[빅데이터][스몰 데이터] 발렌타인 데이 분석 연습_ 진행중

[빅데이터][스몰 데이터] 발렌타인 데이 분석 연습_ 진행중

발렌타인데이? 한국에서만 난리일끼?

그래서?

구글트렌즈 데이터를 활용해서 발렌타인데이가 가지는 의미를

국내와 전세계를 비교해서 기초 검토에서 출발

먼저 

구글 트렌즈 자체만을 활용한 대략적 흐름 파악 결과는 추가적인 분석으로 이어질 수 있으므로

데이터를 다운로드 받아 R을 활용한 추가 분석 실시

## ----------------

##  plotting google trends weekly data

##  keyword == "valentineday" world

require(xlsx)

gt_vd <- read.xlsx("valentineday_K_02.xlsx", 1, stringsAsFactors=FALSE)

gt_vd$dweek <- as.Date(substr(gt_bd$Week, 1, 10))

gt_vd$valentinesday <- as.numeric(gt_vd$valentinesday)

gt_vd$gift  <- as.numeric(gt_vd$gift )

gt_vd$boyf  <- as.numeric(gt_vd$boyf )

gt_vd$girlf    <- as.numeric(gt_vd$girlf )

require(ggplot2) ; require(scales)     # essential 

# -------------

# sample code to save output chart 

# jpeg(filename = "big_Data_201401.jpeg", 

# width = 960, height = 480, units = "px", 

# pointsize = 14,

# quality = 100)

# attach(gt_vd)

# ggplot(gt_vd, aes(dweek, valentinesday)) + geom_line() + # scale_x_date(labels=date_format("%Y-%m" )) + xlab("") + # ylab("google trends index")

# dev.off()

#-----------------------

#-------------------------

# create timeseries chart

# to use only from 2010

gt_vd1 <- gt_vd[ as.numeric(substr(gt_vd$dweek,1,4))>=2010 , ]

attach(gt_vd1)

ggplot(gt_vd1, aes(dweek, valentinesday)) + geom_line() + scale_x_date(labels=date_format("%Y-%m" )) + xlab("") + ylab("google trends index")

#-----------

# yearly overlay comparison

gt_vd1 <- gt_vd[ as.numeric(substr(gt_vd$dweek,1,4))>=2010 , ]

gt_vd1$mon <- ifelse(as.numeric(substr(gt_vd1$dweek,23,24)<=3), 

substr(gt_vd1$dweek, 6, 7), substr(gt_vd1$dweek, 19, 20)) 

gt_vd1$yr <- substr(gt_vd1$dweek, 1,4)

# require(sqldf)

gt_vd2 <- sqldf('select distinct yr, mon,

    avg(valentinesday) as valentinesday ,

    avg(gift) as gift ,

    avg(boyf) as boyf ,

    avg(girlf) as girlf      

    from gt_vd1 group by yr, mon

 ')

require(ggplot2)

# location = south korea

ggplot(data = gt_vd2, aes(x=as.numeric(gt_vd2$mon), y=gt_vd2$valentinesday)) + geom_line(aes(colour=gt_vd2$yr))

#----------

# 

# interpretation: gift fluctuates year by year

ggplot(data = gt_vd2, aes(x=as.numeric(gt_vd2$mon), y=gt_vd2$gift)) + geom_line(aes(colour=gt_vd2$yr)) + labs(title="Valentines Day")

# interpretation: girls dont care BF

ggplot(data = gt_vd2, aes(x=as.numeric(gt_vd2$mon), y=gt_vd2$boyf)) + geom_line(aes(colour=gt_vd2$yr)) + labs(title="BF")

# interpretation: boys DO care GF?

ggplot(data = gt_vd2, aes(x=as.numeric(gt_vd2$mon), y=gt_vd2$girlf)) + geom_line(aes(colour=gt_vd2$yr))  + labs(title="GF")

 yr mon valentinesday  gift  boyf girlf    ymoni

#-----------------------

# analysis using modeling

# use regression to investigate relationships

gt_vd2$i_bfgf <- (gt_vd2$boyf - gt_vd2$girlf) / (gt_vd2$boyf + gt_vd2$girlf)

# we can consider other variables from other resources too

# we can expand analysis  i_bfgf is an example

gt_vd2$ymoni <- as.numeric(as.character(gt_vd2$yr))+ (as.numeric(gt_vd2$mon)/(12*10))

fit_gift <- lm(gt_vd2$gift ~ as.numeric(gt_vd2$yr) + gt_vd2$ymoni  + gt_vd2$boyf + gt_vd2$girlf + gt_vd2$i_bfgf  + gt_vd2$valentinesday, data=gt_vd2)

summary(fit_gift ) # show results

# interpretation :: valentinesday.... is a critical event

# valentines day is just an one time event ... scarce!!

# analysis is not that reliable

# require(randomForest)

rf_gift = randomForest(gt_vd2$gift ~ as.numeric(gt_vd2$yr) + gt_vd2$ymoni  + gt_vd2$boyf + gt_vd2$girlf + gt_vd2$i_bfgf  + gt_vd2$valentinesday , data=gt_vd2, mrty=10 , importance=TRUE, do.trace=10, ntree=10000)

varImpPlot(rf_gift)

# this time, valentineday is the target

fit_vday <- lm(gt_vd2$valentinesday ~ as.numeric(gt_vd2$yr) + gt_vd2$ymoni  + gt_vd2$boyf + gt_vd2$girlf + gt_vd2$i_bfgf  + gt_vd2$gift, data=gt_vd2)

summary(fit_gift ) # show results

rf_vday = randomForest(gt_vd2$valentinesday ~ as.numeric(gt_vd2$yr) + gt_vd2$ymoni  + gt_vd2$boyf + gt_vd2$girlf + gt_vd2$i_bfgf  + gt_vd2$gift , data=gt_vd2, mrty=10 , importance=TRUE, do.trace=10, ntree=10000)

varImpPlot(rf_vday)

# interpretation : valentine's day is something for gift!!

# people google valentinesday is the signal of gift search

#-------- 결과 ----------