├── .gitignore
├── README.md
├── speedviolations.Rproj
└── highviolaters.R


/.gitignore:
--------------------------------------------------------------------------------
1 | .Rproj.user
2 | .Rhistory
3 | .RData
4 | .httr-oauth
5 | .DS_Store
6 | .quarto
7 | highviolaters2025full.csv
8 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # speedviolations
2 | 
3 | Data files were created with `highviolaters.R`
4 | 
5 | 2024 -- complete
6 | 
7 | 2025 -- rows with num_ticket equal to 1 were filtered out
8 | 


--------------------------------------------------------------------------------
/speedviolations.Rproj:
--------------------------------------------------------------------------------
 1 | Version: 1.0
 2 | 
 3 | RestoreWorkspace: Default
 4 | SaveWorkspace: Default
 5 | AlwaysSaveHistory: Default
 6 | 
 7 | EnableCodeIndexing: Yes
 8 | UseSpacesForTab: Yes
 9 | NumSpacesForTab: 2
10 | Encoding: UTF-8
11 | 
12 | RnwWeave: Sweave
13 | LaTeX: pdfLaTeX
14 | 


--------------------------------------------------------------------------------
/highviolaters.R:
--------------------------------------------------------------------------------
 1 | library(tidyverse)
 2 | library(data.table)
 3 | 
 4 | # Downloaded dataset from: https://dev.socrata.com/foundry/data.cityofnewyork.us/nc67-uf89
 5 | df2 = fread("~/Downloads/Open_Parking_and_Camera_Violations_20251213.csv")
 6 | 
 7 | df2024 <- df2  |> filter(str_detect(`Issue Date`, "2024")) 
 8 | 
 9 | df2024$Date <- as.Date(df2024$`Issue Date`, format = "%m/%d/%Y")
10 | 
11 | df2024$`Amount Due` <- readr::parse_number(df2024$`Amount Due`)
12 | 
13 | df2024$In_judgment <- ifelse(df2024$`Judgment Entry Date` != "", TRUE, FALSE)
14 | 
15 | highviolaters <- df2024 |> 
16 |   group_by(State, Plate, In_judgment) |> 
17 |   summarize(total_amt = sum(`Amount Due`),
18 |             num_tickets = n())
19 | 
20 | highviolaters <- highviolaters |> 
21 |   filter(total_amt != 0)
22 | 
23 | write_csv(highviolaters, "data/highviolaters2024.csv")
24 | 
25 | df2025 <- df2  |> filter(str_detect(`Issue Date`, "2025")) 
26 | 
27 | df2025$Date <- as.Date(df2025$`Issue Date`, format = "%m/%d/%Y")
28 | 
29 | df2025$`Amount Due` <- readr::parse_number(df2025$`Amount Due`)
30 | 
31 | df2025$In_judgment <- ifelse(df2025$`Judgment Entry Date` != "", TRUE, FALSE)
32 | 
33 | highviolaters <- df2025 |> 
34 |   group_by(State, Plate, In_judgment) |> 
35 |   summarize(total_amt = sum(`Amount Due`),
36 |             num_tickets = n())
37 | 
38 | highviolaters <- highviolaters |> 
39 |   filter(total_amt != 0)
40 | 
41 | write_csv(highviolaters, "data/highviolaters2025full.csv")
42 | 
43 | highviolaters <- highviolaters |> 
44 |   filter(num_tickets > 1)
45 | 
46 | write_csv(highviolaters, "data/highviolaters2025.csv")
47 | 


--------------------------------------------------------------------------------