学生信息管理系统

import pandas as pd

from nltk import word_tokenize, pos_tag

import re

# 假设有一个CSV文件包含学生的报名信息

df = pd.read_csv('students.csv')

def extract_info(text):

tokens = word_tokenize(text)

tagged = pos_tag(tokens)

info = {}

for word, tag in tagged:

if tag == 'NNP': # 名词，如姓名

info['name'] = word

elif tag == 'CD': # 数字，如学号

info['student_id'] = word

elif re.match(r'^\d{11}$', word): # 手机号

info['phone'] = word

elif '@' in word: # 邮箱

info['email'] = word

return info

df['info'] = df['text'].apply(extract_info)

df.to_csv('processed_students.csv', index=False)

from transformers import AutoTokenizer, AutoModelForTokenClassification

from transformers import pipeline

model_name = "bert-base-uncased"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForTokenClassification.from_pretrained(model_name)

ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)

text = "张三，学号202310101，电话13800138000，邮箱zhangsan@example.com"

results = ner_pipeline(text)

for result in results:

print(f"实体: {result['word']}，类型: {result['entity']}")

import mysql.connector

db = mysql.connector.connect(

host="localhost",

user="root",

password="password",

database="student_db"

)

cursor = db.cursor()

sql = "INSERT INTO students (name, student_id, phone, email) VALUES (%s, %s, %s, %s)"

val = ("张三", "202310101", "13800138000", "zhangsan@example.com")

cursor.execute(sql, val)

db.commit()

from sklearn.cluster import KMeans

import numpy as np

# 假设有10个学生的兴趣和专业向量

X = np.array([

[1, 2], # 学生A：喜欢编程，计算机专业

[2, 1], # 学生B：喜欢数学，数学专业

[3, 4], # 学生C：喜欢艺术，美术专业

[4, 3], # 学生D：喜欢音乐，音乐专业

[5, 6], # 学生E：喜欢工程，机械专业

[6, 5], # 学生F：喜欢物理，物理专业

[7, 8], # 学生G：喜欢文学，中文专业

[8, 7], # 学生H：喜欢历史，历史专业

[9, 10], # 学生I：喜欢经济，金融专业

[10, 9] # 学生J：喜欢法律，法学专业

])

kmeans = KMeans(n_clusters=3)

kmeans.fit(X)

labels = kmeans.labels_

for i, label in enumerate(labels):

print(f"学生{i+1}被分配到班级{label}")

from sklearn.metrics.pairwise import cosine_similarity

import numpy as np

# 学生兴趣向量

student_vector = np.array([1, 0, 1, 0]) # 假设学生喜欢编程和数学

# 课程特征矩阵

course_matrix = np.array([

[1, 0, 0, 0], # 课程A：编程

[0, 1, 0, 0], # 课程B：数学

[0, 0, 1, 0], # 课程C：艺术

[0, 0, 0, 1], # 课程D：体育

])

similarities = cosine_similarity(student_vector.reshape(1, -1), course_matrix).flatten()

for i, sim in enumerate(similarities):

print(f"课程{i+1}相似度: {sim:.2f}")