PROJECT_2

WINE

setwd('C:/Users/Administrator/Desktop/R Analysis/Fast Campus')

read.csv('wine.csv') -> df

#-----------------------------------
#   NA 값 확인 
#----------------------------------
colSums(is.na(df))

##                Class              Alcohol                 Acid 
##                    0                    0                    0 
##                  Ash           Alcalinity            Magnesium 
##                    0                    0                    0 
##        Total_phenols           Flavanoids Nonflavanoid_phenols 
##                    0                    0                    0 
##      Proanthocyanins      color_intensity                  Hue 
##                    0                    0                    0 
##               X0D280              proline 
##                    0                    0

#-----------------------------------
#   기초 통계량 확인  
#----------------------------------

summary(df[,-1])

##     Alcohol           Acid           Ash          Alcalinity   
##  Min.   :11.03   Min.   :0.74   Min.   :1.360   Min.   :10.60  
##  1st Qu.:12.36   1st Qu.:1.60   1st Qu.:2.210   1st Qu.:17.20  
##  Median :13.05   Median :1.87   Median :2.360   Median :19.50  
##  Mean   :12.99   Mean   :2.34   Mean   :2.366   Mean   :19.52  
##  3rd Qu.:13.67   3rd Qu.:3.10   3rd Qu.:2.560   3rd Qu.:21.50  
##  Max.   :14.83   Max.   :5.80   Max.   :3.230   Max.   :30.00  
##    Magnesium      Total_phenols     Flavanoids    Nonflavanoid_phenols
##  Min.   : 70.00   Min.   :0.980   Min.   :0.340   Min.   :0.1300      
##  1st Qu.: 88.00   1st Qu.:1.740   1st Qu.:1.200   1st Qu.:0.2700      
##  Median : 98.00   Median :2.350   Median :2.130   Median :0.3400      
##  Mean   : 99.59   Mean   :2.292   Mean   :2.023   Mean   :0.3623      
##  3rd Qu.:107.00   3rd Qu.:2.800   3rd Qu.:2.860   3rd Qu.:0.4400      
##  Max.   :162.00   Max.   :3.880   Max.   :5.080   Max.   :0.6600      
##  Proanthocyanins color_intensity       Hue            X0D280     
##  Min.   :0.410   Min.   : 1.280   Min.   :0.480   Min.   :1.270  
##  1st Qu.:1.250   1st Qu.: 3.210   1st Qu.:0.780   1st Qu.:1.930  
##  Median :1.550   Median : 4.680   Median :0.960   Median :2.780  
##  Mean   :1.587   Mean   : 5.055   Mean   :0.957   Mean   :2.604  
##  3rd Qu.:1.950   3rd Qu.: 6.200   3rd Qu.:1.120   3rd Qu.:3.170  
##  Max.   :3.580   Max.   :13.000   Max.   :1.710   Max.   :4.000  
##     proline      
##  Min.   : 278.0  
##  1st Qu.: 500.0  
##  Median : 672.0  
##  Mean   : 745.1  
##  3rd Qu.: 985.0  
##  Max.   :1680.0

#---------------------------------------------------------------
#  BOX PLOT - Class 변수를 뺀 나머지는 모두 연속형 : 분포도 확인 
#---------------------------------------------------------------

boxplot(df[,-1])

Data Preparation

df.train <- df[,-1] #class 제외 


#---------------------------------------------------------------
#  표준화 Scaling  
#---------------------------------------------------------------

scale(df.train) -> df.train.scale

1. 반복구매를 할 때, 유사한 종류의 와인을 구매할 것이다.

2. 가끔 새로운 와인을 구매할 것 이다.

-> 유사도 거리 -> 군집분석을 통한 유사종류/다른 종류 와인 분류 -> 와인을 각 상품칸에 적절하게 배치 하기 -> 반응을 확인하기

Euclidian Distance K means K medoids Hierarchical Clustering

Euclidian Distance

유사도 행렬을 구해서, 같은/다른 와인으로 분류해주기

차순 정렬로 가까운 거리의 와인들을 살펴본다

dist(df.train.scale, method = 'euclidean') %>% 
  as.matrix() -> df.dist

K-MEANS

#---------------------------------------------------------------
#  군집 개수 설정해주기 
#---------------------------------------------------------------


set.seed(1234)


fviz_nbclust(df.train.scale, 
             kmeans, 
             method = 'wss', 
             k.max=15)+theme_classic()

fviz_nbclust(df.train.scale, 
             kmeans, 
             method = 'silhouette', 
             k.max=15)+theme_classic()

K-mean Modelling

kmeans(df.train.scale, 
       centers = 3, 
       iter.max = 1000) -> df.kmeans

plot(df.kmeans, df.train.scale)

