def lookup_negative_items(self, negative_users, **kwargs):
output = np.zeros(shape=negative_users.shape,
dtype=rconst.ITEM_DTYPE) - 1
left_index = self.index_bounds[negative_users]
right_index = self.index_bounds[negative_users + 1] - 1
num_positives = right_index - left_index + 1
num_negatives = self._num_items - num_positives
neg_item_choice = stat_utils.very_slightly_biased_randint(
num_negatives)
# Shortcuts:
# For points where the negative is greater than or equal to the tally before
# the last positive point there is no need to bisect. Instead the item id
# corresponding to the negative item choice is simply:
# last_postive_index + 1 + (neg_choice - last_negative_tally)
# Similarly, if the selection is less than the tally at the first positive
# then the item_id is simply the selection.
#
# Because MovieLens organizes popular movies into low integers (which is
# preserved through the preprocessing), the first shortcut is very
# efficient, allowing ~60% of samples to bypass the bisection. For the same
# reason, the second shortcut is rarely triggered (<0.02%) and is therefore
# not worth implementing.
use_shortcut = neg_item_choice >= self._total_negatives[right_index]
output[use_shortcut] = (
self._sorted_train_pos_items[right_index] + 1 +
(neg_item_choice -
self._total_negatives[right_index]))[use_shortcut]
if np.all(use_shortcut):
# The bisection code is ill-posed when there are no elements.
return output
not_use_shortcut = np.logical_not(use_shortcut)
left_index = left_index[not_use_shortcut]
right_index = right_index[not_use_shortcut]
neg_item_choice = neg_item_choice[not_use_shortcut]
num_loops = np.max(
np.ceil(np.log2(num_positives[not_use_shortcut])).astype(np.int32))
for i in range(num_loops):
mid_index = (left_index + right_index) // 2
right_criteria = self._total_negatives[mid_index] > neg_item_choice
left_criteria = np.logical_not(right_criteria)
right_index[right_criteria] = mid_index[right_criteria]
left_index[left_criteria] = mid_index[left_criteria]
# Expected state after bisection pass:
# The right index is the smallest index whose tally is greater than the
# negative item choice index.
assert np.all((right_index - left_index) <= 1)
output[not_use_shortcut] = (
self._sorted_train_pos_items[right_index] -
(self._total_negatives[right_index] - neg_item_choice))
assert np.all(output >= 0)
return output
def lookup_negative_items(self, negative_users, **kwargs):
output = np.zeros(shape=negative_users.shape, dtype=rconst.ITEM_DTYPE) - 1
left_index = self.index_bounds[negative_users]
right_index = self.index_bounds[negative_users + 1] - 1
num_positives = right_index - left_index + 1
num_negatives = self._num_items - num_positives
neg_item_choice = stat_utils.very_slightly_biased_randint(num_negatives)
# Shortcuts:
# For points where the negative is greater than or equal to the tally before
# the last positive point there is no need to bisect. Instead the item id
# corresponding to the negative item choice is simply:
# last_postive_index + 1 + (neg_choice - last_negative_tally)
# Similarly, if the selection is less than the tally at the first positive
# then the item_id is simply the selection.
#
# Because MovieLens organizes popular movies into low integers (which is
# preserved through the preprocessing), the first shortcut is very
# efficient, allowing ~60% of samples to bypass the bisection. For the same
# reason, the second shortcut is rarely triggered (<0.02%) and is therefore
# not worth implementing.
use_shortcut = neg_item_choice >= self._total_negatives[right_index]
output[use_shortcut] = (
self._sorted_train_pos_items[right_index] + 1 +
(neg_item_choice - self._total_negatives[right_index])
)[use_shortcut]
if np.all(use_shortcut):
# The bisection code is ill-posed when there are no elements.
return output
not_use_shortcut = np.logical_not(use_shortcut)
left_index = left_index[not_use_shortcut]
right_index = right_index[not_use_shortcut]
neg_item_choice = neg_item_choice[not_use_shortcut]
num_loops = np.max(
np.ceil(np.log2(num_positives[not_use_shortcut])).astype(np.int32))
for i in range(num_loops):
mid_index = (left_index + right_index) // 2
right_criteria = self._total_negatives[mid_index] > neg_item_choice
left_criteria = np.logical_not(right_criteria)
right_index[right_criteria] = mid_index[right_criteria]
left_index[left_criteria] = mid_index[left_criteria]
# Expected state after bisection pass:
# The right index is the smallest index whose tally is greater than the
# negative item choice index.
assert np.all((right_index - left_index) <= 1)
output[not_use_shortcut] = (
self._sorted_train_pos_items[right_index] -
(self._total_negatives[right_index] - neg_item_choice)
)
assert np.all(output >= 0)
return output
def lookup_negative_items(self, negative_users, **kwargs):
negative_item_choice = stat_utils.very_slightly_biased_randint(
self._per_user_neg_count[negative_users])
return self._negative_table[negative_users, negative_item_choice]
def lookup_negative_items(self, negative_users, **kwargs):
negative_item_choice = stat_utils.very_slightly_biased_randint(
self._per_user_neg_count[negative_users])
return self._negative_table[negative_users, negative_item_choice]
