Market Basket Analysis - 購物籃分析 (關聯分析) II
gcchen
2023-02-16
關聯規則的視覺化
透過圖形的方式，可藉由視覺化方式，更直觀地顯示出關聯分析的結果。 這需要用到 R 的擴充套件 arulesViz。
此處介紹一些此套件相關的簡單應用。
首先安裝與載入 arulesViz 套件
# install.packages("arulesViz", repos="http://cran.us.r-project.org")
library (arulesViz) ## Warning: 套件 'arulesViz' 是用 R 版本 4.1.3 來建造的## 載入需要的套件：arules## Warning: 套件 'arules' 是用 R 版本 4.1.3 來建造的## 載入需要的套件：Matrix## Warning: 套件 'Matrix' 是用 R 版本 4.1.3 來建造的##
## 載入套件：'arules'## 下列物件被遮斷自 'package:base':
##
## abbreviate, writelibrary (arules) # 因為需要用到 Groceries 資料集
data("Groceries") 接下來將支持度設置為 0.002，信賴度設置為 0.5，並將所得之關聯規則命名為 rules06。
rules06 = apriori (Groceries, parameter = list ( support=0.002, confidence=0.5 ) ) ## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.5 0.1 1 none FALSE TRUE 5 0.002 1
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 19
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.01s].
## sorting and recoding items ... [147 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 done [0.01s].
## writing ... [1098 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].rules06 # 顯示 rules06 產生的關聯規則項數 ## set of 1098 rules接下來對 rules06 繪製散佈圖：
plot(rules06)## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
圖中的每個點描述了相對應規則的支持度 (橫軸) 與信賴度 (縱軸)，而顏色的深淺則由 lift (提升度) 值的高低來決定。可以透過參數設定，變更橫縱軸與顏色所對應的變量，例如：
plot(rules06, measure=c("support", "lift"), shading ="confidence")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
由於觀察圖形，無法確認感興趣的規則對應到的是哪些商品，這個問題可以透過設置互動參數來克服 (可互動部分無法以網頁呈現，另行以程式與操作說明)
# plot(rules06, interactive=TRUE)此外，我們還可以將 shading 參數設置為 “order” 來繪製出一種特殊的散佈圖- “two-key plot”，而關聯規則的顏色深淺代表其中所含有的商品的多少，商品的種類 (order) 越多，點的顏色越深。
plot(rules06, shading="order", control=list(main = "Two-key plot"))## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
接下來我們將圖形類型變更為 “grouped” 來產生 “grouped matrix” 圖形，以 lift 參數來看，關聯性最強 (圓點顏色最深) 的兩組產品是 硬質乳酪 (hard cheese) 及 黃油 (butter) 等產品與 生/酸奶油 (whipped/sour cream)，而以 support 參數來看，則是特色起司 (specialty cheese) 及 奶油起司 (cream cheese) 等產品 與 全脂牛奶 (whole milk) 關聯性最強 (圓點尺寸最大)。
plot(rules06, method= "grouped")
至於 method 參數，還可以修改為 “matrix”。“matrix3D”、“paracoord” 等：
plot(rules06[1:50], method="matrix", measure="lift")## Itemsets in Antecedent (LHS)
## [1] "{other vegetables,rice}"
## [2] "{whole milk,rice}"
## [3] "{herbs,whole milk}"
## [4] "{citrus fruit,herbs}"
## [5] "{herbs,yogurt}"
## [6] "{whole milk,specialty cheese}"
## [7] "{root vegetables,rice}"
## [8] "{herbs,whipped/sour cream}"
## [9] "{herbs,other vegetables}"
## [10] "{tropical fruit,herbs}"
## [11] "{herbs,rolls/buns}"
## [12] "{turkey,whole milk}"
## [13] "{root vegetables,processed cheese}"
## [14] "{whole milk,frozen fish}"
## [15] "{yogurt,specialty cheese}"
## [16] "{whole milk,canned vegetables}"
## [17] "{yogurt,frozen fish}"
## [18] "{whole milk,frozen dessert}"
## [19] "{root vegetables,herbs}"
## [20] "{specialty cheese}"
## [21] "{whole milk,roll products }"
## [22] "{whole milk,dishes}"
## [23] "{rice}"
## [24] "{cereals}"
## [25] "{root vegetables,pasta}"
## [26] "{tropical fruit,semi-finished bread}"
## [27] "{other vegetables,frozen fish}"
## [28] "{other vegetables,pot plants}"
## [29] "{other vegetables,frozen dessert}"
## [30] "{semi-finished bread,soda}"
## [31] "{jam}"
## [32] "{other vegetables,cake bar}"
## [33] "{turkey,other vegetables}"
## [34] "{yogurt,pot plants}"
## [35] "{other vegetables,specialty cheese}"
## [36] "{baking powder}"
## [37] "{processed cheese,white bread}"
## [38] "{other vegetables,pasta}"
## Itemsets in Consequent (RHS)
## [1] "{whole milk}" "{other vegetables}" "{yogurt}"
## [4] "{root vegetables}"
inspect(rules06[1:50])## lhs rhs support confidence coverage lift count
