def create_lang_vec(filename, lv, cluster_sizes, N=N, k=k):
total_lang = np.zeros((1,N))
# generate english vector
for cz in cluster_sizes:
print "generating language vector of cluster size", cz
# which alphabet to use
lang_vector = random_idx.generate_RI_text_fast(N, lv, cz, ordered, filename, alphabet)#"preprocessed_texts/AliceInWonderland.txt", alph)
total_lang += lang_vector
return total_lang
def log_generate_RI_text_fast(N, RI_letters, cluster_sz, ordered, text_name, alph=alphabet):
text_vector = random_idx.generate_RI_text_fast(N, RI_letters, cluster_sz, ordered, text_name, alph)
text_vector = np.log2(text_vector)
return text_vector
def log_generate_RI_text_fast(N, RI_letters, cluster_sz, ordered, text_name, alph=alphabet):
text_vector = random_idx.generate_RI_text_fast(N, RI_letters, cluster_sz, ordered, text_name, alph)
text_vector = np.log2(text_vector)
return text_vector