tom-plugin/lang_main_config_old2.toml
2025-01-23 12:05:13 +01:00

63 lines
1.4 KiB
TOML

# lang_main: Config file
[paths]
inputs = './lang-data/in'
# results = './results/dummy_N_1000/'
# dataset = '../data/Dummy_Dataset_N_1000.csv'
results = './lang-data/out'
models = './lang-models/converted'
[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 = false
time_analysis_skip = true
[preprocess]
date_cols = [
"VorgangsDatum",
"ErledigungsDatum",
"Arbeitsbeginn",
"ErstellungsDatum",
]
threshold_amount_characters = 5
threshold_similarity = 0.8
[graph_postprocessing]
threshold_edge_number = 500
# threshold_edge_weight = 150
[time_analysis.uniqueness]
threshold_unique_texts = 4
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 = [
# 'VorgangsTypName',
# 'VorgangsArtText',
# 'VorgangsBeschreibung',
# ]
input_features = [
'VorgangsBeschreibung',
]
activity_feature = 'VorgangsTypName'
activity_types = [
'Reparaturauftrag (Portal)',
'Störungsmeldung',
]
threshold_num_acitivities = 1
threshold_similarity = 0.8