Ideal Point Estimation in the New Mexico House: A W-NOMINATE Analysis

pacman::p_load(wnominate, pscl, ggplot2, knitr, devtools, ggrepel, data.table, dplyr, tidyr, DT)
source("/home/jtimm/Dropbox/GitHub/blog/r/scale_voteview.R")

# Load legislator metadata
legis <- read.csv("/home/jtimm/Dropbox/GitHub/git-projects/newmexico-political-data/data-raw/open.pluralpolicy.com/nm-57th-congress-yr1/nm.csv") |>
  rename(voter_id = id) |>
  mutate(
    chamber = case_when(
      current_chamber == "lower" ~ "H",
      current_chamber == "upper" ~ "S",
      TRUE               ~ NA_character_
    ),
    party = case_when(
      current_party %in% c("Democratic")  ~ "D",
      current_party %in% c("Republican")  ~ "R",
      current_party %in% c("Independent") ~ "I",
      TRUE                        ~ "I"
    ),
    legis_label = paste(chamber, current_district, party, family_name, sep = "_")
  )

# Load OpenStates vote data files
open_dir <- "/home/jtimm/Dropbox/GitHub/git-projects/newmexico-political-data/data-raw/open.pluralpolicy.com/nm-57th-congress-yr1/NM_2025_csv_3LAtJwe7Zs1ldDHVVcwMRa/NM/2025/"

files <- list.files(open_dir, full.names = TRUE)
names(files) <- sub("\\.csv$", "", basename(files))
df_list <- lapply(files, read.csv, stringsAsFactors = FALSE)

# Calculate participation rates from vote data
# First get all House votes (from votes.csv, not vote_people)
house_votes <- df_list$NM_2025_votes |>
  filter(motion_text == 'house passage') |>
  pull(id)

total_votes_session <- length(house_votes)

# Get vote data for House members - join correctly on voter_id
vote_data_raw <- df_list$NM_2025_vote_people |>
  filter(voter_id != '')  |> 
  left_join(legis) |>
  filter(grepl('H_', legis_label)) |>
  filter(vote_event_id %in% house_votes) |>
  select(legis_label, vote_event_id, option)


vd2 <- vote_data_raw |>
  count(legis_label, option) |>
  tidyr::pivot_wider(id_cols = legis_label,
                     names_from = option,
                     values_from = n)

# Calculate attendance and participation metrics
participation <- vd2 |>
  mutate(
    # Add party column
    party = case_when(
      grepl("_D_", legis_label) ~ "D",
      grepl("_R_", legis_label) ~ "R",
      TRUE ~ "I"
    ),
    # Replace NA with 0 for vote counts
    yes = ifelse(is.na(yes), 0, yes),
    no = ifelse(is.na(no), 0, no),
    excused = ifelse(is.na(excused), 0, excused),
    absent = ifelse(is.na(absent), 0, absent),
    # Calculate votes cast (yes + no)
    votes_cast = yes + no,
    # Attendance: (yes + no) / (yes + no + absent)
    # Excludes excused absences from denominator
    attendance_pct = ifelse((votes_cast + absent) > 0,
                            (votes_cast / (votes_cast + absent)) * 100,
                            0),
    attendance_pct_rounded = round(attendance_pct, 1),
    # Participation: (yes + no) / (yes + no + excused + absent)
    # Includes everything in denominator
    participation_pct = ifelse((votes_cast + excused + absent) > 0,
                               (votes_cast / (votes_cast + excused + absent)) * 100,
                               0),
    participation_pct_rounded = round(participation_pct, 1)
  ) |>
  arrange(participation_pct)

participation |>
  select(legis_label, party, votes_cast, excused, absent, attendance_pct_rounded, participation_pct_rounded) |>
  DT::datatable(
    caption  = "Attendance and participation rates by legislator",
    colnames = c("Legislator", "Party", "Votes Cast", "Excused", "Absent", "Attendance %", "Participation %"),
    options = list(
      pageLength = 10,
      scrollX = TRUE,
      order = list(list(6, 'asc'))
    ),
    rownames = FALSE
  )

x <- df_list$NM_2025_vote_people |>
  filter(voter_id != '')  |> 
  left_join(legis) |>
  select(legis_label, vote_event_id, option) |>
  filter(grepl('H_', legis_label))

wide <- x |>
  mutate(option = case_when(
    option %in% c("yes", "aye") ~ 1L,
    option %in% c("no",  "nay") ~ 6L,
    TRUE                        ~ NA_integer_
  )) |>
  pivot_wider(
    names_from  = vote_event_id,
    values_from = option
  )

mat    <- wide |> select(-legis_label) |> as.matrix()
vnames <- colnames(mat)

