#データフレーム名変更
df <- EVS_WVS_Joint_Stata_v4_0
#パッケージ読み込み
library(dplyr)
library(purrr)
library(ggplot2)
library(stringr)


##変数処理
#左右イデオロギーのDKNAダミー変数作成
df <- df %>% mutate(lrdk = e033)
df <- df %>% mutate(lrdk = case_when(
  lrdk >= 1 & lrdk <= 10 ~ 1,
  lrdk == -1 ~ 0,
  lrdk >= -5 & lrdk <= -3 ~ NA_real_,
  TRUE ~ lrdk
))
#分析使用変数の欠損値処理
df <- df %>% mutate(across(c("e033", "g006", "g257", "a124_06", "b008", "d059", "f118", "e114", "e235"), ~ case_when(
  . >= -5 & . <= -1 ~ NA_real_,
  TRUE ~ .
)))
#環境設問の回答3を処理
df <- df %>% mutate(b008 = case_when(
  b008 == 3 ~ NA_real_,
  TRUE ~ b008
))
#解釈簡単化のためg006とg257の正負を逆に
df$g006 <- 5 - df$g006
df$g257 <- 5 - df$g257

#dfにoecd変数を挿入
df <- df %>%
  mutate(oecd = ifelse(cntry_an %in% c('AR','AT','AU','BG','CA','CH','CL','CO','CZ','DE','DK','EE','ES','FI','FR','GB','GR','HU','IS','IT','JP','KR','LT','LV','MN','MX','NL','NO','NZ','PL','PR','PT','RO','SE','SI','SK','TW','US'), 1, 0))


#補助関数の事前作成。目的①国により無回答変数がある場合には分析対象から外し結果でNAを返す（エラー回避）。目的②表示桁数の設定。目的③相関係数とp値算出の補助関数を分ける。
handle_cor <- function(x, y) {
  if (sum(complete.cases(x, y)) > 1) {
    return(round(cor(x, y, use = "complete.obs"), 3))
  } else {
    return(NA)
  }
}

handle_cor_test <- function(x, y) {
  if (sum(complete.cases(x, y)) > 1) {
    return(round(cor.test(x, y, use = "complete.obs")$p.value, 3))
  } else {
    return(NA)
  }
}

#相関係数とp値の一覧が並んだ行列Zを作成
Z <- df %>%
  group_by(cntry_an) %>%
  summarise(
    cor_g006a124 = handle_cor(g006, a124_06),
    p_value_g006a124 = handle_cor_test(g006, a124_06),
    cor_e033g006 = handle_cor(e033, g006),
    p_value_e033g006 = handle_cor_test(e033, g006),
    cor_e033g257 = handle_cor(e033, g257),
    p_value_e033g257 = handle_cor_test(e033, g257),
    cor_e033a124 = handle_cor(e033, a124_06),
    p_value_e033a124 = handle_cor_test(e033, a124_06),
    cor_g257b008 = handle_cor(g257, b008),
    p_value_g257b008 = handle_cor_test(g257, b008),
    cor_g257d059 = handle_cor(g257, d059),
    p_value_g257d059 = handle_cor_test(g257, d059),
    cor_g257f118 = handle_cor(g257, f118),
    p_value_g257f118 = handle_cor_test(g257, f118),
	cor_g257e235 = handle_cor(g257, e235),
    p_value_g257e235 = handle_cor_test(g257, e235),
	cor_g006e235 = handle_cor(g006, e235),
    p_value_g006e235 = handle_cor_test(g006, e235),
	cor_a124e235 = handle_cor(a124_06, e235),
    p_value_a124e235 = handle_cor_test(a124_06, e235)
  )

