Last active
October 27, 2021 13:55
-
-
Save goodbyegangster/0dbdc9164935ac28e4f66a4c9f3ce6f9 to your computer and use it in GitHub Desktop.
negative-positive analyzer script for shikiho-data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import csv, glob, MeCab | |
result_file = "XXXXXXXX" | |
dic_file = "XXXXXXXX" | |
shikiho_file = "XXXXXXXX" | |
headmsg = ["code","comment","value"] | |
wordtable = {} | |
with open(dic_file, newline="") as dicfile: | |
dic = csv.reader(dicfile, delimiter=":") | |
for row in dic: | |
wordtable[row[0]] = row[3] | |
m = MeCab.Tagger("") | |
with open(result_file, "w") as resultfile: | |
csvwriter = csv.writer(resultfile, quoting=csv.QUOTE_ALL) | |
csvwriter.writerow(headmsg) | |
output_files = glob.glob(shikiho_file) | |
for output_file in output_files: | |
with open(output_file, newline="") as outputs: | |
value_list = [] | |
output = csv.reader(outputs) | |
next(output, None) | |
for row in output: | |
m.parse("") | |
node = m.parseToNode(row[12]+row[13]) | |
while node: | |
featurelist = node.feature.split(",") | |
if featurelist[0] in ["名詞", "動詞", "形容詞", "副詞"]: | |
for key, value in wordtable.items(): | |
if featurelist[6] == key: | |
value_list.append(float(value)) | |
node = node.next | |
csvwriter.writerow([row[0],row[12]+row[13],sum(value_list)/len(value_list)]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment