Introduction

This project analyzes the crime data from the City of Chicago for May 26 and 27, 2024 to understand patterns and trends in criminal activity. I chose this topic because I visited Chicago last year and was warned about the high crime rate there, so, I decided to analyze the crime data to find out the facts myself. As a tourist, I want to find out:

What is the nature of most common crimes that tourists should be concerned about?
What are the places where these crimes are mostly committed?
When are these crimes committed during the day? Is there a pattern to guide the tourists?
Which is the safest community area to stay in Chicago?
Which districts have high crime rate that tourists have to be aware about?

Getting Started

Importing the Data

For this analysis, we use a dataset provided by the City of Chicago which includes records of reported crimes. The dataset contains information such as the type of crime, the date, and the location.

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

dataset_url <- "https://data.cityofchicago.org/resource/ijzp-q8t2.csv"
crime_data <- read.csv(dataset_url, check.names = FALSE, stringsAsFactors = FALSE, header = TRUE)

#Displaying the data
head(crime_data)

##         id case_number                    date                  block iucr
## 1 13476551    JH283367 2024-05-29T00:00:00.000 035XX N PINE GROVE AVE 0810
## 2 13477420    JH284435 2024-05-29T00:00:00.000    061XX S PRAIRIE AVE 0420
## 3 13476295    JH282996 2024-05-29T00:00:00.000         088XX S ADA ST 0486
## 4 13476461    JH283196 2024-05-29T00:00:00.000 053XX N CUMBERLAND AVE 0560
## 5 13483428    JH291862 2024-05-29T00:00:00.000        015XX W 81ST ST 1220
## 6 13477931    JH285093 2024-05-29T00:00:00.000    042XX N WOLCOTT AVE 0820
##         primary_type                             description
## 1              THEFT                               OVER $500
## 2            BATTERY AGGRAVATED - KNIFE / CUTTING INSTRUMENT
## 3            BATTERY                 DOMESTIC BATTERY SIMPLE
## 4            ASSAULT                                  SIMPLE
## 5 DECEPTIVE PRACTICE        THEFT OF LOST / MISLAID PROPERTY
## 6              THEFT                          $500 AND UNDER
##              location_description arrest domestic beat district ward
## 1                          STREET  false    false 1925       19   46
## 2                       APARTMENT   true     true  311        3   20
## 3                       RESIDENCE  false     true 2222       22   21
## 4                          STREET  false    false 1614       16   41
## 5                       APARTMENT  false    false  612        6   17
## 6 RESIDENCE - YARD (FRONT / BACK)  false    false 1912       19   47
##   community_area fbi_code x_coordinate y_coordinate year
## 1              6       06      1171599      1923832 2024
## 2             40      04B      1179093      1864377 2024
## 3             71      08B      1168875      1846163 2024
## 4             76      08A      1119314      1934514 2024
## 5             71       11           NA           NA 2024
## 6              5       06      1163062      1928197 2024
##                updated_on latitude longitude
## 1 2024-06-05T15:41:03.000 41.94646 -87.64465
## 2 2024-06-05T15:41:03.000 41.78314 -87.61893
## 3 2024-06-05T15:41:03.000 41.73339 -87.65692
## 4 2024-06-05T15:41:03.000 41.97676 -87.83661
## 5 2024-06-05T15:41:03.000       NA        NA
## 6 2024-06-05T15:41:03.000 41.95862 -87.67591
##                               location
## 1  \n,  \n(41.946458557, -87.64465454)
## 2 \n,  \n(41.783142005, -87.618927866)
## 3 \n,  \n(41.733387234, -87.656915358)
## 4 \n,  \n(41.976763216, -87.836613764)
## 5                                     
## 6 \n,  \n(41.958620269, -87.675910698)

We will use several libraries for data manipulation, visualization, and analysis, including tidyverse for data manipulation and ggplot2 for visualization.

library(tidyverse)
library(ggplot2)

Summary of Crime Data

The dataset includes fields such as the date of the crime, the primary type of crime, the description, and the location.

