def test_misses_cost_with_pgbs(self):
# Sensitive closed itemsets whose support needs to be reduced
sensitive_IS = {frozenset(['1', '2']), frozenset(['4'])}
# PGBS needs input in this format
sensitive_IL = pd.DataFrame(
{'itemset': [list(l) for l in sensitive_IS],
'threshold': [self.sigma_min, self.sigma_min]})
original_database = self.basket_sets.copy()
modified_database = self.basket_sets.copy()
# No return value, instead it modifies input database in place
pgbs(modified_database, sensitive_IL)
# Get all itemsets and supports in D (original_database)
sigma_model = 1 / len(original_database)
original_IS = fpgrowth(original_database, min_support=sigma_model, use_colnames=True, verbose=False)
# Get all itemsets and supports in D' (modified_database)
mofidied_F_IS = fpgrowth(modified_database, min_support=sigma_model, use_colnames=True, verbose=False)
# Find set of non-sensitive frequent itemsets in D
a = remove_sensitive_subsets(original_IS, self.sensitive_IS)
# Find set of non-sensitive frequent itemsets in D'
b = remove_sensitive_subsets(mofidied_F_IS[mofidied_F_IS["support"] >= self.sigma_min], self.sensitive_IS)
mc = misses_cost(a, b)
self.assertEqual(mc, 0.18181818181818182)
def test_misses_cost_with_rps(self):
# Produce a sanitised DB with sensitive IS's support below sigma_min
sanitized_closed_IS = rps(model=self.original_Closed_IS,
sensitiveItemsets=self.sensitive_IS,
supportThreshold=self.sigma_min)
# Convert from closed to frequent itemsets
sanitised_F_IS = itemsets_from_closed_itemsets(closed_itemsets=sanitized_closed_IS,
possible_itemsets=self.original_IS['itemsets'])
# Find set of non-sensitive frequent itemsets in D
a = remove_sensitive_subsets(self.original_Freq_IS, self.sensitive_IS)
# Find set of non-sensitive frequent itemsets in D'
b = remove_sensitive_subsets(sanitised_F_IS[sanitised_F_IS["support"] >= self.sigma_min], self.sensitive_IS)
mc = misses_cost(a, b)
self.assertEqual(mc, 0.0)
def main(datasets, algorithm, i):
#Create the base of a table
table_11 = pd.DataFrame(columns=[
'Model', 'Support threshold', 'Model threshold', 'Sensitive itemsets',
'Number of FI before sanitization',
'Number of FI containing an element of S before sanitization',
'Information loss expected', 'Number of FI after sanitization',
'Number of FI containing an element of S after RPS', 'Hiding failure',
'Artifactual patterns', 'Misses cost', 'Side effects factor',
'Information loss', 'RPS Time'
])
table_10 = pd.DataFrame(columns=[
'Dataset', 'Model threshold', 'Number of Closed frequent itemsets',
'Number of frequent itemsets', 'Time closed itemsets'
])
#Loop through datasets
for dataset in datasets:
sigma_model = datasets[dataset][0]
#Load dataset
data = im.import_dataset(dataset)
data = data.astype('bool') #This may be needed for some datasets
print("\n", dataset, "imported\n")
#Start total timer
total_time_start = time.time()
#Convert to closed itemsets
current_model, freq_model = get_closed_itemsets(data, sigma_model)
new_row = {
'Dataset': dataset,
'Model threshold': sigma_model,
'Number of Closed frequent itemsets': len(current_model),
'Number of frequent itemsets': len(freq_model),
'Time closed itemsets': time.time() - total_time_start
}
print(new_row)
table_10 = table_10.append(new_row, ignore_index=True)
table_10.to_csv('table_10.csv')
#Loop through support thresholds
for sigma_min in datasets[dataset][1:]:
print("\n", dataset, "FI:", sigma_min)
#Find original frequent itemsets at frequency sigma min
freq_original = freq_model.loc[freq_model["support"] >= sigma_min]
for k_freq in [10, 30]:
print("-", dataset, ":", k_freq, "Sensitive itemsets")
#Copy the model so we can edit it directly
copied_model = current_model.copy()
#We pick sensitive itemsets here
sensitive_IS = get_top_k_sensitive_itemsets(
freq_original, k_freq)
num_FI_containing_S = count_FI_containing_S(
freq_original, sensitive_IS)
if algorithm == "RPS":
#Start timer for RPS portion
total_time_start = time.time()
#Run RPS
sanitized_closed_IS = rps(model=copied_model,
sensitiveItemsets=sensitive_IS,
supportThreshold=sigma_min)
elif algorithm == "MRPS":
#Convert to pandas format for MRPS input
sensitive_IS_pandas = pd.DataFrame(
