def gridSearch(c_values, k_values, per_epoch=200): # 网格搜索聚类类簇数量和截断长度
re = {}
for ci, c_num in enumerate(c_values):
re[c_num] = {}
for ki, k_num in enumerate(k_values):
print(ci * len(k_values) + ki + 1, "/",
len(c_values) * len(k_values))
mng = PathManager("virushare-20-original")
# findOptK(mng.WordEmbedMatrix(), k_range=(2,100))
apiCluster(mng.WordEmbedMatrix(),
mng.DataRoot() + "MarkovClusterMapping.json",
cluster_num=c_num)
makeClusteredData(
json_path=mng.Folder(),
cluster_path=mng.DataRoot() + "MarkovClusterMapping.json",
word_map_path=mng.WordIndexMap(),
dump_path=mng.DataRoot() + "MarkovClusteredData.npy",
max_len=k_num)
a = scoreMarkovEpisode(clustered_data_path=mng.DataRoot() +
"MarkovClusteredData.npy",
epoch=per_epoch,
n_cluster=c_num,
maxlen=k_num,
verbose=False)
re[c_num][k_num] = a
return re
# f.write(f"> {j+1}\n")
# f.write(fa_strs[j]+"\n")
# except Exception as e:
# print(f"len={len(fa_strs)} i={i} j={j} msg={str(e)}")
# raise RuntimeError
if __name__ == '__main__':
mng = PathManager("HKS-api")
# apiCluster(mng.WordEmbedMatrix(), mng.DataRoot()+"CategoryMapping.json")
# convertApiCategory(clst_path=mng.DataRoot()+"CategoryMapping.json",
# word_map_path=mng.WordIndexMap(),
# json_path=mng.DatasetBase()+'all-rmsub/',
# str_dump_path=mng.DataRoot()+"CategorizedStringData(rmsub).json")
# genFamilyProtoByMSA(str_path=mng.DataRoot()+"CategorizedStringData.json",
# work_space="D:/datasets/virushare-20-original/data/family_protos/",
# proto_dump_path=mng.DataRoot()+"FamilyProtos.txt")
# scoreEpisodeAlignment(str_path=mng.DataRoot()+"CategorizedStringData(rmsub).json",
# epoch=300,
# log_path=mng.DataRoot()+'logs/runlog.txt',
# acc_dump_path=mng.DataRoot()+"logs/Align-Virushare20-%dshot-%dway.json"%(k,n))
multi_process_align(
str_path=mng.DataRoot() + "CategorizedStringData(rmsub).json",
epoch=1000,
acc_dump_path=mng.DataRoot() + "logs/Align-HKS-%dshot-%dway.json" %
(k, n),
process_num=4)
# accs = loadJson(mng.DataRoot()+"logs/Align-HKS-%dshot-%dway.json"%(k,n))['acc']
# print("Avg acc:", sum(accs)/len(accs))
# print("Interval:", calBeliefeInterval(accs))
# print("Len:", len(accs))
# dump_path=mng.DataRozot()+"MarkovClusteredData.npy",
# max_len=seq_len)
# scoreMarkovEpisode(clustered_data_path=mng.DataRoot()+"MarkovClusteredData.npy",
# epoch=2000,
# n_cluster=n_cluster,
# maxlen=seq_len)
# re = gridSearch(c_values=list(range(*n_range)),
# k_values=[i*50 for i in range(1,11)],
# per_epoch=1000)
# dumpJson(re, mng.DataRoot()+"GSs/GridSearchResult-%dshot-%dway-virushare20.json"%(k,n))
# re = loadJson(mng.DataRoot()+"GSs/GridSearchResult-%dshot-%dway-virushare20.json"%(k,n))
# n_cluster, seq_len = extractBestParam(re)
# n_cluster = int(n_cluster)
# seq_len = int(seq_len)
apiCluster(mng.WordEmbedMatrix(),
mng.DataRoot() + "MarkovClusterMapping.json",
cluster_num=n_cluster)
makeClusteredData(json_path=mng.Folder(),
cluster_path=mng.DataRoot() +
"MarkovClusterMapping.json",
word_map_path=mng.WordIndexMap(),
dump_path=mng.DataRoot() + "MarkovClusteredData.npy",
max_len=seq_len)
scoreMarkovEpisode(clustered_data_path=mng.DataRoot() +
"MarkovClusteredData.npy",
epoch=epoch,
n_cluster=n_cluster,
maxlen=seq_len)