# Summary statistics of the dataset
summary(crime_data)

##        id           case_number            date              block          
##  Min.   :   28141   Length:1000        Length:1000        Length:1000       
##  1st Qu.:13475193   Class :character   Class :character   Class :character  
##  Median :13475804   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :13422351                                                           
##  3rd Qu.:13476384                                                           
##  Max.   :13484068                                                           
##                                                                             
##      iucr           primary_type       description        location_description
##  Length:1000        Length:1000        Length:1000        Length:1000         
##  Class :character   Class :character   Class :character   Class :character    
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character    
##                                                                               
##                                                                               
##                                                                               
##                                                                               
##     arrest            domestic              beat           district    
##  Length:1000        Length:1000        Min.   : 111.0   Min.   : 1.00  
##  Class :character   Class :character   1st Qu.: 529.2   1st Qu.: 5.00  
##  Mode  :character   Mode  :character   Median :1113.0   Median :11.00  
##                                        Mean   :1162.3   Mean   :11.39  
##                                        3rd Qu.:1723.0   3rd Qu.:17.00  
##                                        Max.   :2535.0   Max.   :25.00  
##                                                                        
##       ward       community_area    fbi_code          x_coordinate    
##  Min.   : 1.00   Min.   : 1.00   Length:1000        Min.   :1097306  
##  1st Qu.: 9.00   1st Qu.:22.00   Class :character   1st Qu.:1154308  
##  Median :22.00   Median :32.00   Mode  :character   Median :1167592  
##  Mean   :22.81   Mean   :36.39                      Mean   :1165716  
##  3rd Qu.:34.00   3rd Qu.:53.00                      3rd Qu.:1176794  
##  Max.   :50.00   Max.   :77.00                      Max.   :1204787  
##                                                     NA's   :11       
##   y_coordinate          year       updated_on           latitude    
##  Min.   :1816604   Min.   :2024   Length:1000        Min.   :41.65  
##  1st Qu.:1859197   1st Qu.:2024   Class :character   1st Qu.:41.77  
##  Median :1893721   Median :2024   Mode  :character   Median :41.86  
##  Mean   :1886939   Mean   :2024                      Mean   :41.85  
##  3rd Qu.:1909988   3rd Qu.:2024                      3rd Qu.:41.91  
##  Max.   :1950563   Max.   :2024                      Max.   :42.02  
##  NA's   :11                                          NA's   :11     
##    longitude        location        
##  Min.   :-87.92   Length:1000       
##  1st Qu.:-87.71   Class :character  
##  Median :-87.66   Mode  :character  
##  Mean   :-87.67                     
##  3rd Qu.:-87.63                     
##  Max.   :-87.53                     
##  NA's   :11

# Verifying correct column names as data set
colnames(crime_data)

##  [1] "id"                   "case_number"          "date"                
##  [4] "block"                "iucr"                 "primary_type"        
##  [7] "description"          "location_description" "arrest"              
## [10] "domestic"             "beat"                 "district"            
## [13] "ward"                 "community_area"       "fbi_code"            
## [16] "x_coordinate"         "y_coordinate"         "year"                
## [19] "updated_on"           "latitude"             "longitude"           
## [22] "location"

# Verifying rows
head(crime_data)

##         id case_number                    date                  block iucr
## 1 13476551    JH283367 2024-05-29T00:00:00.000 035XX N PINE GROVE AVE 0810
## 2 13477420    JH284435 2024-05-29T00:00:00.000    061XX S PRAIRIE AVE 0420
## 3 13476295    JH282996 2024-05-29T00:00:00.000         088XX S ADA ST 0486
## 4 13476461    JH283196 2024-05-29T00:00:00.000 053XX N CUMBERLAND AVE 0560
## 5 13483428    JH291862 2024-05-29T00:00:00.000        015XX W 81ST ST 1220
## 6 13477931    JH285093 2024-05-29T00:00:00.000    042XX N WOLCOTT AVE 0820
##         primary_type                             description
## 1              THEFT                               OVER $500
## 2            BATTERY AGGRAVATED - KNIFE / CUTTING INSTRUMENT
## 3            BATTERY                 DOMESTIC BATTERY SIMPLE
## 4            ASSAULT                                  SIMPLE
## 5 DECEPTIVE PRACTICE        THEFT OF LOST / MISLAID PROPERTY
## 6              THEFT                          $500 AND UNDER
##              location_description arrest domestic beat district ward
## 1                          STREET  false    false 1925       19   46
## 2                       APARTMENT   true     true  311        3   20
## 3                       RESIDENCE  false     true 2222       22   21
## 4                          STREET  false    false 1614       16   41
## 5                       APARTMENT  false    false  612        6   17
## 6 RESIDENCE - YARD (FRONT / BACK)  false    false 1912       19   47
##   community_area fbi_code x_coordinate y_coordinate year
## 1              6       06      1171599      1923832 2024
## 2             40      04B      1179093      1864377 2024
## 3             71      08B      1168875      1846163 2024
## 4             76      08A      1119314      1934514 2024
## 5             71       11           NA           NA 2024
## 6              5       06      1163062      1928197 2024
##                updated_on latitude longitude
## 1 2024-06-05T15:41:03.000 41.94646 -87.64465
## 2 2024-06-05T15:41:03.000 41.78314 -87.61893
## 3 2024-06-05T15:41:03.000 41.73339 -87.65692
## 4 2024-06-05T15:41:03.000 41.97676 -87.83661
## 5 2024-06-05T15:41:03.000       NA        NA
## 6 2024-06-05T15:41:03.000 41.95862 -87.67591
##                               location
## 1  \n,  \n(41.946458557, -87.64465454)
## 2 \n,  \n(41.783142005, -87.618927866)
## 3 \n,  \n(41.733387234, -87.656915358)
## 4 \n,  \n(41.976763216, -87.836613764)
## 5                                     
## 6 \n,  \n(41.958620269, -87.675910698)

