configurationfile.cof

# MAIN function
[CLUSTER]
filename = "train_set.txt"    
clusters = 14
max = 0.9
min = 3
chars = ["-","\.","/","_","%%"]


# filename: string 
#               the name of log file you want to deal with
#
# clusters: int
#       the number of cluster you want to get
#
# max: float in range [0.0, 1.0] or int, default=1.0, 
#       When building the vocabulary ignore terms that have a 
#       document frequency strictly higher than the given threshold 
#       (corpus-specific stop words). If float, the parameter 
#       represents a proportion of documents, integer absolute counts.
#
# min: float in range [0.0, 1.0] or int, default=1
#       When building the vocabulary ignore terms that have a document 
#       frequency strictly lower than the given threshold. This value 
#       is also called cut-off in the literature. If float, the parameter 
#       represents a proportion of documents, integer absolute counts. 
#
# chars: list of string, the chars not used for split log
#