Python人工智能识别陆游和苏轼的古诗

用简洁的代码实现人工智能识别古诗的效果

第一步：导库

import pandas as pd
import numpy as np
import jieba
from sklearn.naive_bayes import *
from sklearn.model_selection import *
from sklearn.feature_extraction.text import *

sklearn库是人工智能的常用库。另外三个是数据预处理的常用库。

第二步：数据预处理

with open("sushi.txt", "r", encoding='utf-8') as txt:
    text1 = txt.read()
    list1 = jieba.lcut(text1)#jieba把句子断成词语

with open("luyou.txt", "r", encoding='utf-8') as txt:
    text2 = txt.read()
    list2 = jieba.lcut(text2)#jieba把句子断成词语

#给古诗词语贴标签
ss_features = []
for ss in list1:
    ss_features.append((ss,"苏轼"))
    
ly_features = []
for ly in list2:
    ly_features.append((ly,"陆游"))

这样，就完成了给古诗词语贴标签的步骤。
然后把这些词语分成训练组和测试组：

words = ss_features + ly_features
df = pd.DataFrame(words) 

split_data = train_test_split(df[0], df[1], random_state = 3)
x_train = split_data[0]
x_test = split_data[1]
y_train = split_data[2]
y_test = split_data[3]
tv = TfidfVectorizer()
x_train = tv.fit_transform(x_train)
x_test = tv.transform(x_test)

第三步：人工智能大展身手

clt = MultinomialNB()#编码器

clt.fit(x_train, y_train)#训练模型
print(clt.score(x_test, y_test))#打分

不要看就这么三行，但功能极强

第四步：实现功能

poem = input("请输入苏轼或陆游的诗句：")
poem_features = jieba.lcut(poem)

print(poem_features)
df2 = pd.DataFrame(poem_features) 
t_word = tv.transform(df2[0])
res = clt.predict(t_word)
print(res)