data=[(sensitive_IS),
np.full((len(sensitive_IS)), sigma_min),
np.full((len(sensitive_IS)), sigma_min - 0.5 *
(sigma_min - sigma_model))]).T
sensitive_IS_pandas.columns = [
'itemset', 'upper_threshold', 'lower_threshold'
]
#Start timer for RPS portion
total_time_start = time.time()
#Run RPS random threshold
sanitized_closed_IS = rps_two_thresholds(
model=copied_model,
sensitiveItemsets=sensitive_IS_pandas)
#Reproduce frequent itemsets
sanitized_DB = itemsets_from_closed_itemsets(
closed_itemsets=sanitized_closed_IS,
possible_itemsets=freq_model['itemsets'])
rps_time = time.time()
#Calculating metrics
#Variables needed
freq_sanitized = sanitized_DB.loc[
sanitized_DB["support"] >= sigma_min]
#Sensitive subsets of frequent itemsets
freq_sanitized_sensitive = get_sensitive_subsets(
freq_sanitized, sensitive_IS)
freq_original_sensitive = get_sensitive_subsets(
freq_original, sensitive_IS)
#Non sensitive subset of frequent itemsets
freq_sanitized_nonsensitive = remove_sensitive_subsets(
freq_sanitized, sensitive_IS)["itemsets"]
freq_original_nonsensitive = remove_sensitive_subsets(
freq_original, sensitive_IS)["itemsets"]
#Calculation of metrics
hiding_f = hiding_failure(freq_original_sensitive["itemsets"],
freq_sanitized_sensitive["itemsets"])
artifactual_p = artifactual_patterns(
set(freq_original["itemsets"]),
set(freq_sanitized["itemsets"]))
misses_c = misses_cost(freq_original_nonsensitive.copy(),
freq_sanitized_nonsensitive.copy())
side_effect_fac = side_effects_factor(
set(freq_original["itemsets"]),
set(freq_sanitized["itemsets"]),
set(freq_original_sensitive["itemsets"]))
#Information loss between frequent itemsets in original and sanitized at sigma model
information_l = information_loss(freq_model.copy(),
sanitized_DB)
#Expected information loss if all sensitive frequent itemsets had their support reduced to sigma min
expected_information_l = expected_information_loss(
freq_model.copy(), freq_original_sensitive.copy(),
sigma_min)
#Calculate the end time of this iteration
end_time = rps_time - total_time_start
#Threshold sanitized database by threshold_min to get frequent itemsets
print(f'- RPS time: {end_time}')
#Plot support graphs
dual_support_graph_distribution(
freq_model, sanitized_DB, sigma_model, dataset + "_" +
str(i) + "_" + str(sigma_min) + "_" + str(k_freq))
#Find number of FI in sanitized database containing sensitive itemsets
num_FI_containing_S_RPS = count_FI_containing_S(
freq_sanitized, sensitive_IS)
#Add to row of table
new_row = {
'Model': dataset,
'Model threshold': sigma_model,
'Support threshold': sigma_min,
'Sensitive itemsets': k_freq,
'Number of FI before sanitization': len(freq_original),
'Number of FI containing an element of S before sanitization':
num_FI_containing_S,
'Information loss expected': expected_information_l,
'Number of FI after sanitization': len(freq_sanitized),
'Number of FI containing an element of S after RPS':
num_FI_containing_S_RPS,
'Hiding failure': hiding_f,
'Artifactual patterns': artifactual_p,
'Misses cost': misses_c,
'Side effects factor': side_effect_fac,
'Information loss': information_l,
'RPS Time': end_time
}
#Update after each one just so we are sure we are recording results
table_11 = table_11.append(new_row, ignore_index=True)
table_11.to_csv('table_11_' + str(i) + '.csv')
def main(datasets):
#Create the base of a table
table_11 = pd.DataFrame(columns=['Model',
'Support threshold',
'Model threshold',
'Sensitive itemsets',
'Number of FI before sanitization',
'Information loss expected',
'Number of FI after sanitization',
'Number of FI containing an element of S after RPS',
'Hiding failure',
'Artifactual patterns',
'Misses cost',
'Side effects factor',
'Information loss',
'PGBS time'])
#Loop through datasets
for dataset in datasets:
sigma_model = datasets[dataset][0]
#Load dataset
data = im.import_dataset(dataset)
data = data.astype('bool') #This may be needed for some datasets
print("\n", dataset, "imported\n")
#Get frequent itemsets
freq_model = fpgrowth(data, min_support=sigma_model, use_colnames=True)
#Loop through support thresholds
for sigma_min in datasets[dataset][1:]:
print("\n", dataset, "FI:", sigma_min)
