def calculate_information_gain_star(dataset, classification_file, rule_set, rule_number):
if 'users' in dataset:
df_dataset = pandas.read_csv(dataset)
attribute = rules.attributes(rule_set,rule_number)
if isinstance(attribute,list):
attribute_list = []
attrs = df_dataset[attribute].values
for attr in attrs:
rule_output = rules.rules(rule_set, rule_number, attr)
if rule_output == 1:
number_satisfied = 1
else:
number_satisfied = 0
attribute_list.append(number_satisfied)
else:
attribute_list = df_dataset[attribute].values
df_classification = pandas.read_csv(classification_file)
classification_list = df_classification['class'].values
print(classification_list)
print(attribute_list)
information_gain_star = info_gain.info_gain(classification_list, attribute_list)
else:
attribute = rules.attributes(rule_set, rule_number)
df_dataset = pandas.read_csv(dataset)
user_id_list = list(set(df_dataset['user_id'].values))
df_classification = pandas.read_csv(classification_file)
attr_values = []
real_classes = []
for user_id in user_id_list:
df_user = df_dataset.loc[df_dataset['user_id'] == user_id]
attribute_list = df_user[attribute].values
attribute_value = attribute_list[0]
number_satisfied = 0
if rule_number == 22:
number_satisfied = len(df_user[attribute].unique())
elif rule_number == 3 and rule_set == 'social_bakers':
number_satisfied = df_user[attribute].value_counts().max()
else:
for attr in attribute_list:
rule_output = rules.rules(rule_set, rule_number, attr)
if rule_output == 1:
number_satisfied += 1
attr_values.append(number_satisfied)
df_class = df_classification.loc[df_classification['id'] == user_id]
real_class = df_class['class'].values[0]
real_classes.append(real_class)
information_gain_star = info_gain.info_gain(real_classes, attr_values)
return information_gain_star
def check_rule(rule_set, number, row):
attribute = rules.attributes(rule_set, number)
if isinstance(attribute, list):
attribute_value = []
for attr in attribute:
attribute_value.append(row[attr])
else:
attribute_value = row[attribute]
rule_output = rules.rules(rule_set, number, attribute_value)
return rule_output
def check_rule(rule_set, number, rules_dict, row):
attribute = rules.attributes(rule_set, number)
if isinstance(attribute, list):
attribute_value = []
for attr in attribute:
attribute_value.append(row[attr])
else:
attribute_value = row[attribute]
rule_output = rules.rules(rule_set, number, attribute_value)
if rule_output == 1:
rule_index = 'rule_' + str(number)
rules_dict[rule_index] = True
return rules_dict
def check_vdb_rule(rule_set, number, row, df_row):
rule_satisfied = 0
attribute = rules.attributes(rule_set, number)
if number == 4:
attribute_value = []
attribute_value.append(row[attribute])
attribute_value.append(df_row[attribute])
elif number == 3:
attribute_value = df_row
else:
if isinstance(attribute, list):
attribute_value = []
for attr in attribute:
attribute_value.append(row[attr])
else:
attribute_value = row[attribute]
rule_output = rules.rules(rule_set, number, attribute_value)
return rule_output
def calculate_pearson_correlation_coefficient_star(bas_dataset, classification_file, rule_set, rule_number):
#calculate pearson correlation coefficient * for a non-numerical attribute of the users dataset
if 'users' in bas_dataset and ((rule_number in [2,3,4,9] and rule_set == 'camsani_calzolari') or (rule_number in [1,4] and rule_set == 'van_den_beld')):
attribute = rules.attributes(rule_set, rule_number)
df_dataset = pandas.read_csv(bas_dataset)
attribute_list = df_dataset[attribute].values
attr_values = []
for attr in attribute_list:
if rule_number == 4:
rule_output = rules.rules(rule_set, rule_number, [attr, df_dataset[attribute]])
else:
rule_output = rules.rules(rule_set, rule_number, attr)
if rule_output == 1:
number_satisfied = 1
else:
number_satisfied = 0
attr_values.append(number_satisfied)
df_attr = pandas.DataFrame(attr_values, columns =[attribute])
df_classification = pandas.read_csv(classification_file)
df_class = df_classification['class']
df_pcc_star = pandas.concat([df_attr, df_class], axis=1)
pearson_correlation_coefficient_star = df_pcc_star.corr(method='pearson')
#calculate pearson correlation coefficient * for a numerical attribute of the users dataset
elif 'users' in bas_dataset:
attribute = rules.attributes(rule_set, rule_number)
df_dataset = pandas.read_csv(bas_dataset)
df_attribute = df_dataset[attribute]
df_numerical_attribute = df_attribute.fillna(0)
df_classification = pandas.read_csv(classification_file)
df_class = df_classification['class']
df_pcc_star = pandas.concat([df_numerical_attribute, df_class], axis=1)
pearson_correlation_coefficient_star = df_pcc_star.corr(method='pearson')
#calculate pearson correlation coefficient * for an attribute of the tweets dataset
else:
attribute = rules.attributes(rule_set, rule_number)
df_dataset = pandas.read_csv(bas_dataset)
user_id_list = list(set(df_dataset['user_id'].values))
df_classification = pandas.read_csv(classification_file)
attr_values = []
real_classes = []
for user_id in user_id_list:
df_user = df_dataset.loc[df_dataset['user_id'] == user_id]
attribute_list = df_user[attribute].values
attribute_value = attribute_list[0]
number_satisfied = 0
if rule_number == 22:
number_satisfied = len(df_user[attribute].unique())
elif rule_number == 3 and rule_set == 'social_bakers':
number_satisfied = df_user[attribute].value_counts().max()
else:
for attr in attribute_list:
rule_output = rules.rules(rule_set, rule_number, attr)
if rule_output == 1:
number_satisfied += 1
attr_values.append(number_satisfied)
df_class = df_classification.loc[df_classification['id'] == user_id]
real_class = df_class['class'].values
real_classes.append(real_class)
df_attr = pandas.DataFrame(attr_values, columns =[attribute])
df_cl = pandas.DataFrame(real_classes, columns =['class'])
df_pcc_star = pandas.concat([df_attr, df_cl], axis=1)
pearson_correlation_coefficient_star = df_pcc_star.corr(method='pearson')
return pearson_correlation_coefficient_star