def tag_values(estimator, tags_array, items_array, tag_to_item, seeker_profile,
tag_pop, outfile):
'''
Saves the value of each individual tag.
'''
#Value for each tag
print('#tag_id', 'rho', 'surprisal', 'dkl', 'dkl*rho', 'dkl/surprisal',
'n_items', 'prob_tag', 'pop_tag', 'mean_pti', file=outfile)
prob_tags = estimator.vect_prob_tag(tags_array)
for i, tag_id in enumerate(tags_array):
#Probabilities
prob_tag_items = estimator.vect_prob_tag_given_item(items_array,
tag_id)
prob_tag = prob_tags[i]
prob_item_seeker_tag = (prob_tag_items / prob_tag) * seeker_profile
prob_item_seeker_tag /= prob_item_seeker_tag.sum() #Renormalize
prob_items_tagged = seeker_profile[tag_to_item[tag_id]]
#Metrics
dkl = entropy.kullback_leiber_divergence(prob_item_seeker_tag,
seeker_profile)
rho = np.mean(prob_items_tagged)
surprisal = np.mean(1.0 / -np.log2(prob_items_tagged))
mean_pti = np.mean(prob_tag_items[tag_to_item[tag_id]])
pop_tag = tag_pop[tag_id]
print(tag_id, rho, surprisal, dkl, rho * dkl, dkl * surprisal,
len(prob_items_tagged), prob_tag, pop_tag, mean_pti, file=outfile)
def test_kl3(self):
x_probs = np.array([0.25, 0.20, 0, 0.55])
xy_probs = np.array([0.20, 0, 0.25, 0.55])
self.assertAlmostEqual(entropy.kullback_leiber_divergence(x_probs,
xy_probs),
float('inf'))
def test_kl2(self):
x_probs = np.array([0.04, 0.16] * 5 + [0])
xy_probs = np.array([0.02, 0.18] * 5 + [0])
dkl = 0
for i in range(len(x_probs) - 1):
div = x_probs[i] / xy_probs[i]
dkl += x_probs[i] * math.log(div, 2)
self.assertAlmostEqual(entropy.kullback_leiber_divergence(x_probs,
xy_probs),
dkl)
def tag_values(estimator, tags_array, items_array, tag_to_item, seeker_profile,
tag_pop, outfile):
'''
Saves the value of each individual tag.
'''
#Value for each tag
print('#tag_id',
'rho',
'surprisal',
'dkl',
'dkl*rho',
'dkl/surprisal',
'n_items',
'prob_tag',
'pop_tag',
'mean_pti',
file=outfile)
prob_tags = estimator.vect_prob_tag(tags_array)
for i, tag_id in enumerate(tags_array):
#Probabilities
prob_tag_items = estimator.vect_prob_tag_given_item(
items_array, tag_id)
prob_tag = prob_tags[i]
prob_item_seeker_tag = (prob_tag_items / prob_tag) * seeker_profile
prob_item_seeker_tag /= prob_item_seeker_tag.sum() #Renormalize
prob_items_tagged = seeker_profile[tag_to_item[tag_id]]
#Metrics
dkl = entropy.kullback_leiber_divergence(prob_item_seeker_tag,
seeker_profile)
rho = np.mean(prob_items_tagged)
surprisal = np.mean(1.0 / -np.log2(prob_items_tagged))
mean_pti = np.mean(prob_tag_items[tag_to_item[tag_id]])
pop_tag = tag_pop[tag_id]
print(tag_id,
rho,
surprisal,
dkl,
rho * dkl,
dkl * surprisal,
len(prob_items_tagged),
prob_tag,
pop_tag,
mean_pti,
file=outfile)
