added test cases

src/lang_main/analysis/shared.py

@@ -112,8 +112,6 @@ def candidates_by_index(
     )
     # cosine similarity
     cos_sim = cast(npt.NDArray, model.similarity(embds, embds).numpy())
-    # TODO check removal
-    # cos_sim = cast(npt.NDArray, sentence_transformers.util.cos_sim(embds, embds).numpy())
     np.fill_diagonal(cos_sim, 0.0)
     cos_sim = np.triu(cos_sim)
     cos_sim_idx = np.argwhere(cos_sim >= cos_sim_threshold)

src/lang_main/analysis/timeline.py

@@ -142,7 +142,7 @@ def filter_activities_per_obj_id(
     threshold_num_activities: int = 1,
 ) -> tuple[DataFrame, Series]:
     data = data.copy()
-    # filter only relevant activities count occurrences for each ObjectID
+    # filter only relevant activities, count occurrences for each ObjectID
     logger.info('Filtering activities per ObjectID...')
     filt_rel_activities = data[activity_feature].isin(relevant_activity_types)
     data_filter_activities = data.loc[filt_rel_activities].copy()
@@ -249,6 +249,7 @@ def _transform_timeline_candidates(
 def _map_obj_id_to_texts(
     data: DataFrame,
     feature_obj_id: str = 'ObjektID',
+    feature_obj_text: str = 'HObjektText',
 ) -> dict[ObjectID, str]:
     data = data.copy()
     obj_ids = cast(Iterable[ObjectID], data[feature_obj_id].unique())
@@ -256,9 +257,9 @@ def _map_obj_id_to_texts(
     obj_id_to_text: dict[ObjectID, str] = {}
 
     for obj_id in tqdm(obj_ids):
-        data_per_obj = cast(DataFrame, data.loc[data['ObjektID'] == obj_id])
+        data_per_obj = cast(DataFrame, data.loc[data[feature_obj_id] == obj_id])
         # just take first entry
-        obj_text = cast(str, data_per_obj['HObjektText'].dropna().iat[0])
+        obj_text = cast(str, data_per_obj[feature_obj_text].dropna().iat[0])
         obj_text = obj_text.strip(r' ,.:')
         obj_id_to_text[obj_id] = obj_text
 
@@ -272,6 +273,7 @@ def get_timeline_candidates(
     model: SentenceTransformer,
     cos_sim_threshold: float,
     feature_obj_id: str = 'ObjektID',
+    feature_obj_text: str = 'HObjektText',
     model_input_feature: str = 'nlp_model_input',
 ) -> tuple[TimelineCandidates, dict[ObjectID, str]]:
     logger.info('Obtaining timeline candidates...')
@@ -290,6 +292,7 @@ def get_timeline_candidates(
     map_obj_text = _map_obj_id_to_texts(
         data=data,
         feature_obj_id=feature_obj_id,
+        feature_obj_text=feature_obj_text,
     )
     logger.info('ObjectIDs successfully mapped to text descriptors.')
 

src/lang_main/constants.py

@@ -145,6 +145,9 @@ UNIQUE_CRITERION_FEATURE: Final[str] = CONFIG['time_analysis']['uniqueness'][
     'criterion_feature'
 ]
 FEATURE_NAME_OBJ_ID: Final[str] = CONFIG['time_analysis']['uniqueness']['feature_name_obj_id']
+FEATURE_NAME_OBJ_TEXT: Final[str] = CONFIG['time_analysis']['uniqueness'][
+    'feature_name_obj_text'
+]
 # ** time_analysis.preparation
 # NAME_DELTA_FEAT_TO_REPAIR: Final[str] = 'delta_to_repair'
 CONFIG['time_analysis']['preparation']['name_delta_feat_to_repair']

src/lang_main/lang_main_config.toml

@@ -42,6 +42,7 @@ threshold_edge_number = 330
 threshold_unique_texts = 4
 criterion_feature = 'HObjektText'
 feature_name_obj_id = 'ObjektID'
+feature_name_obj_text = 'HObjektText'
 
 [time_analysis.preparation]
 name_delta_feat_to_repair = 'Zeitspanne bis zur Behebung [Tage]'

src/lang_main/pipelines/predefined.py

@@ -29,6 +29,7 @@ from lang_main.constants import (
     CYTO_BASE_NETWORK_NAME,
     DATE_COLS,
     FEATURE_NAME_OBJ_ID,
+    FEATURE_NAME_OBJ_TEXT,
     MODEL_INPUT_FEATURES,
     NAME_DELTA_FEAT_TO_REPAIR,
     SAVE_PATH_FOLDER,
@@ -287,6 +288,7 @@ def build_timeline_pipe() -> Pipeline:
             'model': STFR_MODEL,
             'cos_sim_threshold': THRESHOLD_TIMELINE_SIMILARITY,
             'feature_obj_id': FEATURE_NAME_OBJ_ID,
+            'feature_obj_text': FEATURE_NAME_OBJ_TEXT,
             'model_input_feature': 'nlp_model_input',
         },
         save_result=True,