Python文章相关性分析---金庸武侠小说分析-2018.1.16

with open(‘names.txt‘) as f:
    data = [line.strip()  for line in f.readlines()]
novels = data[::2]
names = data[1::2]

novel_names = {k: v.split() for k, v in zip(novels, names)}
//可以在这里打印下看是不是都读取过

//开始分词并加载
for _, names in novel_names.items():#.iteritems():（Python2的旧写法）for name in names:
        jieba.add_word(name)
with open("kongfu.txt",encoding=‘UTF-8‘) as f:
    kungfu_names = [line.strip() 
                    for line in f.readlines()]
with open("bangs.txt") as f:
    bang_names = [line.strip() 
                  for line in f.readlines()]

for name in kungfu_names:
    jieba.add_word(name)
  

for name in bang_names:
    jieba.add_word(name)

novels = ["书剑恩仇录", "天龙八部","碧血剑","越女剑","飞狐外传","侠客行","射雕英雄传","神雕侠侣","连城诀","鸳鸯刀","倚天屠龙记","白马啸西风","笑傲江湖","雪山飞狐","鹿鼎记"]
//你知道的：飞雪连天射白鹿，笑书神侠倚碧鸳
sentences = []

for novel in novels:
    with open(‘{}.txt‘.format(novel),encoding=‘UTF-8‘) as f:
        data = [line.strip() 
                for line in f.readlines() 
                if line.strip()]
    for line in data:
        words = list(jieba.cut(line))
        sentences.append(words)
        
model = gensim.models.Word2Vec(sentences, 
                               size=200, #100
                               window=5, 
                               min_count=5, 
                               workers=4)

//便于使用的方法
def get_gongfu(a, b, c):
    d, _ = model1.most_similar(positive=[c, b], negative=[a])[0]
    print (c,d)
//使用举例一
print (‘-------------若黄蓉使出打狗棒法，郭靖会怎样？-------------------------‘)
get_gongfu("黄蓉","打狗棒法","郭靖")
print (‘-------------若黄蓉拿着打狗棒，郭靖又会拿啥？-------------------------‘)
get_gongfu("黄蓉","打狗棒","郭靖")

                输出结果：
-------------相关性:乔峰-------------------------
%% 虚竹 0.8226621747016907
%% 慕容复 0.809000551700592
%% 段正淳 0.808856725692749
%% 木婉清 0.7898266315460205
%% 童姥 0.7881260514259338
%% 袁承志 0.7863771915435791
%% 全冠清 0.7761101722717285
%% 谢烟客 0.7738543748855591
%% 俞莲舟 0.7663788199424744
%% 陆菲青 0.7651679515838623
-------------相关性:阿朱-------------------------
阿紫 0.8502078056335449
王语嫣 0.8323276042938232
木婉清 0.8188427090644836
方怡 0.81195068359375
钟灵 0.8042664527893066
仪琳 0.7905520796775818
青青 0.7837553024291992
香香公主 0.7774882316589355
盈盈 0.7765697836875916
马夫人 0.7628135681152344
-------------相关性:降龙十八掌-------------------------
打狗棒法 0.9099119901657104
太极拳 0.8792168498039246
空明拳 0.8742830157279968
绝招 0.864672064781189
一阳指 0.8576483726501465
蛤蟆功 0.8443030714988708
心法 0.8419612646102905
棒法 0.840523362159729
罗汉拳 0.838168740272522
小擒拿手 0.8356980085372925
-------------若黄蓉使出打狗棒法，郭靖会怎样？-------------------------
郭靖 降龙十八掌
-------------若黄蓉拿着打狗棒，郭靖又会拿啥？-------------------------
郭靖 令旗