Emre Usta 11/10/2019
The Interbank Card Center (BKM) was established in 1990 with the partnership of 13 public and private Turkish banks for the purpose of providing solutions to the common problems and developing the rules and standards of credit and debit cards in Turkey, within the card payment system.
The dataset we used in this analysis from BKM includes number and volume of transactions made with credit card and debit card with respect to merchandise category group in Turkey.
# Creating a function to filter year and month on the URL
filterYearMonth <-
function(year,month) {
url <- paste('https://bkm.com.tr/en/secilen-aya-ait-sektorel-gelisim/?filter_year=',year,'&filter_month=',month,'&List=Lis'
,sep=''
,collapse = NULL)
return(url)
}
year <-c('2017','2018','2019')
month <- c('01','02','03','04','05','06','07','08','09','10','11','12')
raw_df_full <- ''
for (i in 1:length(year)) {
for (j in 1:length(month)) {
if (year[i]=='2019' & month[j]=='07') {
break
}
url<-filterYearMonth(year[i],month[j])
page <- read_html(url)
raw_df <-
page %>%
html_nodes("table") %>%.[(4)] %>%
html_table(page, fill = TRUE,header = FALSE) %>%
as.data.frame() %>%
slice(3:max(nrow(.)))
# Replacing N/A values with 0 and adding year and month columns
raw_df <-
raw_df %>%
mutate_if(is.numeric,funs(ifelse(is.na(.),0,.))) %>%
mutate(year = year[i],month = month[j])
# Appending raw_df into raw_df_full in each iteration
raw_df_full<-rbind(raw_df_full,raw_df)
}
}
# Adding column names
colnames(raw_df_full) <- c('merchant_category','cc_transaction_count','dc_transaction_count','cc_transaction_amount','dc_transaction_amount','year','month')
raw_df_full <- raw_df_full %>% slice(-c(1))df_cc_dc <-
raw_df_full %>%
filter(merchant_category == 'TOTAL') %>%
group_by(year) %>%
summarise(credit_card_cnt = sum(as.numeric((gsub("\\.", "",cc_transaction_count))),na.rm = T),
debit_card_cnt = sum(as.numeric((gsub("\\.", "",dc_transaction_count))),na.rm = T))
df_card_type <- data.frame(year,card_type = c("Credit","Debit")
,cnt=c(df_cc_dc$credit_card_cnt,df_cc_dc$debit_card_cnt))
df_cc_dc## # A tibble: 3 x 3
## year credit_card_cnt debit_card_cnt
## <chr> <dbl> <dbl>
## 1 2017 3367634485 1421081163
## 2 2018 3787647630 1834645929
## 3 2019 2044419739 1055668267
ggplot(df_card_type, aes(x=card_type, y=cnt, fill=card_type))+
geom_bar(stat="identity")+
#geom_text(aes(label=cnt), vjust=1.6, color="black", size=3.5)+
geom_text(aes(label=format(cnt,big.mark = ",")), vjust=1.6, color="black", size=2.8)+
theme_minimal()+
labs(x="Card Type",y="# of Transactions",title="Number of Transactions with Respect to Card Type Through Years")+
theme(axis.text.x = element_text()) +
facet_wrap(~year)
df_category <-
raw_df_full %>%
filter(merchant_category != 'TOTAL') %>% #Filtering out sub-total
group_by(year,merchant_category) %>%
summarise(credit_card_cnt = sum(as.numeric((gsub("\\.", "",cc_transaction_count))),na.rm = T),
debit_card_cnt = sum(as.numeric((gsub("\\.", "",dc_transaction_count))),na.rm = T)) %>%
arrange(year,desc(credit_card_cnt)) %>%
mutate(rwn =row_number()) %>%
filter(rwn<=3)
df_category## # A tibble: 9 x 5
## # Groups: year [3]
## year merchant_category credit_card_cnt debit_card_cnt rwn
## <chr> <chr> <dbl> <dbl> <int>
## 1 2017 MARKETS AND SHOPPING CENTERS 1008859555 470178217 1
## 2 2017 FOOD 377919390 301403819 2
## 3 2017 CLOTHING AND ACCESSORY 331246861 107065272 3
## 4 2018 MARKETS AND SHOPPING CENTERS 1138691242 580057869 1
## 5 2018 FOOD 454714664 368313677 2
## 6 2018 PETROL STATIONS 336479726 118657680 3
## 7 2019 MARKETS AND SHOPPING CENTERS 615280253 342461968 1
## 8 2019 FOOD 254907222 231259184 2
## 9 2019 VARIOUS FOOD 179587854 106714408 3
ggplot(df_category, aes(x=year, y=credit_card_cnt, fill=merchant_category))+
geom_bar(stat="identity")+
theme_minimal()+
labs(y="# of Transactions",title="Top 3 Merchant Category Group with Most Credit Card Transactions",fill="Category")+
theme(axis.text.x = element_text())