# summary of data set by providing dimensions
str(crime_data)

## 'data.frame':    1000 obs. of  22 variables:
##  $ id                  : int  13476551 13477420 13476295 13476461 13483428 13477931 13477597 13476780 13477155 13478047 ...
##  $ case_number         : chr  "JH283367" "JH284435" "JH282996" "JH283196" ...
##  $ date                : chr  "2024-05-29T00:00:00.000" "2024-05-29T00:00:00.000" "2024-05-29T00:00:00.000" "2024-05-29T00:00:00.000" ...
##  $ block               : chr  "035XX N PINE GROVE AVE" "061XX S PRAIRIE AVE" "088XX S ADA ST" "053XX N CUMBERLAND AVE" ...
##  $ iucr                : chr  "0810" "0420" "0486" "0560" ...
##  $ primary_type        : chr  "THEFT" "BATTERY" "BATTERY" "ASSAULT" ...
##  $ description         : chr  "OVER $500" "AGGRAVATED - KNIFE / CUTTING INSTRUMENT" "DOMESTIC BATTERY SIMPLE" "SIMPLE" ...
##  $ location_description: chr  "STREET" "APARTMENT" "RESIDENCE" "STREET" ...
##  $ arrest              : chr  "false" "true" "false" "false" ...
##  $ domestic            : chr  "false" "true" "true" "false" ...
##  $ beat                : int  1925 311 2222 1614 612 1912 1135 313 122 2512 ...
##  $ district            : int  19 3 22 16 6 19 11 3 1 25 ...
##  $ ward                : int  46 20 21 41 17 47 28 20 42 36 ...
##  $ community_area      : int  6 40 71 76 71 5 29 42 32 19 ...
##  $ fbi_code            : chr  "06" "04B" "08B" "08A" ...
##  $ x_coordinate        : int  1171599 1179093 1168875 1119314 NA 1163062 1157861 1181638 1173971 1135571 ...
##  $ y_coordinate        : int  1923832 1864377 1846163 1934514 NA 1928197 1895062 1863877 1899133 1914247 ...
##  $ year                : int  2024 2024 2024 2024 2024 2024 2024 2024 2024 2024 ...
##  $ updated_on          : chr  "2024-06-05T15:41:03.000" "2024-06-05T15:41:03.000" "2024-06-05T15:41:03.000" "2024-06-05T15:41:03.000" ...
##  $ latitude            : num  41.9 41.8 41.7 42 NA ...
##  $ longitude           : num  -87.6 -87.6 -87.7 -87.8 NA ...
##  $ location            : chr  "\n,  \n(41.946458557, -87.64465454)" "\n,  \n(41.783142005, -87.618927866)" "\n,  \n(41.733387234, -87.656915358)" "\n,  \n(41.976763216, -87.836613764)" ...

Handling Missing Values

We handle missing values by replacing them with “Unknown” where appropriate. The date column is converted to a suitable format for analysis.

