Oğuz Çolak BKM Assignment
library(tidyverse)
library(rvest)
library(ggplot2)
library(scales)
library(dplyr)Gathering Data
filtered_date<- function(filtered_year,filtered_month) {
url <- paste('https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=',filtered_year,'&filter_month=',filtered_month,'&List=Listele', sep='', collapse = NULL)
return(url)
}
year_info <-c('2015','2016','2017','2018','2019')
month_info <- c('01','02','03','04','05','06','07','08','09','10','11','12')
gathered_data <- ''
for (i in 1:length(year_info)) {
for (j in 1:length(month_info)) {
if (year_info[i]=='2019' & month_info[j]=='07') {break}
url<-filtered_date(year_info[i],month_info[j])
page <- read_html(url)
df <- page%>%html_nodes("table") %>%.[(4)] %>% html_table(page, fill = TRUE,header = FALSE) %>% as.data.frame()
df <- df %>%mutate_if(is.numeric,funs(ifelse(is.na(.),0,.))) %>% mutate(yearmonth=paste(year_info[i],month_info[j],sep='-'))
gathered_data<-rbind(gathered_data,df)
}
}Preparing Data
This process includes removing first column, updating column names and editing of numeric values.
colnames(gathered_data) <- c("isyeri_grubu", "islem_adet_kredi_kart", "islem_adet_banka_kart",
"islem_tutar_kredi_kart", "islem_tutar_banka_kart", "tarih")
gathered_data <- gathered_data %>% slice(2:max(nrow(.))) %>% filter(isyeri_grubu !='TOPLAM')
gathered_data <- gathered_data %>% filter(isyeri_grubu !='İşyeri Grubu')
head(gathered_data, 5)## isyeri_grubu islem_adet_kredi_kart
## 1 ARABA KİRALAMA 145.150
## 2 ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA 2.630.077
## 3 BENZİN VE YAKIT İSTASYONLARI 19.577.823
## 4 ÇEŞİTLİ GIDA 17.780.721
## 5 DOĞRUDAN PAZARLAMA 537.690
## islem_adet_banka_kart islem_tutar_kredi_kart islem_tutar_banka_kart
## 1 12.932 78,47 2,59
## 2 310.014 1.269,03 47,57
## 3 3.838.459 3.196,04 226,34
## 4 6.219.640 2.435,24 174,03
## 5 46.977 92,95 2,82
## tarih
## 1 2015-01
## 2 2015-01
## 3 2015-01
## 4 2015-01
## 5 2015-01- isyeri_grubu: İşyeri Grubu
- islem_adet_kredi_kart: İşlem Adedi (Kredi Kartı)
- islem_adet_banka_kart: İşlem Adedi (Banka Kartı)
- islem_tutar_kredi_kart: İşlem Tutarı / Milyon TL (Kredi Kartı)
- islem_tutar_banka_kart: İşlem Tutarı / Milyon TL (Banka Kartı)
- tarih: İşlem Tarihi (Yıl-Ay)
gathered_data[,2:5] <- as.data.frame(lapply(gathered_data[,2:5], function(x) as.numeric(gsub(",", ".", gsub("\\.", "", x)))))
head(gathered_data, 5)## isyeri_grubu islem_adet_kredi_kart
## 1 ARABA KİRALAMA 145150
## 2 ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA 2630077
## 3 BENZİN VE YAKIT İSTASYONLARI 19577823
## 4 ÇEŞİTLİ GIDA 17780721
## 5 DOĞRUDAN PAZARLAMA 537690
## islem_adet_banka_kart islem_tutar_kredi_kart islem_tutar_banka_kart
## 1 12932 78.47 2.59
## 2 310014 1269.03 47.57
## 3 3838459 3196.04 226.34
## 4 6219640 2435.24 174.03
## 5 46977 92.95 2.82
## tarih
## 1 2015-01
## 2 2015-01
## 3 2015-01
## 4 2015-01
## 5 2015-01Analysis 1: Amount of Credit Card and Debit Card Transactions by Sector
1.1: Preparing data