#---------------------------------------------------------------
#  Centers Clustering - Bar Graph
#---------------------------------------------------------------


df.kmeans$centers #각 군집별 평균값 확인 

##      Alcohol       Acid        Ash Alcalinity   Magnesium Total_phenols
## 1  0.8333649 -0.3013131  0.3661731 -0.6065538  0.56922228    0.88768039
## 2  0.1736447  0.8642504  0.1871775  0.5168437 -0.06497127   -0.97106500
## 3 -0.9183253 -0.3953334 -0.4905017  0.1637039 -0.48321576   -0.07114136
##    Flavanoids Nonflavanoid_phenols Proanthocyanins color_intensity        Hue
## 1  0.98016451          -0.56173008      0.57583669       0.1702296  0.4753467
## 2 -1.20624204           0.71915195     -0.77171004       0.9378162 -1.1566204
## 3  0.02658937          -0.03709561      0.06509498      -0.8955790  0.4614076
##       X0D280    proline
## 1  0.7753334  1.1296451
## 2 -1.2872265 -0.4002655
## 3  0.2823571 -0.7460740

barplot(t(df.kmeans$centers), beside = T, col=2:14)
legend("topleft", colnames(df.train.scale), fill = 2:14, 
       cex = 0.3, bty= 'n')

df$kmean_cluster <- df.kmeans$cluster

head(df,3)

##   Class Alcohol Acid  Ash Alcalinity Magnesium Total_phenols Flavanoids
## 1     1   13.20 1.78 2.14       11.2       100          2.65       2.76
## 2     1   13.16 2.36 2.67       18.6       101          2.80       3.24
## 3     1   14.37 1.95 2.50       16.8       113          3.85       3.49
##   Nonflavanoid_phenols Proanthocyanins color_intensity  Hue X0D280 proline
## 1                 0.26            1.28            4.38 1.05   3.40    1050
## 2                 0.30            2.81            5.68 1.03   3.17    1185
## 3                 0.24            2.18            7.80 0.86   3.45    1480
##   kmean_cluster
## 1             1
## 2             1
## 3             1

K-Medoid

Cluster package- pam

set.seed(1234)

fviz_nbclust(df.train.scale, 
             pam, 
             method = 'wss', 
             k.max = 15)+
  ggtitle("Elbow Method")

fviz_nbclust(df.train.scale, 
             pam, 
             method = 'silhouette',
             k.max = 15)

pam(df.train.scale, k=3) ->df.kmedoids

plot(df.kmedoids)

barplot(t(df.kmedoids$medoids), beside = T, col = 2:14)
legend("bottomleft", colnames(df.train.scale), fill=2:14, cex=0.3)

df.kmedoids$clustering -> df$kmedois_cluster


head(df,3)

##   Class Alcohol Acid  Ash Alcalinity Magnesium Total_phenols Flavanoids
## 1     1   13.20 1.78 2.14       11.2       100          2.65       2.76
## 2     1   13.16 2.36 2.67       18.6       101          2.80       3.24
## 3     1   14.37 1.95 2.50       16.8       113          3.85       3.49
##   Nonflavanoid_phenols Proanthocyanins color_intensity  Hue X0D280 proline
## 1                 0.26            1.28            4.38 1.05   3.40    1050
## 2                 0.30            2.81            5.68 1.03   3.17    1185
## 3                 0.24            2.18            7.80 0.86   3.45    1480
##   kmean_cluster kmedois_cluster
## 1             1               1
## 2             1               1
## 3             1               1

Hierarchical Clustering

fviz_nbclust(df.train.scale, 
             hcut, 
             method = 'wss',
             k.max=15)

fviz_nbclust(df.train.scale,
             hcut, 
             method = 'silhouette', 
             k.max = 15)

hclust(dist(df.train.scale), method = 'single')-> df.hclust.single 

hclust(dist(df.train.scale), method = 'complete')-> df.hclust.cplt


hclust(dist(df.train.scale), method = 'average')-> df.hclust.avg


hclust(dist(df.train.scale), method = 'ward.D')-> df.hclust.ward

par(mfrow=(c(2,2)))

plot(df.hclust.single, hang=-1, cex=0.4)
rect.hclust(df.hclust.single, k=3, border='skyblue')


plot(df.hclust.cplt, hang = -1, cex=0.4)
rect.hclust(df.hclust.cplt, k=3, border='skyblue')


plot(df.hclust.avg, hang=-1, cex=0.4)
rect.hclust(df.hclust.avg, k=3, border='skyblue')


plot(df.hclust.ward, hang = -1, cex=0.4)
rect.hclust(df.hclust.ward, k=3, border='skyblue')

군집 할당하기 (Ward)

#--------------------------------------------------------------------
#   군집화 및 군집 할당 
#-------------------------------------------------------------------


cutree(df.hclust.ward, k=3) -> hclust_cluster

df$cluster_cluster <- hclust_cluster


head(df,3)

##   Class Alcohol Acid  Ash Alcalinity Magnesium Total_phenols Flavanoids
## 1     1   13.20 1.78 2.14       11.2       100          2.65       2.76
## 2     1   13.16 2.36 2.67       18.6       101          2.80       3.24
## 3     1   14.37 1.95 2.50       16.8       113          3.85       3.49
##   Nonflavanoid_phenols Proanthocyanins color_intensity  Hue X0D280 proline
## 1                 0.26            1.28            4.38 1.05   3.40    1050
## 2                 0.30            2.81            5.68 1.03   3.17    1185
## 3                 0.24            2.18            7.80 0.86   3.45    1480
##   kmean_cluster kmedois_cluster cluster_cluster
## 1             1               1               1
## 2             1               1               1
## 3             1               1               1

```