Created
January 7, 2022 07:45
-
-
Save pandanote-info/12062c080b972ba940a7dd4a5745407e to your computer and use it in GitHub Desktop.
転置インデックスもどきのデータをベクトル化するためのPython3のプログラム片。
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
with open(inputfile, encoding='utf-8') as fh: | |
freqlist = json.load(fh) | |
words = [] | |
articleids = [] | |
for k,v in freqlist.items(): | |
words.append(k) | |
for vv in v: | |
a,f = vv.split(",") | |
aa = int(a) | |
if aa not in articleids: | |
articleids.append(aa) | |
articleids.sort() | |
alen = len(articleids) | |
wlen = len(words) | |
bow = lil_matrix((alen,wlen)) | |
for k,v in freqlist.items(): | |
wi = words.index(k) | |
for vv in v: | |
a,f = map(int,vv.split(",")) | |
bow[articleids.index(a),wi] = f | |
nzelemnum = len(bow.nonzero()[0]) | |
print("{0:d} {1:d} {2:d}".format(alen,wlen,nzelemnum)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment