library(dplyr)
## Warning: package 'dplyr' was built under R version 4.3.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.3.2
data= read.csv("C:/Users/Chafiaa/Downloads/489q-934x.csv")
head(data)
df2 <- data[data$cause_of_death == 'Firearm-related injury',]
head(df2)
columns_to_exclude <- c(
"rate_type", "unit", "rate_overall", "rate_sex_female", "rate_sex_male",
"rate_age_1_4", "rate_age_5_14", "rate_age_15_24", "rate_age_25_34",
"rate_age_35_44", "rate_age_45_54", "rate_age_55_64", "rate_65_74",
"rate_age_75_84", "rate_age_85_plus"
)
# exclude specific columns
df3 <- df2[, !names(df2) %in% columns_to_exclude]
head(df3)
df4 <- df3[c(7), ]
head(df4)
df5 <- df4 %>% select(-c(time_period, cause_of_death))
# rename columns
head(df5)
df6 <- df5 %>% rename("Year" = "year_and_quarter",
"AL" = "rate_alabama",
"AK" = "rate_alaska",
"AZ" = "rate_arizona",
"AR" = "rate_arkansas",
"CA" = "rate_california",
"CO" = "rate_colorado",
"CT" = "rate_connecticut",
"DC" = "rate_district_of_columbia",
"DE" = "rate_delaware",
"FL" = "rate_florida",
"GA" = "rate_georgia",
"HI" = "rate_hawaii",
"ID" = "rate_idaho",
"IL" = "rate_illinois",
"IN" = "rate_indiana",
"IA" = "rate_iowa",
"KS" = "rate_kansas",
"KY" = "rate_kentucky",
"LA" = "rate_louisiana",
"ME" = "rate_maine",
"MD" = "rate_maryland",
"MA" = "rate_massachusetts",
"MI" = "rate_michigan",
"MN" = "rate_minnesota",
"MS" = "rate_mississippi",
"MO" = "rate_missouri",
"MT" = "rate_montana",
"NC" = "rate_north_carolina",
"ND" = "rate_north_dakota",
"NE" = "rate_nebraska",
"NV" = "rate_nevada",
"NH" = "rate_new_hampshire",
"NJ" = "rate_new_jersey",
"NM" = "rate_new_mexico",
"NY" = "rate_new_york",
"OH" = "rate_ohio",
"OK" = "rate_oklahoma",
"OR" = "rate_oregon",
"PA" = "rate_pennsylvania",
"RI" = "rate_rhode_island",
"SC" = "rate_south_carolina",
"SD" = "rate_south_dakota",
"TN" = "rate_tennessee",
"TX" = "rate_texas",
"UT" = "rate_utah",
"VT" = "rate_vermont",
"VA" = "rate_virginia",
"WA" = "rate_washington",
"WV" = "rate_west_virginia",
"WI" = "rate_wisconsin",
"WY" = "rate_wyoming")
head(df6)
df6$Year <- sub("2020 Q4", "2020", df6$Year)
head(df6)
row.names(df6) <- NULL
head(df6)
df6 <- df6 %>% select(-c(Year))
head(df6)
#creat and rename columns
MORTALITYRATE <- df6 %>%
pivot_longer(cols = everything(),
names_to = "State.a",
values_to = "Mortality.Rate")
head(MORTALITYRATE)
MORTALITYRATE$ID <- seq_along(MORTALITYRATE$State.a)
head(MORTALITYRATE)# data that we can work with
GLAW <- read.csv("https://raw.githubusercontent.com/enidroman/Data_608_Knowledge_and_Visual_Analytics/main/2020%20GUN%20LAW%20SCORECARD.csv")
head(GLAW)
columns_to_exclude2 <- c(
"Gun.Law.Strength.Ranked.", "Grade", "Gun.Death.Rate.Ranked.", "Gun.Death.Rate.per.100K.", "X",
"X.1"
)
# remove some columns & use ID
GLAW1<- GLAW[, !names(GLAW) %in% columns_to_exclude2]
colnames(GLAW1)[colnames(GLAW1) == "Grade.Rank"] <- "Rank"
GLAW1$ID <- seq_along(GLAW1$State)
GLAW1 <- GLAW1[, c("ID", "State", "Rank")]
head(GLAW1)
MORTALITY_GUNLAW <- merge(MORTALITYRATE, GLAW1, by = "ID")
head(MORTALITY_GUNLAW)
library(plotly)
## Warning: package 'plotly' was built under R version 4.3.3
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.3.2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggplot2)
heat_map1 <- plot_geo(MORTALITY_GUNLAW, locations = ~State.a, text = ~State, z = ~Mortality.Rate) %>%
add_trace(
type = "choropleth",
colors = "Purples",
locationmode = "USA-states"
) %>%
colorbar(title = "Mortality Rate") %>%
layout(
title = "Mortality Rate in USA",
geo = list(
scope = "usa",
projection = list(type = "albers usa"),
showlakes = TRUE,
lakecolor = toRGB("white")
),
annotations = list(
list(
x = 0.5,
y = .95,
xref = "paper",
yref = "paper",
text = "Gun violence and mass shootings are a regular occurrence in USA",
showarrow = FALSE,
font = list(size = 14)
),
list(
x = 0.05,
y = 0.05,
xref = "paper",
yref = "paper",
text = "The number of deaths per 100,000 total population.",
showarrow = FALSE
)
)
)
heat_map1
# From this map we can see that the highest-rated mortality rate is close to 30 or more: Mississippi has the highest mortality rate followed by Louisiana then Alaska, New Mexico and Wyoming .
heat_map2 <- plot_geo(MORTALITY_GUNLAW, locations = ~State.a, text = ~State, z = ~Rank) %>%
add_trace(
type = "choropleth",
colors = "Purples",
locationmode = "USA-states"
) %>%
colorbar(title = "Gun Law Rank") %>%
layout(
title = "Gun Law Rank in USA",
geo = list(
scope = "usa",
projection = list(type = "albers usa"),
showlakes = TRUE,
lakecolor = toRGB("white")
),
annotations = list(
list(
x = 0.05,
y = 1.00,
xref = "paper",
yref = "paper",
text = " Gun laws reduce firearm gun deaths?",
showarrow = FALSE,
font = list(size = 14)
),
list(
x = 0.05,
y = 0.05,
xref = "paper",
yref = "paper",
text = "Rank is from 1 being an A and 5 being an F",
showarrow = FALSE
)
)
)
heat_map2
# The lowest-ranked states on gun law in USA: Mississippi, Louisiana, Alaska, Main, and Wyoming
# From the 02 heat maps that I created, I can say that in states where the gun law is a failure like Alaska, Mississippi, the mortality related to gun violence seems to be high, therefore we can say that when gun laws are strict it will be safe and the mortality related to guns will be lower .