data = read.table("D:/Fall 2021/DA Application/project/marketing_campaign.csv", sep = "\t", header = TRUE)
df = data.frame(data)
head(df)
## ID Year_Birth Education Marital_Status Income Kidhome Teenhome Dt_Customer
## 1 5524 1957 Graduation Single 58138 0 0 04-09-2012
## 2 2174 1954 Graduation Single 46344 1 1 08-03-2014
## 3 4141 1965 Graduation Together 71613 0 0 21-08-2013
## 4 6182 1984 Graduation Together 26646 1 0 10-02-2014
## 5 5324 1981 PhD Married 58293 1 0 19-01-2014
## 6 7446 1967 Master Together 62513 0 1 09-09-2013
## Recency MntWines MntFruits MntMeatProducts MntFishProducts MntSweetProducts
## 1 58 635 88 546 172 88
## 2 38 11 1 6 2 1
## 3 26 426 49 127 111 21
## 4 26 11 4 20 10 3
## 5 94 173 43 118 46 27
## 6 16 520 42 98 0 42
## MntGoldProds NumDealsPurchases NumWebPurchases NumCatalogPurchases
## 1 88 3 8 10
## 2 6 2 1 1
## 3 42 1 8 2
## 4 5 2 2 0
## 5 15 5 5 3
## 6 14 2 6 4
## NumStorePurchases NumWebVisitsMonth AcceptedCmp3 AcceptedCmp4 AcceptedCmp5
## 1 4 7 0 0 0
## 2 2 5 0 0 0
## 3 10 4 0 0 0
## 4 4 6 0 0 0
## 5 6 5 0 0 0
## 6 10 6 0 0 0
## AcceptedCmp1 AcceptedCmp2 Complain Z_CostContact Z_Revenue Response
## 1 0 0 0 3 11 1
## 2 0 0 0 3 11 0
## 3 0 0 0 3 11 0
## 4 0 0 0 3 11 0
## 5 0 0 0 3 11 0
## 6 0 0 0 3 11 0
sum(is.na(df))
## [1] 24
df = na.omit(df)
str(df)
## 'data.frame': 2216 obs. of 29 variables:
## $ ID : int 5524 2174 4141 6182 5324 7446 965 6177 4855 5899 ...
## $ Year_Birth : int 1957 1954 1965 1984 1981 1967 1971 1985 1974 1950 ...
## $ Education : chr "Graduation" "Graduation" "Graduation" "Graduation" ...
## $ Marital_Status : chr "Single" "Single" "Together" "Together" ...
## $ Income : int 58138 46344 71613 26646 58293 62513 55635 33454 30351 5648 ...
## $ Kidhome : int 0 1 0 1 1 0 0 1 1 1 ...
## $ Teenhome : int 0 1 0 0 0 1 1 0 0 1 ...
## $ Dt_Customer : chr "04-09-2012" "08-03-2014" "21-08-2013" "10-02-2014" ...
## $ Recency : int 58 38 26 26 94 16 34 32 19 68 ...
## $ MntWines : int 635 11 426 11 173 520 235 76 14 28 ...
## $ MntFruits : int 88 1 49 4 43 42 65 10 0 0 ...
## $ MntMeatProducts : int 546 6 127 20 118 98 164 56 24 6 ...
## $ MntFishProducts : int 172 2 111 10 46 0 50 3 3 1 ...
## $ MntSweetProducts : int 88 1 21 3 27 42 49 1 3 1 ...
## $ MntGoldProds : int 88 6 42 5 15 14 27 23 2 13 ...
## $ NumDealsPurchases : int 3 2 1 2 5 2 4 2 1 1 ...
## $ NumWebPurchases : int 8 1 8 2 5 6 7 4 3 1 ...
## $ NumCatalogPurchases: int 10 1 2 0 3 4 3 0 0 0 ...
## $ NumStorePurchases : int 4 2 10 4 6 10 7 4 2 0 ...
## $ NumWebVisitsMonth : int 7 5 4 6 5 6 6 8 9 20 ...
## $ AcceptedCmp3 : int 0 0 0 0 0 0 0 0 0 1 ...
## $ AcceptedCmp4 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AcceptedCmp5 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AcceptedCmp1 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ AcceptedCmp2 : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Complain : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Z_CostContact : int 3 3 3 3 3 3 3 3 3 3 ...
