Dataset basics

# Author: Christian Brodbeck <christianbrodbeck@nyu.edu>
from eelbrain import *
import numpy

A dataset can be constructed column by column, by adding one variable after another:

# initialize an empty Dataset:
ds = Dataset()
# numeric values are added as Var object:
ds['y'] = Var(numpy.random.normal(0, 1, 6))
# categorical data as represented in Factors:
ds['a'] = Factor(['a', 'b', 'c'], repeat=2)
# A variable that's equal in all cases can be assigned quickly:
ds[:, 'z'] = 0.
# check the result:
ds

y	a	z
-0.83716	a	0
1.2414	a	0
1.053	b	0
-0.96077	b	0
-1.6302	c	0
-0.15546	c	0

For larger datasets it can be more convenient to print only the first few cases…

ds.head()

y	a	z
-0.83716	a	0
1.2414	a	0
1.053	b	0
-0.96077	b	0
-1.6302	c	0
-0.15546	c	0

… or a summary of variables:

ds.summary()

Key	Type	Values
y	Var	-1.63023, -0.960768, -0.837161, -0.155464, 1.05296, 1.24142
a	Factor	a:2, b:2, c:2
z	Var	0:6

Dataset: 6 cases

An alternative way of constructing a dataset is case by case (i.e., row by row):

rows = []
for i in range(6):
    subject = f'S{i}'
    y = numpy.random.normal(0, 1)
    a = 'abc'[i % 3]
    rows.append([subject, y, a])
ds = Dataset.from_caselist(['subject', 'y', 'a'], rows, random='subject')
ds

subject	y	a
S0	0.67705	a
S1	2.1915	b
S2	0.3462	c
S3	-0.8938	a
S4	1.2179	b
S5	-0.22032	c

Example

Below is a simple example using data objects (for more, see the Examples):

y = numpy.empty(21)
y[:14] = numpy.random.normal(0, 1, 14)
y[14:] = numpy.random.normal(2, 1, 7)
ds = Dataset({
    'a': Factor('abc', 'A', repeat=7),
    'y': Var(y, 'Y'),
})
ds

a	y
a	1.0333
a	0.61647
a	0.65359
a	-0.77592
a	0.2152
a	-1.1321
a	-0.10215
b	-0.47641
b	0.77615
b	-0.11093
b	-1.1939
b	-1.0134
b	0.39957
b	-0.00026489
c	1.2807
c	0.2931
c	2.3684
c	1.5308
c	1.93
c	2.0482
c	0.34986

table.frequencies('a', data=ds)

a	n
a	7
b	7
c	7

test.ANOVA('y', 'a', data=ds)

	SS	df	MS	F	p
a	10.54	2	5.27	8.74**	.002
Residuals	10.86	18	0.60
Total	21.39	20

test.pairwise('y', 'a', data=ds, corr='Hochberg')

Pairwise T-Tests (independent samples)

	b	c
a	t12 = 0.75 p = .466 pc = .466	t12 = -3.09* p = .009 pc = .028
b		t12 = -3.97** p = .002 pc = .009

(* Corrected after Hochberg, 1988)

t = test.pairwise('y', 'a', data=ds, corr='Hochberg')
print(t.get_tex())

\begin{center}
\begin{tabular}{lll}
\toprule
 & b & c \\
\midrule
a & $t_{12} = 0.75^{   \ \ \ }$\\
$p = .466$\\
$p_{c} = .466$ & $t_{12} = -3.09^{*  \ \ }$\\
$p = .009$\\
$p_{c} = .028$ \\
b &  & $t_{12} = -3.97^{** \ }$\\
$p = .002$\\
$p_{c} = .009$ \\
\bottomrule
\end{tabular}
\end{center}

p = plot.Boxplot('y', 'a', data=ds, title="My Boxplot", ylabel="value", corr='Hochberg')