Partisanship and Competitive Elections: Notebook 5
Keith Colella
2023-05-14
library(tidyverse)
library(kableExtra)
library(tigris)
library(sf)District-Level Ideology Survey
This notebook collects a number of measures of district competitiveness / ideological leanings and maps them to the candidates dataframe from previous notebooks. The output of this notebook will serve as the final dataset for this project’s ultimate statistical analysis.
Survey-Based District-Level Ideology Scores
The first measure comes from a 2022 study gathering more than a decade of survey data to model ideology at the district level (https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/BQKU4M). As with many of the partisanship scores, the scale is oriented such that “lower values are associated with politically left preferences and higher values with politically right preferences.” So, I will normalize the scores between -1 and 1, then take the absolute value. The results scores will then be oriented such that 0 indicates closeness to the political center and 1 indicates closeness to ideological wings, matching the orientation of the partisanship scores from notebook 4.
load('data/aip_district_ideology_v2022a.RData')
district_ideology <- table
rm(table)
district_ideology %>% head()## # A tibble: 6 × 14
## cd_fips state mrp_ideology_se mrp_ideology irt_ideology_unweighted
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 1000 Delaware 0.0696 -0.0459 -0.0182
## 2 1000 Delaware 0.0429 -0.0213 -0.0651
## 3 1000 Delaware 0.0409 -0.0710 -0.0798
## 4 1000 Delaware 0.0409 -0.0710 -0.0735
## 5 1000 Delaware 0.0409 -0.0710 -0.0763
## 6 101 Alabama 0.0687 0.201 0.185
## # ℹ 9 more variables: self_ideology <dbl>, self_ideology_se <dbl>,
## # irt_ideology_unweighted_sd <dbl>, irt_ideology_unweighted_se <dbl>,
## # sample_size <dbl>, demshare_pres <dbl>, presidential_year <dbl>,
## # congress <dbl>, survey_period <chr>district_ideology %>%
filter(congress == 118) %>%
ggplot() +
geom_freqpoly(aes(mrp_ideology)) +
geom_freqpoly(aes(irt_ideology_unweighted), color = 'red')## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
min_score <- min(district_ideology$mrp_ideology, na.rm = TRUE)
max_score <- max(district_ideology$mrp_ideology, na.rm = TRUE)
district_ideology <- district_ideology %>%
mutate(mrp_norm = 2 * (mrp_ideology - min_score) / (max_score - min_score) - 1,
mrp_norm_abs = abs(mrp_norm))
min_score <- min(district_ideology$irt_ideology_unweighted, na.rm = TRUE)
max_score <- max(district_ideology$irt_ideology_unweighted, na.rm = TRUE)
district_ideology <- district_ideology %>%
mutate(itr_norm = 2 * (irt_ideology_unweighted - min_score) / (max_score - min_score) - 1,
itr_norm_abs = abs(itr_norm))
district_ideology %>%
filter(congress == 118) %>%
ggplot() +
geom_freqpoly(aes(mrp_norm)) +
geom_freqpoly(aes(itr_norm), color = 'red')## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
district_ideology %>%
filter(congress == 118) %>%
ggplot() +
geom_freqpoly(aes(mrp_norm_abs)) +
geom_freqpoly(aes(itr_norm_abs), color = 'red')## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
Cook Partisan Voting Index
The next measure is the Cook PVI (https://www.cookpolitical.com/cook-pvi/2022-partisan-voting-index/district-map-and-list). This measure uses historical voting results to assign each congressional district a score from far left to far right. As above, we’ll normalize the score between -1 and 1 and take the absolutely value
cookpvi <- read_csv('data/cook_pvi.csv')## New names:
## Rows: 435 Columns: 9
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (9): district, name, party, district_description, pvi, biden, trump...7,...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `trump` -> `trump...7`
## • `trump` -> `trump...9`cookpvi <- cookpvi %>%
rename(trump2020 = trump...7,
trump2016 = trump...9) %>%
mutate(pvi_num =
case_when(str_detect(pvi,'R') ~ as.numeric(str_extract(pvi,'[0-9]+')),
str_detect(pvi,'D') ~ as.numeric(str_extract(pvi,'[0-9]+'))*-1,
TRUE ~ 0))
min_score <- min(cookpvi$pvi_num)
max_score <- max(cookpvi$pvi_num)
cookpvi <- cookpvi %>%
mutate(pvi_abs = abs(pvi_num),
pvi_norm = 2 * (pvi_num - min_score) / (max_score - min_score) - 1,
pvi_norm_abs = abs(pvi_norm))
cookpvi %>%
ggplot() +
geom_freqpoly(aes(pvi_norm_abs), bins = 20)
cookpvi %>%
ggplot() +
geom_freqpoly(aes(pvi_abs), bins = 20, color = 'red')
Efficiency Gap
The final measure is the Efficiency Gap. This metric is frequently cited in political science literature as a measure of gerrymandering (see Stephanopoulos, Nicholas, and McGhee. “Partisan Gerrymandering and the Efficiency Gap.”). The Efficiency Gap measures “wasted” votes, framed as the amount of (i) votes cast for a candidate who didn’t win, or (ii) votes cast for a candidate who did win in excess of the number of votes required to win.