#国名表記の変更（略称から国号ヘ）
Z$cntry_an2 <- Z$cntry_an
Z <- Z %>%
  mutate(
    cntry_an2 = str_replace(cntry_an2, "AR", "アルゼンチン"),
    cntry_an2 = str_replace(cntry_an2, "AT", "オーストリア"),
    cntry_an2 = str_replace(cntry_an2, "AU", "オーストラリア"),
	cntry_an2 = str_replace(cntry_an2, "BG", "ブルガリア"),
    cntry_an2 = str_replace(cntry_an2, "CA", "カナダ"),
    cntry_an2 = str_replace(cntry_an2, "CH", "スイス"),
    cntry_an2 = str_replace(cntry_an2, "CL", "チリ"),
    cntry_an2 = str_replace(cntry_an2, "CO", "コロンビア"),
    cntry_an2 = str_replace(cntry_an2, "CZ", "チェコ"),
    cntry_an2 = str_replace(cntry_an2, "DE", "ドイツ"),
    cntry_an2 = str_replace(cntry_an2, "DK", "デンマーク"),
    cntry_an2 = str_replace(cntry_an2, "EE", "エストニア"),
    cntry_an2 = str_replace(cntry_an2, "ES", "スペイン"),	
    cntry_an2 = str_replace(cntry_an2, "FI", "フィンランド"),
    cntry_an2 = str_replace(cntry_an2, "FR", "フランス"),
    cntry_an2 = str_replace(cntry_an2, "GB", "イギリス"),
    cntry_an2 = str_replace(cntry_an2, "GR", "ギリシャ"),
    cntry_an2 = str_replace(cntry_an2, "HU", "ハンガリー"),
    cntry_an2 = str_replace(cntry_an2, "IS", "アイスランド"),
    cntry_an2 = str_replace(cntry_an2, "IT", "イタリア"),
    cntry_an2 = str_replace(cntry_an2, "JP", "日本"),
    cntry_an2 = str_replace(cntry_an2, "KR", "韓国"),
    cntry_an2 = str_replace(cntry_an2, "LT", "リトアニア"),
    cntry_an2 = str_replace(cntry_an2, "LV", "ラトビア"),
	cntry_an2 = str_replace(cntry_an2, "MN", "モンゴル"),
    cntry_an2 = str_replace(cntry_an2, "MX", "メキシコ"),
    cntry_an2 = str_replace(cntry_an2, "NL", "オランダ"),
    cntry_an2 = str_replace(cntry_an2, "NO", "ノルウェー"),
    cntry_an2 = str_replace(cntry_an2, "NZ", "ﾆｭｰｼﾞｰﾗﾝﾄﾞ"),
    cntry_an2 = str_replace(cntry_an2, "PL", "ポーランド"),
    cntry_an2 = str_replace(cntry_an2, "PR", "プエルトリコ"),
    cntry_an2 = str_replace(cntry_an2, "PT", "ポルトガル"),
	cntry_an2 = str_replace(cntry_an2, "RO", "ルーマニア"),
    cntry_an2 = str_replace(cntry_an2, "SE", "スウェーデン"),
    cntry_an2 = str_replace(cntry_an2, "SI", "スロベニア"),
    cntry_an2 = str_replace(cntry_an2, "SK", "スロバキア"),
    cntry_an2 = str_replace(cntry_an2, "TW", "台湾"),
    cntry_an2 = str_replace(cntry_an2, "US", "アメリカ")
	)

#OECDダミーの作成
Z <- Z %>%
  mutate(oecd = ifelse(cntry_an %in% c('AR','AT','AU','BG','CA','CH','CL','CO','CZ','DE','DK','EE','ES','FI','FR','GB','GR','HU','IS','IT','JP','KR','LT','LV','MN','MX','NL','NO','NZ','PL','PR','PT','RO','SE','SI','SK','TW','US'), 1, 0))

##行列Zを元に図表を作っていく##

##図０．１の３ナショナリズム相関
cor.test(df$g006, df$a124_06)
cor.test(df$g257, df$a124_06)
cor.test(df$g257, df$g006)
#ウェイトをかける場合
library(weights)
wtd.cor(df$g257, df$g006, w = df$pwght)
wtd.cor(df$g257, df$a124_06, w = df$pwght)
wtd.cor(df$g006, df$a124_06, w = df$pwght)