## [1] {cereals} => {whole milk} 0.003660397 0.6428571 0.005693950 2.515917 36
## [2] {jam} => {whole milk} 0.002948653 0.5471698 0.005388917 2.141431 29
## [3] {specialty cheese} => {other vegetables} 0.004270463 0.5000000 0.008540925 2.584078 42
## [4] {rice} => {other vegetables} 0.003965430 0.5200000 0.007625826 2.687441 39
## [5] {rice} => {whole milk} 0.004677173 0.6133333 0.007625826 2.400371 46
## [6] {baking powder} => {whole milk} 0.009252669 0.5229885 0.017691917 2.046793 91
## [7] {yogurt,
## specialty cheese} => {whole milk} 0.002033554 0.7142857 0.002846975 2.795464 20
## [8] {whole milk,
## specialty cheese} => {yogurt} 0.002033554 0.5405405 0.003762074 3.874793 20
## [9] {other vegetables,
## specialty cheese} => {whole milk} 0.002236909 0.5238095 0.004270463 2.050007 22
## [10] {whole milk,
## specialty cheese} => {other vegetables} 0.002236909 0.5945946 0.003762074 3.072957 22
## [11] {turkey,
## other vegetables} => {whole milk} 0.002135231 0.5384615 0.003965430 2.107349 21
## [12] {turkey,
## whole milk} => {other vegetables} 0.002135231 0.5833333 0.003660397 3.014757 21
## [13] {root vegetables,
## rice} => {other vegetables} 0.002236909 0.7096774 0.003152008 3.667723 22
## [14] {other vegetables,
## rice} => {root vegetables} 0.002236909 0.5641026 0.003965430 5.175325 22
## [15] {root vegetables,
## rice} => {whole milk} 0.002440264 0.7741935 0.003152008 3.029922 24
## [16] {whole milk,
## rice} => {root vegetables} 0.002440264 0.5217391 0.004677173 4.786665 24
## [17] {other vegetables,
## rice} => {whole milk} 0.002643620 0.6666667 0.003965430 2.609099 26
## [18] {whole milk,
## rice} => {other vegetables} 0.002643620 0.5652174 0.004677173 2.921131 26
## [19] {other vegetables,
## frozen dessert} => {whole milk} 0.002033554 0.5555556 0.003660397 2.174249 20
## [20] {whole milk,
## frozen dessert} => {other vegetables} 0.002033554 0.5128205 0.003965430 2.650336 20
## [21] {whole milk,
## canned vegetables} => {other vegetables} 0.002033554 0.5263158 0.003863752 2.720082 20
## [22] {whole milk,
## roll products } => {other vegetables} 0.002338587 0.5000000 0.004677173 2.584078 23
## [23] {yogurt,
## frozen fish} => {whole milk} 0.002236909 0.6875000 0.003253686 2.690634 22
## [24] {other vegetables,
## frozen fish} => {whole milk} 0.002745297 0.5869565 0.004677173 2.297142 27
## [25] {whole milk,
## frozen fish} => {other vegetables} 0.002745297 0.5510204 0.004982206 2.847759 27
## [26] {other vegetables,
## cake bar} => {whole milk} 0.002033554 0.5405405 0.003762074 2.115486 20
## [27] {whole milk,
## dishes} => {other vegetables} 0.002643620 0.5000000 0.005287239 2.584078 26
## [28] {yogurt,
## pot plants} => {whole milk} 0.002033554 0.5263158 0.003863752 2.059815 20
## [29] {other vegetables,
## pot plants} => {whole milk} 0.002440264 0.5581395 0.004372140 2.184362 24
## [30] {root vegetables,
## pasta} => {whole milk} 0.002338587 0.6052632 0.003863752 2.368788 23
## [31] {other vegetables,
## pasta} => {whole milk} 0.002135231 0.5000000 0.004270463 1.956825 21
## [32] {herbs,
## whipped/sour cream} => {other vegetables} 0.002033554 0.6451613 0.003152008 3.334294 20
## [33] {citrus fruit,
## herbs} => {other vegetables} 0.002135231 