SOC712 HW2
Import ‘FBI Crime Data 2016’ dataset
library(readr, verbose = FALSE)
FBI <- read_csv("J:/SOC712/R12022524_SL050.csv", col_names = TRUE)## Parsed with column specification:
## cols(
## .default = col_character()
## )## See spec(...) for full column specifications.head(FBI)Therer are 2,589 observations and 35 variables.
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionnames(FBI)## [1] "FIPS"
## [2] "Name of Area"
## [3] "Qualifying Name"
## [4] "Nation"
## [5] "State"
## [6] "County"
## [7] "Total Population (2016 est.)"
## [8] "Total Violent and Property Crimes"
## [9] "Total Violent and Property Crimes: Violent Crimes"
## [10] "Total Violent and Property Crimes: Property Crimes"
## [11] "Total Violent and Property Crimes Rate"
## [12] "Total Violent and Property Crimes Rate: Violent Crimes Rate"
## [13] "Total Violent and Property Crimes Rate: Property Crimes Rate"
## [14] "Total Violent Crimes"
## [15] "Total Violent Crimes: Murders and Nonnegligent Manslaughters"
## [16] "Total Violent Crimes: Rape Revised Definition"
## [17] "Total Violent Crimes: Rape Legacy Definition"
## [18] "Total Violent Crimes: Robberies"
## [19] "Total Violent Crimes: Aggravated Assaults"
## [20] "Total Violent Crimes Rate"
## [21] "Total Violent Crimes Rate: Murders and Nonnegligent Manslaughters Rate"
## [22] "Total Violent Crimes Rate: Rape Revised Definition Rate"
## [23] "Total Violent Crimes Rate: Rape Legacy Definition Rate"
## [24] "Total Violent Crimes Rate: Robberies Rate"
## [25] "Total Violent Crimes Rate: Aggravated Assaults Rate"
## [26] "Total Property Crimes"
## [27] "Total Property Crimes: Burglaries"
## [28] "Total Property Crimes: Larcenies"
## [29] "Total Property Crimes: Motor Vehicle Thefts"
## [30] "Total Property Crimes Rate"
## [31] "Total Property Crimes Rate: Burglaries Rate"
## [32] "Total Property Crimes Rate: Larcenies Rate"
## [33] "Total Property Crimes Rate: Motor Vehicle Thefts Rate"
## [34] "Arsons"
## [35] "Arsons Rate"dim(FBI)## [1] 2589 35FBI_sel <- select(FBI, "Qualifying Name", "State", ("Total Population (2016 est.)" : "Arsons Rate"))
dim(FBI_sel)## [1] 2589 31arrange(FBI_sel, State)Creating new variables of different states.
AL <- filter(FBI_sel, State == "01")
head(AL)AZ <- filter(FBI_sel, State == "04")
AR <- filter(FBI_sel, State == "05")
CA <- filter(FBI_sel, State == "06")
CO <- filter(FBI_sel, State == "08")
DE <- filter(FBI_sel, State == "10")
FL <- filter(FBI_sel, State == "12")
GA <- filter(FBI_sel, State == "13")
HI <- filter(FBI_sel, State == "15")
ID <- filter(FBI_sel, State == "16")
IL <- filter(FBI_sel, State == "17")
IN <- filter(FBI_sel, State == "18")
IA <- filter(FBI_sel, State == "19")
KS <- filter(FBI_sel, State == "20")
KY <- filter(FBI_sel, State == "21")
LA <- filter(FBI_sel, State == "22")
ME <- filter(FBI_sel, State == "23")
MD <- filter(FBI_sel, State == "24")
MI <- filter(FBI_sel, State == "26")
MN <- filter(FBI_sel, State == "27")
MS <- filter(FBI_sel, State == "28")
MS <- filter(FBI_sel, State == "29")
MT <- filter(FBI_sel, State == "30")
NE <- filter(FBI_sel, State == "31")
NV <- filter(FBI_sel, State == "32")
NH <- filter(FBI_sel, State == "33")
NJ <- filter(FBI_sel, State == "34")
NM <- filter(FBI_sel, State == "35")
NY <- filter(FBI_sel, State == "36")
NC <- filter(FBI_sel, State == "37")
ND <- filter(FBI_sel, State == "38")
OH <- filter(FBI_sel, State == "39")
OK <- filter(FBI_sel, State == "40")
OR <- filter(FBI_sel, State == "41")
PA <- filter(FBI_sel, State == "42")
SC <- filter(FBI_sel, State == "45")
SD <- filter(FBI_sel, State == "46")
TN <- filter(FBI_sel, State == "47")
TX <- filter(FBI_sel, State == "48")
UT <- filter(FBI_sel, State == "49")
VT <- filter(FBI_sel, State == "50")
VA <- filter(FBI_sel, State == "51")
WA <- filter(FBI_sel, State == "53")
WV <- filter(FBI_sel, State == "54")
WI <- filter(FBI_sel, State == "55")
WY <- filter(FBI_sel, State == "56")According to the U.S. Census Bureau The 10 Most Populous States on July 1, 2015, are, by order: 1. California (CA) 2. Texas (TX) 3. Florida (FL) 4. New York (NY) 5. Illinois (IL) 6. Pennsylvania (PA) 7. Ohio (OH) 8. Georgia (GA) 9. North Carolina (NC) 10. Michigan (MI)
