Align datasets

Shows how to combine information from two datasets describing the same cases, but not necessarily in the same order.

# Author: Christian Brodbeck <christianbrodbeck@nyu.edu>
import random
import string

from eelbrain import *


# Generate a dataset with known sequence
ds = Dataset()
ds['ascii'] = Factor(string.ascii_lowercase)
# Add an index variable to the dataset to later identify the cases
ds.index()

# Generate two shuffled copies of the dataset (and print them to confirm that
# they are shuffled)
ds1 = ds[random.sample(range(ds.n_cases), 15)]
ds1.head()

#	ascii	index
0	x	23
1	w	22
2	m	12
3	r	17
4	a	0
5	j	9
6	p	15
7	g	6
8	v	21
9	y	24

ds2 = ds[random.sample(range(ds.n_cases), 16)]
ds2.head()

#	ascii	index
0	w	22
1	l	11
2	k	10
3	n	13
4	v	21
5	i	8
6	d	3
7	p	15
8	u	20
9	t	19

Align the datasets

Use the "index" variable added above to identify cases and align the two datasets

ds1_aligned, ds2_aligned = align(ds1, ds2, 'index')

# show the ascii sequences for the two datasets next to each other to
# demonstrate that they are aligned
ds1_aligned['ascii_ds2'] = ds2_aligned['ascii']
ds1_aligned

#	ascii	index	ascii_ds2
0	w	22	w
1	p	15	p
2	v	21	v
3	b	1	b
4	i	8	i
5	s	18	s
6	n	13	n