150 lines
3.7 KiB
Python
150 lines
3.7 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
import csv
|
|
import sys
|
|
from miscellaneous import *
|
|
import time
|
|
from datetime import datetime
|
|
import re
|
|
import textacy
|
|
from textacy.preprocess import normalize_whitespace
|
|
from scipy import *
|
|
import os
|
|
|
|
csv.field_size_limit(sys.maxsize)
|
|
FILEPATH = os.path.dirname(os.path.realpath(__file__)) + "/"
|
|
|
|
# load config
|
|
config_ini = FILEPATH + "config.ini"
|
|
|
|
config = ConfigParser.ConfigParser()
|
|
with open(config_ini) as f:
|
|
config.read_file(f)
|
|
|
|
|
|
|
|
def ticketcsv_to_textStream(path2csv, content_collumn_name):
|
|
"""
|
|
:param path2csv: string
|
|
:param content_collumn_name: string
|
|
|
|
:return: string-generator
|
|
"""
|
|
stream = textacy.fileio.read_csv(path2csv, delimiter=";") # ,encoding='utf8')
|
|
content_collumn = 0 # standardvalue
|
|
|
|
for i, lst in enumerate(stream):
|
|
if i == 0:
|
|
# look for desired column
|
|
for j, col in enumerate(lst):
|
|
if col == content_collumn_name:
|
|
content_collumn = j
|
|
else:
|
|
yield lst[content_collumn]
|
|
|
|
|
|
def ticket_csv_to_DictStream(path2csv,content_collumn_name):
|
|
"""
|
|
:param path2csv: string
|
|
:param content_collumn_name: string
|
|
|
|
:return: dict-generator
|
|
"""
|
|
stream = textacy.fileio.read_csv(path2csv, delimiter=";") # ,encoding='utf8')
|
|
|
|
content_collumn = 0 # standardvalue
|
|
metaindices = []
|
|
metalist = []
|
|
|
|
metadata_template = {}
|
|
for i, lst in enumerate(stream):
|
|
if i == 0:
|
|
for j, col in enumerate(lst):
|
|
if "icketNumb" in col:
|
|
col = "TicketNumber"
|
|
metalist.append(str(col))
|
|
metaindices.append(j)
|
|
metadata_template = dict(
|
|
zip(metalist, metaindices)) # zB {'Subject' : 1, 'categoryName' : 3, 'Solution' : 10}
|
|
|
|
else:
|
|
metadata = metadata_template.copy()
|
|
for key, value in metadata.items():
|
|
metadata[key] = lst[value]
|
|
yield metadata
|
|
|
|
|
|
|
|
##################################################################################################
|
|
|
|
|
|
|
|
content_collumn_name = config.get("tickets","content_collumn_name")
|
|
|
|
|
|
path2de_csv = FILEPATH + config.get("de_corpus","input")
|
|
corpus_de_path = FILEPATH + config.get("de_corpus", "path")
|
|
|
|
|
|
|
|
|
|
|
|
def ticketcsv2Corpus(path2_csv, corpus_path, content_collumn_name, lang, printrandom=0):
|
|
"""
|
|
Use textacy to create a Corpus out of the ITMC-Ticket.csv
|
|
|
|
:param path2_csv: str
|
|
:param corpus_path: str
|
|
:param content_collumn_name: str the Collumn which is used as the Docs text
|
|
:param lang: str standard 2-letter language
|
|
:param printrandom: print n random Documents
|
|
:return: textacy.Corpus
|
|
"""
|
|
|
|
# print paths
|
|
path_csv_split = path2_csv.split("/")
|
|
filename = path_csv_split[len(path_csv_split) - 1]
|
|
|
|
logprint("Corporization of {0} at {1}".format(filename, datetime.now()))
|
|
|
|
|
|
raw_corpus = textacy.Corpus(lang)
|
|
|
|
## add files to textacy-corpi,
|
|
raw_corpus.add_texts(
|
|
ticketcsv_to_textStream(path2_csv, content_collumn_name),
|
|
ticket_csv_to_DictStream(path2_csv,content_collumn_name)
|
|
)
|
|
|
|
|
|
# leere docs aus corpi kicken
|
|
raw_corpus.remove(lambda doc: len(doc) == 0)
|
|
|
|
logprint("corpus-length: {}".format(len(raw_corpus)))
|
|
|
|
|
|
|
|
# save corpus
|
|
raw_name = lang + "_raw"
|
|
save_corpus(corpus=raw_corpus, corpus_path=corpus_path, corpus_name=raw_name)
|
|
|
|
return raw_corpus
|
|
|
|
|
|
def main():
|
|
start = time.time()
|
|
|
|
|
|
|
|
raw_corpus = ticketcsv2Corpus(path2de_csv,corpus_de_path,content_collumn_name,lang="de")
|
|
|
|
|
|
|
|
|
|
end = time.time()
|
|
logprint("Time Elapsed Corporization:{0} min".format((end - start) / 60))
|
|
return raw_corpus
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |