1.Introduction

Data contains “Sectoral Distribution of Expenditures in 6 Months in 2019”.

The web site is here: BKM-Secilen aya ait sektorel gelisim

library(tidyverse)
library(ggplot2)
library(rvest)

2.Download Raw Data and Organize Data

url <- "https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=2019&filter_month=1"
page <- read_html(url)
bkm_tablo_1 <- html_table(page, fill = TRUE)[[4]][-c(1:2),]


for(i in 2:6) {
  url <- paste("https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=2019&filter_month=", i, sep = "")
  page <- read_html(url)
  bkm_tablo_1 <- bind_rows(bkm_tablo_1, html_table(page, fill = TRUE)[[4]][-c(1:2),-1])
}

sec <- c(bkm_tablo_1 %>% select(X1) %>%  filter(X1 != "NA"))
sec_1 <- c(rep(sec[["X1"]], times=6))

bkm_tablo_2 <- bkm_tablo_1 %>% mutate(X1 = sec_1) %>% filter(X1 != "TOPLAM")

month_1 <- c(rep(1:6, times=1, each=26))
bkm_tablo_3 <- bkm_tablo_2 %>% mutate(Month = month_1)
bkm_tablo_4  <- as.data.frame(lapply(bkm_tablo_3, function(x) as.numeric(gsub(",", ".", gsub("\\.", "", x)))))
## Warning in FUN(X[[i]], ...): Zorlamadan dolayı ortaya çıkan NAs
bkm_tablo_4 [,1] <- bkm_tablo_3[,1]

colnames(bkm_tablo_4)<-c("Sector","CC_num","DC_num","CC_volume","DC_volume","Months")
head(bkm_tablo_4)
##                                   Sector   CC_num   DC_num CC_volume
## 1                         ARABA KİRALAMA   256372    49296    195.13
## 2 ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA  2967019   642136   2185.84
## 3           BENZİN VE YAKIT İSTASYONLARI 25277186  8684036   5066.04
## 4                     BIREYSEL EMEKLILIK  2271587      697    716.42
## 5                           ÇEŞİTLİ GIDA 28362091 15221891   4473.98
## 6                     DOĞRUDAN PAZARLAMA   757602    40038    678.99
##   DC_volume Months
## 1     14.77      1
## 2    127.16      1
## 3    680.01      1
## 4      0.30      1
## 5    673.70      1
## 6      7.81      1

3.Let’s see if there is a corelation between “Araba Kiralama”, “Araç Kiralama” and “Benzin ve Yakıt İstasyonları” in terms of volume. Do they change in a similar trend over a 6 month period?

focused <- c("ARABA KİRALAMA","ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA","BENZİN VE YAKIT İSTASYONLARI")
bkm_analysis_1 <- bkm_tablo_4 %>% filter(Sector %in% focused) %>% mutate(SUM_VOLUME = CC_volume + DC_volume) %>% group_by(Months) 
ggplot(bkm_analysis_1,aes(x=Months, y=SUM_VOLUME, color=Sector)) +
  geom_line()