## $ Z_Revenue : int 11 11 11 11 11 11 11 11 11 11 ...
## $ Response : int 1 0 0 0 0 0 0 0 1 0 ...
## - attr(*, "na.action")= 'omit' Named int [1:24] 11 28 44 49 59 72 91 92 93 129 ...
## ..- attr(*, "names")= chr [1:24] "11" "28" "44" "49" ...
df$Age = 2021 - df$Year_Birth
df$Education[df$Education == "2n Cycle"] = "UG"
df$Education[df$Education == "Basic"] = "UG"
df$Education[df$Education == "Graduation"] = "PG"
df$Education[df$Education == "Master"] = "PG"
df$Education[df$Education == "PhD"] = "PG"
df$Marital_Status[df$Marital_Status == "Divorced"] = "Single"
df$Marital_Status[df$Marital_Status == "Absurd"] = "Single"
df$Marital_Status[df$Marital_Status == "YOLO"] = "Single"
df$Marital_Status[df$Marital_Status == "Widow"] = "Single"
df$Marital_Status[df$Marital_Status == "Together"] = "Couple"
df$Marital_Status[df$Marital_Status == "Married"] = "Couple"
df$Marital_Status[df$Marital_Status == "Alone"] = "Single"
df$Customer_year <- str_sub(df$Dt_Customer, -4)
df$Customer_year <- as.numeric(df$Customer_year)
df$Customer_Seniority <- 2021 - df$Customer_year
df$Child <- df$Kidhome + df$Teenhome
df$Amt_Spent <- df$MntWines + df$MntFishProducts + df$MntFruits + df$MntGoldProds + df$MntMeatProducts + df$MntSweetProducts
df$Num_Purchases_made <- df$NumWebPurchases +df$NumCatalogPurchases + df$NumStorePurchases
df <- df[c(30, 3, 4, 5, 33, 32, 9, 34, 35, 16, 20)]
corrgram(df, order=TRUE, lower.panel=panel.ellipse, upper.panel=panel.pts, text.panel=panel.txt, diag.panel=panel.minmax, main="Correlaton between various variables ")
data2 <- df
data2$Education <- unclass(as.factor(data2$Education))
data2$Marital_Status <- unclass(as.factor(data2$Marital_Status))
data2$Education <- as.numeric(data2$Education)
data2$Marital_Status <- as.numeric(data2$Marital_Status)
corrgram(data2[-c(1)], order = TRUE, lower.panel = panel.shade,
upper.panel = NULL, text.panel = panel.txt, main = "Customer Data")
plot(df)
age_plot <- ggplot(data = df, aes(Age))
age_plot + geom_density()
edu_plot1 <- ggplot(data = df, aes(Education))
edu_plot1 + geom_histogram(stat = "count")
## Warning: Ignoring unknown parameters: binwidth, bins, pad
eduplot = ggplot(df, aes(x=Education,y=Income,fill=Education))+ylim(0,180000)+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2, notch=T)