# Converting the date column into the proper date format
crime_data$date <- as.POSIXct(crime_data$date, format="%Y-%m-%dT%H:%M:%OS")

colSums(is.na(crime_data))

##                   id          case_number                 date 
##                    0                    0                    0 
##                block                 iucr         primary_type 
##                    0                    0                    0 
##          description location_description               arrest 
##                    0                    0                    0 
##             domestic                 beat             district 
##                    0                    0                    0 
##                 ward       community_area             fbi_code 
##                    0                    0                    0 
##         x_coordinate         y_coordinate                 year 
##                   11                   11                    0 
##           updated_on             latitude            longitude 
##                    0                   11                   11 
##             location 
##                    0

crime_data <- crime_data %>%
  mutate(across(everything(), ~ifelse(is.na(.), "Unknown", .)))

crime_data <- crime_data %>%
  filter(!is.na(date))

# cleaned data
head(crime_data)

##         id case_number       date                  block iucr
## 1 13476551    JH283367 1716966000 035XX N PINE GROVE AVE 0810
## 2 13477420    JH284435 1716966000    061XX S PRAIRIE AVE 0420
## 3 13476295    JH282996 1716966000         088XX S ADA ST 0486
## 4 13476461    JH283196 1716966000 053XX N CUMBERLAND AVE 0560
## 5 13483428    JH291862 1716966000        015XX W 81ST ST 1220
## 6 13477931    JH285093 1716966000    042XX N WOLCOTT AVE 0820
##         primary_type                             description
## 1              THEFT                               OVER $500
## 2            BATTERY AGGRAVATED - KNIFE / CUTTING INSTRUMENT
## 3            BATTERY                 DOMESTIC BATTERY SIMPLE
## 4            ASSAULT                                  SIMPLE
## 5 DECEPTIVE PRACTICE        THEFT OF LOST / MISLAID PROPERTY
## 6              THEFT                          $500 AND UNDER
##              location_description arrest domestic beat district ward
## 1                          STREET  false    false 1925       19   46
## 2                       APARTMENT   true     true  311        3   20
## 3                       RESIDENCE  false     true 2222       22   21
## 4                          STREET  false    false 1614       16   41
## 5                       APARTMENT  false    false  612        6   17
## 6 RESIDENCE - YARD (FRONT / BACK)  false    false 1912       19   47
##   community_area fbi_code x_coordinate y_coordinate year
## 1              6       06      1171599      1923832 2024
## 2             40      04B      1179093      1864377 2024
## 3             71      08B      1168875      1846163 2024
## 4             76      08A      1119314      1934514 2024
## 5             71       11      Unknown      Unknown 2024
## 6              5       06      1163062      1928197 2024
##                updated_on     latitude     longitude
## 1 2024-06-05T15:41:03.000 41.946458557  -87.64465454
## 2 2024-06-05T15:41:03.000 41.783142005 -87.618927866
## 3 2024-06-05T15:41:03.000 41.733387234 -87.656915358
## 4 2024-06-05T15:41:03.000 41.976763216 -87.836613764
## 5 2024-06-05T15:41:03.000      Unknown       Unknown
## 6 2024-06-05T15:41:03.000 41.958620269 -87.675910698
##                               location
## 1  \n,  \n(41.946458557, -87.64465454)
## 2 \n,  \n(41.783142005, -87.618927866)
## 3 \n,  \n(41.733387234, -87.656915358)
## 4 \n,  \n(41.976763216, -87.836613764)
## 5                                     
## 6 \n,  \n(41.958620269, -87.675910698)

Number of Crimes during the course of the day

crime_data$date <- as.POSIXct(crime_data$date, format="%Y-%m-%d %H:%M:%S")

crime_data <- crime_data %>%
  mutate(date_hour = format(date, "%Y-%m-%d %H:00:00"))

hourly_counts <- crime_data %>%
  count(date_hour) %>%
  mutate(date_hour = as.POSIXct(date_hour, format="%Y-%m-%d %H:%M:%S"))

hourly_counts <- hourly_counts %>%
  mutate(day = format(date_hour, "%Y-%m-%d"))

# Plotting graph
ggplot(hourly_counts, aes(x = date_hour, y = n, fill = day)) +
  geom_bar(stat = "identity", color = "black") +
  geom_text(aes(label = format(date_hour, "%I %p")), vjust = -0.5, size = 2.5) +
  theme_minimal() +
  labs(title = "Crimes Over Time by Hour", x = "Date and Hour", y = "Count of Crimes") +
  theme(axis.text.x = element_blank(), axis.ticks.x = element_blank()) +
  scale_fill_manual(values = c("2024-05-27" = "#FFB6C1", "2024-05-28" = "#ADD8E6", "2024-05-29" = "#98FB98")) +
  guides(fill = guide_legend(title = "Day"))

Inference:

The crimes are generally high throughout the day except in the night from 1 AM to 9 AM.

Statistical Analysis

Frequency of Crime Types

We conduct a frequency analysis to identify the most common types of crimes.

