Homework2

讀取Purchase 資料

library(dplyr)

## Warning: package 'dplyr' was built under R version 3.2.5

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

download.file('https://github.com/ywchiu/rtibame/raw/master/Data/purchase.csv', 'purchase.csv')

#使用colClasses 轉型
purchase <- read.csv('purchase.csv', header=TRUE, colClasses = c('integer', 'POSIXct', NA, NA, NA, 'integer', 'numeric'))

求出最踴躍購買的時段

#根據小時計算
hour.buy.stat <- purchase %>% select(Time, Quantity) %>% mutate(Hour=format(Time, '%H')) %>% group_by(Hour) %>% summarise(sum(Quantity))

plot(hour.buy.stat, type='l')

#根據日子計算
day.buy.stat <- purchase %>% select(Time, Quantity) %>% mutate(Day=format(Time, '%d')) %>% group_by(Day) %>% summarise(sum(Quantity))

plot(day.buy.stat , type='l')

#求出使用者購買數量頻率
purchase %>% select(Quantity) %>% table()

## .
##     1     2     3     4     5     6     7     8     9    10    11    12 
## 49296  3403  1344   238   171   113    23    36    12   111     3     3 
##    13    15    16    18    20    21    24    25    30 
##     1     2     1     1     8     1     2     1     2

求出購買金額最高的使用者

purchase %>% select(User, Quantity, Price) %>% mutate(Buy = Quantity * Price) %>% select(User, Buy) %>% group_by(User) %>% summarise(sum(Buy)) %>% arrange(desc(`sum(Buy)`)) %>% head(3)

## # A tibble: 3 x 2
##          User sum(Buy)
##        <fctr>    <dbl>
## 1  U166708333  2942744
## 2  U142809250   747550
## 3 U1006283751   515688

# 前10大VIP
top10.user <- purchase %>% select(User, Quantity, Price) %>% mutate(Buy = Quantity * Price) %>% select(User, Buy) %>% group_by(User) %>% summarise(sum(Buy)) %>% arrange(desc(`sum(Buy)`)) %>% head(10)

colnames(top10.user) = c('User', 'Buy')
barplot(height=top10.user$Buy, name=top10.user$User)

尾數定價驗證

table(purchase$Price %% 10)

## 
##     0     1     2     3     4     5     6     7     8     9 
## 17645   702  1515   676  1290  2302  1927   548  3959 24157