eduplot
## Warning: Removed 1 rows containing non-finite values (stat_boxplot).
edu_plot2 <- ggplot(data = df, aes(Income, fill = Education))
edu_plot2 + geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
df = subset(df,df$Income<666665)
library(caret)
dmy <- dummyVars(" ~ .", data = df, fullRank = T)
dat_transformed <- data.frame(predict(dmy, newdata = df))
glimpse(dat_transformed)
## Rows: 2,215
## Columns: 11
## $ Age <dbl> 64, 67, 56, 37, 40, 54, 50, 36, 47, 71, 45, 62, 6~
## $ EducationUG <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0~
## $ Marital_StatusSingle <dbl> 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0~
## $ Income <dbl> 58138, 46344, 71613, 26646, 58293, 62513, 55635, ~
## $ Child <dbl> 0, 2, 0, 1, 1, 1, 1, 1, 1, 2, 0, 0, 2, 0, 0, 2, 0~
## $ Customer_Seniority <dbl> 9, 7, 8, 7, 7, 8, 9, 8, 8, 7, 9, 8, 8, 9, 9, 9, 9~
## $ Recency <dbl> 58, 38, 26, 26, 94, 16, 34, 32, 19, 68, 59, 82, 5~
## $ Amt_Spent <dbl> 1617, 27, 776, 53, 422, 716, 590, 169, 46, 49, 61~
## $ Num_Purchases_made <dbl> 22, 4, 20, 6, 14, 20, 17, 8, 5, 1, 5, 15, 12, 4, ~
## $ NumDealsPurchases <dbl> 3, 2, 1, 2, 5, 2, 4, 2, 1, 1, 1, 1, 3, 1, 1, 3, 2~
## $ NumWebVisitsMonth <dbl> 7, 5, 4, 6, 5, 6, 6, 8, 9, 20, 8, 2, 6, 8, 3, 8, ~
dfc = dat_transformed[-c(4)]
str(dfc)
## 'data.frame': 2215 obs. of 10 variables:
## $ Age : num 64 67 56 37 40 54 50 36 47 71 ...
## $ EducationUG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ Marital_StatusSingle: num 1 1 0 0 0 0 1 0 0 0 ...
## $ Child : num 0 2 0 1 1 1 1 1 1 2 ...
## $ Customer_Seniority : num 9 7 8 7 7 8 9 8 8 7 ...
## $ Recency : num 58 38 26 26 94 16 34 32 19 68 ...
## $ Amt_Spent : num 1617 27 776 53 422 ...
## $ Num_Purchases_made : num 22 4 20 6 14 20 17 8 5 1 ...
## $ NumDealsPurchases : num 3 2 1 2 5 2 4 2 1 1 ...
## $ NumWebVisitsMonth : num 7 5 4 6 5 6 6 8 9 20 ...
library(factoextra)
## Warning: package 'factoextra' was built under R version 4.1.2
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
fviz_nbclust(dfc,kmeans,method="wss")+geom_vline(xintercept=3,linetype=2)
set.seed(123)
km.res<- kmeans(dfc,3,nstart=10)
print(km.res$centers)
## Age EducationUG Marital_StatusSingle Child Customer_Seniority
## 1 50.77689 0.13944223 0.3474104 1.2302789 7.909163
## 2 54.68220 0.09983361 0.3594010 0.7504160 8.004992
## 3 52.91643 0.05292479 0.3732591 0.2869081 8.133705
## Recency Amt_Spent Num_Purchases_made NumDealsPurchases NumWebVisitsMonth
## 1 48.64940 152.7586 7.258167 2.339442 6.314741
## 2 48.80865 921.4676 19.131448 2.728785 4.379368
## 3 50.69638 1670.4819 20.091922 1.584958 3.409471
print(km.res$size)
## [1] 1255 601 359
print(km.res$betweenss/km.res$totss)
## [1] 0.8976134
print(km.res$totss)
## [1] 807143674
print(km.res$betweenss)
## [1] 724503006
print(km.res$withinss)
## [1] 28087287 27493826 27059556
fviz_cluster(km.res, dfc, geom = "point",ellipse.type = "norm",repel = TRUE)
plot_ly(x = dfc$Income ,
y = dfc$Amt_Spent,
z = dfc$Num_Purchases_made,
type = "scatter3d",
mode = "markers",
color = as.factor(km.res$cluster))
dfc['cluster']=as.factor(km.res$cluster)
spentplot = ggplot(dfc, aes(x=cluster,y=Amt_Spent,fill=cluster))+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2, notch=T)
spentplot
spentplot = ggplot(dfc, aes(x=cluster,y=Age,fill=cluster))+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2, notch=T)
spentplot
numdealplot = ggplot(dfc, aes(x=cluster,y=NumDealsPurchases,fill=cluster))+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2)
numdealplot
dfc$Income = df$Income
incomeplot = ggplot(dfc, aes(x=cluster,y=Income,fill=cluster))+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2, notch=T)
incomeplot
numdealplot = ggplot(dfc, aes(x=cluster,y=Customer_Seniority,fill=cluster))+geom_boxplot(outlier.colour="black", outlier.shape=16,outlier.size=2)
numdealplot