wide |>
  select(1:6) |>
  head(10) |>
  DT::datatable(
    caption = "Sample vote matrix: 10 legislators, 5 roll calls (1 = Yea, 6 = Nay, NA = absent/excused)",
    colnames = c("Legislator", paste("Vote", 1:5)),
    options = list(
      pageLength = 10,
      dom = 't',
      ordering = FALSE
    ),
    rownames = FALSE
  )

roll_obj <- pscl::rollcall(
  data        = mat,
  yea         = 1,
  nay         = 6,
  missing     = NA,
  legis.names = wide$legis_label,
  vote.names  = vnames
)

ideal_points_2D <- wnominate::wnominate(roll_obj, dims = 2, polarity = c(1, 2))

actual_ids <- colnames(roll_obj$votes)

bill_analysis <- data.frame(
    vote_event_id = actual_ids,
    spread1       = ideal_points_2D$rollcalls[, "spread1D"],
    spread2       = ideal_points_2D$rollcalls[, "spread2D"],
    midpoint      = ideal_points_2D$rollcalls[, "midpoint1D"],
    stringsAsFactors = FALSE
) |>
  left_join(
    df_list$NM_2025_votes |> select(id, bill_id) |> rename(vote_event_id = id),
    by = "vote_event_id"
  ) |>
  left_join(df_list$NM_2025_bills, by = c("bill_id" = "id"))

plot_rollcall <- function(bill_id_str,
                          bill_analysis,
                          ideal_points_2D,
                          roll_obj,
                          legis) {

  params <- bill_analysis |>
    filter(identifier == bill_id_str) |>
    slice(1)

  if (nrow(params) == 0) stop("'", bill_id_str, "' not found in bill_analysis")

  vid   <- params$vote_event_id
  # Cutting line geometry: slope and intercept on the -coord1D axis.
  # Normal vector (spread1, spread2) perpendicular to the line;
  # line passes through midpoint on dim1, 0 on dim2.
  # Rearranging for x = -coord1D: slope = spread1/spread2, intercept = -midpoint/spread2
  m_cut <- -(-params$spread1 / params$spread2)
  b_cut <- -(params$midpoint  / params$spread2)

  # Clip cutting line to unit circle via intersection with x^2 + y^2 = 1.
  # Substituting y = m*x + b: (1+m^2)*x^2 + 2mb*x + (b^2-1) = 0
  cl_A    <- 1 + m_cut^2
  cl_disc <- 4 * (1 - b_cut^2 + m_cut^2)
  cl_seg  <- if (cl_disc >= 0) {
    x1 <- (-2 * m_cut * b_cut - sqrt(cl_disc)) / (2 * cl_A)
    x2 <- (-2 * m_cut * b_cut + sqrt(cl_disc)) / (2 * cl_A)
    data.frame(x1 = x1, y1 = m_cut * x1 + b_cut,
               x2 = x2, y2 = m_cut * x2 + b_cut)
  } else NULL

  leg_names <- rownames(ideal_points_2D$legislators)

  plot_df <- as.data.frame(ideal_points_2D$legislators) |>
    mutate(
      legis_name = leg_names,
      party_raw  = legis[match(leg_names, legis$legis_label), ]$party,
      vote_raw   = roll_obj$votes[, vid],
      party_prefix = case_when(party_raw == "D" ~ "Dem",
                               party_raw == "R" ~ "Rep",
                               TRUE             ~ "Rep"),
      vote_suffix  = case_when(vote_raw == 1 ~ "Yea",
                               vote_raw == 6 ~ "Nay",
                               TRUE          ~ "Not Voting"),
      Party_Member_Vote = factor(
        paste0(party_prefix, ": ", vote_suffix),
        levels = levels(Party_Member_Vote)
      )
    )

  ggplot(plot_df,
         aes(x = -coord1D, y = coord2D,
             color = Party_Member_Vote,
             fill  = Party_Member_Vote,
             shape = Party_Member_Vote)) +
    geom_point(size = 3, stroke = 0.5) +
    annotate("path",
             x = cos(seq(0, 2 * pi, length.out = 300)),
             y = sin(seq(0, 2 * pi, length.out = 300)),
             color = "gray", linewidth = 0.25) +
    (if (!is.null(cl_seg))
      geom_segment(data = cl_seg,
                   aes(x = x1, y = y1, xend = x2, yend = y2),
                   color = "gray40", linewidth = 0.45,
                   inherit.aes = FALSE)) +
    scale_color_rollcall() +
    scale_fill_rollcall() +
    scale_shape_rollcall() +
    coord_fixed(ratio = 1, xlim = c(-1.1, 1.1), ylim = c(-1.1, 1.1)) +
    theme_minimal() +
    labs(
      title = paste0(params$identifier, ": ", params$title),
      x     = "First Dimension",
      y     = "Second Dimension",
      color = NULL, fill = NULL, shape = NULL
    ) +
    theme(
      plot.title = element_text(size = 14),
      legend.position = "bottom"
    )
}