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	b	1
1	g	6
2	d	3
3	e	4
4	p	15
5	h	7
6	s	18
7	z	25
8	o	14
9	y	24

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

#	ascii	index
0	w	22
1	i	8
2	b	1
3	c	2
4	r	17
5	d	3
6	q	16
7	h	7
8	v	21
9	n	13

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	b	1	b
1	d	3	d
2	e	4	e
3	h	7	h
4	s	18	s
5	z	25	z
6	o	14	o
7	i	8	i
8	v	21	v
9	m	12	m