#分析その0(図2.2:ナショナルプライドと排外主義相関)
# 欠損値等を除く作業
Z0 <- subset(Z, oecd == 1)
Z0 <- na.omit(Z0)
# プロットの色と形を変数yに応じて設定
Z0$shape <- cut(Z0$p_value_g006a124, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
Z0$color <- cut(Z0$p_value_g006a124, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
# xの値でデータフレームをソート
Z0_sorted <- Z0[order(Z0$cor_g006a124), ]
# プロット作成
ggplot(Z0_sorted, aes(y = reorder(cntry_an2, cor_g006a124), x = cor_g006a124, shape = shape, col = color)) +
  geom_point(size = 4) +
  scale_color_identity() +
  scale_shape_identity() +
  xlab("ナショナルプライドと排外主義の相関係数") +
  ylab("") +
  geom_vline(xintercept = 0) +
  ggtitle("") +
  theme_minimal()

#分析その1（図3.1:ナショナルアイデンティティと左右認識）
# 欠損値等を除く作業
Z2 <- na.omit(Z)
Z2 <- subset(Z2, oecd == 1)
# プロットの色と形を変数yに応じて設定
Z2$shape <- cut(Z2$p_value_e033g257, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
Z2$color <- cut(Z2$p_value_e033g257, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
# xの値でデータフレームをソート
Z2_sorted <- Z2[order(Z2$cor_e033g257), ]
# プロット作成
ggplot(Z2_sorted, aes(y = reorder(cntry_an2, cor_e033g257), x = cor_e033g257, shape = shape, col = color)) +
  geom_point(size = 4) +
  scale_color_identity() +
  scale_shape_identity() +
  xlab("政治左右と帰属意識の相関係数") +
  ylab("") +
  geom_vline(xintercept = 0) +
  ggtitle("") +
  theme_minimal()


#分析その１（図3.2a:ナショナルプライドと左右認識）
# 欠損値等を除く作業
Z1 <- na.omit(Z)
Z1 <- subset(Z1, oecd == 1)
# プロットの色を変数yに応じて設定
Z1$shape <- cut(Z1$p_value_e033g006, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
Z1$color <- cut(Z1$p_value_e033g006, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
# xの値でデータフレームをソート
Z1_sorted <- Z1[order(Z1$cor_e033g006), ]
# プロット作成
ggplot(Z1_sorted, aes(y = reorder(cntry_an2, cor_e033g006), x = cor_e033g006, shape = shape, col = color)) +
  geom_point(size = 4) +
  scale_color_identity() +
  scale_shape_identity() +
  xlab("政治左右とナショナルプライドの相関係数") +
  ylab("") +
  geom_vline(xintercept = 0) +
  ggtitle("") +
  theme_minimal()


#分析その3（図3.2b:排外主義と左右認識）形を変える場合
# 欠損値等を除く作業
Z3 <- na.omit(Z)
Z3 <- subset(Z3, oecd == 1)
# プロットの色を変数yに応じて設定
Z3$shape <- cut(Z3$p_value_e033a124, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
Z3$color <- cut(Z3$p_value_e033a124, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
# xの値でデータフレームをソート
Z3_sorted <- Z3[order(Z3$cor_e033a124), ]
# プロット作成
ggplot(Z3_sorted, aes(y = reorder(cntry_an2, cor_e033a124), x = cor_e033a124, shape=shape, col = color)) +
  geom_point(size = 4) +
  scale_color_identity() +
  scale_shape_identity() +
  xlab("政治左右と排外主義の相関係数") +
  ylab("") +
  geom_vline(xintercept = 0) +
  ggtitle("") +
  theme_minimal()


