forked from KEMT/zpwiki
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
# load data
|
|
|
|
filename = 'ner/skner/skner.jsonl'
|
|
file = open(filename, 'rt', encoding='utf-8')
|
|
text = file.read()
|
|
|
|
# count articles
|
|
countAccept = text.count('accept')
|
|
countReject = text.count('reject')
|
|
countSkip = text.count('ignore')
|
|
countSpans = text.count('tokens')
|
|
# count entities
|
|
countPER = text.count('PER')
|
|
countLOC = text.count('LOC')
|
|
countORG = text.count('ORG')
|
|
countMISC = text.count('MISC')
|
|
|
|
underline = '\033[04m'
|
|
reset = '\033[0m'
|
|
red = '\033[31m'
|
|
green='\033[32m'
|
|
gray='\033[37m'
|
|
|
|
# table v1
|
|
#from lib import TableIt
|
|
#table1 = [
|
|
# ['Prijatých', countAccept],
|
|
# ['Zamietnutých', countReject],
|
|
# ['Preskočených', countSkip],
|
|
# ['------------', '------------'],
|
|
# ['Spolu', countSpans]
|
|
#]
|
|
#
|
|
#table = [
|
|
# ['Entita', 'Počet'],
|
|
# ['PER', countPER],
|
|
# ['LOC', countLOC],
|
|
# ['ORG', countORG],
|
|
# ['MISC', countMISC]
|
|
#]
|
|
#print('\nPočet anotovaných článkov:')
|
|
#TableIt.printTable(table1)
|
|
#print('\nPočet jednotlivých entít:')
|
|
#TableIt.printTable(table, useFieldNames=True, color=(26, 156, 171))
|
|
|
|
# table v2
|
|
print(underline + '\nPočet anotovaných článkov:' + reset)
|
|
print(green + "%-15s %-20s" %("Prijatých", countAccept) + reset)
|
|
print(red + "%-15s %-15s" %("Zamietnutých", countReject) + reset)
|
|
print(gray + "%-15s %-15s" %("Preskočených", countSkip) + reset)
|
|
print("%-15s" %("---------------------"))
|
|
print("%-15s %-15s" %("Spolu", countSpans))
|
|
|
|
print(underline + '\nPočet jednotlivých entít:' + reset)
|
|
print("%-10s %-10s" %("Entita:", "Počet:"))
|
|
print("%-10s" %("----------------"))
|
|
print("%-10s %-10s" %("PER", countPER))
|
|
print("%-10s %-10s" %("LOC", countLOC))
|
|
print("%-10s %-10s" %("ORG", countORG))
|
|
print("%-10s %-10s" %("MISC", countMISC)) |