Created
March 26, 2016 10:49
-
-
Save iwata-n/b2111405229b52b75320 to your computer and use it in GitHub Desktop.
世界のビールと音楽の組み合わせをデータ分析で最適化!で作ったソース
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# イベントページ | |
# http://connpass.com/event/27829/ | |
# パッケージのインストール | |
# install.packages("arules") | |
# install.packages("arulesViz") | |
library(arules) | |
library(arulesViz) | |
data <- read.csv("music.csv", fileEncoding = "UTF-8") | |
# head(data) # コンソールで表示 | |
# View(data) # エクセルっぽく表で表示 | |
# data[1, 1] # 特定の要素だけ表示 | |
# data[1,] # 行を表示 | |
# data[,2] # 列を表示 | |
# データフレーム型だとアソシエーション分析に入れれないので変える | |
data <- data[, -1] # 参加者情報は不要なので除く | |
data[, 1] <- as.factor(data[, 1]) # 型の変換(factor型へ変換) | |
data[, 2] <- as.factor(data[, 2]) | |
data <- as(data, "transactions") | |
# par(family = "Osaka") # Macの場合フォントファミリーを指定する | |
itemFrequencyPlot(data, type = "relative") | |
# アソシエーション分析する | |
rules <- apriori(data, parameter = list(support = 0.01, confidence = 0.01, minlen = 2)) | |
# rules <- apriori(data, parameter = list(support = 0.01, confidence = 0.01)) | |
# しきい値以上でフィルター | |
rules <- subset(rules, subset = (lift > 1.0)) | |
# サポート血が大きい順に並べ替え | |
rules <- sort(rules, by = "support") | |
# コンソールで表示 | |
inspect(head(rules, n = 10)) | |
# csvで書き出す | |
write.csv(as(rules, "data.frame"), file = "結果.csv", row.names = FALSE, fileEncoding = "UTF-8") | |
# 関係図で表示 | |
plot( | |
rules, | |
method = "graph", | |
control = list( | |
type = "items", | |
cex = 1.0 | |
) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment