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	g	6
1	k	10
2	e	4
3	b	1
4	f	5
5	y	24
6	z	25
7	n	13
8	h	7
9	w	22

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

#	ascii	index
0	n	13
1	s	18
2	z	25
3	p	15
4	b	1
5	e	4
6	g	6
7	o	14
8	k	10
9	d	3

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	g	6	g
1	k	10	k
2	e	4	e
3	b	1	b
4	y	24	y
5	z	25	z
6	n	13	n
7	h	7	h
8	u	20	u
9	l	11	l
10	x	23	x