Data structure for apriori algorithm

87 Views Asked by At

How can I restructure my data in Python to use the Apriori algorithm? I have a dataset with two columns: "Article" and "ID". The "Article" column contains either a single number or a list of numbers. I want to convert the data into a matrix format where each article corresponds to a column, each transaction corresponds to a row, and the values are filled with "true" or "false" depending on whether the article exists in the corresponding transaction. For example, given the following data:

| ID  | Articles  |  
| ID1 | [1, 2, 3] | 
| ID2 | [1, 2]    | 
| ID3 | 4         | 

I want to convert it to the following format:

|     | 1   | 2   |   3 | 4     |  
| ID1 | true| true| true| false | 
| ID2 | true| true|false| false |
| ID3 |false|false|false| true  | 

This matrix format will allow me to apply the Apriori algorithm. how to achieve this?

0

There are 0 best solutions below