# lang_main: Config file

[paths]
inputs = './inputs/'
# results = './results/dummy_N_1000/'
# dataset = '../data/Dummy_Dataset_N_1000.csv'
results = './results/test_20240807/'
dataset = '../data/02_202307/Export4.csv'

[logging]
enabled = true
stderr = true
file = true

# only debugging features, production-ready pipelines should always
# be fully executed
[control]
preprocessing_skip = false
token_analysis_skip = true
graph_postprocessing_skip = true
graph_rescaling_skip = true
graph_static_rendering_skip = true
time_analysis_skip = true

[preprocess]
date_cols = [
    "VorgangsDatum",
    "ErledigungsDatum",
    "Arbeitsbeginn",
    "ErstellungsDatum",
]
threshold_amount_characters = 5
threshold_similarity = 0.8

[graph_postprocessing]
threshold_edge_number = 330
# threshold_edge_weight = 150

[time_analysis.uniqueness]
threshold_unique_texts = 4
criterion_feature = 'HObjektText'
feature_name_obj_id = 'ObjektID'

[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 = [
#     'VorgangsTypName',
#     'VorgangsArtText',
#     'VorgangsBeschreibung',
# ]
input_features = [
    'VorgangsBeschreibung',
]
activity_feature = 'VorgangsTypName'
activity_types = [
    'Reparaturauftrag (Portal)',
    'Störungsmeldung',
]
threshold_num_acitivities = 1
threshold_similarity = 0.8