islem_adet_toplam<-gathered_data %>% mutate( toplam= (islem_adet_kredi_kart+islem_adet_banka_kart))%>% select(isyeri_grubu,tarih,toplam)%>%filter(toplam!=0)
head(islem_adet_toplam, 5)## isyeri_grubu tarih toplam
## 1 ARABA KİRALAMA 2015-01 158082
## 2 ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA 2015-01 2940091
## 3 BENZİN VE YAKIT İSTASYONLARI 2015-01 23416282
## 4 ÇEŞİTLİ GIDA 2015-01 24000361
## 5 DOĞRUDAN PAZARLAMA 2015-01 584667islem_adet_toplam_2015<-islem_adet_toplam %>% filter(grepl("^2015", tarih))
islem_adet_toplam_2016<-islem_adet_toplam %>% filter(grepl("^2016", tarih))
islem_adet_toplam_2017<-islem_adet_toplam %>% filter(grepl("^2017", tarih))
islem_adet_toplam_2018<-islem_adet_toplam %>% filter(grepl("^2018", tarih))
islem_adet_toplam_2019<-islem_adet_toplam %>% filter(grepl("^2019", tarih))library(plyr)toplam_islem_adet_2015<-ddply(islem_adet_toplam_2015,"isyeri_grubu",numcolwise(sum))
toplam_islem_adet_2016<-ddply(islem_adet_toplam_2016,"isyeri_grubu",numcolwise(sum))
toplam_islem_adet_2017<-ddply(islem_adet_toplam_2017,"isyeri_grubu",numcolwise(sum))
toplam_islem_adet_2018<-ddply(islem_adet_toplam_2018,"isyeri_grubu",numcolwise(sum))
toplam_islem_adet_2019<-ddply(islem_adet_toplam_2019,"isyeri_grubu",numcolwise(sum))yil_bilgisi <- rep("2015",length(toplam_islem_adet_2015))
islem_adet_2015 <- cbind(toplam_islem_adet_2015, yil_bilgisi)
yil_bilgisi <- rep("2016",length(toplam_islem_adet_2016))
islem_adet_2016 <- cbind(toplam_islem_adet_2016, yil_bilgisi)
yil_bilgisi <- rep("2017",length(toplam_islem_adet_2017))
islem_adet_2017 <- cbind(toplam_islem_adet_2017, yil_bilgisi)
yil_bilgisi <- rep("2018",length(toplam_islem_adet_2018))
islem_adet_2018 <- cbind(toplam_islem_adet_2018, yil_bilgisi)
yil_bilgisi <- rep("2019",length(toplam_islem_adet_2019))
islem_adet_2019 <- cbind(toplam_islem_adet_2019, yil_bilgisi)
toplam_islem_adet <- rbind(islem_adet_2015, islem_adet_2016, islem_adet_2017, islem_adet_2018, islem_adet_2019)
toplam_islem_adet$yil_bilgisi <- as.character(toplam_islem_adet$yil_bilgisi)
head(toplam_islem_adet, 5)## isyeri_grubu toplam yil_bilgisi
## 1 ARABA KİRALAMA 2614919 2015
## 2 ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA 37155247 2015
## 3 BENZİN VE YAKIT İSTASYONLARI 328867342 2015
## 4 BIREYSEL EMEKLILIK 17675490 2015
## 5 ÇEŞİTLİ GIDA 314425502 20151.2: Annual Transactions on Sectoral Basis
General View
ggplot(data = toplam_islem_adet, aes(x = yil_bilgisi, y = toplam/1000000, group = 1)) +
geom_line() +
facet_wrap(~ isyeri_grubu) +
labs(subtitle = "Annual Transactions on Sectoral Basis", y="Total Transaction (x1M)", x="Year")
Annual Transactions on Sectoral Basis 2015
library(ggplot2)
library(dplyr)
islem_adet_2015 %>%
tail(25) %>%
