attacks/privacy_attacks.py [217:242]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    elif params.dataset == 'adult':
        columns = ["age", "workClass", "fnlwgt", "education", "education-num","marital-status", "occupation", "relationship","race", "sex", "capital-gain", "capital-loss", "hours-per-week", "native-country", "income"]
        train_data = pd.read_csv(params.data_root+'/adult.data', names=columns, sep=' *, *', na_values='?')
        test_data  = pd.read_csv(params.data_root+'/adult.test', names=columns, sep=' *, *', skiprows=1, na_values='?')

        original_train=train_data
        original_test=test_data
        num_train = len(original_train)
        original = pd.concat([original_train, original_test])
        labels = original['income']
        labels = labels.replace('<=50K', 0).replace('>50K', 1)
        labels = labels.replace('<=50K.', 0).replace('>50K.', 1)

        # Remove target 
        del original["income"]

        data = adult_data_transform(original)
        train_data = data[:num_train]
        train_labels = labels[:num_train]
        test_data = data[num_train:]
        test_labels = labels[num_train:]

        test_data=torch.tensor(test_data.to_numpy()).float()
        train_data=torch.tensor(train_data.to_numpy()).float()
        test_labels=torch.tensor(test_labels.to_numpy(dtype='int64')).long()
        train_labels=torch.tensor(train_labels.to_numpy(dtype='int64')).long()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



datasets/__init__.py [268:294]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    elif params.dataset == 'adult':

        columns = ["age", "workClass", "fnlwgt", "education", "education-num","marital-status", "occupation", "relationship","race", "sex", "capital-gain", "capital-loss", "hours-per-week", "native-country", "income"]
        train_data = pd.read_csv(params.data_root+'/adult.data', names=columns, sep=' *, *', na_values='?')
        test_data  = pd.read_csv(params.data_root+'/adult.test', names=columns, sep=' *, *', skiprows=1, na_values='?')

        original_train=train_data
        original_test=test_data
        num_train = len(original_train)
        original = pd.concat([original_train, original_test])
        labels = original['income']
        labels = labels.replace('<=50K', 0).replace('>50K', 1)
        labels = labels.replace('<=50K.', 0).replace('>50K.', 1)

        # Remove target 
        del original["income"]

        data = adult_data_transform(original)
        train_data = data[:num_train]
        train_labels = labels[:num_train]
        test_data = data[num_train:]
        test_labels = labels[num_train:]

        test_data=torch.tensor(test_data.to_numpy()).float()
        train_data=torch.tensor(train_data.to_numpy()).float()
        test_labels=torch.tensor(test_labels.to_numpy(dtype='int64')).long()
        train_labels=torch.tensor(train_labels.to_numpy(dtype='int64')).long()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -