def evaluation_occupancy_statistics(n, df_subsampled_from,day_profile):
anonymity_level = n
mode = "arrival"
rep_mode = 'mean'
subsample_size_max = int(comb(len(df_subsampled_from),2))
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max))
sp = Subsampling(data=df_subsampled_from)
data_pair, data_pair_all_index = sp.uniform_sampling(subsample_size=subsample_size, seed = None)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest='statistics', stat_type=mode)
similarity_label, data_subsample = sim.label_via_silhouette_analysis(range_n_clusters=range(2,8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
lm = Linear_Metric()
lm.train(data_pair, similarity_label)
dm = Deep_Metric()
dm.train(data_pair, similarity_label)
# step 6: the original database is privatized using the learned metric
sanitized_profile = util.sanitize_data(day_profile, distance_metric="deep",anonymity_level=anonymity_level,
rep_mode=rep_mode, deep_model=lm)
sanitized_profile_deep = util.sanitize_data(day_profile, distance_metric="deep",anonymity_level=anonymity_level,
rep_mode=rep_mode, deep_model=dm)
# (optionally for evaluation purpose) Evaluating the information loss of the sanitized database
loss_learned_metric = pe.get_statistics_loss(data_gt=day_profile,
data_sanitized=sanitized_profile.round(),
mode = mode)
loss_learned_metric_deep = pe.get_statistics_loss(data_gt=day_profile,
data_sanitized=sanitized_profile_deep.round(),
mode = mode)
print('anonymity level %s' % anonymity_level)
print("sampled size %s" % subsample_size)
print("information loss with best metric %s" % loss_best_metric)
print("information loss with generic metric %s" % loss_generic_metric)
print("information loss with learned metric %s" % loss_learned_metric)
print("information loss with learned metric deep %s" % (loss_learned_metric_deep))
return (sanitized_profile_best, sanitized_profile_baseline, sanitized_profile, sanitized_profile_deep), (loss_best_metric, loss_generic_metric, loss_learned_metric, loss_learned_metric_deep), subsample_size
mode=interest,
window=window)
print("information loss with learned metric %s" % loss_generic_metric)
df_subsampled_from = sanitized_profile_baseline.drop_duplicates().sample(
frac=1)
subsample_size_max = int(comb(len(df_subsampled_from), 2))
print('total number of pairs is %s' % subsample_size_max)
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max / 2))
sp = Subsampling(data=df_subsampled_from)
data_pair = sp.uniform_sampling(subsample_size=subsample_size)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest='statistics',
stat_type=interest,
window=window)
similarity_label, class_label = sim.label_via_silhouette_analysis(
range_n_clusters=range(2, 8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
# lam_vec is a set of candidate lambda's for weighting the l1-norm penalty in the metric learning optimization problem.
# The lambda that achieves lowest testing error will be selected for generating the distance metric
dist_metric = mel.learn_with_simialrity_label_regularization(
data=data_pair, label=similarity_label, lam_vec=[10], train_portion=0.8)
# step 6: the original database is privatized using the learned metric
sanitized_profile = util.sanitize_data(day_profile,
distance_metric="mahalanobis",
window=window)
loss_generic_metric = pe.get_information_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_baseline.round(),
window=window)
df_subsampled_from = day_profile_metric_learn
subsample_size_max = int(comb(len(df_subsampled_from), 2))
print('total number of pairs is %s' % len(df_subsampled_from))
## obtain ground truth similarity labels
sp = Subsampling(data=df_subsampled_from)