# Frequency of crime types
crime_type_freq <- crime_data %>%
  group_by(primary_type) %>%
  summarize(Frequency = n()) %>%
  arrange(desc(Frequency))

# Displaying the top crime types
head(crime_type_freq, 10)

## # A tibble: 10 × 2
##    primary_type        Frequency
##    <chr>                   <int>
##  1 BATTERY                   192
##  2 THEFT                     190
##  3 ASSAULT                   128
##  4 CRIMINAL DAMAGE           111
##  5 OTHER OFFENSE              76
##  6 MOTOR VEHICLE THEFT        71
##  7 BURGLARY                   46
##  8 WEAPONS VIOLATION          37
##  9 DECEPTIVE PRACTICE         35
## 10 ROBBERY                    30

Crimes by Type

We visualize the distribution of different types of crimes using a plot.

# Plotting graph
ggplot(crime_data, aes(x = primary_type)) +
  geom_bar(fill = "blue", color = "black") +
  theme_minimal() +
  labs(title = "Crimes by Type", x = "Type of Crime", y = "Count") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

Inference:

The following crimes are more frequent (Evident from the statistical analysis and graph): 1. Theft 2. Battery 3. Assault 4. Criminal Damage 5. Motor Vehicle Theft

For tourists, among the above, the following crimes are of concern:

Theft
Battery
Assault

Although stalking is also a concern for tourists, but the number of reported incidents are low.

Crimes by Location Description

We explore the distribution of crimes by location description.

ggplot(crime_data, aes(x = location_description)) +
  geom_bar(fill = "green", color = "black") +
  theme_minimal() +
  labs(title = "Crimes by Location", x = "Location Description", y = "Count") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

Inference:

Most number of crimes take place in the following areas: 1) Apartment 2) Street 3) Parking lot/ Garage (non residential) 4) Residence 5) Sidewalk 6) Small Retail Store

For tourists, among the above, the following locations are of concern:

Street
Parking lot/ Garage (non residential)
Sidewalk
Small Retail Store

Crimes by Location Description for Theft, Assault, and Battery

# Filtering the data to include only Theft, Assault, and Battery
filtered_crime_data <- crime_data %>%
  filter(primary_type %in% c("THEFT", "ASSAULT", "BATTERY"))

location_counts <- filtered_crime_data %>%
  count(location_description) %>%
  filter(n > 0) %>%
  filter(location_description %in% c("STREET", "PARKING LOT / GARAGE (NON RESIDENTIAL)", "SIDEWALK", "SMALL RETAIL STORE"))

# Plotting
ggplot(location_counts, aes(x = reorder(location_description, n), y = n)) +
  geom_bar(stat = "identity", fill = "green", color = "black") +
  theme_minimal() +
  labs(title = "Crimes by Location (Theft, Assault, Battery)", x = "Location Description", y = "Count") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 6))

  coord_flip()

## <ggproto object: Class CoordFlip, CoordCartesian, Coord, gg>
##     aspect: function
##     backtransform_range: function
##     clip: on
##     default: FALSE
##     distance: function
##     expand: TRUE
##     is_free: function
##     is_linear: function
##     labels: function
##     limits: list
##     modify_scales: function
##     range: function
##     render_axis_h: function
##     render_axis_v: function
##     render_bg: function
##     render_fg: function
##     setup_data: function
##     setup_layout: function
##     setup_panel_guides: function
##     setup_panel_params: function
##     setup_params: function
##     train_panel_guides: function
##     transform: function
##     super:  <ggproto object: Class CoordFlip, CoordCartesian, Coord, gg>

Inference:

The tourists have to stay vigilant at all these four locations.

Crimes Over Time by Hour for Theft, Assault, and Battery

crime_data$date <- as.POSIXct(crime_data$date, format="%Y-%m-%d %H:%M:%S")

# Filtering data for Theft, Assault, and Battery
filtered_crime_data <- crime_data %>%
  filter(primary_type %in% c("THEFT", "ASSAULT", "BATTERY")) %>%
  mutate(date_hour = format(date, "%Y-%m-%d %H:00:00"))

hourly_counts <- filtered_crime_data %>%
  count(date_hour) %>%
  mutate(date_hour = as.POSIXct(date_hour, format="%Y-%m-%d %H:%M:%S"))

hourly_counts <- hourly_counts %>%
  mutate(day = format(date_hour, "%Y-%m-%d"))

# Plotting the graph
ggplot(hourly_counts, aes(x = date_hour, y = n, fill = day)) +
  geom_bar(stat = "identity", color = "black") +
  scale_x_datetime(date_breaks= "1 hour", date_labels = "%I %p") +  # Format x-axis to show hour
  theme_minimal() +
  labs(title = "Crimes Over Time by Hour for Theft, Assault, and Battery", x = "Hour", y = "Count of Crimes") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +  # Rotate x-axis labels
  scale_fill_manual(values = c("2024-05-27" = "pink", "2024-05-28" = "blue", "2024-05-29" = "purple")) +
  guides(fill = guide_legend(title = "Day"))

Interference:

These three crimes are generally high throughout the day except in the night from 1 AM to 7 AM. It is therefore important to stay vigilant when outside at all time.

