Apply suggestions from code review

🔥 add Pits suggestions

Co-authored-by: Pit Buttchereit <[email protected]>

tracex_project/extraction/logic/module.py

@@ -36,9 +36,9 @@ def execute(
         Executes the logic of the module. Override this to define your own module.
 
         Keyword arguments:
-        _input -- Any additional input to the module
-        patient_journey -- The patient journey as text
-        patient_journey_sentences -- The same patient journey as a list of sentences
+        _input -- Any additional input to the module.
+        patient_journey -- The patient journey as text.
+        patient_journey_sentences -- The same patient journey as a list of sentences.
         """
         self.patient_journey = patient_journey
         self.patient_journey_sentences = patient_journey_sentences
@@ -57,8 +57,8 @@ def execute_and_save(
         Executes the logic of the module and saves the result to the database. Override this to define your own module.
 
         Keyword arguments:
-        patient_journey -- The patient journey as text
-        patient_journey_sentences -- The same patient journey as a list of sentences
+        patient_journey -- The patient journey as text.
+        patient_journey_sentences -- The same patient journey as a list of sentences.
         """
         self.patient_journey = patient_journey
         self.patient_journey_sentences = patient_journey_sentences

tracex_project/extraction/logic/modules/module_activity_labeler.py

@@ -27,7 +27,7 @@ def execute(
         patient_journey: str = None,
         patient_journey_sentences: List[str] = None,
         cohort=None,
-    ):
+    ) -> pd.DataFrame:
         """
         Extracts the activity labels from the patient journey with the following steps:
         1. Number the patient journey sentences to enable selecting a specific range of sentences.
@@ -45,7 +45,7 @@ def execute(
         patient_journey_numbered: str = self.__number_patient_journey_sentences(
             patient_journey_sentences
         )
-        activity_labels = self.__extract_activities(patient_journey_numbered, condition)
+        activity_labels: pd.DataFrame = self.__extract_activities(patient_journey_numbered, condition)
 
         return activity_labels
 
@@ -65,7 +65,7 @@ def __number_patient_journey_sentences(patient_journey_sentences: List[str]) ->
         return patient_journey_numbered
 
     @staticmethod
-    def __extract_activities(patient_journey_numbered: str, condition: Optional[str]):
+    def __extract_activities(patient_journey_numbered: str, condition: Optional[str]) -> pd.DataFrame:
         """
         Converts a patient journey, where every sentence is numbered, to a DataFrame with the activity labels by
         extracting the activity labels from the patient journey.

tracex_project/extraction/logic/modules/module_event_type_classifier.py

@@ -29,7 +29,7 @@ def execute(
         patient_journey=None,
         patient_journey_sentences=None,
         cohort=None,
-    ):
+    ) -> pd.DataFrame:
         """Classifies corresponding event types for all activity labels in a dataframe."""
         super().execute(
             df,

tracex_project/extraction/logic/modules/module_location_extractor.py

@@ -27,7 +27,7 @@ def execute(
         patient_journey=None,
         patient_journey_sentences=None,
         cohort=None,
-    ):
+    ) -> pd.DataFrame:
         """Extracts the location information for each activity in a dataframe."""
         super().execute(
             df,

tracex_project/extraction/logic/modules/module_metrics_analyzer.py

@@ -31,7 +31,7 @@ def execute(
         patient_journey=None,
         patient_journey_sentences=None,
         cohort=None,
-    ):
+    ) -> pd.DataFrame:
         """Measures the output of the pipeline based on specified metrics.
         These metrics are 'activity relevance' and 'timestamp correctness'."""
         super().execute(

tracex_project/extraction/logic/modules/module_time_extractor.py

@@ -28,7 +28,7 @@ def execute(
         patient_journey=None,
         patient_journey_sentences: List[str] = None,
         cohort=None,
-    ):
+    ) -> pd.DataFrame:
         """This function extracts the time information from the patient journey.
         For each activity label, the start date, end date and duration are extracted."""
         super().execute(

tracex_project/extraction/logic/orchestrator.py

@@ -162,7 +162,7 @@ def initialize_modules(self):
         }
         return modules
 
-    def run(self, view=None):
+    def run(self, view=None) -> pd.DataFrame:
         """Run the modules and set default values for modules not executed."""
         modules = self.initialize_modules()
         execution_step: int = 1

tracex_project/tracex/logic/utils.py

@@ -208,7 +208,7 @@ def dataframe_to_xes(df, name, activity_key):
         return file_path
 
     @staticmethod
-    def text_to_sentence_list(text):
+    def text_to_sentence_list(text: str) -> List[str]:
         """Converts a text into a list of its sentences."""
         text = text.replace("\n", " ")
         # This regex looks for periods, question marks, or exclamation marks,
@@ -292,7 +292,7 @@ def set_default_timestamps(df):
         df["time:duration"] = "00:01:00"
 
     @staticmethod
-    def delete_metrics_columns(df: pd.DataFrame):
+    def delete_metrics_columns(df: pd.DataFrame) -> pd.DataFrame:
         """Delete metrics columns from the dataframe."""
         df = df.drop(
             columns=[