data_pair_all, data_pair_all_index = sp.uniform_sampling(
subsample_size=subsample_size_max, seed=0)
sim = Similarity(data=data_pair_all)
sim.extract_interested_attribute(interest=interest, window=window)
similarity_label_all, class_label_all = sim.label_via_silhouette_analysis(
range_n_clusters=range(2, 8))
similarity_label_all_series = pd.Series(similarity_label_all)
similarity_label_all_series.index = data_pair_all_index
print('similarity balance is %s' %
[sum(similarity_label_all),
len(similarity_label_all)])
k_init = 50
mc_num = 5
seed_vec = np.arange(mc_num)
run_sample_size = 300
## active sampling
def evaluation_occupancy_statistics(n, mode="arrival"):
day_profile1 = pd.read_pickle('./dataset/dataframe_all_binary.pkl')
day_profile1 = day_profile1.fillna(0)
day_profile1[day_profile1 > 0] = 1
res = 15
day_profile = day_profile1.iloc[:90, 0::
res] # subsample the database to improve the speed for demonstration purpose
day_profile2 = day_profile1.iloc[
90:-1, 0::
res] # subsample the database to improve the speed for demonstration purpose
rep_mode = 'mean'
anonymity_level = n
sanitized_profile_best = util.sanitize_data(
day_profile,
distance_metric='self-defined',
anonymity_level=anonymity_level,
rep_mode=rep_mode,
mode=mode)
sanitized_profile_baseline = util.sanitize_data(
day_profile,
distance_metric='euclidean',
anonymity_level=anonymity_level,
rep_mode=rep_mode)
loss_best_metric = pe.get_statistics_loss(
data_gt=day_profile, data_sanitized=sanitized_profile_best, mode=mode)
loss_generic_metric = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_baseline,
mode=mode)
df_subsampled_from = day_profile2.sample(frac=1)
subsample_size_max = int(comb(len(df_subsampled_from), 2))
print('total number of pairs is %s' % len(df_subsampled_from))
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max))
sp = Subsampling(data=df_subsampled_from)
data_pair, data_pair_all_index = sp.uniform_sampling(
subsample_size=subsample_size, seed=None)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest='statistics', stat_type=mode)
similarity_label, data_subsample = sim.label_via_silhouette_analysis(
range_n_clusters=range(2, 8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
lm = Linear_Metric()
lm.train(data_pair, similarity_label)
dm = Deep_Metric()
dm.train(data_pair, similarity_label)
# step 6: the original database is privatized using the learned metric
sanitized_profile = util.sanitize_data(day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=lm)
sanitized_profile_deep = util.sanitize_data(
day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=dm)
# (optionally for evaluation purpose) Evaluating the information loss of the sanitized database
loss_learned_metric = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile.round(),
mode=mode)
loss_learned_metric_deep = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_deep.round(),
mode=mode)
print('anonymity level %s' % anonymity_level)
print("sampled size %s" % subsample_size)
print("information loss with best metric %s" % loss_best_metric)
print("information loss with generic metric %s" % loss_generic_metric)
print("information loss with learned metric %s" % loss_learned_metric)
print("information loss with learned metric deep %s" %
(loss_learned_metric_deep))
return (sanitized_profile_best, sanitized_profile_baseline,
sanitized_profile,
sanitized_profile_deep), (loss_best_metric, loss_generic_metric,
loss_learned_metric,
loss_learned_metric_deep), subsample_size
def evaluation_total_usage(n):
"""
In the demo, we will showcase an example of special purpose publication.
