Pylint + Github workflow

.github/workflows/maven.yml

@@ -334,7 +334,8 @@ jobs:
           elif [[ ${{matrix.benchmark}} == anonymization ]]; then
             java -jar benchbase.jar -b tpcc -c config/mysql/sample_tpcc_config.xml --create=true --load=true --execute=false --json-histograms results/histograms.json
             java -jar benchbase.jar -b tpcc -c config/mysql/sample_${{matrix.benchmark}}_config.xml --anonymize=true
-            exit 0
+            mysql -h127.0.0.1 -P$MYSQL_PORT -uadmin -ppassword -e "RENAME TABLE item TO item_original,item_anonymized TO item;"
+            java -jar benchbase.jar -b tpcc -c config/mysql/sample_tpcc_config.xml --execute=true --json-histograms results/histograms.json
           elif [[ ${{matrix.benchmark}} == tpcc-with-reconnects ]]; then
             # See Also: WITH_SERVICE_INTERRUPTIONS=true docker/build-run-benchmark-with-docker.sh
             java -jar benchbase.jar -b tpcc -c config/mysql/sample_tpcc_config.xml --create=true --load=true

scripts/anonymization/src/anonymizer.py

@@ -4,19 +4,31 @@
 import sys
 import xml.etree.ElementTree as ET
 import pandas as pd
-from modules.jdbc_handler import JDBCHandler
+
 from configuration.config_parser import XMLParser
 from configuration.configurations import DPConfig, SensitiveConfig, ContinuousConfig
+
 from modules.dp_anonymizer import DifferentialPrivacyAnonymizer
 from modules.sensitive_anonymizer import SensitiveAnonymizer
-
+from modules.jdbc_handler import JDBCHandler
 
 def anonymize(
     dataset: pd.DataFrame,
     anon_config: DPConfig,
     cont_config: ContinuousConfig,
     sens_config: SensitiveConfig,
 ):
+    """Function that runs differential privacy and sensitive value anonymization
+
+    Args:
+        dataset (pd.DataFrame): The original dataset
+        anon_config (DPConfig): The Differential Privacy Configuration
+        cont_config (ContinuousConfig): The Configuration for Continuous Values
+        sens_config (SensitiveConfig): The Configuration for Sensitive Values
+
+    Returns:
+        pd.DataFrame: The Anonymized Dataset
+    """
 
     dp_data = dataset
     if anon_config:
@@ -36,6 +48,14 @@ def anonymize_db(
     sens_config: SensitiveConfig,
     cont_config: ContinuousConfig,
 ):
+    """Entry function that handles data pulling, anonymization and data pushing back to the DB
+
+    Args:
+        jdbc_handler (JDBCHandler): The JDBC Information
+        anon_config (DPConfig): The Differential Privacy Configuration
+        cont_config (ContinuousConfig): The Configuration for Continuous Values
+        sens_config (SensitiveConfig): The Configuration for Sensitive Values
+    """
 
     jdbc_handler.start_jvm()
 

scripts/anonymization/src/configuration/config_parser.py

@@ -44,7 +44,8 @@ def get_config(self):
         # Exit the program if not enough basic information (name of a table) is available
         if table_name is None:
             sys.exit(
-                "There was no name provided for the table that should be anonymized. Program is exiting now!"
+                "There was no name provided for the table that should be anonymized.\n"
+                + "Program is exiting now!"
             )
 
         print(f"Parsing config for table: {table_name}")

scripts/anonymization/src/modules/dp_anonymizer.py

@@ -1,16 +1,37 @@
+"""Module that handles differential privacy anonymization
+"""
+
 import time
+import pandas as pd
+
 from snsynth import Synthesizer
 from configuration.configurations import DPConfig,ContinuousConfig
-import pandas as pd
 from .preprocessor import Preprocessor
 
 class DifferentialPrivacyAnonymizer():
+    """A class that holds all necessary information for differential privacy anonymization
+
+    Attributes
+    ----------
+    dataset : pd.DataFrame
+        The full dataset
+    anon_config : DPConfig
+        The configuration of all columns of the dataset
+    cont_config : ContinuousConfig
+        The specific configuration of all continuous columns of the dataset
+    """
+
     def __init__(self,  dataset: pd.DataFrame, anon_config: DPConfig, cont_config: ContinuousConfig):
         self.dataset = dataset
         self.anon_config = anon_config
         self.cont_config = cont_config
 
     def run_anonymization(self):
+        """Function that runs differential privacy algorithms
+
+        Returns:
+            pd.DataFrame: The resulting differentially private dataset
+        """
 
         alg = self.anon_config.algorithm
         eps = float(self.anon_config.epsilon)
@@ -38,7 +59,7 @@ def run_anonymization(self):
                     categorical_columns=cat,
                     continuous_columns=cont,
                     ordinal_columns=ordi,
-                    transformer=Preprocessor(self.anon_config).getTransformer(
+                    transformer=Preprocessor(self.anon_config).get_transformer(
                         self.dataset, self.cont_config
                     ),
                     nullable=nullable_flag,
@@ -64,7 +85,6 @@ def run_anonymization(self):
 
         anon_data = self.__add_ignorable(anon_data,saved_indexes,saved_columns)
 
