* Steps from Dec 4, 2022

* 1. Get Member Ideology Data from https://voteview.com/articles/data_help_members (HSall_members.csv)

* 2. Insert two columns on the left of the "HSall_members.csv" file

* 3. Paste this into the A column (starting in row 2): =IF(D2="House",CONCATENATE("replace party=",I2," if icpsr==",E2),".")

* 4. Paste this into the B column (starting in row 2): =IF(D2="House",CONCATENATE("replace ICPSRname=","""",L2,""""," if icpsr==",E2),".")

* 5. Get House data (house_BridgeIdealPoints_1951_2020.csv) from https://michaelbailey.georgetown.domains/bridge-ideal-points-2020/

* 6. Import "house_BridgeIdealPoints_1951_2020.csv" into Stata using:

import delimited G:\house_BridgeIdealPoints_1951_2020.csv

* 7. Run these commands in Stata:

gen party = .
gen ICPSRname="."

* 8. Copy the A column into a Stata do file. Copy the B column into a Stata do file. Then run the do file.

* 9. Run these commands in Stata:

gen south = 0 
replace south = 1 if state_abbrev == "AL" /* Alabama */
replace south = 1 if state_abbrev == "AR" /* Arkansas */
replace south = 1 if state_abbrev == "FL" /* Florida */
replace south = 1 if state_abbrev == "GA" /* Georgia */
replace south = 1 if state_abbrev == "LA" /* Louisiana */
replace south = 1 if state_abbrev == "MS" /* Mississippi */
replace south = 1 if state_abbrev == "NC" /* North Carolina */
replace south = 1 if state_abbrev == "SC" /* South Carolina */
replace south = 1 if state_abbrev == "TN" /* Tennessee */
replace south = 1 if state_abbrev == "TX" /* Texas */
replace south = 1 if state_abbrev == "VA" /* Virginia */

egen gop         = mean(ideal) if party==200, by(year)
egen dem         = mean(ideal) if party==100, by(year)
egen demsouth    = mean(ideal) if party==100 & south==1, by(year)
egen demnonsouth = mean(ideal) if party==100 & south==0, by(year)

gen     group = "."
replace group = "GOP"         if party==200
replace group = "DemSouth"    if party==100 & south==1
replace group = "DemNonSouth" if party==100 & south==0
drop if group == "."

twoway (scatter gop year, mcolor(red)) (scatter demsouth year, mcolor(dknavy)) (scatter demnonsouth year, mcolor(ltblue))

* 10. Export to a CSV file

export delimited using "G:\bailey polarization.csv"

* 11. Open R and run these commands:

DATA <- read.csv(file.choose(), header=TRUE)

library(tidyverse)

ggplot(data=DATA, aes(x=year, y=ideal, color=group)) +
   geom_hline(yintercept=0, col="white") +
   geom_point(stat="summary", fun="mean") +
   scale_color_manual(breaks=c("GOP","DemSouth","DemNonSouth"), labels=c("GOP","Dem South","Dem NonSouth"), values=c("red","blue4","blue1")) +
   scale_x_continuous(breaks=seq(1950,2020,10), labels=seq(1950,2020,10), expand=c(0,0), limits=c(1950,2020), sec.axis=dup_axis()) +
   scale_y_continuous(breaks=seq(-2,2,1), labels=seq(-2,2,1), expand=c(0,0), limits=c(-2.5,2.5), sec.axis=dup_axis()) +
   labs(title="Mean ideology by party in the U.S. House of Representatives", caption="Data source: Bailey Bridge Ideal Points (https://michaelbailey.georgetown.domains/bridge-ideal-points-2020/)") +
   theme(
        plot.background    = element_rect(fill="white"),
        plot.margin        = unit(c(0.5,0.5,0.5,0.5),"cm"),
        plot.title         = element_text(face="bold", margin=margin(t=0, b=0), size=15, hjust=0.5),
        plot.subtitle      = element_text(size=12, hjust=0.5, margin=margin(b=7)),
        plot.caption       = element_text(size=10, hjust=0, margin=margin(t=7)),
        panel.background   = element_rect(fill="gray90", color="black", size=0.5, linetype="solid"),
        panel.border       = element_rect(fill=NA, color="black", linetype="solid", size=1.5),
        panel.grid.major.x = element_blank(), 
        panel.grid.major.y = element_blank(),
        panel.grid.minor.x = element_blank(), 
        panel.grid.minor.y = element_blank(),
        panel.spacing.x    = unit(1, "lines"),
        panel.spacing.y    = unit(1, "lines"),
        axis.text.x        = element_text(size=12, color="black", margin=margin(t=7, b=7)),
        axis.text.x.top    = element_text(size=12, color="black", margin=margin(t=7, b=7)),
        axis.text.y        = element_text(size=12, color="black", margin=margin(l=7, r=7)),
        axis.text.y.right  = element_text(size=12, color="black", margin=margin(l=7, r=7)),
        axis.ticks.y       = element_blank(),
        axis.ticks.x       = element_blank(),
        axis.title.y       = element_blank(),
        axis.title.x       = element_blank(),
        legend.position    = "right",
        legend.text        = element_text(size=12, color="black"),
        legend.title       = element_blank())

ggsave(file="G:Bailey polarization 2022.svg", width=10, height=5)

11. Run this in R:

DATA$party <- recode(DATA$group, "DemSouth"="Dem", "DemNonSouth"="Dem")

12. Run the above ggplot2 command, but change these lines:

ggplot(data=DATA, aes(x=year, y=ideal, color=party)) +
   scale_color_manual(breaks=c("GOP","Dem"), labels=c("GOP","Dem"), values=c("red","blue3")) +