tor-gu

import numpy as np
from matplotlib import pyplot as plt
from scipy.optimize import LinearConstraint, minimize

np.random.seed(3737)

LO, HI = 0, 100
n = 100  # Number of points
k = 73  # Points to remove

tor-gu

library(tidyverse)
library(tigris)
library(njmunicipalities)
library(njelections)
county_names <- njmunicipalities::counties |> pull(county)

# Get the map of NJ
options(tigris_use_cache = TRUE)
nj_municipality_map <- county_names %>%
  map_df( ~ county_subdivisions("NJ", county = ., class = "sf")) |>

tor-gu

library(tidyverse)
library(future)
library(furrr)
library(gganimate)
plan(multisession, workers = 12)

cf_init <- function(D) {
  r = as.integer(floor((sqrt(D))))
  list(
    D = D, r = r, a = r, b = r, c = D - r ^ 2

tor-gu

# Tidyverse packages
library(dplyr)
library(magrittr)
library(purrr)

# Maps and census libraries
# *** Note: CENSUS API Key required ***
library(sf)
library(tidycensus)
library(tigris)

tor-gu

library(tidyverse)
library(lubridate)
library(njoaguof)

# Get number proportion of incidents with body worn camera or any video
# by county and by 4-month interval
# devtools::install_github("tor-gu/njoaguof")
video_by_county <- incident %>%
  left_join(incident_video_type) %>%
  select(form_id,

tor-gu

library(tidyverse)

# Get number of incidents of selected types of force by county
# devtools::install_github("tor-gu/njoaguof")
library(njoaguof)
force_type_by_county <- incident %>%
  right_join(incident_subject_force_type) %>%
  mutate(
    force_type =
      fct_collapse(