added test cases

src/lang_main/analysis/shared.py

@@ -5,9 +5,6 @@ from typing import cast
 import networkx as nx
 import numpy as np
 import numpy.typing as npt
-
-# import sentence_transformers # TODO check removal
-# import sentence_transformers.util # TODO check removal
 from networkx import Graph
 from pandas import DataFrame, Series
 from sentence_transformers import SentenceTransformer

src/lang_main/analysis/timeline.py

@@ -47,7 +47,7 @@ def _non_relevant_obj_ids(
         feats_per_obj_id = feats_per_obj_id.dropna()
         unique_feats_per_obj_id = len(feats_per_obj_id.unique())
 
-        if unique_feats_per_obj_id > thresh_unique_feat_per_id:
+        if unique_feats_per_obj_id >= thresh_unique_feat_per_id:
             ids_to_ignore.add(obj_id)
 
     return tuple(ids_to_ignore)

src/lang_main/model_loader.py

@@ -119,7 +119,7 @@ def _preprocess_STFR_model_name(
             raise FileNotFoundError(
                 f'Target model >{model_name}< not found under {model_path}'
             )
-        model_name_or_path = str(model_path)
+        model_name_or_path = str(model_path)  # pragma: no cover
     else:
         model_name_or_path = model_name
 

src/lang_main/pipelines/predefined.py

@@ -30,11 +30,12 @@ from lang_main.constants import (
     DATE_COLS,
     FEATURE_NAME_OBJ_ID,
     FEATURE_NAME_OBJ_TEXT,
+    MAX_EDGE_NUMBER,
     MODEL_INPUT_FEATURES,
     NAME_DELTA_FEAT_TO_REPAIR,
     SAVE_PATH_FOLDER,
+    TARGET_FEATURE,
     THRESHOLD_AMOUNT_CHARACTERS,
-    THRESHOLD_EDGE_NUMBER,
     THRESHOLD_NUM_ACTIVITIES,
     THRESHOLD_SIMILARITY,
     THRESHOLD_TIMELINE_SIMILARITY,
@@ -72,7 +73,7 @@ def build_base_target_feature_pipe() -> Pipeline:
     pipe_target_feat.add(
         entry_wise_cleansing,
         {
-            'target_features': ('VorgangsBeschreibung',),
+            'target_features': (TARGET_FEATURE,),
             'cleansing_func': clean_string_slim,
         },
         save_result=True,
@@ -81,7 +82,7 @@ def build_base_target_feature_pipe() -> Pipeline:
     pipe_target_feat.add(
         analyse_feature,
         {
-            'target_feature': 'VorgangsBeschreibung',
+            'target_feature': TARGET_FEATURE,
         },
         save_result=True,
     )
@@ -140,7 +141,7 @@ def build_tk_graph_post_pipe() -> Pipeline:
     pipe_graph_postprocessing.add(
         graphs.filter_graph_by_number_edges,
         {
-            'limit': THRESHOLD_EDGE_NUMBER,
+            'limit': MAX_EDGE_NUMBER,
             'property': 'weight',
         },
     )