STA313 Draft.Rmd

---
title: "STA313 Final"
author: "Eric Yin"
date: "`r Sys.Date()`"
output: html_document
runtime: shiny
---

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


```{r}
library(tidyverse)
```


```{r}
kaggle_raw <- read.csv("US Mass Shooting 1966-2019 (cleaned).csv")
mj_raw <- read.csv("Mother Jones - Mass Shootings Database, 1982 - 2022 - Sheet1.csv")

##functions

#defined function just to make column splitting easier
reassign <- function(column, final) {
  temp <- c()
  for (i in 1:length(column)){
     temp <- append(temp, column[[i]][final])
  }
  return(temp)
}

#defined function to change a repeated typo
change <- function(column, typo, correction){
  temp <- c()
  for (i in 1:length(column)){
    if(identical(column[i],typo)){
      temp <- append(temp, correction)
      } else {
    temp <- append(temp, column[i])
      }
  }
  return(temp)
}


##creating date columns

#create month label
kaggle_raw <- kaggle_raw %>% mutate(Month = str_split(Date, "/"))
kaggle_raw$Month <- reassign(kaggle_raw$Month, 1)
kaggle_raw <- kaggle_raw %>% mutate(Month = as.numeric(Month))

#confirms no weird categories plus sums to total observations
# kaggle_raw %>% group_by(Month) %>% summarize(n= n())
# sum((kaggle_raw %>% group_by(Month) %>% summarize(n= n()))$n)

#create year label
kaggle_raw <- kaggle_raw %>% mutate(Year = str_split(Date, "/"))
kaggle_raw$Year <- reassign(kaggle_raw$Year, 3)
kaggle_raw <- kaggle_raw %>% mutate(Year = case_when(Year > 19 ~ paste0("19", as.character(Year)), TRUE ~ paste0("20", as.character(Year)))) %>% mutate(Year = as.numeric(Year))

#confirms no weird categories plus sums to total observations
# kaggle_raw %>% group_by(Year) %>% summarize(n= n()) %>% arrange(desc(Year)) %>% print(n = 50)
# sum((kaggle_raw %>% group_by(Year) %>% summarize(n= n()))$n)

#create day label
kaggle_raw <- kaggle_raw %>% mutate(Day = str_split(Date, "/"))
kaggle_raw$Day <- reassign(kaggle_raw$Day, 2)
kaggle_raw <- kaggle_raw %>% mutate(Day = as.numeric(Day))

#confirms no weird categories plus sums to total observations
# kaggle_raw %>% group_by(Day) %>% summarize(n= n()) %>% arrange(desc(Day)) %>% print(n = 50)
# sum((kaggle_raw %>% group_by(Day) %>% summarize(n= n()))$n)

## same for mj

#create month label
mj_raw <- mj_raw %>% mutate(Month = str_split(date, "/"))
mj_raw$Month <- reassign(mj_raw$Month, 1)
mj_raw <- mj_raw %>% mutate(Month = as.numeric(Month))

#confirms no weird categories plus sums to total observations
# mj_raw %>% group_by(Month) %>% summarize(n= n())
# sum((mj_raw %>% group_by(Month) %>% summarize(n= n()))$n)

#create day label
mj_raw <- mj_raw %>% mutate(Day = str_split(date, "/"))
mj_raw$Day <- reassign(mj_raw$Day, 2)
mj_raw <- mj_raw %>% mutate(Day = as.numeric(Day))

# #confirms no weird categories plus sums to total observations
# mj_raw %>% group_by(Day) %>% summarize(n= n()) %>% arrange(desc(Day)) %>% print(n = 50)
# sum((mj_raw %>% group_by(Day) %>% summarize(n= n()))$n)

#this one is duplicated with slightly different locations
mj_raw <- mj_raw %>% filter(location != "Parkland, Washington")

##merging data

#add columns in from mj
newnames <- c("MJ.Summary", "Prior.MH", "MH.Details", "Legal.Weapons", "Obtained.Where", "Weapon.Type", "Weapon.Details", "Main.Source", "MH.Source", "Extra.Source", "Shooting.Type")

oldnames <- c("summary", "prior_signs_mental_health_issues", "mental_health_details", "weapons_obtained_legally", "where_obtained", "weapon_type", "weapon_details", "sources", "mental_health_sources", "sources_additional_age", "type")

#select new columns that we need, plus rearrange them
mj_raw <- mj_raw %>% dplyr::select(location, year, Month, Day, all_of(oldnames))
colnames(mj_raw) <- c("Location", "Year", "Month", "Day", newnames)

#join data
joined_data <- left_join(kaggle_raw, mj_raw, by = c("Location", "Year", "Month", "Day"))


#dataset manipulation

#create state variable
data <- joined_data %>% mutate(State = str_trim(reassign(str_split(joined_data$Location, ", "), 2))) %>% mutate(State = change(State, "CA", "California") %>% change("NV", "Nevada") %>% change("Lousiana", "Louisiana") %>% change("San Diego", "California") %>% change("Souderton", "Pennsylvania")) %>% mutate(State = case_when(is.na(State) ~ "Washington", TRUE ~ State))

#clean Cause
data <- data %>% mutate(Cause = str_to_title(Cause)) %>% mutate(Cause = case_when(Cause == "-999" ~ "Unknown",
                                          Cause %in% c("Breakup", "Domestic Disputer", "Domestic Dispute") ~ "Domestic",
                                          Cause %in% c("Anger", "Fight", "Argue", "Assaulting", "Business Dispute", "Fight", "Frustration", "Neighbors Conflict", "Revenge") ~ "Anger",
                                          Cause %in% c("Suspension", "Unemployment", "Failing Exams") ~ "Employment/School Related",
                                          Cause %in% c("Drunk", "Fun", "Robbery") ~ "Other",
                                          Cause %in% c("Racism", "Religious Radicalism") ~ "Religion/Race Related",
                                          TRUE ~ Cause))



#clean weapon types

# data <- data %>% mutate(Handgun = grepl("handgun", str_to_lower(Weapon.Type)) | grepl("pistol", str_to_lower(Weapon.Type)) | grepl("revolver", str_to_lower(Weapon.Type)), Rifle = grepl("rifle", str_to_lower(Weapon.Type)), Shotgun = grepl("shotgun", str_to_lower(Weapon.Type)))

data <- data %>% mutate(Weapon.Type = case_when(
  is.na(Weapon.Type) ~ "Unknown",
  TRUE ~ Weapon.Type
))

#check listings
# data %>% group_by(State) %>% summarize(n = n()) %>% arrange(State) %>% print(n = 50)

#confirm no data was lost
# nrow(data)
# sum((data %>% group_by(State) %>% summarize(n = n()))$n)

write.csv(data,file='STA313_Final_Project/finaldata_313.csv', row.names=FALSE)