ggplot( aes(x=toplam/1000000, y=isyeri_grubu, group = 1)) +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Sectors", x="Total Transaction (x1M)")+
ggtitle("Annual Transactions on Sectoral Basis 2015")
Annual Transactions on Sectoral Basis 2016
library(ggplot2)
library(dplyr)
islem_adet_2016 %>%
tail(25) %>%
ggplot( aes(x=toplam/1000000, y=isyeri_grubu, group = 1)) +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Sectors", x="Total Transaction (x1M)")+
ggtitle("Annual Transactions on Sectoral Basis 2016")
Annual Transactions on Sectoral Basis 2017
library(ggplot2)
library(dplyr)
islem_adet_2017 %>%
tail(25) %>%
ggplot( aes(x=toplam/1000000, y=isyeri_grubu, group = 1)) +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Sectors", x="Total Transaction (x1M)")+
ggtitle("Annual Transactions on Sectoral Basis 2017")
Annual Transactions on Sectoral Basis 2018
library(ggplot2)
library(dplyr)
islem_adet_2018 %>%
tail(25) %>%
ggplot( aes(x=toplam/1000000, y=isyeri_grubu, group = 1)) +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Sectors", x="Total Transaction (x1M)")+
ggtitle("Annual Transactions on Sectoral Basis 2018")
Annual Transactions on Sectoral Basis 2019 (January-June)
library(ggplot2)
library(dplyr)
islem_adet_2019 %>%
tail(25) %>%
ggplot( aes(x=toplam/1000000, y=isyeri_grubu, group = 1)) +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Sectors", x="Total Transaction (x1M)")+
ggtitle("Annual Transactions on Sectoral Basis 2019")
Analysis 2: Total Annual Transactions on Year Basis
2.1: Preparing Data
ia_15<-sum(islem_adet_2015[2])
ia_16<-sum(islem_adet_2016[2])
ia_17<-sum(islem_adet_2017[2])
ia_18<-sum(islem_adet_2018[2])
ia_19<-sum(islem_adet_2019[2])
yil_info=c("2015", "2016", "2017", "2018", "2019")
yillik_toplam=c(ia_15,ia_16, ia_17, ia_18, ia_19)
analysis_2=data.frame(yil_info, yillik_toplam)2.2: Analysis
library(ggplot2)
library(dplyr)
analysis_2 %>%
tail(10) %>%
ggplot( aes(x=yil_info, y=yillik_toplam/1000000, group = 1)) +
geom_line() +
geom_point(shape=21, color="black", fill="blue", size=6) +
labs(y="Total Transaction (x1M)", x="Year")+
ggtitle("Total Annual Transactions")
Analysis 3: Top 5 Sectors of the Last 5 Years
Preparing Data
analysis_3 <- aggregate(toplam_islem_adet$toplam, by=list(isyeri_grubu=toplam_islem_adet$isyeri_grubu), FUN=sum)
colnames(analysis_3) <- c("Sector", "tum_yillar_toplam")
analysis_3 <- analysis_3[order(analysis_3$tum_yillar_toplam, decreasing = TRUE),]
analysis_3_top5 <- analysis_3 %>% slice(1:5)
head(analysis_3_top5, 5)## Sector tum_yillar_toplam
## 1 MARKET VE ALIŞVERİŞ MERKEZLERİ 6683639038
## 2 YEMEK 2957529416
## 3 GİYİM VE AKSESUAR 1936595062
## 4 ÇEŞİTLİ GIDA 1835255084
## 5 BENZİN VE YAKIT İSTASYONLARI 1773317842Top 5 Sectors
library(ggplot2)
ggplot(analysis_3_top5, aes(x="Sector", y=tum_yillar_toplam/1000000, fill=Sector)) +
geom_bar(stat="identity", width=1) +
labs(y="Total Transaction (x1M)", x="Sector")+
coord_polar("y", start=0)