#分析その4（図4.1ジェンダー平等意識d59およびLGBT権利意識f118とナショナルアイデンティティ）
# 2相関の平均値データを作成
Z$genlgbt <- (Z$cor_g257d059 + Z$cor_g257f118)/2
# 欠損値等を除く作業
Z4 <- na.omit(Z)
Z4 <- subset(Z4, oecd == 1)
# プロットの色を変数yに応じて設定
Z4$color4a <- cut(Z4$p_value_g257d059, breaks = c(-Inf, 0.05, Inf), labels = c("black", "gray75"))
Z4$color4b <- cut(Z4$p_value_g257f118, breaks = c(-Inf, 0.05, Inf), labels = c("black", "gray75"))
Z4$shape4a <- cut(Z4$p_value_g257d059, breaks = c(-Inf, 0.05, Inf), labels = c("▲", "△"))
Z4$shape4b <- cut(Z4$p_value_g257f118, breaks = c(-Inf, 0.05, Inf), labels = c("▼", "▽"))
# プロット作成
ggplot(Z4) +
  geom_point(aes(x = cor_g257d059,  y = reorder(cntry_an2, genlgbt), col=color4a, shape=shape4a)) +
  geom_point(aes(x = cor_g257f118,  y = reorder(cntry_an2, genlgbt), col=color4b, shape=shape4b)) +
  labs(title = " ", x = " ", y = " ") +
  geom_vline(xintercept = 0) + 
  scale_color_identity() +
  scale_shape_identity() +
  theme_bw() +
  theme(legend.position = "none") 

#分析その5（図4.2:環境主義とナショナルアイデンティティ）
# 欠損値等を除く作業
Z5 <- na.omit(Z)
Z5 <- subset(Z5, oecd == 1)
# プロットの色を変数yに応じて設定
Z5$color5 <- cut(Z5$p_value_g257b008, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
Z5$shape5 <- cut(Z5$p_value_g257b008, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
# プロット作成
ggplot(Z5) +
  geom_point(size=4, aes(x = cor_g257b008,  y = reorder(cntry_an2, cor_g257b008), shape = shape5, color=color5)) +
  labs(title = " ", x = " ", y = " ") +
  geom_vline(xintercept = 0) + 
  scale_color_identity() +
  scale_shape_identity() +
  theme_bw() +
  theme(legend.position = "none") 
  
  
#分析その6（図5.1 ナショナルアイデンティティ・ナショナルプライドと民主的規範）
# 2相関の平均値データを作成
Z$democ <- (Z$cor_g257e235 + Z$cor_g006e235)/2
# 欠損値等を除く作業
Z6 <- na.omit(Z)
Z6 <- subset(Z6, oecd == 1)
# プロットの色を変数yに応じて設定
Z6$color6a <- cut(Z6$p_value_g257e235, breaks = c(-Inf, 0.05, Inf), labels = c("black", "gray75"))
Z6$color6b <- cut(Z6$p_value_g006e235, breaks = c(-Inf, 0.05, Inf), labels = c("black", "gray75"))
Z6$shape6a <- cut(Z6$p_value_g257e235, breaks = c(-Inf, 0.05, Inf), labels = c("▲", "△"))
Z6$shape6b <- cut(Z6$p_value_g006e235, breaks = c(-Inf, 0.05, Inf), labels = c("▼", "▽"))
# プロット作成
ggplot(Z6) +
  geom_point(aes(x = cor_g257e235,  y = reorder(cntry_an2, democ), col=color6a, shape=shape6a)) +
  geom_point(aes(x = cor_g006e235,  y = reorder(cntry_an2, democ), col=color6b, shape=shape6b)) +
  labs(title = " ", x = " ", y = " ") +
  geom_vline(xintercept = 0) + 
  scale_color_identity() +
  scale_shape_identity() +
  theme_bw() +
  theme(legend.position = "none") 
  
#分析その7（図5.2 排外主義と民主的規範）
# 2相関の平均値データを作成
# 欠損値等を除く作業
Z7 <- na.omit(Z)
Z7 <- subset(Z7, oecd == 1)
# プロットの色を変数yに応じて設定
Z7$color7 <- cut(Z7$p_value_a124e235, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("black", "gray30", "gray60"))
Z7$shape7 <- cut(Z7$p_value_a124e235, breaks = c(-Inf, 0.01, 0.05, Inf), labels = c("●", "◆", "×"))
# プロット作成
ggplot(Z7) +
  geom_point(size=4, aes(x = cor_a124e235,  y = reorder(cntry_an2, cor_a124e235), shape = shape7, color=color7)) +
  labs(title = " ", x = " ", y = " ") +
  geom_vline(xintercept = 0) + 
  scale_color_identity() +
  scale_shape_identity() +
  theme_bw() +
  theme(legend.position = "none")