Trend of number of crimes by district

# Calculate the counts of crimes by district
district_counts <- crime_data %>%
  count(district) %>%
  filter(n > 0) 

# Create the plot
ggplot(district_counts, aes(x = reorder(as.factor(district), -n), y = n)) +
  geom_bar(stat = "identity", fill = "blue", color = "black") +
  theme_minimal() +
  labs(title = "Number of Crimes by District", x = "District", y = "Count of Crimes") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Inference:

District 16 and 20 are safe relative to others.

Trend of Theft, Battery and Assault in District 20

# Convert date column to POSIXct if it's not already
crime_data$date <- as.POSIXct(crime_data$date, format="%Y-%m-%d %H:%M:%S")

# Filtering data for district 20
district_20_data <- crime_data %>%
  filter(district == 20)

# Aggregate the counts of crimes by community area for Theft, Assault, and Battery
community_area_counts <- district_20_data %>%
  filter(primary_type %in% c("THEFT", "ASSAULT", "BATTERY")) %>%
  count(community_area)

# Create a complete sequence of community areas
all_community_areas <- unique(district_20_data$community_area)

# Ensure all community areas are represented
community_area_counts <- community_area_counts %>%
  complete(community_area = all_community_areas, fill = list(n = 0))

# Plotting the graph
ggplot(community_area_counts, aes(x = as.factor(community_area), y = n)) +
  geom_bar(stat = "identity", fill = "lightblue", color = "black") +
  geom_text(aes(label = n), vjust = -0.5, color = "black") +
  theme_minimal() +
  labs(title = "Number of Crimes by Community Area in District 20",
       x = "Community Area", y = "Count of Crimes") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

Inference:

The safest place for tourists to stay in Chicago is Community Area 2 in District 20 where no crime of battery, theft and assault are reported on the given dates.

Results:

Safety Report for Tourists

What is the nature of most common crimes that tourists should be concerned about? Conclusion: The most frequent types of crimes concerning the tourists are theft, battery, and assault.
What are the places where these crimes are mostly committed? Conclusion: These crimes are mostly committed on the streets, sidewalks, small retail stores, and non-residential parking lots. All these areas are generally full of tourists.
When are these crimes committed during the day? Is there a pattern to guide the tourists? Conclusion: These crimes are being committed throughout the day except in the night (1 AM - 7 AM). The tourists therefore must stay vigilant when outdoors.
Which is the safest community area to stay in Chicago? Conclusion: The safest place for tourists to stay in Chicago is Community Area 2 in District 20 where no crime of battery, theft and assault are reported on the given dates.
Which districts have high crime rate that tourists have to be aware about? Conclusion: The top 5 districts with highest reported crimes are: 3, 12, 11, 6, and 8.

Conclusion:

In conclusion, our analysis of Chicago’s crime data revealed significant insights into the types and locations of crimes, as well as their temporal patterns. These findings can inform law enforcement strategies, policy-making, and community initiatives aimed at reducing crime and enhancing public safety. By understanding where and when crimes are most likely to occur, stakeholders can develop more effective approaches to crime prevention and resource allocation, ultimately contributing to a safer Chicago.

Project 1: Anuvi Batra

2024-06-06

Introduction

Getting Started

Importing the Data

Summary of Crime Data

Handling Missing Values

Number of Crimes during the course of the day

Inference:

Statistical Analysis

Frequency of Crime Types

Crimes by Type

Inference:

For tourists, among the above, the following crimes are of concern:

Crimes by Location Description

Inference:

For tourists, among the above, the following locations are of concern:

Crimes by Location Description for Theft, Assault, and Battery

Inference:

Crimes Over Time by Hour for Theft, Assault, and Battery

Interference:

Trend of number of crimes by district

Inference:

Trend of Theft, Battery and Assault in District 20

Inference:

Results:

Safety Report for Tourists

Conclusion: