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	j	9
1	p	15
2	x	23
3	q	16
4	r	17
5	n	13
6	g	6
7	h	7
8	z	25
9	b	1

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

#	ascii	index
0	m	12
1	o	14
2	z	25
3	f	5
4	t	19
5	i	8
6	h	7
7	v	21
8	l	11
9	x	23

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	p	15	p
1	x	23	x
2	n	13	n
3	h	7	h
4	z	25	z
5	t	19	t