BKM Assignment
Dost Karaahmetli
November 7, 2019
library(dplyr)
library(tidyverse)
library(ggplot2)
library(rvest)
library(grid)
library(scales)Step 1 - Data Preparation for Analysis as of end of 2018
Download and read year end data 2018 from the website
url <- "https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=2018&filter_month=12&List=Listele"
page <- read_html(url)
year_end_2018 <- html_table(page, fill=TRUE)
glimpse(year_end_2018)## List of 4
## $ :'data.frame': 2 obs. of 3 variables:
## ..$ X1: chr [1:2] "SEÇILEN AYA AIT SEKTÖREL GELISIM" "Seçilen Aya Ait Sektörel Gelisim"
## ..$ X2: chr [1:2] "Seçilen Aya Ait Sektörel Gelisim" NA
## ..$ X3: chr [1:2] "Seçilen Aya Ait Sektörel Gelisim" NA
## $ :'data.frame': 1 obs. of 1 variable:
## ..$ X1: chr "Seçilen Aya Ait Sektörel Gelisim"
## $ :'data.frame': 1 obs. of 1 variable:
## ..$ X1: chr "Yil:\n 2019201820172016201520142013201220112010Ay:\n "| __truncated__
## $ :'data.frame': 29 obs. of 5 variables:
## ..$ X1: chr [1:29] "Isyeri Grubu" "Isyeri Grubu" "ARABA KIRALAMA" "ARAÇ KIRALAMA-SATIS/SERVIS/YEDEK PARÇA" ...
## ..$ X2: chr [1:29] "Islem Adedi" "Islem Adedi(Kredi Karti)" "266.038" "3.361.371" ...
## ..$ X3: chr [1:29] "Islem Adedi" "Islem Adedi (Banka Karti)" "50.722" "709.323" ...
## ..$ X4: chr [1:29] "Islem Tutari (Milyon TL)" "Islem Tutari \n (Kredi Karti)" "199,57" "2.804,73" ...
## ..$ X5: chr [1:29] "Islem Tutari (Milyon TL)" "Islem Tutari \n (Banka Karti)" "16,54" "147,82" ...Select the columns and processing of raw data, since I’m only interested in CC data.
year_end_2018 <- year_end_2018[[4]] %>% slice(-(1:2)) %>% filter(X1 != "TOPLAM") %>% select(1, 2, 4)
colnames(year_end_2018) <- c("isyeri", "islem_adedi", "islem_tutari")
year_end_2018## isyeri islem_adedi islem_tutari
## 1 ARABA KIRALAMA 266.038 199,57
## 2 ARAÇ KIRALAMA-SATIS/SERVIS/YEDEK PARÇA 3.361.371 2.804,73
## 3 BENZIN VE YAKIT ISTASYONLARI 27.007.860 5.490,44
## 4 BIREYSEL EMEKLILIK 2.254.844 668,84
## 5 ÇESITLI GIDA 28.278.290 4.609,98
## 6 DOGRUDAN PAZARLAMA 803.029 750,34
## 7 EGITIM / KIRTASIYE / OFIS MALZEMELERI 6.889.839 1.417,88
## 8 ELEKTRIK-ELEKTRONIK ESYA, BILGISAYAR 7.980.083 3.917,89
## 9 GIYIM VE AKSESUAR 28.162.255 5.224,67
## 10 HAVAYOLLARI 1.757.052 1.211,97
## 11 HIZMET SEKTÖRLERI 23.010.866 4.529,13
## 12 KAMU/VERGI ODEMELERI 2.744.917 1.372,60
## 13 KONAKLAMA 1.564.436 964,62
## 14 KULÃœP / DERNEK /SOSYAL HIZMETLER 1.164.357 243,98
## 15 KUMARHANE/IÇKILI YERLER 546.548 225,65
## 16 KUYUMCULAR 863.939 892,64
## 17 MARKET VE ALISVERIS MERKEZLERI 104.967.591 11.412,56
## 18 MOBILYA VE DEKORASYON 5.114.674 2.556,26
## 19 MÃœTEAHHIT ISLERI 622.598 776,39
## 20 SAGLIK/SAGLIK ÃœRÃœNLERI/KOZMETIK 15.354.372 2.501,57
## 21 SEYAHAT ACENTELERI/TASIMACILIK 5.685.982 1.583,93
## 22 SIGORTA 5.190.237 3.409,63
## 23 TELEKOMÃœNIKASYON 18.453.861 1.773,13
## 24 YAPI MALZEMELERI, HIRDAVAT, NALBURIYE 3.424.605 2.675,00
## 25 YEMEK 40.487.702 2.314,60
## 26 DIGER 4.943.785 1.351,30Changing Character Columns to Numeric Values
year_end_2018$islem_adedi <- as.numeric(gsub("\\.","", year_end_2018$islem_adedi))
year_end_2018$islem_tutari <- as.numeric(gsub(",",".",gsub("\\.","", year_end_2018$islem_tutari)))
str(year_end_2018)## 'data.frame': 26 obs. of 3 variables:
## $ isyeri : chr "ARABA KIRALAMA" "ARAÇ KIRALAMA-SATIS/SERVIS/YEDEK PARÇA" "BENZIN VE YAKIT ISTASYONLARI" "BIREYSEL EMEKLILIK" ...