I was unable to locate a readily available measure of the effiency gap, so I’ll calculate my own using historical election data from the MIT Election Lab (https://electionlab.mit.edu/data).
elections <- read_csv('data/1976-2020-house.csv')## Rows: 31103 Columns: 20
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): state, state_po, office, district, stage, candidate, party, mode
## dbl (7): year, state_fips, state_cen, state_ic, candidatevotes, totalvotes, ...
## lgl (5): runoff, special, writein, unofficial, fusion_ticket
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.elections <- elections %>%
filter(stage == 'GEN',
year > 2010) %>%
mutate(yearStateDist = paste0(year, state_po, district))
elections <- elections %>%
group_by(yearStateDist) %>%
mutate(result = case_when(candidatevotes == max(candidatevotes) ~ 'winner',
candidatevotes != max(candidatevotes) ~ 'loser')) %>%
ungroup()
elections <- elections %>%
mutate(wastedVotes = case_when(result == 'winner' ~ (candidatevotes - (totalvotes %/% 2)),
result == 'loser' ~ candidatevotes),
wastedVotes = case_when(party == 'DEMOCRAT' ~ -wastedVotes,
party == 'REPUBLICAN' ~ wastedVotes,
TRUE ~ 0))
eff_gap <- elections %>%
group_by(year, state_po, district) %>%
summarize(netWastedVotes = sum(wastedVotes),
totalVotes = sum(totalvotes),
eff_gap = abs(netWastedVotes / totalVotes),
.groups = 'drop') %>%
group_by(state_po, district) %>%
summarize(avg_eff_gap = mean(eff_gap),
.groups = 'keep') %>%
ungroup()
summary(eff_gap)## state_po district avg_eff_gap
## Length:436 Length:436 Min. :0.005533
## Class :character Class :character 1st Qu.:0.059444
## Mode :character Mode :character Median :0.094613
## Mean :0.101799
## 3rd Qu.:0.132682
## Max. :0.465411
## NA's :1eff_gap %>%
ggplot(aes(avg_eff_gap)) +
geom_histogram(binwidth = 0.02)## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
eff_gap <- eff_gap %>%
mutate(avg_eff_gap = if_else(avg_eff_gap > 0.25, 0.25, avg_eff_gap))
min_score <- min(eff_gap$avg_eff_gap, na.rm = TRUE)
max_score <- max(eff_gap$avg_eff_gap, na.rm = TRUE)
eff_gap <- eff_gap %>%
mutate(avg_eff_gap_norm = (avg_eff_gap - min_score) / (max_score - min_score))
eff_gap %>%
ggplot(aes(avg_eff_gap_norm)) +
geom_histogram(binwidth = 0.05)## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).
eff_gap %>%
arrange(desc(avg_eff_gap))## # A tibble: 436 × 4
## state_po district avg_eff_gap avg_eff_gap_norm
## <chr> <chr> <dbl> <dbl>
## 1 FL 010 0.25 1
## 2 FL 012 0.25 1
## 3 FL 014 0.25 1
## 4 FL 015 0.25 1
## 5 FL 021 0.25 1
## 6 FL 025 0.25 1
## 7 FL 027 0.25 1
## 8 GA 003 0.25 1
## 9 GA 005 0.25 1
## 10 OK 001 0.25 1
## # ℹ 426 more rowsUnified Dataset
Finally, I’ll combine datasets together and map them to the candidates dataframe.
