BKM Assignment
1.BKM Dataset
BKM data includes the numerical values for transactions made from credit card and debit card, including the number of transactions and transaction amount.
Loading required libraries for analysis
library(rvest)
library(tidyverse)
library(reshape2)all_data <- lst()
for (month in 1:6) {
html_string <- paste("https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=2019&filter_month=",
month,sep='')
bkm_sektor <- read_html(html_string)
bkm_table <- html_nodes(bkm_sektor, "table")
my_table <- html_table(bkm_table[4],fill = TRUE) %>% as.data.frame() %>% slice(3:max(nrow(.)-1))
my_table <- my_table %>% mutate(MONHT=month)
all_data <- rbind(all_data,my_table)
}
colnames(all_data) <- c("work_group", "cc_sales_volume",
"bc_sales_volume", "cc_trans_cost", "bc_trans_cost","MONTH")
all_data$cc_sales_volume <- as.numeric(str_replace_all(all_data$cc_sales_volume, pattern=fixed("."), ""))
all_data$bc_sales_volume <- as.numeric(str_replace_all(all_data$bc_sales_volume, pattern=fixed("."), ""))
all_data$cc_trans_cost<-str_replace_all(all_data$cc_trans_cost, pattern=fixed("."), "")
all_data$cc_trans_cost<-as.numeric(str_replace_all(all_data$cc_trans_cost, pattern=fixed(","), "."))
all_data$bc_trans_cost<-str_replace_all(all_data$bc_trans_cost, pattern=fixed("."), "")
all_data$bc_trans_cost<-as.numeric(str_replace_all(all_data$bc_trans_cost, pattern=fixed(","), "."))
head(all_data)## work_group cc_sales_volume bc_sales_volume cc_trans_cost bc_trans_cost MONTH
## 1 ARABA KIRALAMA 256372 49296 195.13 14.77 1
## 2 ARAÇ KIRALAMA-SATIS/SERVIS/YEDEK PARÇA 2967019 642136 2185.84 127.16 1
## 3 BENZIN VE YAKIT ISTASYONLARI 25277186 8684036 5066.04 680.01 1
## 4 BIREYSEL EMEKLILIK 2271587 697 716.42 0.30 1
## 5 ÇESITLI GIDA 28362091 15221891 4473.98 673.70 1
## 6 DOGRUDAN PAZARLAMA 757602 40038 678.99 7.81 1Analysis 1 - Calculating Unit Price of Transactions and Monthly Comparision (BIREYSEL EMEKLILIK)
Calculating unit price of transactions by Credit Card and Bank Card. Then using ggplot to monthly comparision.
analysis_1_CC <- all_data %>% filter(work_group == "BIREYSEL EMEKLILIK") %>% mutate(UNITPRICE=cc_trans_cost*1000000/cc_sales_volume, type='Credit Card')
analysis_1_BC <- all_data %>% filter(work_group == "BIREYSEL EMEKLILIK") %>% mutate(UNITPRICE=bc_trans_cost*1000000/bc_sales_volume, type='Bank Card')
analysis_1 <- rbind(analysis_1_CC,analysis_1_BC)
print(analysis_1)## work_group cc_sales_volume bc_sales_volume cc_trans_cost bc_trans_cost MONTH UNITPRICE type
## 1 BIREYSEL EMEKLILIK 2271587 697 716.42 0.30 1 315.3830 Credit Card
## 2 BIREYSEL EMEKLILIK 2075842 1106 656.63 0.41 2 316.3198 Credit Card
## 3 BIREYSEL EMEKLILIK 2280331 1474 753.15 0.61 3 330.2810 Credit Card
## 4 BIREYSEL EMEKLILIK 2142251 1445 700.94 0.55 4 327.1979 Credit Card
## 5 BIREYSEL EMEKLILIK 2202538 1566 736.35 0.62 5 334.3189 Credit Card
## 6 BIREYSEL EMEKLILIK 2060390 1256 686.98 0.42 6 333.4223 Credit Card
## 7 BIREYSEL EMEKLILIK 2271587 697 716.42 0.30 1 430.4161 Bank Card
## 8 BIREYSEL EMEKLILIK 2075842 1106 656.63 0.41 2 370.7052 Bank Card
## 9 BIREYSEL EMEKLILIK 2280331 1474 753.15 0.61 3 413.8399 Bank Card
## 10 BIREYSEL EMEKLILIK 2142251 1445 700.94 0.55 4 380.6228 Bank Card
## 11 BIREYSEL EMEKLILIK 2202538 1566 736.35 0.62 5 395.9132 Bank Card
## 12 BIREYSEL EMEKLILIK 2060390 1256 686.98 0.42 6 334.3949 Bank Cardggplot(analysis_1, aes(x=MONTH, y=UNITPRICE, fill=type))+geom_bar(stat="identity",position="dodge")+labs(x="Month",y="Unit Price of Transaction",title="Unit Price of Transactions and Monthly Comparision(BIREYSEL EMEKLILIK)")
### Analysis 2 - The Distribution of Total Expenditures by Work Groups
analysis_2 <- all_data %>% select(MONTH,work_group,cc_sales_volume,bc_sales_volume) %>% mutate(Sales_sum = cc_sales_volume+bc_sales_volume)
analysis_2 <- analysis_2 %>% group_by(work_group)%>% summarise(Sales_sum=sum(Sales_sum)) %>%mutate(Sales_sum, sales_percentage = Sales_sum / sum(Sales_sum) * 100)%>% arrange(desc(Sales_sum))
Top_Five_Sector<-head(analysis_2,5)
print(Top_Five_Sector)## # A tibble: 5 x 3
## work_group Sales_sum sales_percentage
## <chr> <dbl> <dbl>
## 1 MARKET VE ALISVERIS MERKEZLERI 957742221 30.9
## 2 YEMEK 486166406 15.7
## 3 ÇESITLI GIDA 286302262 9.24
## 4 BENZIN VE YAKIT ISTASYONLARI 228279355 7.36
## 5 GIYIM VE AKSESUAR 226946321 7.32ggplot(Top_Five_Sector, aes(x="", y=sales_percentage, fill=factor(work_group))) + geom_bar(stat="identity", width=1) + coord_polar("y", start=0) +geom_text(aes(label = paste0(round(sales_percentage), "%")), position = position_stack(vjust = 0.5)) + labs(x = NULL, y = NULL, fill = NULL, title = "Sales Percentage Over Top Five Work Group") + theme_classic() + theme(axis.line = element_blank(),
axis.text = element_blank(),
axis.ticks = element_blank(),
plot.title = element_text(hjust = 0.5, color = "#666666"))