Second Assignment - BKM Homework With Rvest

BKM’s Sector Improvement Report include transaction counts and transaction volumes of Credit Cards/Banking Cards in different sector groups. We will analyse the data from 2019-January to 2019 July ## Recommended Libraries

library(rvest)
library(dplyr)
library(ggplot2)
library(knitr)
library(tidyverse)
options(width = 999)

Data Access

for (i in 1:6){
target_url = paste("https://bkm.com.tr/secilen-aya-ait-sektorel-gelisim/?filter_year=2019&filter_month=",
                   i,sep='',collapse = NULL)
content = read_html(target_url)
table = bind_rows
bkm_df = content %>%
      html_nodes("table") %>%.[(4)] %>% 
      html_table(page, fill = TRUE,header = FALSE) %>% 
      as.data.frame() %>%
      slice(3:max(nrow(.) - 1))
bkm_df = bkm_df %>%mutate_if(is.numeric,funs(ifelse(is.na(.),0,.))) %>%  mutate(month=i)
bkm_df_total = rbind(bkm_df)
}

colnames(bkm_df_total) <- c('Category','CC_Transaction_Count','Debit_Transaction_Count','CC_Transaction_Amount'
                            ,'Debit_Transaction_Amount', 'Month')

## Cleaning the data format
bkm_df_total$CC_Transaction_Count <- as.numeric(str_replace_all(bkm_df_total$CC_Transaction_Count, pattern=fixed("."), ""))
bkm_df_total$Debit_Transaction_Count <- as.numeric(str_replace_all(bkm_df_total$Debit_Transaction_Count, pattern=fixed("."), ""))
bkm_df_total$CC_Transaction_Amount <- str_replace_all(bkm_df_total$CC_Transaction_Amount, pattern=fixed("."), "")
bkm_df_total$Debit_Transaction_Amount <- str_replace_all(bkm_df_total$Debit_Transaction_Amount, pattern=fixed("."), "")

bkm_df_total$CC_Transaction_Amount <- as.numeric(str_replace_all(bkm_df_total$CC_Transaction_Amount, pattern=fixed(","), "."))
bkm_df_total$Debit_Transaction_Amount <- as.numeric(str_replace_all(bkm_df_total$Debit_Transaction_Amount, pattern=fixed(","), "."))

## Let's see our data
kable(head(bkm_df_total), format="html", align = ("crrrrr"))

Category	CC_Transaction_Count	Debit_Transaction_Count	CC_Transaction_Amount	Debit_Transaction_Amount	Month
ARABA KİRALAMA	306426	77113	256.63	43.79	6
ARAÇ KİRALAMA-SATIŞ/SERVİS/YEDEK PARÇA	3335321	902483	2588.91	190.61	6
BENZİN VE YAKIT İSTASYONLARI	32572382	13813215	6515.69	1195.27	6
BIREYSEL EMEKLILIK	2060390	1256	686.98	0.42	6
ÇEŞİTLİ GIDA	31076151	20446524	5147.68	994.90	6
DOĞRUDAN PAZARLAMA	738068	45268	723.68	21.26	6

Analysis

1. Unit Transaction Amount of Categories

## replication
unit_transactions <- bkm_df_total
## unit transaction amounts of cc and debit seperately
unit_transactions <- unit_transactions %>% mutate(unit_credit_amount = 1000000 * CC_Transaction_Amount / CC_Transaction_Count, unit_debit_amount = 1000000* Debit_Transaction_Amount / Debit_Transaction_Count)
## unit transaction percentages
unit_transactions <- unit_transactions %>% transmute(Category, Month, cc_percentage = 100 * unit_credit_amount / sum(unit_credit_amount), debit_percentage = 100 * unit_debit_amount / sum(unit_debit_amount))
## group by category to sum up all month data
unit_transactions <- unit_transactions %>% group_by(Category) %>% mutate(debit_percentage = sum(debit_percentage), cc_percentage = sum(cc_percentage))
ggplot(unit_transactions, aes(x=reorder(Category,cc_percentage+debit_percentage), y=cc_percentage+debit_percentage)) + geom_bar(aes(fill = cc_percentage+debit_percentage), stat = "identity",position ="stack") + coord_flip() + geom_point() + labs(x="Category",y="Unit Transaction Percentage ",title="Unit Transaction Percentage of Categories ",fill="Percentage")

2. Top 5 Categories of Transaction Counts

## replication
top_5 <- bkm_df_total 
top_5 <- top_5 %>% group_by(Category) %>% mutate(all_transactions = sum(CC_Transaction_Count) + sum(Debit_Transaction_Count)) %>% arrange(desc(all_transactions))
top_5 <- top_5[1:5,]
ggplot(top_5, aes(x="", y=all_transactions/1000000, fill=Category)) + geom_bar(stat="identity", width=1) + coord_polar("y", start=0) +  labs(x = NULL, y = NULL, fill = NULL, title = "Transaction Count Chart of Top 5 Categories")