restructuring project

.gitignore

@@ -4,6 +4,14 @@ data/
 datasets/
 **/spacy*/output/
 **/iframe_figures/
+reports/
+logs/
+profiling/
+misc/
+docs/
+
+# config
+*.code-workspace
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

lang_main_config_old.toml

@@ -1,59 +0,0 @@
-# d-opt -- lang_main: config file
-
-[paths]
-inputs = './lang-data/in/'
-results = './lang-data/out/'
-models = './lang-models'
-
-[models]
-use_large_model = true
-
-[logging]
-enabled = true
-stderr = true
-file = true
-
-# control which pipelines are executed
-[control]
-preprocessing_skip = false
-token_analysis_skip = false
-graph_postprocessing_skip = false
-graph_rescaling_skip = false
-graph_static_rendering_skip = true
-time_analysis_skip = true
-
-[preprocess]
-date_cols = [
-    "VorgangsDatum",
-    "ErledigungsDatum",
-    "Arbeitsbeginn",
-    "ErstellungsDatum",
-]
-target_feature = "VorgangsBeschreibung"
-threshold_amount_characters = 5
-threshold_similarity = 0.92
-
-[graph_postprocessing]
-max_edge_number = -1
-
-[time_analysis.uniqueness]
-threshold_unique_texts = 5
-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]'
-name_delta_feat_to_next_failure = 'Zeitspanne bis zum nächsten Ereignis [Tage]'
-
-[time_analysis.model_input]
-input_features = [
-    'VorgangsBeschreibung',
-]
-activity_feature = 'VorgangsTypName'
-activity_types = [
-    'Reparaturauftrag (Portal)',
-    'Störungsmeldung',
-]
-threshold_num_activities = 1
-threshold_similarity = 0.8

python/README.txt

@@ -1 +0,0 @@
-only used to simulate directory tree in final solution