added material for practical class on rmarkdown into a seperate repostiory

.Rproj.user

.Rhistory

.RData

.Ruserdata

# -> 0) set up

rm(list=ls())

library(OECD)

library(dplyr)

library(zoo)

library(ggplot2)

library(plotly)

# -> 0) load data structure for qna

dataset <- "qna"

url <- paste0("https://stats.oecd.org/restsdmx/sdmx.ashx/GetDataStructure/", dataset)

data_structure <- readsdmx::read_sdmx(url)

data_structure %>%

  filter(id == c("CL_QNA_SUBJECT"),

         value %in% c("B1G", "B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")) %>%

  select(value, en_description) %>%

  kable(col.names = c("Code", "Description"))

# -> 1) load data

dataset <- "QNA"

start_time <- as.Date("2010-01-01")

end_time <- as.Date("2023-10-01")

# Note: Q1: 2020-01-01; Q2: 2020-04-01; Q3: 2020-07-01; Q4: 2020-10-01

filter = list(LOCATION = c("DEU", "FRA"),

              SUBJECT = c("B1G", "B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U"),

              MEASURE = c("LNBQRSA"),

              FREQUENCY = c("Q"))

qna_dat <- get_dataset(dataset, filter, start_time, end_time)

# check

head(qna_dat)

tail(qna_dat)

# save original data

save(qna_dat, file = "./01_data/qna_dat_00.RData")

# handle values

class(qna_dat$ObsValue)

qna_dat$ObsValue <- as.numeric(qna_dat$ObsValue)

# handle dates

class(qna_dat$Time)

qna_dat$TIME <- as.yearqtr(qna_dat$Time, "%Y-Q%q")

# check

head(qna_dat)

tail(qna_dat)

# transform data ----

qna_dat <- qna_dat %>%

  left_join(

    qna_dat %>%

      filter(SUBJECT == "B1G") %>%

      select(LOCATION, Time, ObsValue) %>%

      rename(B1G_lev = ObsValue),

    by = c("LOCATION", "Time")

  ) %>%

  group_by(LOCATION, SUBJECT) %>%

  mutate(

    lev = ObsValue,

    gro = (lev - lag(lev))/lag(lev)*100,

    sha = (lev)/B1G_lev*100,

    gro_con = gro*lag(lev)/lag(B1G_lev)

  )

# check 

head(qna_dat)

tail(qna_dat)

# save transformed data ----

save(qna_dat, file = "./01_data/qna_dat_01.RData")

# -> 0) set up

rm(list=ls())

library(OECD)

library(dplyr)

library(zoo)

library(ggplot2)

library(plotly)

# -> 1) load data

# load transformed data

load("../01_data/qna_dat_01.RData")

# visualize data no 1 ----

# Germany, contribution to growth

plot_ger <- qna_dat %>%

  filter(LOCATION %in% c("DEU")) %>%

  ggplot(aes(x = TIME, y = gro_con)) + 

  geom_bar(data = . %>% filter(SUBJECT %in% c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")),

           aes(fill = SUBJECT), 

           position = "stack", 

           stat = "identity") +

  geom_point(data = . %>% filter(SUBJECT %in% c("B1G")),

             aes(y = gro, group = SUBJECT), size = 0.5) + 

  geom_line(data = . %>% filter(SUBJECT %in% c("B1G")),

            aes(y = gro, group = SUBJECT), size = 0.5) +

  scale_fill_discrete(name = "", 

                      labels = c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")) +

  scale_x_yearqtr(

    breaks = seq(from = min(qna_dat$TIME), to = max(qna_dat$TIME), by = 1),

    minor_breaks = seq(from = min(qna_dat$TIME), to = max(qna_dat$TIME), by = 1/4),

    format = "%Y-Q%q",

    expand = c(0, 0)

  ) +

  scale_y_continuous(

    breaks = seq(from = -20, to = 20, by = 2),

    minor_breaks = seq(from = -20, to = 20, by = 1)

  ) +

  labs(

    title = "QNA - Output Components (growth rate (line) contribution to growth rate (bars))",

    subtitle = paste0("Last observation: ", max(qna_dat$TIME)),

    caption = "Source: OECD",

    x = "", y = "QoQ change in % (line) and contribution in %-points (bars)"

  ) +

  scale_color_discrete(name = "", 

                       labels = c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")) +

  theme(legend.position = "bottom")

# Framce, contribution to growth

plot_fra <- qna_dat %>%

  filter(LOCATION %in% c("FRA")) %>%

  ggplot(aes(x = TIME, y = gro_con)) + 

  geom_bar(data = . %>% filter(SUBJECT %in% c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")),

           aes(fill = SUBJECT), 

           position = "stack", 

           stat = "identity") +

  geom_point(data = . %>% filter(SUBJECT %in% c("B1G")),

             aes(y = gro, group = SUBJECT), size = 0.5) + 

  geom_line(data = . %>% filter(SUBJECT %in% c("B1G")),

            aes(y = gro, group = SUBJECT), size = 0.5) +

  scale_fill_discrete(name = "", 

                      labels = c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")) +

  scale_x_yearqtr(

    breaks = seq(from = min(qna_dat$TIME), to = max(qna_dat$TIME), by = 1),

    minor_breaks = seq(from = min(qna_dat$TIME), to = max(qna_dat$TIME), by = 1/4),

    format = "%Y-Q%q",

    expand = c(0, 0)

  ) +

  scale_y_continuous(

    breaks = seq(from = -20, to = 20, by = 2),

    minor_breaks = seq(from = -20, to = 20, by = 1)

  ) +

  labs(

    title = "QNA - Output Components (growth rate (line) contribution to growth rate (bars))",

    subtitle = paste0("Last observation: ", max(qna_dat$TIME)),

    caption = "Source: OECD",

    x = "", y = "QoQ change in % (line) and contribution in %-points (bars)"

  ) +

  scale_color_discrete(name = "", 

                       labels = c("B1GVA", "B1GVB_E", "B1GVF", "B1GVG_I", "B1GVJ", "B1GVK", "B1GVL", "B1GVM_N", "B1GVO_Q", "B1GVR_U")) +

  theme(legend.position = "bottom")

# visualize data no 2 ----

# Germany, contribution to growth

ggplotly(plot_ger)

# France, contribution to growth

ggplotly(plot_fra)