0.7241379 0.002948653 3.742457 21
## [34] {tropical fruit,
## herbs} => {whole milk} 0.002338587 0.8214286 0.002846975 3.214783 23
## [35] {herbs,
## yogurt} => {root vegetables} 0.002033554 0.5714286 0.003558719 5.242537 20
## [36] {root vegetables,
## herbs} => {other vegetables} 0.003863752 0.5507246 0.007015760 2.846231 38
## [37] {herbs,
## other vegetables} => {root vegetables} 0.003863752 0.5000000 0.007727504 4.587220 38
## [38] {root vegetables,
## herbs} => {whole milk} 0.004168785 0.5942029 0.007015760 2.325502 41
## [39] {herbs,
## whole milk} => {root vegetables} 0.004168785 0.5394737 0.007727504 4.949369 41
## [40] {herbs,
## yogurt} => {other vegetables} 0.002033554 0.5714286 0.003558719 2.953232 20
## [41] {herbs,
## yogurt} => {whole milk} 0.002135231 0.6000000 0.003558719 2.348189 21
## [42] {herbs,
## rolls/buns} => {whole milk} 0.002440264 0.8000000 0.003050330 3.130919 24
## [43] {herbs,
## other vegetables} => {whole milk} 0.004067107 0.5263158 0.007727504 2.059815 40
## [44] {herbs,
## whole milk} => {other vegetables} 0.004067107 0.5263158 0.007727504 2.720082 40
## [45] {processed cheese,
## white bread} => {whole milk} 0.002135231 0.5121951 0.004168785 2.004552 21
## [46] {root vegetables,
## processed cheese} => {other vegetables} 0.002135231 0.6774194 0.003152008 3.501009 21
## [47] {root vegetables,
## processed cheese} => {whole milk} 0.002033554 0.6451613 0.003152008 2.524935 20
## [48] {tropical fruit,
## semi-finished bread} => {other vegetables} 0.002236909 0.5238095 0.004270463 2.707129 22
## [49] {tropical fruit,
## semi-finished bread} => {whole milk} 0.002135231 0.5000000 0.004270463 1.956825 21
## [50] {semi-finished bread,
## soda} => {whole milk} 0.002236909 0.5500000 0.004067107 2.152507 22plot(rules06[1:50], method="matrix3D", measure="lift")## Warning in plot.rules(rules06[1:50], method = "matrix3D", measure = "lift"):
## method 'matrix3D' is deprecated use method 'matrix' with engine '3d'## Itemsets in Antecedent (LHS)
## [1] "{other vegetables,rice}"
## [2] "{whole milk,rice}"
## [3] "{herbs,whole milk}"
## [4] "{citrus fruit,herbs}"
## [5] "{herbs,yogurt}"
## [6] "{whole milk,specialty cheese}"
## [7] "{root vegetables,rice}"
## [8] "{herbs,whipped/sour cream}"
## [9] "{herbs,other vegetables}"
## [10] "{tropical fruit,herbs}"
## [11] "{herbs,rolls/buns}"
## [12] "{turkey,whole milk}"
## [13] "{root vegetables,processed cheese}"
## [14] "{whole milk,frozen fish}"
## [15] "{yogurt,specialty cheese}"
## [16] "{whole milk,canned vegetables}"
## [17] "{yogurt,frozen fish}"
## [18] "{whole milk,frozen dessert}"
## [19] "{root vegetables,herbs}"
## [20] "{specialty cheese}"
## [21] "{whole milk,roll products }"
## [22] "{whole milk,dishes}"
## [23] "{rice}"
## [24] "{cereals}"
## [25] "{root vegetables,pasta}"
## [26] "{tropical fruit,semi-finished bread}"
## [27] "{other vegetables,frozen fish}"
## [28] "{other vegetables,pot plants}"
## [29] "{other vegetables,frozen dessert}"
## [30] "{semi-finished bread,soda}"
## [31] "{jam}"
## [32] "{other vegetables,cake bar}"
## [33] "{turkey,other vegetables}"
## [34] "{yogurt,pot plants}"
## [35] "{other vegetables,specialty cheese}"
## [36] "{baking powder}"
## [37] "{processed cheese,white bread}"
## [38] "{other vegetables,pasta}"
## Itemsets in Consequent (RHS)
## [1] "{whole milk}" "{other vegetables}" "{yogurt}"
## [4] "{root vegetables}"
plot(rules06[1:50], method="paracoord")