```


```{r}
class(data$Year)



max = 2019
min = 1966
response = "Fatalities"

temp <- data %>% filter(Year < max) %>% filter(Year > min)
feds <- read.csv("STA313_Final_Project/federal_laws.csv")

t <- temp %>% group_by(Year) %>% summarize(n = n())
x <- tibble(Year = c(1969:2019), count = rep(0, 51))
y <- left_join(x, t, by = c("Year")) %>%  mutate(n = case_when(is.na(n) ~ 0, TRUE ~ as.numeric(as.character(n))))

product <- temp %>% group_by(Year) %>% 
  summarise(count = sum(Fatalities)) %>% 
  ggplot(aes(x = Year, y = count)) + geom_line()

product_laws <- geom_point(data = (temp %>% filter(Year %in% feds$Year_Implemented) %>% group_by(Year) %>% summarise(count = sum(Fatalities))), aes(x = Year, y = count)) 

product + product_laws + geom_label()


```

```{r}
policies <- read.csv("../policies.csv")

p <- policies%>% filter(Year < 1981, Type == "background check") %>% mutate(X1 = str_split(X1, "\n"), X2 = str_split(X2, "\n"), X3 = str_split(X3, "\n"), X4 = str_split(X4, "\n"))


final_list <- list()
bc <- c("X2")

for(i in nrow(p)){
  p2 <- p %>% select(all_of(bc))
  tlist <- list()
    for(j in 1:length(bc)){
      tlist[[length(tlist) + 1]] <- p2[,j][[1]]
    }
  final_list[[length(final_list) + 1]] <- Reduce(intersect, tlist)
}

Reduce(intersect, final_list)

df1 <- 

ggplot() + geom_line(aes(x = 1:10, y = 1:10)) + geom_line(aes(x = 1:10, y = -1:-10))


