Charlottesville Crime Report

1. Data Loading
2. Data preparation (please contact me for the proprocessing)
   1. Formatting the Year
   2. Crime type allocation
3. Data mining
   1. Year-wise crime counts
   2. Gender-wise crime counts
   3. Race-wise crime counts

1. Data Loading

Arrests<- read_csv("Arrests.csv")  ## Uncleaned data

## Rows: 13777 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): ArrestDatetime, Statute, StatuteDescription, Street, Race, Sex
## dbl (2): ArrestID, HouseNumber
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

2. Data Preparation

(hidden; please ask me if you need this part of code)

2b. Formatting Date

2b. Crime-type allocation

3. Data mining

3a. Year-wise crime counts

ggplot(data=Arrests,aes(x=Year,fill=CrimeType))+ 
  geom_bar(position='stack') + theme_classic() +
  scale_fill_manual(values = c("steelblue", "cadetblue",
                               "darkseagreen","bisque","coral","coral3")) +
   
  xlab("Year") + ylab("Crimes Count")+
  ggtitle("Charlottesville Crime Report (2017 - 2021)")+ 
  theme(plot.title = element_text(hjust = 0.5,size=32))+
  theme(axis.text.x=element_text(size=18),
        axis.title.x =element_text(size=18),
        axis.text.y = element_text(size=18),
        axis.title.y= element_text(size=18),
        legend.text = element_text(size=12),
        legend.title = element_text(size=16))

3b. Gender-wise crime counts

# Cleaning the Gender variable
remove=  which(Arrests$Sex=="Unknown" | is.na(Arrests$Sex)) 
Arrests_Gender<- Arrests[-remove,]  

ggplot(data=Arrests_Gender,aes(x=Year,fill=CrimeType))+ 
  geom_bar(position='stack') + theme_classic() +
  scale_fill_manual(values = c("steelblue", "cadetblue",
                               "darkseagreen","bisque","coral","coral3")) +
   
  xlab("Year") + ylab("Crimes Count")+
  ggtitle("Charlottesville Crime Report (2017 - 2021)")+ 
  theme(plot.title = element_text(hjust = 0.5,size=32))+
  theme(axis.text.x=element_text(size=20),
        axis.title.x =element_text(size=20),
        axis.text.y = element_text(size=20),
        axis.title.y= element_text(size=20),
        legend.text = element_text(size=15),
        legend.title = element_text(size=20),
        strip.text = element_text(size = 20))+
  facet_wrap(~Sex,)

3c. Race-wise crime counts

# Cleaning the Gender variable
remove= c(which(is.na(Arrests$Race)),which(Arrests$Race=="doc"),which( Arrests$Race=="nwt"), which( Arrests$Race=="jpg"),which( Arrests$Race=="Unknown"))
Arrests_Race<-Arrests[-remove,]

ggplot(data=Arrests_Race,aes(x=Year,fill=CrimeType))+ 
  geom_bar(position='stack') + theme_classic() +
  scale_fill_manual(values = c("steelblue", "cadetblue",
                               "darkseagreen","bisque","coral","coral3")) +
   
  xlab("Year") + ylab("Crimes Count")+
  ggtitle("Charlottesville Crime Report (2017 - 2021)")+ 
  theme(plot.title = element_text(hjust = 0.5,size=32))+
  theme(axis.text.x=element_text(size=20),
        axis.title.x =element_text(size=20),
        axis.text.y = element_text(size=20),
        axis.title.y= element_text(size=20),
        legend.text = element_text(size=15),
        legend.title = element_text(size=20),
        strip.text = element_text(size = 20))+
  facet_wrap(~Race,scales = "free_y")