Analyses of Boston Crimes
Brian Riely
2026-10-11
Introduction
The data used in this analysis is titled “Boston Crimes.” The information provided by this data set includes the details of crimes that have been committed from Jan 1, 2023-Dec 29, 2024
Dataset
The 17 column names are: incident_number, offense_code, offense_code_group, offense_description, district, reporting_area, shooting, occurred_on_date, year, month, day_of_week, hour, ucr_part, street, lat, long, location
There are 155,959 rows.
There are 332, 030 NA’s in the data frame; however, offense_description,
district, year, month, day_of_week, hour, and street have zero NA’s.
Findings
The following tabs provide detailed information regarding crimes that happened Boston from Jan 1, 2023 to Dec 29, 2024
Tab 1
The bar chart shows the 10 worse districts in the Boston area. D4 covers the South End neighborhood of Boston, along with parts of Back Bay, lower Roxbury, and the Fenway area. B2 covers the neighborhood of Roxbury
df <- read.csv("//apporto.com/dfs/LOYOLA/Users/briely_loyola/Desktop/2023 to date.csv")
library(dplyr)
library(DescTools)
library(ggplot2)
library(data.table)
library(scales)
# count the number of criminal offensives in each district
DistrictCount <- data.frame(count(df,DISTRICT ))
#compute the values of the top 10
DistrictCount<-DistrictCount[order(DistrictCount$n, decreasing = TRUE),]
result = DistrictCount[1:10,]
# set up a way to label each bar in the bar graph
values = result$n
# create bar graph
ggplot(DistrictCount[1:10,], aes(x =reorder(DISTRICT,-n),y = n ))+
geom_bar(colour ="darkblue", fill="lightblue", stat = "identity")+
labs(title = "Number of Crimes in Boston Districts (Top 10)", x = "District", y = "Number of Incidents")+
theme(plot.title=element_text(hjust = 0.5))+
geom_text(aes(label = values),vjust= -0.5,color="black")
Tab 2
The stacked bar chart shows the number of crimes per month for the worst 10 districts
df <- read.csv("//apporto.com/dfs/LOYOLA/Users/briely_loyola/Desktop/2023 to date.csv")
head(df)
library(dplyr)
library(DescTools)
library(ggplot2)
library(data.table)
library(scales)
# count the number of criminal offensives in each district
DistrictCount <- data.frame(count(df,DISTRICT ))
DistrictCount
#compute the values of the top 10
DistrictCount<-DistrictCount[order(DistrictCount$n, decreasing = TRUE),]
result = DistrictCount[1:10,]
df_reasons <-count(df, DISTRICT)
head(df_reasons)
df_reasons <- df_reasons[order(df_reasons$n,decreasing = TRUE),]
top_reasons <- df_reasons$DISTRICT[1:10]
top_reasons
new_df <- df %>%
filter(DISTRICT %in% top_reasons)%>%
select(MONTH,DISTRICT)%>%
group_by(DISTRICT,MONTH)%>%
summarise(n=length(DISTRICT),.groups = 'keep')%>%
data.frame()
head(new_df)
agg_tot <-new_df %>%
select(DISTRICT,n) %>%
group_by(DISTRICT) %>%
summarise(tot = sum(n),.groups = 'keep')%>%
data.frame()
agg_tot
library(RColorBrewer)
library(ggthemes)
library(plyr)
str(new_df)
new_df$MONTH<-as.factor(new_df$MONTH)
ggplot(new_df, aes(x = reorder(DISTRICT,n,sum), y =n,fill = MONTH ))+
geom_bar(stat="identity")+
coord_flip()+
labs(title="Number of Crimes by Districts in Boston", x="Districts in Boston", y = "Number of Crimes")+
theme_light()+
theme(plot.title=element_text(hjust=0.5))+
scale_fill_brewer(palette = "Paired")+