In this assignment, I will Compare if the above order applies to the crime rate (Violent and property crimes separately)
Computing states: total population, total violent and property crimes, total violent crimes, and total property crimes
CA_var = select(CA, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
TX_var = select(TX, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
FL_var = select(FL, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
NY_var = select(NY, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
IL_var = select(IL, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
PA_var = select(PA, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
OH_var = select(OH, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
GA_var = select(GA, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
NC_var = select(NC, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
MI_var = select(MI, "Total Population (2016 est.)", "Total Violent and Property Crimes", "Total Violent and Property Crimes: Violent Crimes", "Total Violent and Property Crimes: Property Crimes")
class(TX_var) ## [1] "tbl_df" "tbl" "data.frame"CA_val <- type.convert(CA_var)
CA_fin <- colSums(CA_val, na.rm = TRUE)
TX_val <- type.convert(TX_var)
TX_fin <- colSums(TX_val, na.rm = TRUE)
CA_val <- type.convert(CA_val)
CA_fin <- colSums(CA_val, na.rm = TRUE)
FL_var <- type.convert(FL_var)
FL_fin <- colSums(FL_var, na.rm = TRUE)
NY_var <- type.convert(NY_var)
NY_fin <- colSums(NY_var, na.rm = TRUE)
IL_var <- type.convert(IL_var)
IL_fin <- colSums(IL_var, na.rm = TRUE)
PA_var <- type.convert(PA_var)
PA_fin <- colSums(PA_var, na.rm = TRUE)
OH_var <- type.convert(OH_var)
OH_fin <- colSums(OH_var, na.rm = TRUE)
GA_var <- type.convert(GA_var)
GA_fin <- colSums(GA_var, na.rm = TRUE)
NC_var <- type.convert(NC_var)
NC_fin <- colSums(NC_var, na.rm = TRUE)
MI_var <- type.convert(MI_var)
MI_fin <- colSums(MI_var, na.rm = TRUE)data <- data.frame(CA = CA_fin, TX = TX_fin, FL = FL_fin, NY = NY_fin, IL = IL_fin, PA = PA_fin, OH = OH_fin, GA = GA_fin, NC = NC_fin, MI = MI_fin)
datatable = t(data)
table## Total Population (2016 est.) Total Violent and Property Crimes
## CA 38379130 129923
## TX 27635924 138052
## FL 19660770 248222
## NY 9943131 47097
## IL 12286935 18455
## PA 7188286 44
## OH 8522964 40570
## GA 8066326 136817
## NC 6696357 48468
## MI 9607636 33971
## Total Violent and Property Crimes: Violent Crimes
## CA 26286
## TX 19850
## FL 37499
## NY 4179
## IL 2328
## PA 37
## OH 2832
## GA 15650
## NC 4565
## MI 5643
## Total Violent and Property Crimes: Property Crimes
## CA 103637
## TX 118202
## FL 210723
## NY 42918
## IL 16127
## PA 7
## OH 37738
## GA 121167
## NC 43903
## MI 28328Renaming and Calculating
as_tibble(table)table <- as.data.frame(table)
sapply(table, class)## Total Population (2016 est.)
## "numeric"
## Total Violent and Property Crimes
## "numeric"
## Total Violent and Property Crimes: Violent Crimes
## "numeric"
## Total Violent and Property Crimes: Property Crimes
## "numeric"table <- rename(table, Total_Population = "Total Population (2016 est.)", Total_Crimes = "Total Violent and Property Crimes", Total_Violent_Crimes = "Total Violent and Property Crimes: Violent Crimes", Total_Property_Crimes = "Total Violent and Property Crimes: Property Crimes")
table1 <- mutate(table, Violent_Crime_Rate = Total_Violent_Crimes / Total_Population * 100000, Property_Crime_Rate = Total_Property_Crimes / Total_Population * 100000)
State <- list("CA", "TX", "FL", "NY", "IL", "PA", "OH", "GA", "NC", "MI")
table1$State <- State
table1 <- select(table1, State, Total_Population, Total_Crimes, Total_Violent_Crimes, Total_Property_Crimes, Violent_Crime_Rate, Property_Crime_Rate)
table1Visualization
library(ggplot2)
ggplot(data = table1, aes(Violent_Crime_Rate)) + geom_histogram(color = 'red', bins = 10) + labs(title = paste("Violent Crime Rates of 10 States"))
ggplot(data = table1, aes(Property_Crime_Rate)) + geom_histogram(color = 'blue', bins = 10) + labs(title = paste("Property Crime Rates of 10 States"))
References
United States Census Bureau. (2015). North Carolina Becomes Ninth State With 10 Million or More People, Census Bureau Reports. Retrieved from https://www.census.gov/newsroom/press-releases/2015/cb15-215.html