TF-IDFの計算用のサンプルコード片

tfidf.py.sample

# TF
aa = bow.copy()
np.set_printoptions(threshold=np.inf,formatter={'float': '{:.8f}'.format})
for i in range(0,dim[0]):
    ar = bow.getrow(i)
    rowsum = np.matrix.sum(ar.todense())
    arr = ar/rowsum
    aa[i] = arr

# IDF(ln)
for j in range(0,dim[1]):
    ac = aa.getcol(j)
    idf = math.log(dim[0]/ac.getnnz())
    aa[0:dim[0],j] = ac*idf