geom_text(data=agg_tot, aes(x=DISTRICT,y = tot, label=tot, fill=NULL),hjust=-0.1)+
scale_y_continuous(labels=comma, limits = c(0,25000))
Tab 3
Shows the number of crimes per hour
df <- read.csv("//apporto.com/dfs/LOYOLA/Users/briely_loyola/Desktop/2023 to date.csv")
#check to make sure the data file is correct
library(dplyr)
library(ggplot2)
library(scales)
library(ggthemes)
library(ggrepel)
hours_df<-df %>%
select(HOUR) %>%
group_by(HOUR) %>%
summarise(n = length(HOUR), .groups ='keep') %>%
data.frame()
#check to make sure data is correct
#check to make sure hour is an integer
#str(hours_df)
x_axis_labels = min(hours_df$HOUR):max(hours_df$HOUR)
hi_lo <- hours_df %>%
filter(n == min(n) | n == max(n)) %>%
data.frame()
ggplot(hours_df, aes(x =HOUR, y = n))+
geom_line(color = 'black', linewidth =1)+
geom_point(shape =21, size=4, color = 'red', fill = 'white')+
labs(x ="Hour",y = "Number of Crimes", title="Number of Crimes by Hour", caption="Source: Boston Crime Data")+
scale_y_continuous(labels=comma)+
theme_light()+
theme(plot.title=element_text(hjust = 0.5))+
scale_x_continuous(labels=x_axis_labels, breaks=x_axis_labels,minor_breaks=NULL)+
geom_point(data = hours_df %>% filter(HOUR == 23), aes(x = HOUR, y = n), shape = 21, size = 4, fill = 'red', color = 'red') +
geom_point(data= hi_lo,aes(x =HOUR, y = n), shape =21, size =4, fill = 'red',color = 'red')+
geom_label_repel(aes(label = ifelse(n==max(n) | n==min(n)|HOUR == max(HOUR), scales::comma(n), "")),
box.padding = 2,
point.padding = 1,
size = 4,
color='Grey50',
segment.color='darkblue')
### Tab 4
This chart shows the number of crimes per month and for each month, it shows the number of crimes per day.
df <- read.csv("//apporto.com/dfs/LOYOLA/Users/briely_loyola/Desktop/2023 to date.csv")
#check to make sure the data file is correct
head(df)## INCIDENT_NUMBER OFFENSE_CODE OFFENSE_CODE_GROUP OFFENSE_DESCRIPTION DISTRICT
## 1 232007173 3115 NA INVESTIGATE PERSON B3
## 2 232004454 3301 NA VERBAL DISPUTE B2
## 3 232006290 3115 NA INVESTIGATE PERSON A1
## 4 232024939 3114 NA INVESTIGATE PROPERTY B3
## 5 232006708 423 NA ASSAULT - AGGRAVATED B2
## 6 232007629 3115 NA INVESTIGATE PERSON E5
## REPORTING_AREA SHOOTING OCCURRED_ON_DATE YEAR MONTH DAY_OF_WEEK HOUR
## 1 0 2023-01-27 22:44:00+00 2023 1 Friday 22
## 2 316 0 2023-01-17 20:21:00+00 2023 1 Tuesday 20
## 3 0 2023-01-24 00:00:00+00 2023 1 Tuesday 0
## 4 0 2023-03-31 17:14:00+00 2023 3 Friday 17
## 5 0 2023-01-26 09:00:00+00 2023 1 Thursday 9
## 6 681 0 2023-01-29 14:55:00+00 2023 1 Sunday 14
## UCR_PART STREET Lat
## 1 NA FAVRE ST 42.27166
## 2 NA HAROLD ST 42.31260
## 3 NA HANOVER ST 42.36570
## 4 NA BLUE HILL AVE 42.29279
## 5 NA HUTCHINGS ST 42.31027
## 6 NA WASHINGTON ST & METROPOLITAN AVE\nBOSTON MA 02131\n 42.28141
## Long Location
## 1 -71.09953 (42.271661031027065, -71.09953455161765)
## 2 -71.09288 (42.3125962960786, -71.09287583752645)
## 3 -71.05289 (42.3656993584582, -71.05289203191269)
## 4 -71.08852 (42.29278799134922, -71.08851953962399)
## 5 -71.08931 (42.310268910354935, -71.08931055058088)
## 6 -71.13355 (42.28140997944129, -71.13355001769462)library(dplyr)
library(ggplot2)
colnames(df)## [1] "INCIDENT_NUMBER" "OFFENSE_CODE" "OFFENSE_CODE_GROUP"
