Options

# transaction data to binary incidence matrix

Hi all,

I am quite new user at Rapidminer and I want to transform transaction data to a binary incidence matrix.

Let me assume the intial transaction data is:

A B C

1 1 1

1 2 1

2 1 1

2 2 1

2 3 1

3 1 1

3 3 1

Where A stands for the customer id - B for the product id - C for the number of products purchased

Thus, the transformation that I would like to do would be as:

A C_1.0 C_2.0 C_3.0

1 1 1 0

2 1 1 1

3 1 0 1

In order to do so I perform the following process with the following operators:

1. Read Excel (where I choose A and B to be polynomial variables and C integer)

2. Pivot (where I choose - group attribute : A - index attribute : B - weight aggregation: sum )

However this results to the following

Row No. A C

1 1 1

2 2 1

3 3 1

I guess that my mistake is something quite simple, but I ve been struggling a lot. :-\

Please let me know if you have any comments.

Thanks,

Marios

I am quite new user at Rapidminer and I want to transform transaction data to a binary incidence matrix.

Let me assume the intial transaction data is:

A B C

1 1 1

1 2 1

2 1 1

2 2 1

2 3 1

3 1 1

3 3 1

Where A stands for the customer id - B for the product id - C for the number of products purchased

Thus, the transformation that I would like to do would be as:

A C_1.0 C_2.0 C_3.0

1 1 1 0

2 1 1 1

3 1 0 1

In order to do so I perform the following process with the following operators:

1. Read Excel (where I choose A and B to be polynomial variables and C integer)

2. Pivot (where I choose - group attribute : A - index attribute : B - weight aggregation: sum )

However this results to the following

Row No. A C

1 1 1

2 2 1

3 3 1

I guess that my mistake is something quite simple, but I ve been struggling a lot. :-\

Please let me know if you have any comments.

Thanks,

Marios

0

## Answers

578Unicorn