可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效，请关闭广告屏蔽插件后再试):
问题:
I read data from a csv file, the data has 3 columns, one is transaction id, the other two are product and product catagory. I need to convert this into transactions in order to use the apriori function in arules. It shows an error when I convert to transactions:
dat
If the data only have two columns, it can work by:
trans4
But I don't know how to convert when I have 3 columns. Usually there are the additional columns likes category attributes, customer attributes. so the column usually large than 2 columns. need to find rules between multiple columns.
回答1:
I have found some information that worked for me on this website. Let me copy relevant paragraph:
The dataframe can be in either a normalized (single) form or a flat file (basket) form.
When the file is in basket form it means that each record represents a transaction where the items in the basket are represented by columns.
When the dataset is in single form it means that each record represents one single item and each item contains a transaction id.
To load transactions from file, use read.transactions. In both your and my case file is in the single form.
I've used following code to load .csv file as transactions:
trans = read.transactions("some_data.csv", format = "single", sep = ",", cols = c("transactionID", "productID"))
To fully understand above command, take a look at read.transactions manual, available after typing ?read.transactions in R console.
回答2:
I was attempting to do the same thing and after I factored all my columns in the data.frame I was working with, I still could not coerce it into an itemMatrix of transactions. Then I realized I never re-loaded the "arules" package for the session I was working in. Very stupid mistake, but just wanted to mention it in case anyone else runs into the same problem, try the simple stuff first:
library("arules")
回答3:
You need to first convert "Transaction_id" into a factor variable.