## [4] "OFFENSE_DESCRIPTION" "DISTRICT" "REPORTING_AREA"
## [7] "SHOOTING" "OCCURRED_ON_DATE" "YEAR"
## [10] "MONTH" "DAY_OF_WEEK" "HOUR"
## [13] "UCR_PART" "STREET" "Lat"
## [16] "Long" "Location"library(scales)
library(ggthemes)
library(RColorBrewer)
# change numbers 1,2, etc to January, February, etc
df$month_name <- month.name[df$MONTH]
#head(df$month_name)
days_df <- df %>%
select(month_name, DAY_OF_WEEK) %>%
group_by(month_name, DAY_OF_WEEK) %>%
summarise(n = length(DAY_OF_WEEK), .groups = 'keep') %>%
data.frame()
#head(days_df)
ggplot(days_df, aes(x=DAY_OF_WEEK, y=n, fill=month_name)) +
geom_bar(stat="identity", position = "dodge") +
theme_light() +
theme(plot.title = element_text(hjust=0.5)) +
scale_y_continuous(labels=comma) +
labs (title = "Multiple Bar Charts -Total Crimes by Month and by Day",
x = "Day of the Week",
y = "Number of Crimes",
fill = "month_name")+
scale_fill_brewer(palette = "Paired") +
facet_wrap(~month_name,ncol=4,nrow = 3)+
#need to have days shown vertical and not horizontal
theme(axis.text.x=element_text(angle=90, size=8))
Tab 5
This chart shows the percentage of shooting per day
# change numbers 1,2, etc to January, February, etc
df$month_name <- month.name[df$MONTH]
#head(df$month_name)
days_df <- df %>%
select(month_name, DAY_OF_WEEK) %>%
group_by(month_name, DAY_OF_WEEK) %>%
summarise(n = length(DAY_OF_WEEK), .groups = 'keep') %>%
data.frame()
#head(days_df)
ggplot(days_df, aes(x=DAY_OF_WEEK, y=n, fill=month_name)) +
geom_bar(stat="identity", position = "dodge") +
theme_light() +
theme(plot.title = element_text(hjust=0.5)) +
scale_y_continuous(labels=comma) +
labs (title = "Multiple Bar Charts -Total Crimes by Month and by Day",
x = "Day of the Week",
y = "Number of Crimes",
fill = "month_name")+
scale_fill_brewer(palette = "Paired") +
facet_wrap(~month_name,ncol=4,nrow = 3)+
#need to have days shown vertical and not horizontal
theme(axis.text.x=element_text(angle=90, size=8))
Conclusion
The findings of this analysis provide a detailed evaluation of the crimes that have occurred in Boston from Jan 1, 2023 to Dec 29, 2024. The first tab depicts the worse 10 districts in Boston. The worse district was D4, which covers the South End neighborhood of Boston, along with parts of Back Bay, lower Roxbury, and the Fenway area. The second worse district was B2, which covers the neighborhood of Roxbury. This shows people should be cautious when entering the neighborhood of Roxbury. The second tab further looks at the number of crimes committed in the worse 10 districts in Boston per month. No month really stands out. Tab three shows the number of crimes per hour. The worse is around midnight. The safest time is between 3am to 6 am. Tab 4 depicts the total crimes buy month and day. No particle day stands out for every month, but there is a trend that Fridays are the worse. Tab 5 shows the number of crimes involving a gun per day. Although the percentage are low, Saturday and Sunday are the worse (1%) and Wednesday has the lowest percentage (0.5%) This analysis provides information on where the worse crimes are committed, the days of the month where the worse crimes are committed and the worse times and safest times for crimes. This information should be useful for someone planning a trip to Boston