def dist(self, column):
"""
Return frequency distribution of one column.
Parameters
----------
column : str
column name, whose distribution will be return
"""
if len(self._dt) == 0:
for c in self._columns:
self._dt[c] = {}
if self.first[c].categorical:
bins = self.first[c].domain
counts1 = self.first[c].counts(bins=bins)
counts2 = self.second[c].counts(bins=bins)
else:
min_, max_ = self.first[c].domain
# the domain from two data set are same;
# extend the domain to human-readable range
bins = normalize_range(min_, max_ + 1)
counts1 = self.first[c].counts(bins=bins)
counts2 = self.second[c].counts(bins=bins)
# Note: index, value of np.histogram has different length
bins = bins[:-1]
self._dt[c]['bins'] = bins
# stack arrays vertically
self._dt[c]['counts'] = np.vstack((counts1, counts2))
return self._dt[column]['bins'], self._dt[column]['counts']
def dist(self, column):
"""
Return frequency distribution of one column.
Parameters
----------
column : str
column name, whose distribution will be return
"""
if column not in self.columns:
raise ValueError(f"{column} is not in current dataset.")
if self.fst[column].categorical:
bins = self.fst[column].domain
fst_counts = self.fst[column].counts(bins=bins)
snd_counts = self.snd[column].counts(bins=bins)
else:
min_, max_ = self.fst[column].domain
# the domain from two data set are same;
# extend the domain to human-readable range
bins = normalize_range(min_, max_ + 1)
fst_counts = self.fst[column].counts(bins=bins)
snd_counts = self.snd[column].counts(bins=bins)
# Note: index, value of np.histogram has different length
bins = bins[:-1]
# stack arrays vertically
return bins, np.vstack((fst_counts, snd_counts))
def test_normalize_range_ints():
from numpy.random import randint
for i in range(50):
start = randint(0, 5)
stop = randint(start + 1, 200)
bins = randint(8, 30)
ints = normalize_range(start, stop, bins)
assert len(ints) <= bins + 1
def test_normalize_range_floats():
from numpy.random import randint, rand
for i in range(50):
start = round(randint(0, 5) * rand(), 4)
stop = round(randint(0, 200) * rand(), 4) + 5
bins = randint(8, 30)
floats = normalize_range(start, stop, bins)
assert len(floats) <= bins + 1