# 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