The data user wants the published energy database to maximally retain the information about peak-time energy usage
"""
# Initialization of some useful classes
util = Utilities()
pe = PerformanceEvaluation()
# step 1: get the database to be published
day_profile = pd.read_pickle('dataset/dataframe_all_energy.pkl')
day_profile = day_profile.fillna(0)
day_profile = day_profile.iloc[
0:90, 0::
4] # subsample the database to improve the speed for demonstration purpose
day_profile.index = range(len(day_profile.index))
rep_mode = 'mean'
anonymity_level = n # desired anonymity level
# step 2: data user specifies his/her interest. In the example, the data user is interested in preserving the
# information of the cumulative energy use during peak time. In this case, he/she would also need to specify the
# starting and ending time of the peak usage time
interest = 'window-usage'
window = [17, 21]
sanitized_profile_best = util.sanitize_data(
day_profile,
distance_metric='self-defined',
anonymity_level=anonymity_level,
rep_mode=rep_mode,
mode=interest,
window=window)
# step 3: pre-sanitize the database
sanitized_profile_baseline = util.sanitize_data(
day_profile,
distance_metric='euclidean',
anonymity_level=anonymity_level,
rep_mode=rep_mode)
loss_best_metric = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_best,
mode=interest,
window=window)
loss_generic_metric = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_baseline,
mode=interest,
window=window)
# print("information loss with learned metric %s" % loss_generic_metric)
df_subsampled_from = sanitized_profile_baseline.drop_duplicates().sample(
frac=1)
subsample_size_max = int(comb(len(df_subsampled_from), 2))
print('total number of pairs is %s' % subsample_size_max)
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max))
sp = Subsampling(data=df_subsampled_from)
data_pair, data_pair_all_index = sp.uniform_sampling(
subsample_size=subsample_size, seed=None)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest='statistics',
stat_type=interest,
window=window)
similarity_label, data_subsample = sim.label_via_silhouette_analysis(
range_n_clusters=range(2, 8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
lm = Linear_Metric()
lm.train(data_pair, similarity_label)
dm = Deep_Metric()
dm.train(data_pair, similarity_label)
# step 6: the original database is privatized using the learned metric
sanitized_profile_deep = util.sanitize_data(
day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=dm,
window=window)
sanitized_profile = util.sanitize_data(day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=lm,
window=window)
# (optionally for evaluation purpose) Evaluating the information loss of the sanitized database
loss_learned_metric_deep = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_deep.round(),
mode=interest,
window=window)
loss_learned_metric = pe.get_statistics_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile,
mode=interest,
window=window)
print('anonymity level %s' % anonymity_level)
print("sampled size %s" % subsample_size)
print("information loss with best metric %s" % loss_best_metric)
print("information loss with generic metric %s" % loss_generic_metric)
print("information loss with learned metric %s" % loss_learned_metric)
print("information loss with learned metric deep %s" %
(loss_learned_metric_deep))
return (sanitized_profile_best, sanitized_profile_baseline,
sanitized_profile,
sanitized_profile_deep), (loss_best_metric, loss_generic_metric,
loss_learned_metric,
loss_learned_metric_deep), subsample_size
def evaluation_occupancy_window(n):
# step 1: get the database to be published
day_profile1 = pd.read_pickle('./dataset/dataframe_all_binary.pkl')
day_profile1 = day_profile1.fillna(0)
day_profile = day_profile1.iloc[0:90,0::60]
day_profile2 = day_profile1.iloc[90:135,0::60]
day_profile.dropna()
day_profile2.dropna()
rep_mode = 'mean'
anonymity_level = n # desired anonymity level
# step 2: data user specifies his/her interest. In the example, the data user is interested in preserving the
# information of a segment of entire time series. In this case, he/she would also need to specify the starting and
# ending time of the time series segment of interest.
interest = 'segment'
window = [11,15] # window specifies the starting and ending time of the period that the data user is interested in
# step 3: pre-sanitize the database
sanitized_profile_best = util.sanitize_data(day_profile, distance_metric = 'self-defined',
anonymity_level = anonymity_level, rep_mode = rep_mode,
mode = interest, window = window)
sanitized_profile_baseline = util.sanitize_data(day_profile, distance_metric='euclidean',
anonymity_level=anonymity_level, rep_mode = rep_mode)
loss_best_metric = pe.get_information_loss(data_gt=day_profile, data_sanitized=sanitized_profile_best,
window=window)
loss_generic_metric = pe.get_information_loss(data_gt=day_profile,
data_sanitized=sanitized_profile_baseline.round(),
window=window)
df_subsampled_from = day_profile2.sample(frac=1)
subsample_size_max = int(comb(len(df_subsampled_from),2))
print('total number of pairs is %s' % len(df_subsampled_from))
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max))
sp = Subsampling(data=df_subsampled_from)
data_pair, data_pair_all_index = sp.uniform_sampling(subsample_size=subsample_size, seed = None)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest=interest, window=window)
similarity_label, data_subsample = sim.label_via_silhouette_analysis(range_n_clusters=range(2,8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
lm = Linear_Metric()
lm.train(data_pair, similarity_label)
dm = Deep_Metric()
dm.train(data_pair, similarity_label)
