AS5-1：RiTW資料探索

---

pacman::p_load(dplyr,ggplot2,tidyr,plotly,stringr)

load("RiTW/ritw01.rdata")
ls()

[1] "Age10"     "Age26"     "Age5"      "DemoQ"     "DemoY107"  "DemoY108" 
[7] "dicRitw01" "Income"   

DemoY108 - 村里季度資料

table(DemoY108$year)

  97   98   99  100  101  102  103  104  105  106  107  108 
7822 7834 7835 7835 7835 7839 7851 7851 7851 7851 7760 7760 

BIG6 = c("桃園市","臺北市","臺中市","臺南市","高雄市","新北市")

Y = DemoY108 %>% select(
  year, vid=`村里代碼`, city=`縣市名稱`, county=`鄉鎮市區名稱`, 
  vname=`村里名稱`, house=`戶數`, pop=`人口數`, fm.ratio=`性比例`, 
  sp.ratio=`扶養比`, elderly=`老化指數`) %>% 
  filter(! city %in% c("連江縣","金門縣","澎湖縣")) %>% 
  mutate(city = case_when(
    city == "臺北縣" ~ "新北市",
    city == "桃園縣" ~ "桃園市",
    city == "高雄縣" ~ "高雄市",
    city == "臺南縣" ~ "臺南市",
    city == "臺中縣" ~ "臺中市",
    TRUE ~ city ))

Y %>% is.na %>% colSums

    year      vid     city   county    vname    house      pop fm.ratio 
       0        0        0        0        0        0        0        0 
sp.ratio  elderly 
       0        0 

Y %>% group_by(year, city) %>% 
  summarise(Pop = sum(pop)) %>%
  ggplot(aes(x=year, y=Pop, col=factor(city)) ) + 
  geom_line(size=1) -> g; ggplotly(g)

df = Y %>% group_by(city, year) %>% summarise(
  `性比例` = sum(fm.ratio*pop)/sum(pop),
  `扶養比` = sum(sp.ratio*pop)/sum(pop),
  `老化指數` = sum(elderly*pop)/sum(pop),
  `人口` = sum(pop)
  ) %>% filter(year %in% seq(99,108,3)) 

scale1 = function(mp=0) scale_color_gradient2(
  midpoint=mp, low="seagreen4", mid="wheat2", high="firebrick2")

df %>% #filter(city %in% BIG6) %>% 
  ggplot(aes(x=`扶養比`, y=`老化指數`, col=`性比例`, size=`人口`, label=year)) +
  geom_point(alpha=1) + scale1(100) + theme_bw() +
  facet_wrap(~city, ncol=4) -> g; ggplotly(g)

df %>% #filter(city %in% BIG6) %>% 
  ggplot(aes(x=`扶養比`, y=`老化指數`, col=`性比例`, size=`人口`, label=city)) +
  geom_point(alpha=1) + scale1(100) + theme_bw() +
  facet_wrap(~year) -> g; ggplotly(g)

DemoQ - 村里季度資料

table(DemoQ$`資料時間`)

100Y1S 100Y2S 100Y3S 100Y4S 101Y1S 101Y2S 101Y3S 101Y4S 102Y1S 102Y2S 102Y3S 
  7581   7500   7443   7460   7534   7471   7464   7450   7534   7451   7482 
102Y4S 103Y1S 103Y2S 103Y3S 103Y4S 104Y1S 104Y2S 104Y3S 104Y4S 105Y1S 105Y2S 
  7519   7585   7535   7501   7500   7531   7531   7506   7535   7623   7542 
105Y3S 105Y4S 106Y1S 106Y2S 106Y3S 106Y4S 107Y1S 107Y2S 107Y3S 107Y4S 108Y1S 
  7530   7502   7610   7514   7544   7549   7600   7461   7461   7442   7514 
108Y2S 108Y3S 108Y4S  97Y1S  97Y2S  97Y3S  97Y4S  98Y1S  98Y2S  98Y3S  98Y4S 
  7464   7466   7502   7503   7411   7386   7435   7483   7406   7403   7441 
 99Y1S  99Y2S  99Y3S  99Y4S 
  7476   7436   7440   7458 

Q = DemoQ %>% transmute(
  year = str_remove(`資料時間`,"Y.*$") %>% as.integer,
  qtr = str_remove(`資料時間`,"^\\d+Y"),
  vid=`村里代碼`, city=`縣市名稱`, county=`鄉鎮市區名稱`, vname=`村里名稱`,
  born=`出生數`, death=`死亡數`, marriage=`結婚對數`, devorce=`離婚對數`, 
  time=`資料時間`
  ) %>% 
  filter(! city %in% c("連江縣","金門縣","澎湖縣")) %>% 
  mutate(city = case_when(
    city == "臺北縣" ~ "新北市",
    city == "桃園縣" ~ "桃園市",
    city == "高雄縣" ~ "高雄市",
    city == "臺南縣" ~ "臺南市",
    city == "臺中縣" ~ "臺中市",
    TRUE ~ city )) %>% 
  mutate_at(vars(born:devorce), ~replace_na(as.integer(.), 0))

group_by(Q, qtr) %>% 
  summarise_at(vars(born:devorce), sum) %>% 
  gather("event", "n", -1) %>% 
  ggplot(aes(x=qtr, y=n)) + geom_bar(stat="identity") +
  facet_wrap(~event, nrow=1)

group_by(Q, time) %>% 
  summarise_at(vars(born:devorce), sum) %>% 
  gather("event", "n", -1) %>% 
  ggplot(aes(x=time, y=n, group=event, col=event)) + 
  geom_line() -> g ; ggplotly(g) 

Warning: Using `as.character()` on a quosure is deprecated as of rlang 0.3.0.
Please use `as_label()` or `as_name()` instead.
This warning is displayed once per session.

group_by(Q, year) %>% 
  summarise_at(vars(born:devorce), sum) %>% 
  gather("event", "n", -1) %>% 
  ggplot(aes(x=year, y=n, col=event)) + 
  geom_line() -> g ; ggplotly(g) 

group_by(Q, city) %>% 
  summarise_at(vars(born:devorce), sum) %>% 
  ggplot(aes(x=death, y=born, col=marriage, size=devorce, label=city)) + 
  geom_point(alpha=0.7) + 
  geom_smooth(method="lm",se=F,color="gold") -> g ; ggplotly(g)