis(n.dodge =1),
                     expand=c(0, 0)) +
    scale_fill_discrete(name = "year")


ggplotly(m) # DC is a gross outlier, consider removal 


```




```{r Interactive Datatables, include=FALSE}

names_yr=c("Year","Violent Crime Rate","Murder Rate","Robbery Rate","Prisoners","Percent Male","Population", "Income","Density")

dt_av_yr=datatable(av_yr,
          class = 'cell-border stripe',
          caption = htmltools::tags$caption(style = 'caption-side: bottom; text-align: center;','Table 1: ',
    htmltools::em(
      'Overall Averages By State')),
    colnames = c(
      names_yr))



names_st=c("State","Violent Crime Rate","Murder Rate","Robbery Rate","Prisoners","Percent Male","Population", "Income","Density")
dt_av_st=datatable(av_st,
          class = 'cell-border stripe',
          caption = htmltools::tags$caption(style = 'caption-side: bottom; text-align: center;','Table 1: ',
    htmltools::em(
      'Overall Averages By State')),
    colnames = c(
      names_st))



#RESPONSE


names_av_st_r=c("State","Mean Violence Rate", "Median Violence Rate", "Standard Deviation Violence Rate","Max Violence Rate","Min Violence Rate" )

dt_av_st_r=datatable(av_st_r,
          class = 'cell-border stripe',
          caption = htmltools::tags$caption(style = 'caption-side: bottom; text-align: center;','Table 1: ',
    htmltools::em(
      'Overall Averages By State')),
    colnames = c(
      names_av_st_r))



names_av_yr_r=c("Year","Mean Violence Rate", "Median Violence Rate", "Standard Deviation Violence Rate","Max Violence Rate","Min Violence Rate" )

dt_av_yr_r=datatable(av_yr_r,
          class = 'cell-border stripe',
          caption = htmltools::tags$caption(style = 'caption-side: bottom; text-align: center;','Table 1: ',
    htmltools::em(
      'Overall Averages By State')),
    colnames = c(
      names_av_yr_r))


```





```{r Average Crime USA Plot, include=FALSE}



crime_fig <- plot_ly(av_yr, x= ~year) %>%
  add_lines(
    y= ~(violent),
    name = "Violent Crime",
    type = 'scatter',
    mode = 'lines+markers') %>%
  
  add_lines(
    y= ~(robbery),
    name = "Robberies",
    visible = T) %>%
  
  add_lines(
    y= ~(murder),
    name = "Murder",
    visible = T) %>%
  
    add_lines(
    y= ~(prisoners),
    name = "Prisoners",
    visible = T) %>%
  
  
    layout(
      title = "Average Crime and Incarceration Rates in the USA",  
      xaxis = list(title = "Year",
                   tickangle = 75),
      yaxis = list(title = "Average per 100k People",
                   margin = margin)) 



crime_fig

```

```{r}
av_yr$other= (100-(av_yr$afam+av_yr$cauc))


crime_fig <- plot_ly(av_yr, x= ~year) %>%
  add_lines(
    y= ~(male),
    name = "Males: Ages 10-29",
    type = 'scatter',
    mode = 'lines+markers') %>%
  
  add_lines(
    y= ~(afam),
    name = "African Americans: Ages 10-64",
    visible = T) %>%
  
  add_lines(
    y= ~(cauc),
    name = "Caucation Americans: Ages 10-64",
    visible = T) %>%

  add_lines(
    y= ~(other),
    name = "Other American Ethnicities: Ages 10-64",
    visible = T) %>%
  
    layout(
      title = "Population Demographics",  
      xaxis = list(title = "Year",
                   tickangle = 75),
      yaxis = list(title = "Average percent of Population",
                   margin = margin),
      legend)
      



crime_fig
```










```{r ref.label=knitr::all_labels(), echo = T, eval = F}
```