def enumerate_splits(self, target_dist: proba.Multinomial):
low = min(h[0].right for h in self.hists.values())
high = min(h[-1].right for h in self.hists.values())
# If only one single value has been observed, then no split can be proposed
if low >= high:
return
yield # not a typo
n_thresholds = min(self.n_splits,
max(map(len, self.hists.values())) - 1)
thresholds = list(decimal_range(start=low, stop=high,
num=n_thresholds))
cdfs = {y: hist.iter_cdf(thresholds) for y, hist in self.hists.items()}
for at in thresholds:
l_dist = {}
r_dist = {}
for y in target_dist:
p_xy = next(cdfs[y]) if y in cdfs else 0. # P(x < t | y)
p_y = target_dist.pmf(y) # P(y)
l_dist[y] = target_dist.n_samples * p_y * p_xy # P(y | x < t)
r_dist[y] = target_dist.n_samples * p_y * (1 - p_xy
) # P(y | x >= t)
l_dist = proba.Multinomial(l_dist)
r_dist = proba.Multinomial(r_dist)
yield LT, at, l_dist, r_dist
def enumerate_splits(self, target_dist: proba.Multinomial):
categories = set(*(p_x.keys() for p_x in self.P_xy.values()))
# There has to be at least two categories for a split to be possible
if len(categories) < 2:
return
yield # not a typo
for cat in categories:
l_dist = {}
r_dist = {}
for y in target_dist:
p_xy = self.P_xy[y].pmf(cat) # P(cat | y)
p_y = target_dist.pmf(y) # P(y)
l_dist[y] = target_dist.n_samples * p_y * p_xy # P(y | cat)
r_dist[y] = target_dist.n_samples * p_y * (1. - p_xy
) # P(y | !cat)
l_dist = proba.Multinomial(l_dist)
r_dist = proba.Multinomial(r_dist)
yield EQ, cat, l_dist, r_dist
def __init__(self,
criterion='gini',
patience=250,
max_depth=5,
min_split_gain=0.,
min_child_samples=20,
confidence=1e-10,
tie_threshold=5e-2,
n_split_points=30,
max_bins=60,
curtail_under=10):
self.criterion = criterion
self.patience = patience
self.max_depth = max_depth
self.min_split_gain = min_split_gain
self.min_child_samples = min_child_samples
self.confidence = confidence
self.tie_threshold = tie_threshold
self.n_split_points = n_split_points
self.max_bins = max_bins
self.curtail_under = curtail_under
self.criterion_func = CRITERIA_CLF[criterion]
self.root = leaf.Leaf(depth=0,
tree=self,
target_dist=proba.Multinomial())
def _make_leaf_dist(self):
return proba.Multinomial()