improved path_handling

scripts/lang_main_config.toml

@@ -1,9 +1,9 @@
 # lang_main: Config file
 
 [paths]
-inputs = 'A:/Arbeitsaufgaben/lang-main/scripts/inputs/'
+inputs = './inputs/'
-results = 'A:/Arbeitsaufgaben/lang-main/scripts/results/test_20240529/'
+results = './results/test_20240529/'
-dataset = 'A:/Arbeitsaufgaben/lang-main/data/02_202307/Export4.csv'
+dataset = '../data/02_202307/Export4.csv'
 #results = './results/Export7/'
 #dataset = './01_03_Rohdaten_202403/Export7_59499_Zeilen.csv'
 #results = './results/Export7_trunc/'

src/lang_main/__init__.py

@@ -26,7 +26,7 @@ USE_INTERNAL_CONFIG: Final[bool] = False
 pkg_dir = Path(__file__).parent
 cfg_path_internal = pkg_dir / CONFIG_FILENAME
 caller_file = Path(inspect.stack()[-1].filename)
-CALLER_PATH: Final[Path] = caller_file.parent
+CALLER_PATH: Final[Path] = caller_file.parent.resolve()
 
 # load config data: internal/external
 if USE_INTERNAL_CONFIG:

src/lang_main/constants.py

@@ -1,12 +1,15 @@
 from pathlib import Path
 from typing import Final
 
-from lang_main import CONFIG
+from lang_main import CALLER_PATH, CONFIG
 
 # ** paths
-INPUT_PATH_FOLDER: Final[Path] = Path(CONFIG['paths']['inputs'])
+input_path_conf = Path(CONFIG['paths']['inputs'])
-SAVE_PATH_FOLDER: Final[Path] = Path(CONFIG['paths']['results'])
+INPUT_PATH_FOLDER: Final[Path] = (CALLER_PATH / input_path_conf).resolve()
-PATH_TO_DATASET: Final[Path] = Path(CONFIG['paths']['dataset'])
+save_path_conf = Path(CONFIG['paths']['results'])
+SAVE_PATH_FOLDER: Final[Path] = (CALLER_PATH / save_path_conf).resolve()
+path_dataset_conf = Path(CONFIG['paths']['dataset'])
+PATH_TO_DATASET: Final[Path] = (CALLER_PATH / path_dataset_conf).resolve()
 # ** control
 DO_PREPROCESSING: Final[bool] = CONFIG['control']['preprocessing']
 SKIP_PREPROCESSING: Final[bool] = CONFIG['control']['preprocessing_skip']

tests/lang_main_config.toml

@@ -0,0 +1,56 @@
+# lang_main: Config file
+
+[paths]
+inputs = '../inputs/'
+results = './results/test_new2/'
+dataset = './01_2_Rohdaten_neu/Export4.csv'
+#results = './results/Export7/'
+#dataset = './01_03_Rohdaten_202403/Export7_59499_Zeilen.csv'
+#results = './results/Export7_trunc/'
+#dataset = './01_03_Rohdaten_202403/Export7_trunc.csv'
+
+[control]
+preprocessing = true
+preprocessing_skip = false
+token_analysis = false
+token_analysis_skip = false
+graph_postprocessing = false
+graph_postprocessing_skip = false
+time_analysis = false
+time_analysis_skip = false
+
+#[export_filenames]
+#filename_cossim_filter_candidates = 'CosSim-FilterCandidates'
+
+[preprocess]
+filename_cossim_filter_candidates = 'CosSim-FilterCandidates'
+date_cols = [
+    "VorgangsDatum", 
+    "ErledigungsDatum", 
+    "Arbeitsbeginn", 
+    "ErstellungsDatum",
+]
+threshold_amount_characters = 5
+threshold_similarity = 0.8
+
+[graph_postprocessing]
+threshold_edge_weight = 150
+
+[time_analysis.uniqueness]
+threshold_unique_texts = 4
+criterion_feature = 'HObjektText'
+feature_name_obj_id = 'ObjektID'
+
+[time_analysis.model_input]
+input_features = [
+    'VorgangsTypName',
+    'VorgangsArtText',
+    'VorgangsBeschreibung',
+]
+activity_feature = 'VorgangsTypName'
+activity_types = [
+    'Reparaturauftrag (Portal)',
+    'Störungsmeldung',
+]
+threshold_num_acitivities = 1
+threshold_similarity = 0.8

tests/pre_test_examples.py

@@ -1,15 +1,9 @@
-import re
+from lang_main.constants import (
+    INPUT_PATH_FOLDER,
+    PATH_TO_DATASET,
+    SAVE_PATH_FOLDER,
+)
 
-
+print(SAVE_PATH_FOLDER, '\n')
-string = """
+print(INPUT_PATH_FOLDER, '\n')
-Hallo mein Name ist Max Mustermann    und ich bin am 01.01.2024 geboren.
+print(PATH_TO_DATASET, '\n')
-"""
-
-patt = r'(\d{1,2}\.)?(\d{1,2}\.)([\d]{2,4})?'
-patt2 = r'[ ]{2,}'
-pattern = re.compile(patt)
-pattern2 = re.compile(patt2)
-res = pattern.sub('', string)
-res = pattern2.sub(' ', res)
-
-print(res)