```


# CODE FOR GGPLOT
```{r}
# this is for incidents by year
temp_data %>% mutate(Year <- as.numeric(Year)) %>% 
  group_by(Year) %>% 
  summarise(count = n()) %>% 
  ggplot(aes(x = Year, y = count,  group=1)) + 
  geom_line(stat = "identity")

# fatalities per year
temp_data %>% mutate(Year <- as.numeric(Year),
                     Fatalities <- as.numeric(Fatalities)) %>% 
  group_by(Year, Fatalities) %>% 
  summarise(count = n()) %>% 
  ggplot(aes(x = Year, y = Fatalities,  group=1)) + 
  geom_line(stat = "identity")


# injured per year 
temp_data %>% mutate(Year <- as.numeric(Year),
                     Injured <- as.numeric(Injured)) %>% 
  group_by(Year, Injured) %>% 
  summarise(count = n()) %>% 
  ggplot(aes(x = Year, y = Injured,  group=1)) + 
  geom_line(stat = "identity")

#victims per year
temp_data %>% mutate(Year <- as.numeric(Year),
                     Total.victims <- as.numeric(Total.victims)) %>% 
  group_by(Year, Total.victims) %>% 
  summarise(count = n()) %>% 
  ggplot(aes(x = Year, y = Total.victims,  group=1)) + 
  geom_line(stat = "identity")

# Group by State
temp_data %>% mutate(Year <- as.numeric(Year)) %>% 
  group_by(Year, State) %>% 
  summarise(count = n()) %>% 
  ggplot(aes(x = Year, y = count,  fill = factor(State))) + 
  geom_bar(stat = "identity", position = "fill")



```

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. 

Hi

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}
library(shiny)
library(dplyr)
library(ggplot2)

```






# Define UI for app that draws a histogram ----
```{r eruptions, echo=FALSE}
ui <- fluidPage(
  
  data <- read.csv("finaldata_313.csv"),
  
  # App title ----
  titlePanel("Us mass shooting"),
  
  # Sidebar layout with input and output definitions ----
  sidebarLayout(
    
    # Sidebar panel for inputs ----
    sidebarPanel(
      
      # Input: Slider for the number of bins ----
      sliderInput(inputId = "bins",
                  label = "Dates:",
                  min = as.Date("1966-01-01","%Y-%m-%d"),
                  max = as.Date("2019-12-31","%Y-%m-%d"),
                  value=as.Date("2016-12-01"),timeFormat="%Y-%m-%d")
    ),
    

    
    # Main panel for displaying outputs ----
    mainPanel(
      
      # Output: Histogram ----
      plotOutput(outputId = "distPlot")
      
    )
  )
)
```


```{r}
shinyServer(function(input, output) {
			output$trendPlot <- renderGraph({
									bins <- input$bins
									x <- temp_data$Year
									min = as.Date("1966-01-01","%Y-%m-%d")
                  max = as.Date("2019-12-31","%Y-%m-%d")
									trace1 <- list(x = x,
																 autobinx = FALSE,
																 xbins = list(start = min,
																							end = max,
																							size =  ((max-min)/bins)
																 							),
																 type = "histogram"
																 )

					data <- list(trace1)
					layout<- list(xaxis =
												list(title = "Ratings",
														 range = c(min, max),
														 autorange = FALSE,
														 autotick = FALSE,
														 tick0 = min,
														 dtick = ((max-min)/bins)
												)
										)

		return(list(
					 list(id = "trendPlot",
								task = "newPlot",
								data = data,
								layout = layout
				)
		))
	})
})
```

```{r eruptions, echo=FALSE}

# Define server logic required to draw a histogram ----
server <- function(input, output) {
  
  # Histogram of the Old Faithful Geyser Data ----
  # with requested number of bins
  # This expression that generates a histogram is wrapped in a call
  # to renderPlot to indicate that:
  #
  # 1. It is "reactive" and therefore should be automatically
  #    re-executed when inputs (input$bins) change
  # 2. Its output type is a plot
  output$distPlot <- renderPlot({
    
    x    <- temp_data$Year
    bins <- seq(min(x), max(x), length.out = input$bins + 1)
    
    temp_data %>% mutate(Year <- as.numeric(Year)) %>% 
       group_by(Year) %>% 
       summarise(count = n()) %>% 
       ggplot(aes(x = Year, y = count,  group=1)) + 
       geom_line(stat = "identity")
    
  })
  
}
```

```{r eruptions, echo=FALSE}

shinyApp(ui, server)
```