Mini Assignment 5

setwd("C:\\Users\\srini\\OneDrive\\Documents\\Urban Analytics")
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, union

Loading the Fatal Encounters Crime Dataset

fatal_encounters=read.csv(file="FatalEncountersData.csv")

View(fatal_encounters)

When analyzing fatal police encounters, I believe there are several key factors to consider, and over time, these recurring factors can reveal distinct patterns. The factors I find most critical for identifying and understanding these patterns across a dataset include gender, race, state, involved agency or agencies, and the highest level of force used. To begin, I will examine the most frequent values in each of these columns to determine if any clear patterns emerge.

most_common_gender=names(which.max(table(fatal_encounters$Gender)))
most_common_race=names(which.max(table(fatal_encounters$Race)))
most_common_state=names(which.max(table(fatal_encounters$State)))
most_common_agency=names(which.max(table(fatal_encounters$Agency.or.agencies.involved)))
most_common_level_of_force=names(which.max(table(fatal_encounters$Highest.level.of.force)))

print(most_common_gender)

## [1] "Male"

print(most_common_race)

## [1] "European-American/White"

print(most_common_state)

## [1] "CA"

print(most_common_agency)

## [1] "Los Angeles Police Department"

print(most_common_level_of_force)

## [1] "Gunshot"

The following graphs illustrate important trends observed in fatal police encounters. These visualizations highlight the distribution of gender, race, and geographic location of incidents, as well as the agencies involved and the most frequent levels of force used. These patterns provide insight into the demographics and circumstances surrounding these tragic events.

Plot 1: Most Common Gender in Fatal Encounters

library(ggplot2)
ggplot(fatal_encounters, aes(x = Gender)) +
  geom_bar() +
  ggtitle("Most Common Gender in Fatal Encounters") +
  xlab("Gender") + ylab("Count")

Plot 2: Race Distribution of Fatal Encounters

fatal_encounters_filtered = fatal_encounters %>%
  filter(Race != "Christopher Anthony Alexander")

ggplot(fatal_encounters_filtered, aes(x = Race)) +
  geom_bar() +
  ggtitle("Race Distribution in Fatal Encounters") +
  xlab("Race") + 
  ylab("Count") + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Plot 3: Distribution of Fatal Encounters by State

library(ggplot2)
library(maps)

fatal_encounters$Longitude=as.numeric(fatal_encounters$Longitude)
fatal_encounters$Latitude=as.numeric(fatal_encounters$Latitude)

## Warning: NAs introduced by coercion

states_map=map_data("state")

ggplot(states_map, aes(x = long, y = lat)) +
  geom_polygon(fill = "white", color = "black") +
  

  geom_point(data = fatal_encounters, aes(x = Longitude, y = Latitude, color = State), size = 1) +
  
  
  ggtitle("Geographic Distribution of Fatal Encounters by State") +
  
  
  theme_minimal()

## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

Plot 4: Highest Level of Force Used

ggplot(fatal_encounters, aes(x = "", fill = Highest.level.of.force)) +
  geom_bar(width = 1) +
  coord_polar(theta = "y") +
  ggtitle("Distribution of Highest Level of Force Used") +
  theme_void()

In this dataset, the most frequently used level of force in fatal police encounters involves firearms. Therefore, I will be plotting the relation between the race and the number of gunshot related fatalities.

Plot 5: Relation between race and gunshot related fatalities

library(ggplot2)
library(dplyr)

# Filter only gunshot fatalities
gunshot_fatalities_race = fatal_encounters %>%
  filter(Highest.level.of.force == "Gunshot") %>%
  group_by(Race) %>%
  summarise(gunshot_count = n()) %>%
  arrange(desc(gunshot_count))

# Create a bar graph
ggplot(gunshot_fatalities_race, aes(x = reorder(Race, -gunshot_count), y = gunshot_count, fill = Race)) +
  geom_bar(stat = "identity") +
  labs(title = "Gunshot-Related Fatalities by Race",
       x = "Race of Victim",
       y = "Number of Gunshot Fatalities") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  scale_fill_brewer(palette = "Set3")

Based on the analysis of the fatal police encounters dataset, a clear pattern emerges from the most common demographic and situational factors involved in these incidents. The majority of the individuals involved in fatal encounters are male, specifically of European-American/White descent. The incidents are most frequently reported in California (CA), with the Los Angeles Police Department being the most commonly involved agency. Additionally, “gunshot” is the most frequently recorded level of force used in these fatal encounters.

These findings point to some significant trends in the data. The prevalence of male victims suggests a gendered pattern in fatal encounters, while the frequent involvement of European-American/White individuals contrasts with broader discussions of racial disparities in police violence, raising questions about the intersection of race, location, and the type of force used. California, particularly Los Angeles, appears to be a hotspot for such incidents, potentially due to its large population and law enforcement practices. The frequent use of firearms highlights the serious nature of these encounters.