-
         return anon_data
 
     def __remove_ignorable(self):
@@ -83,4 +103,5 @@ def __add_ignorable(self,dataset,saved_indexes,saved_columns):
         ignore_columns = self.anon_config.column_classification.hidden
         for ind, col in enumerate(ignore_columns):
             dataset.insert(saved_indexes[ind], col, saved_columns[col])
-        return dataset
+        return dataset
+

scripts/anonymization/src/modules/preprocessor.py

@@ -1,13 +1,25 @@
+"""Module for data transformation
+"""
+
 from snsynth.transform import BinTransformer, TableTransformer
 
 from configuration.configurations import DPConfig, ContinuousConfig
 
 
 class Preprocessor:
+      """A class that transforms the dataset in order to 
+      allow differential privacy algorithms to work with the data
+
+    Attributes
+    ----------
+    config : DPConfig
+        The differential privacy parameters
+    """
+
     def __init__(self, config: DPConfig):
         self.config = config
 
-    def getTransformer(self, dataset, cont_config):
+    def get_transformer(self, dataset, cont_config):
         """Method that returns a TableTransformer object which can be used by DP mechansisms
 
         Args:
@@ -33,12 +45,12 @@ def getTransformer(self, dataset, cont_config):
             continuous_columns=self.config.column_classification.continuous,
             ordinal_columns=self.config.column_classification.ordinal,
             style=style,
-            constraints=self.getConstraints(cont_config, dataset),
+            constraints=self.get_constraints(cont_config, dataset),
         )
         print("Instantiated Transformer")
         return tt
 
-    def getConstraints(self,cont_config: ContinuousConfig, dataset):
+    def get_constraints(self,cont_config: ContinuousConfig, dataset):
         """Helper method that forms constraints from a list of continuous columns
 
         Args:
@@ -71,9 +83,9 @@ def getConstraints(self,cont_config: ContinuousConfig, dataset):
                 else:
                     max_bound = int(upper)
 
-            nullFlag = dataset[col_name].isnull().values.any()
+            null_flag = dataset[col_name].isnull().values.any()
             constraints[col_name] = BinTransformer(
-                bins=bins, lower=min_bound, upper=max_bound, nullable=nullFlag
+                bins=bins, lower=min_bound, upper=max_bound, nullable=null_flag
             )
 
         return constraints

scripts/anonymization/src/modules/sensitive_anonymizer.py

@@ -1,18 +1,34 @@
+"""Module for handling Sensitive Values
+"""
+
 import pandas as pd
-import xml.etree.ElementTree as ET
 
 from configuration.configurations import SensitiveConfig
 from faker import Faker
 
-
 class SensitiveAnonymizer:
+    """A class that holds all information for sensitive anonymization.
+
+    Attributes
+    ----------
+    dataset : pd.DataFrame
+        The full dataset
+    sens_config : SensitiveConfig
+        The configuration of the columns that are sensitive
+    """
+
     def __init__(
         self, dataset: pd.DataFrame, sens_config: SensitiveConfig
     ):
         self.dataset = dataset
         self.sens_config = sens_config
 
     def run_anonymization(self):
+        """Function that runs the actual anonymization of sensitive values
+
+        Returns:
+            pd.DataFrame: A dataset with anonymized sensitive values
+        """
         anon_data = self.dataset.copy()
 
         if self.sens_config:
@@ -63,4 +79,5 @@ def __fake_column(self,
 
         fake.unique.clear()
 
-        return dataset
+        return dataset
+

scripts/anonymization/src/test.py

@@ -43,7 +43,9 @@
 
 
 def test_full_config():
-    """Test method for a full config with dp-anonymization, continuous and sensitive values"""
+    """
+    Test method for a full config with dp-anonymization,continuous and sensitive values
+    """
 
     parameters = ET.fromstring(FULL_CONFIG)
 
@@ -54,7 +56,7 @@ def test_full_config():
     assert anon_config is not None
     assert sens_config is not None
     assert cont_config is not None
-    
+
     dataset = pd.read_csv('test_table.csv')
 
     # Templates Path = None
@@ -79,4 +81,3 @@ def test_minimal_config():
     assert anon_config is not None
     assert sens_config is None
     assert cont_config is None
-