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
# lam_vec is a set of candidate lambda's for weighting the l1-norm penalty in the metric learning optimization problem.
# The lambda that achieves lowest testing error will be selected for generating the distance metric
# step 6: the original database is privatized using the learned metric
sanitized_profile = util.sanitize_data(day_profile, distance_metric="deep",anonymity_level=anonymity_level,
rep_mode=rep_mode, deep_model=lm)
sanitized_profile_deep = util.sanitize_data(day_profile, distance_metric="deep",anonymity_level=anonymity_level,
rep_mode=rep_mode, deep_model=dm)
# (optionally for evaluation purpose) Evaluating the information loss of the sanitized database
loss_learned_metric = pe.get_information_loss(data_gt=day_profile,
data_sanitized=sanitized_profile.round(),
window=window)
loss_learned_metric_deep = pe.get_information_loss(data_gt=day_profile,
data_sanitized=sanitized_profile_deep.round(),
window=window)
print('anonymity level %s' % anonymity_level)
print("sampled size %s" % subsample_size)
print("information loss with best metric %s" % loss_best_metric)
print("information loss with generic metric %s" % loss_generic_metric)
print("information loss with learned metric %s" % loss_learned_metric)
print("information loss with learned metric deep %s" % (loss_learned_metric_deep))
return (sanitized_profile_best, sanitized_profile_baseline, sanitized_profile, sanitized_profile_deep), (loss_best_metric, loss_generic_metric, loss_learned_metric, loss_learned_metric_deep), subsample_size
def evaluation_occupancy_window(n, df_subsampled_from, day_profile):
rep_mode = 'mean'
anonymity_level = n # desired anonymity level
interest = 'segment'
window = [11, 15]
subsample_size_max = int(comb(len(df_subsampled_from), 2))
# step 4: sample a subset of pre-sanitized database and form the data points into pairs
subsample_size = int(round(subsample_size_max))
sp = Subsampling(data=df_subsampled_from)
data_pair, data_pair_all_index = sp.uniform_sampling(
subsample_size=subsample_size, seed=None)
# User receives the data pairs and label the similarity
sim = Similarity(data=data_pair)
sim.extract_interested_attribute(interest=interest, window=window)
similarity_label, data_subsample = sim.label_via_silhouette_analysis(
range_n_clusters=range(2, 8))
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
lm = Linear_Metric()
lm.train(data_pair, similarity_label)
dm = Deep_Metric()
dm.train(data_pair, similarity_label)
# step 5: PAD learns a distance metric that represents the interest of the user from the labeled data pairs
# lam_vec is a set of candidate lambda's for weighting the l1-norm penalty in the metric learning optimization problem.
# The lambda that achieves lowest testing error will be selected for generating the distance metric
# step 6: the original database is privatized using the learned metric
sanitized_profile = util.sanitize_data(day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=lm)
sanitized_profile_deep = util.sanitize_data(
day_profile,
distance_metric="deep",
anonymity_level=anonymity_level,
rep_mode=rep_mode,
deep_model=dm)
# (optionally for evaluation purpose) Evaluating the information loss of the sanitized database
loss_learned_metric = pe.get_information_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile.round(),
window=window)
loss_learned_metric_deep = pe.get_information_loss(
data_gt=day_profile,
data_sanitized=sanitized_profile_deep.round(),
window=window)
print('anonymity level %s' % anonymity_level)
print("sampled size %s" % subsample_size)
print("information loss with best metric %s" % loss_best_metric)
print("information loss with generic metric %s" % loss_generic_metric)
print("information loss with learned metric %s" % loss_learned_metric)
print("information loss with learned metric deep %s" %
(loss_learned_metric_deep))
return (sanitized_profile_best, sanitized_profile_baseline,
sanitized_profile,
sanitized_profile_deep), (loss_best_metric, loss_generic_metric,
loss_learned_metric,
loss_learned_metric_deep), subsample_size