import jieba
list1 = jieba.lcut("中華人民共和國是一個偉大的國家")
print(list1)
print("精確模式："+"/".join(list1))

list2 = jieba.lcut("中華人民共和國是一個偉大的國家",cut_all = True)
print(list2,end=",")
print("全模式："+"/".join(list2))

list3 = jieba.lcut_for_search("中華人民共和國是一個偉大的國家")
print(list3)
print("搜索引擎模式："+"  ".join(list3))

import jieba
text = "中信建投投資公司了一款游戲，中信也投資了一個游戲公司"
word = jieba.lcut(text)
print(word)
# 添加詞
jieba.add_word("中信建投")
jieba.add_word("投資公司")
word1 = jieba.lcut(text)
print(word1)
# 刪除詞
jieba.del_word("中信建投")
word2 = jieba.lcut(text)
print(word2)

import jieba.posseg as pseg
words = pseg.cut("我愛北京天安門")
for i in words:
print(i.word,i.flag)

import  jieba
txt = open("文件路徑", "r", encoding='utf-8').read()    # 打開并讀取文件
words = jieba.lcut(txt)     # 使用精確模式對文本進行分詞
counts = {}     # 通過鍵值對的形式存儲詞語及其出現的次數
for word in words:
    if  len(word) == 1:    # 單個詞語不計算在內
        continue
    else:
        counts[word] = counts.get(word, 0) + 1    # 遍歷所有詞語，每出現一次其對應的值加 1   
items = list(counts.items())     #將鍵值對轉換成列表
items.sort(key=lambda x: x[1], reverse=True)    # 根據詞語出現的次數進行從大到小排序 
for i in range(15):
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

import jieba
excludes = {"將軍","卻說","荊州","二人","不可","不能","如此","如何"}
txt = open("三國演義.txt", "r", encoding='utf-8').read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "諸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "關公" or word == "云長":
        rword = "關羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "劉備"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"
    else:
        rword = word
        counts[rword] = counts.get(rword,0) + 1
    
for i in excludes:
    del counts[i]
    
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))