def fit(self, original, target, original_weight=None, target_weight=None):
"""
Prepare reweighting formula by computing histograms.
:param original: values from original distribution, array-like of shape [n_samples, n_features]
:param target: values from target distribution, array-like of shape [n_samples, n_features]
:param original_weight: weights for samples of original distributions
:param target_weight: weights for samples of original distributions
:return: self
"""
self.n_features_ = None
original, original_weight = self._normalize_input(original, original_weight)
target, target_weight = self._normalize_input(target, target_weight)
target_perc = numpy.linspace(0, 1, self.n_percentiles + 1)[1:-1]
self.edges = []
for axis in range(self.n_features_):
self.edges.append(weighted_quantile(target[:, axis], quantiles=target_perc, sample_weight=target_weight))
bins_weights = []
for data, weights in [(original, original_weight), (target, target_weight)]:
bin_indices = self.compute_bin_indices(data)
bin_w = bincount_nd(bin_indices, weights=weights, shape=[self.n_percentiles] * self.n_features_)
smeared_weights = gaussian_filter(bin_w, sigma=self.n_neighs, truncate=2.5)
bins_weights.append(smeared_weights.clip(self.min_in_the_bin))
bin_orig_weights, bin_targ_weights = bins_weights
self.transition = bin_targ_weights / bin_orig_weights
return self
def check_weighted_percentile(size=100, q_size=20):
random = RandomState()
array = random.permutation(size)
quantiles = random.uniform(size=q_size)
q_permutation = random.permutation(q_size)
result1 = weighted_quantile(array, quantiles)[q_permutation]
result2 = weighted_quantile(array, quantiles[q_permutation])
result3 = weighted_quantile(array[random.permutation(size)], quantiles[q_permutation])
assert numpy.all(result1 == result2) and numpy.all(result1 == result3), 'breaks on permutations'
# checks that order is kept
quantiles = numpy.linspace(0, 1, size * 3)
x = weighted_quantile(array, quantiles, sample_weight=random.exponential(size=size))
assert numpy.all(x == numpy.sort(x)), "doesn't preserve order"
array = numpy.array([0, 1, 2, 5])
# comparing with simple percentiles
for x in random.uniform(size=10):
assert numpy.abs(numpy.percentile(array, x * 100) - weighted_quantile(array, x, old_style=True)) < 1e-7, \
"doesn't coincide with numpy.percentile"
def check_weighted_percentile(size=100, q_size=20):
random = RandomState()
array = random.permutation(size)
quantiles = random.uniform(size=q_size)
q_permutation = random.permutation(q_size)
result1 = weighted_quantile(array, quantiles)[q_permutation]
result2 = weighted_quantile(array, quantiles[q_permutation])
result3 = weighted_quantile(array[random.permutation(size)],
quantiles[q_permutation])
assert numpy.all(result1 == result2) and numpy.all(
result1 == result3), 'breaks on permutations'
# checks that order is kept
quantiles = numpy.linspace(0, 1, size * 3)
x = weighted_quantile(array,
quantiles,
sample_weight=random.exponential(size=size))
assert numpy.all(x == numpy.sort(x)), "doesn't preserve order"
array = numpy.array([0, 1, 2, 5])
# comparing with simple percentiles
for x in random.uniform(size=10):
assert numpy.abs(numpy.percentile(array, x * 100) - weighted_quantile(array, x, old_style=True)) < 1e-7, \
"doesn't coincide with numpy.percentile"
def fit(self, original, target, original_weight=None, target_weight=None):
"""
Prepare reweighting formula by computing histograms.
:param original: values from original distribution, array-like of shape [n_samples, n_features]
:param target: values from target distribution, array-like of shape [n_samples, n_features]
:param original_weight: weights for samples of original distributions
:param target_weight: weights for samples of original distributions
:return: self
"""
self.n_features_ = None
original, original_weight = self._normalize_input(
original, original_weight)
target, target_weight = self._normalize_input(target, target_weight)
target_perc = numpy.linspace(0, 1, self.n_percentiles + 1)[1:-1]
self.edges = []
for axis in range(self.n_features_):
self.edges.append(
weighted_quantile(target[:, axis],
quantiles=target_perc,
sample_weight=target_weight))
bins_weights = []
for data, weights in [(original, original_weight),
(target, target_weight)]:
bin_indices = self.compute_bin_indices(data)
bin_w = bincount_nd(bin_indices,
weights=weights,
shape=[self.n_percentiles] * self.n_features_)
smeared_weights = gaussian_filter(bin_w,
sigma=self.n_neighs,
truncate=2.5)
bins_weights.append(smeared_weights.clip(self.min_in_the_bin))
bin_orig_weights, bin_targ_weights = bins_weights
self.transition = bin_targ_weights / bin_orig_weights
return self
