def test_init12():
outcomes = ['0', '1']
pmf = [1 / 2, 1 / 2]
d = Distribution(outcomes, pmf)
sd = ScalarDistribution.from_distribution(d, base=10)
d.set_base(10)
# Different sample space representations
assert not d.is_approx_equal(sd)
def test_init12():
outcomes = ["0", "1"]
pmf = [1 / 2, 1 / 2]
d = Distribution(outcomes, pmf)
sd = ScalarDistribution.from_distribution(d, base=10)
d.set_base(10)
# Different sample space representations
assert_false(d.is_approx_equal(sd))
def distribution_from_data(d, L, trim=True, base=None):
"""
Returns a distribution over words of length `L` from `d`.
The returned distribution is the naive estimate of the distribution,
which assigns probabilities equal to the number of times a particular
word appeared in the data divided by the total number of times a word
could have appeared in the data.
Roughly, it corresponds to the stationary distribution of a maximum
likelihood estimate of the transition matrix of an (L-1)th order Markov
chain.
Parameters
----------
d : list
A list of symbols to be converted into a distribution.
L : integer
The length of the words for the distribution.
trim : bool
If true, then words with zero probability are trimmed from the
distribution.
base : int or string
The desired base of the returned distribution. If `None`, then the
value of `dit.ditParams['base']` is used.
"""
from dit import ditParams, Distribution
try:
d = list(map(tuple, d))
except TypeError:
pass
if base is None:
base = ditParams['base']
words, _, counts, _ = counts_from_data(d, L, 0)
# We turn the counts to probabilities
pmf = counts / counts.sum()
dist = Distribution(words, pmf, trim=trim)
dist.set_base(base)
if L == 1:
try:
dist = modify_outcomes(dist, lambda o: o[0])
except ditException:
pass
return dist
def test_to_string9():
# Basic
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d.set_base(2)
s = d.to_string()
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: 2
Outcome Class: str
Outcome Length: 2
RV Names: None
x log p(x)
00 -2.0
01 -2.0
10 -2.0
11 -2.0"""
assert_equal(s, s_)
def test_to_string9():
# Basic
outcomes = ['00', '01', '10', '11']
pmf = [1/4]*4
d = Distribution(outcomes, pmf)
d.set_base(2)
s = d.to_string()
s_ = """Class: Distribution
Alphabet: ('0', '1') for all rvs
Base: 2
Outcome Class: str
Outcome Length: 2
RV Names: None
x log p(x)
00 -2.0
01 -2.0
10 -2.0
11 -2.0"""
assert s == s_