## $ islem_adedi : num 266038 3361371 27007860 2254844 28278290 ...
## $ islem_tutari: num 200 2805 5490 669 4610 ...Step 2 - Analysis as of end of 2018
A - Total Number of Transactions and Total CC Spendings per sector
adet <- ggplot(year_end_2018, aes(x=isyeri, y=islem_adedi)) +
geom_bar(stat="identity",fill="steelblue")+ coord_flip() + scale_y_continuous(labels=comma) +
labs(title = "Credit Card Transaction By Sector", x="", y="") +theme_minimal()
tutar <- ggplot(year_end_2018, aes(x=isyeri, y=islem_tutari)) +
geom_bar(stat="identity",fill="lightgreen") + coord_flip() + scale_y_continuous(labels=comma) +
labs(title = "Credit Card Total Spending By Sector", x="", y="") +theme_minimal()
grid.newpage()
grid.draw(rbind(ggplotGrob(adet), ggplotGrob(tutar), size = "last"))
B - Top 10 Sectors in terms of Total CC Spendings
share <- year_end_2018 %>% group_by(isyeri) %>% summarise(islem_tutari = sum(islem_tutari)) %>%
mutate(harcama_payi = islem_tutari/sum(islem_tutari)) %>% top_n(10, harcama_payi)
share_plot <- ggplot(share, aes(x=isyeri, y=islem_tutari, fill=isyeri)) +
geom_bar(stat="identity")+
coord_polar()+
theme(legend.position = "right", axis.text.x = element_text(angle = 0))+
geom_text(aes(y = islem_tutari , label = islem_tutari))+
labs(title = "Sectoral shares")
share_plot
C - Average Spending per Transaction
cart_volume <- year_end_2018 %>% group_by(isyeri) %>% mutate(avg_spending = islem_tutari/islem_adedi*1000000)
cart_volume## # A tibble: 26 x 4
## # Groups: isyeri [26]
## isyeri islem_adedi islem_tutari avg_spending
## <chr> <dbl> <dbl> <dbl>
## 1 ARABA KIRALAMA 266038 200. 750.
## 2 ARAÇ KIRALAMA-SATIS/SERVIS/YEDEK ~ 3361371 2805. 834.
## 3 BENZIN VE YAKIT ISTASYONLARI 27007860 5490. 203.
## 4 BIREYSEL EMEKLILIK 2254844 669. 297.
## 5 ÇESITLI GIDA 28278290 4610. 163.
## 6 DOGRUDAN PAZARLAMA 803029 750. 934.
## 7 EGITIM / KIRTASIYE / OFIS MALZEME~ 6889839 1418. 206.
## 8 ELEKTRIK-ELEKTRONIK ESYA, BILGISA~ 7980083 3918. 491.
## 9 GIYIM VE AKSESUAR 28162255 5225. 186.
## 10 HAVAYOLLARI 1757052 1212. 690.
## # ... with 16 more rowsggplot(cart_volume, aes(x=isyeri, y=avg_spending)) +
geom_bar(stat="identity",fill="orange")+ coord_flip() + scale_y_continuous(labels=comma) +
labs(title = "Amount of Spending per Transaction", x="", y="") +theme_minimal() 