def balanced(**kwargs):
"""balanced(factor_name=num_levels, [factor_name=num_levels, ..., repeat=1])
Create simple balanced factorial designs for testing.
Given some factor names and the number of desired levels for each,
generates a balanced factorial design in the form of a data
dictionary. For example:
.. ipython::
In [1]: balanced(a=2, b=3)
Out[1]:
{'a': ['a1', 'a1', 'a1', 'a2', 'a2', 'a2'],
'b': ['b1', 'b2', 'b3', 'b1', 'b2', 'b3']}
By default it produces exactly one instance of each combination of levels,
but if you want multiple replicates this can be accomplished via the
`repeat` argument:
.. ipython::
In [2]: balanced(a=2, b=2, repeat=2)
Out[2]:
{'a': ['a1', 'a1', 'a2', 'a2', 'a1', 'a1', 'a2', 'a2'],
'b': ['b1', 'b2', 'b1', 'b2', 'b1', 'b2', 'b1', 'b2']}
"""
repeat = kwargs.pop("repeat", 1)
levels = []
names = sorted(kwargs)
for name in names:
level_count = kwargs[name]
levels.append(["%s%s" % (name, i) for i in xrange(1, level_count + 1)])
# zip(*...) does an "unzip"
values = zip(*itertools_product(*levels))
data = {}
for name, value in zip(names, values):
data[name] = list(value) * repeat
return data
def _column_combinations(columns_per_factor):
# For consistency with R, the left-most item iterates fastest:
iterators = [xrange(n) for n in reversed(columns_per_factor)]
for reversed_combo in itertools_product(*iterators):
yield reversed_combo[::-1]
def _column_combinations(columns_per_factor):
# For consistency with R, the left-most item iterates fastest:
iterators = [xrange(n) for n in reversed(columns_per_factor)]
for reversed_combo in itertools_product(*iterators):
yield reversed_combo[::-1]