From 375c31ccf124f072c204f7fbde34d80483ab3e85 Mon Sep 17 00:00:00 2001
From: Caiwen Li <130128348+LisaLi525@users.noreply.github.com>
Date: Wed, 13 Dec 2023 23:10:03 +0200
Subject: [PATCH] Create Market Basket Analysis.R

---
 Market Basket Analysis.R | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 Market Basket Analysis.R

diff --git a/Market Basket Analysis.R b/Market Basket Analysis.R
new file mode 100644
index 0000000..60b647b
--- /dev/null
+++ b/Market Basket Analysis.R	
@@ -0,0 +1,25 @@
+perform_market_basket_analysis <- function(transaction_data) {
+  # Preparing the data for market basket analysis
+  transaction_items <- transaction_data %>%
+    filter(totitemsaleprice > 0) %>%
+    left_join(items_master, by = c("gtin" = "ugtin")) %>%
+    group_by(trandate, tranno) %>%
+    summarise(item_list = paste(ides, collapse = ",")) %>%
+    ungroup() %>%
+    collect()
+
+  # Writing item list to a CSV file
+  write.csv(transaction_items, "itemList.csv", quote = FALSE, row.names = TRUE)
+
+  # Loading the arules package and preparing transactions
+  library(arules)
+  txn <- read.transactions(file = "itemList.csv", rm.duplicates = FALSE, format = "basket", sep = ",", cols = 1)
+  txn@itemInfo$labels <- gsub("\"", "", txn@itemInfo$labels)
+
+  # Running the Apriori algorithm
+  basket_rules <- apriori(txn, parameter = list(minlen = 2, sup = 0.001, conf = 0.01, target = "rules"))
+  df_basket <- as(basket_rules, "data.frame")
+  df_basket$confidence <- df_basket$confidence * 100
+
+  return(df_basket)
+}