#Find original frequent itemsets at frequency sigma min
freq_original = freq_model.loc[freq_model["support"] >= sigma_min]
for k_freq in [10, 30, 50]:
print("-", dataset, ":", k_freq, "Sensitive itemsets")
#Copy the transactions so we can edit it directly
copied_data = data.copy()
#We pick sensitive itemsets here
sensitive_IS = get_top_k_sensitive_itemsets(freq_original, k_freq)
#Start timer for PGBS portion
total_time_start = time.time()
#Convert to pandas format for PGBS input
sensitive_IS_pandas = pd.DataFrame(data=[(sensitive_IS), np.full((len(sensitive_IS)), sigma_min)]).T
sensitive_IS_pandas.columns = ['itemset', 'threshold']
#Run PGBS
print("Running PGBS")
pgbs(copied_data,sensitive_IS_pandas)
print("PGBS run")
pgbs_time = time.time()
sensitive_IS = convert_to_sets(sensitive_IS)
print("FPGrowth")
#Reproduce frequent itemsets
freq_model_sanitized = fpgrowth(copied_data, min_support=sigma_model, use_colnames=True)
#Calculating metrics
#Variables needed
freq_sanitized = freq_model_sanitized.loc[freq_model_sanitized["support"] >= sigma_min]
#Sensitive subsets of frequent itemsets
freq_sanitized_sensitive = get_sensitive_subsets(freq_sanitized, sensitive_IS)
freq_original_sensitive = get_sensitive_subsets(freq_original, sensitive_IS)
#Non sensitive subset of frequent itemsets
freq_sanitized_nonsensitive = remove_sensitive_subsets(freq_sanitized, sensitive_IS)["itemsets"]
freq_original_nonsensitive = remove_sensitive_subsets(freq_original, sensitive_IS)["itemsets"]
#Calculation of metrics
freq_original_sensitive.to_csv("original.csv")
freq_sanitized_sensitive.to_csv("sanitized.csv")
print("len:", len(freq_original_sensitive["itemsets"]), len(freq_sanitized_sensitive["itemsets"]))
hiding_f = hiding_failure(freq_original_sensitive["itemsets"], freq_sanitized_sensitive["itemsets"])
artifactual_p = artifactual_patterns(set(freq_original["itemsets"]), set(freq_sanitized["itemsets"]))
misses_c = misses_cost(freq_original_nonsensitive.copy(), freq_sanitized_nonsensitive.copy())
side_effect_fac = side_effects_factor(set(freq_original["itemsets"]), set(freq_sanitized["itemsets"]), set(freq_original_sensitive["itemsets"]))
#Information loss between frequent itemsets in original and sanitized at sigma model
information_l = information_loss(freq_model.copy(), freq_model_sanitized)
#Expected information loss if all sensitive frequent itemsets had their support reduced to sigma min
expected_information_l = expected_information_loss(freq_model.copy(), freq_original_sensitive.copy(), sigma_min)
#Calculate the end time of this iteration
end_time = pgbs_time - total_time_start
#Threshold sanitized database by threshold_min to get frequent itemsets
print(f'- PGBS time: {end_time}')
#Plot support graphs
dual_support_graph_distribution(freq_model, freq_model_sanitized, sigma_model, dataset+"_PGBS_"+str(sigma_min)+"_"+str(k_freq))
#Find number of FI in sanitized database containing sensitive itemsets
num_FI_containing_S_RPS = count_FI_containing_S(freq_sanitized, sensitive_IS)
#Add to row of table
new_row = {'Model': dataset,
'Model threshold': sigma_model,
'Support threshold': sigma_min,
'Sensitive itemsets': k_freq,
'Number of FI before sanitization': len(freq_original),
'Information loss expected': expected_information_l,
'Number of FI after sanitization': len(freq_sanitized),
'Number of FI containing an element of S after RPS': num_FI_containing_S_RPS,
'Hiding failure': hiding_f,
'Artifactual patterns': artifactual_p,
'Misses cost': misses_c,
'Side effects factor': side_effect_fac,
'Information loss': information_l,
'PGBS time': end_time}
#Update after each one just so we are sure we are recording results
table_11 = table_11.append(new_row, ignore_index=True)
table_11.to_csv('table_pgbs.csv')
def main(datasets):
#Create the base of a table
table_11 = pd.DataFrame(columns=[
'Model', 'Support threshold', 'Model threshold', 'Sensitive itemsets',
'Number of FI before sanitization', 'Information loss expected',
'Number of FI after sanitization',
'Number of FI containing an element of S after SWA', 'Hiding failure',
'Artifactual patterns', 'Misses cost', 'Side effects factor',
'Information loss', 'SWA time'
])
#Loop through datasets
for dataset in datasets:
#Loop through support thresholds #TODO: error running this in the normal way but
#It is not much of a slowdown for SWA to have this here
#Load dataset
sigma_model = datasets[dataset][0]
db = im.import_dataset(dataset)
db = db.astype('bool') #This may be needed for some datasets
print("\n", dataset, "imported")
#Get frequent itemsets
freq_model = fpgrowth(db, min_support=sigma_model, use_colnames=True)
for sigma_min in datasets[dataset][1:]:
print("\n", dataset, "FI:", sigma_min)
#Find original frequent itemsets at frequency sigma min
freq_original = freq_model.loc[freq_model["support"] >= sigma_min]
for k_freq in [10, 30, 50]:
data = im.convert_to_transaction(db)
print(dataset, ":", k_freq, "Sensitive itemsets")
#We pick sensitive itemsets here
sensitive_IS = get_top_k_sensitive_itemsets(
freq_original, k_freq)
#Start timer for SWA portion
total_time_start = time.time()
#Convert to pandas format for SWA input
sensitive_rules = get_disclosures(sensitive_IS, freq_model,
sigma_min)
#Run SWA
SWA(data, sensitive_rules, data.shape[0])
swa_time = time.time()
sensitive_IS = convert_to_sets(sensitive_IS)
data = im.convert_to_matrix(data)
#Reproduce frequent itemsets
freq_model_sanitized = fpgrowth(data,
min_support=sigma_model,
use_colnames=True)
#Calculating metrics
#Variables needed
freq_sanitized = freq_model_sanitized.loc[
freq_model_sanitized["support"] >= sigma_min]
#Sensitive subsets of frequent itemsets
freq_sanitized_sensitive = get_sensitive_subsets(
freq_sanitized, sensitive_IS)
freq_original_sensitive = get_sensitive_subsets(
freq_original, sensitive_IS)
#Non sensitive subset of frequent itemsets
freq_sanitized_nonsensitive = remove_sensitive_subsets(
freq_sanitized, sensitive_IS)["itemsets"]
freq_original_nonsensitive = remove_sensitive_subsets(
freq_original, sensitive_IS)["itemsets"]
#Calculation of metrics
freq_original_sensitive.to_csv("original.csv")
freq_sanitized_sensitive.to_csv("sanitized.csv")
print("- len:", len(freq_original_sensitive["itemsets"]),
len(freq_sanitized_sensitive["itemsets"]))
hiding_f = hiding_failure(freq_original_sensitive["itemsets"],
freq_sanitized_sensitive["itemsets"])
artifactual_p = artifactual_patterns(
set(freq_original["itemsets"]),
set(freq_sanitized["itemsets"]))
misses_c = misses_cost(freq_original_nonsensitive.copy(),
freq_sanitized_nonsensitive.copy())
side_effect_fac = side_effects_factor(
set(freq_original["itemsets"]),
set(freq_sanitized["itemsets"]),
set(freq_original_sensitive["itemsets"]))
#Information loss between frequent itemsets in original and sanitized at sigma model
information_l = information_loss(freq_model.copy(),
freq_model_sanitized)
#Expected information loss if all sensitive frequent itemsets had their support reduced to sigma min
expected_information_l = expected_information_loss(
freq_model.copy(), freq_original_sensitive.copy(),
sigma_min)
#Calculate the end time of this iteration
end_time = swa_time - total_time_start
#Threshold sanitized database by threshold_min to get frequent itemsets
print(f'- SWA time: {end_time}')
#Plot support graphs
dual_support_graph_distribution(
freq_model, freq_model_sanitized, sigma_model,
dataset + "_SWA_" + str(sigma_min) + "_" + str(k_freq))
#Find number of FI in sanitized database containing sensitive itemsets
num_FI_containing_S_RPS = count_FI_containing_S(
freq_sanitized, sensitive_IS)
#Add to row of table
new_row = {
'Model': dataset,
'Model threshold': sigma_model,
'Support threshold': sigma_min,
'Sensitive itemsets': k_freq,
'Number of FI before sanitization': len(freq_original),
'Information loss expected': expected_information_l,
'Number of FI after sanitization': len(freq_sanitized),
'Number of FI containing an element of S after SWA':
num_FI_containing_S_RPS,
'Hiding failure': hiding_f,
'Artifactual patterns': artifactual_p,
'Misses cost': misses_c,
'Side effects factor': side_effect_fac,
'Information loss': information_l,
'SWA time': end_time
}
#Update after each one just so we are sure we are recording results
table_11 = table_11.append(new_row, ignore_index=True)
table_11.to_csv('table_SWA.csv')