python 开发nlp项目代码

以下是一个简单的 Python NLP 项目的代码示例，用于基于用户输入的问题回答：

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize, sent_tokenize
from nltk.stem import WordNetLemmatizer
import string

# 加载停用词
stop_words = set(stopwords.words('english'))

# 初始化词干化器
lemmatizer = WordNetLemmatizer()

def clean_text(text):
    """
    清理文本，删除标点符号、停用词和数字，并将单词转换为它们的基本形式
    """
    # 将文本转换为小写
    text = text.lower()
    # 删除标点符号
    text = text.translate(str.maketrans('', '', string.punctuation))
    # 分词
    words = word_tokenize(text)
    # 删除停用词和数字
    words = [lemmatizer.lemmatize(word) for word in words if (word not in stop_words) and (not word.isdigit())]
    # 将单词重新组合成文本
    cleaned_text = ' '.join(words)
    return cleaned_text

def get_response(user_input):
    """
    根据用户输入返回一个回答
    """
    # 清理用户输入
    cleaned_input = clean_text(user_input)
    # 进行语义分析，这里简单地将问题和答案放在一个字典里
    qa_pairs = {
        "what is your name": "My name is ChitGPT!",
        "how old are you": "I was just created recently, so I'm quite young!",
        "what can you do": "I can answer questions and have a conversation with you!",
        "who created you": "I was created by a team of developers at CSDN!",
        "bye": "Goodbye!"
    }
    # 查找回答
    for question in qa_pairs.keys():
        if cleaned_input == clean_text(question):
            return qa_pairs[question]
    # 如果找不到答案，则返回默认回答
    return "Sorry, I don't understand your question."

# 与用户进行对话
while True:
    user_input = input("You: ")
    if user_input.lower() == 'bye':
        print("ChitGPT: Goodbye!")
        break
    response = get_response(user_input)
    print("ChitGPT:", response)

该代码使用 NLTK 库进行文本清理、预处理和语义分析，然后根据用户输入返回一个回答。当用户输入“bye”时，程序退出。您可以根据自己的需求进行修改和扩展。