Traffic Fines Linear Model Analysis

library(tidyverse)

## Warning: package 'purrr' was built under R version 4.4.3

## ── 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 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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

library(dplyr)
library(ggplot2)
library(pastecs)

## Warning: package 'pastecs' was built under R version 4.4.3

## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract

df <- read.csv("traffic_data.csv")

violfine <- df$ViolFine

stat.desc(violfine)

##      nbr.val     nbr.null       nbr.na          min          max        range 
## 9.548000e+03 2.916000e+03 0.000000e+00 0.000000e+00 5.200000e+02 5.200000e+02 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 9.099470e+05 9.800000e+01 9.530237e+01 8.284820e-01 1.624001e+00 6.553580e+03 
##      std.dev     coef.var 
## 8.095418e+01 8.494457e-01

df_clean <- df %>%
  filter(!is.na(ViolFine))

ggplot(df_clean, aes(x = ViolFine)) +
  geom_histogram(bins = 30, fill = "skyblue", color = "black") +
  theme_minimal() +
  labs(title = "Histogram of ViolFine (Original)", x = "Fine Amount", y = "Count")

df_clean <- df_clean %>%
  mutate(LogFine = log(ViolFine + 1))

ggplot(df_clean, aes(x = LogFine)) +
  geom_histogram(bins = 30, fill = "lightgreen", color = "black") +
  theme_minimal() +
  labs(title = "Histogram of ViolFine (Log Transformed)", x = "Log(Fine + 1)", y = "Count")