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。

freq2matrix.py.example

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))