First, I need to account for states that have only a single congressional district, as the naming convention used to identify that district differs across datasets.
one_dist_state_regex <- 'AK|WY|ND|SD|VT|DE|DC|MT'Then, I’ll prepare the dataframes themselves, aligning the naming of states and districts.
district_ideology <- district_ideology %>%
filter(state != 'NA', !is.na(mrp_ideology), !is.na(irt_ideology_unweighted)) %>%
mutate(cd_fips = sprintf('%04d', as.numeric(cd_fips)),
state_code = str_sub(cd_fips, 1, 2),
district = str_sub(cd_fips, 3, 4)) %>%
left_join(
data.frame(state = state.name,
state_abb = state.abb)) %>%
arrange(cd_fips, desc(congress)) %>%
mutate(state_abb = if_else(is.na(state_abb), 'DC', state_abb),
district = if_else(str_detect(state_abb,one_dist_state_regex),
'00',district),
dupe = duplicated(cd_fips)) %>%
filter(dupe == FALSE) %>%
rename(compete_ideology = mrp_norm_abs)## Joining with `by = join_by(state)`cookpvi <- cookpvi %>%
rename(state_dist = district) %>%
mutate(state = str_sub(state_dist, 1, 2),
district = str_sub(state_dist, 4, 5),
district = if_else(str_detect(state, one_dist_state_regex),
'00', district)) %>%
rename(compete_cookpvi = pvi_norm_abs)
eff_gap <- eff_gap %>%
mutate(district = sprintf('%02d', as.numeric(district)),
district = if_else(str_detect(state_po, one_dist_state_regex),
'00', district)) %>%
rename(compete_eff_gap = avg_eff_gap_norm)Finally, I’ll read in the candidates data and perform the join.
candidates <- read_csv('data/candidates_partisanship.csv')## Rows: 4216 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): fec_id, name, state, party, office, incumbent_challenge, candidate...
## dbl (5): district, govtrack_id, partisan_score_twitter, partisan_score_nomi...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.candidates <- candidates %>%
mutate(district = sprintf('%02d', district),
district = if_else(str_detect(state, one_dist_state_regex),
'00', district)) %>%
left_join(
select(district_ideology, compete_ideology, state_abb, district),
by = c('state' = 'state_abb', 'district')
) %>%
left_join(
select(cookpvi, compete_cookpvi, state, district),
by = c('state', 'district')
) %>%
left_join(
select(eff_gap, compete_eff_gap, state_po, district),
by = c('state' = 'state_po', 'district')
)## Warning in left_join(., select(district_ideology, compete_ideology, state_abb, : Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 155 of `x` matches multiple rows in `y`.
## ℹ Row 309 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.## Warning in left_join(., select(cookpvi, compete_cookpvi, state, district), : Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 155 of `x` matches multiple rows in `y`.
## ℹ Row 295 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.data('fips_codes')
districts_sf <- congressional_districts() %>%
st_simplify(dTolerance = 10000) %>%
data.frame() %>%
left_join(
fips_codes %>%
select(state, state_code) %>%
unique(),
by = c('STATEFP' = 'state_code')
)## Retrieving data for the year 2021##
|
| | 0%
|
| | 1%
|
|= | 1%
|
|= | 2%
|
|== | 2%
|
|== | 3%
|
|== | 4%
|
|=== | 4%
|
|=== | 5%
|
|==== | 5%
|
|==== | 6%
|
|===== | 6%
|
|===== | 7%
|
|===== | 8%
|
|====== | 8%
|
|====== | 9%
|
|======= | 9%
|
|======= | 10%
|
|======= | 11%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========= | 14%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 22%
|
|================ | 23%
|
|================= | 24%
|
|================= | 25%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================= | 34%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 39%
|
|============================ | 40%
|
|============================ | 41%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|============================== | 44%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 46%
|
|================================= | 47%
|
|================================= | 48%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 49%
|
|=================================== | 50%
|
|=================================== | 51%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|===================================== | 54%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 55%
|
|======================================= | 56%
|
|======================================== | 56%
|
|======================================== | 57%
|
|======================================== | 58%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 59%
|
|========================================== | 60%
|
|========================================== | 61%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 62%
|
|============================================ | 63%
|
|============================================ | 64%
|
|============================================= | 64%
|
|============================================= | 65%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 66%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 69%
|
|================================================= | 70%
|
|================================================= | 71%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|=================================================== | 74%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 76%
|
|====================================================== | 77%
|
|====================================================== | 78%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 79%
|
|======================================================== | 80%
|
|======================================================== | 81%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 82%
|
|========================================================== | 83%
|
|========================================================== | 84%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 86%
|
|============================================================= | 87%
|
|============================================================= | 88%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 89%
|
|=============================================================== | 90%
|
|=============================================================== | 91%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 92%
|
|================================================================= | 93%
|
|================================================================= | 94%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 96%
|
|==================================================================== | 97%
|
|==================================================================== | 98%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 99%
|
|======================================================================| 100%states_sf <- states(cb = TRUE) %>%
st_simplify(dTolerance = 1000) %>%
data.frame() %>%
filter(STUSPS != 'AS',
STUSPS != 'GU',
STUSPS != 'MP',
STUSPS != 'VI',
STUSPS != 'PR',)## Retrieving data for the year 2021##
|
| | 0%
|
|= | 1%
|
|= | 2%
|
|== | 2%
|
|== | 3%
|
|=== | 4%
|
|==== | 5%
|
|==== | 6%
|
|===== | 7%
|
|===== | 8%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================ | 24%
|
|================= | 24%
|
|================= | 25%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 27%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 40%
|
|============================ | 41%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|===================================== | 54%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================= | 65%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 80%
|
|======================================================== | 81%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 86%
|
|============================================================= | 87%
|
|============================================================= | 88%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|==================================================================== | 98%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%candidates_sf <- candidates %>%
left_join(
select(districts_sf, state, CD116FP, geometry),
by = c('state', 'district' = 'CD116FP'),
) %>%
left_join(
select(states_sf, STUSPS, geometry), suffix = c('_distr','_state'),
by = c('state' = 'STUSPS')
)I’ll also put together a few geographic visuals, mapping scores onto
a map. I’ll use the tigris package (https://cran.r-project.org/web/packages/tigris/tigris.pdf).
candidates_sf %>%
filter(state != 'HI',
state != 'AK',
state != 'PR') %>%
ggplot() +
geom_sf(aes(geometry = geometry_distr, fill = compete_ideology)) +
geom_sf(aes(geometry = geometry_state), color = 'blue', size = 0.5, fill = NA) +
scale_fill_gradient(low = 'gray100',
high = 'purple') +
theme(legend.position="bottom")
candidates_sf %>%
filter(state != 'HI',
state != 'AK',
state != 'PR') %>%
ggplot() +
geom_sf(aes(geometry = geometry_distr, fill = compete_cookpvi)) +
scale_fill_gradient(low = 'gray100',
high = 'purple') +
theme(legend.position="bottom")
candidates_sf %>%
filter(state != 'HI',
state != 'AK',
state != 'PR') %>%
ggplot() +
geom_sf(aes(geometry = geometry_distr, fill = compete_eff_gap)) +
scale_fill_gradient(low = 'gray100',
high = 'purple') +
theme(legend.position="bottom")
candidates %>%
ggplot(aes(compete_ideology, compete_cookpvi)) +
geom_point() +
geom_smooth(method = 'lm', formula = 'y ~ x')## Warning: Removed 132 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 132 rows containing missing values (`geom_point()`).
candidates %>%
ggplot(aes(compete_ideology, compete_eff_gap)) +
geom_point() +
geom_smooth(method = 'lm', formula = 'y ~ x')## Warning: Removed 204 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 204 rows containing missing values (`geom_point()`).
candidates %>%
ggplot(aes(compete_cookpvi, compete_eff_gap)) +
geom_point() +
geom_smooth(method = 'lm', formula = 'y ~ x')## Warning: Removed 225 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 225 rows containing missing values (`geom_point()`).
Distributions
candidates %>%
mutate(dupe = duplicated(name)) %>%
filter(dupe == FALSE) %>%
ggplot() +
geom_freqpoly(aes(compete_cookpvi, after_stat(density), color = 'blue'), bins = 20) +
geom_freqpoly(aes(compete_eff_gap, after_stat(density), color = 'green'), bins = 20) +
geom_freqpoly(aes(compete_ideology, after_stat(density), color = 'red'), bins = 20) +
scale_colour_manual(name = 'Variable',
values = c('blue' = 'blue', 'green' = 'green', 'red' = 'red'),
labels = c('cookpvi','eff_gap', 'ideology')) +
xlab('Competitiveness Score') +
ylab('Density') +
theme(legend.position = 'bottom')## Warning: Removed 130 rows containing non-finite values (`stat_bin()`).## Warning: Removed 191 rows containing non-finite values (`stat_bin()`).## Warning: Removed 107 rows containing non-finite values (`stat_bin()`).
Export
write_csv(candidates, 'data/candidates_partisan_compete.csv')