学生信息分析系统开发全流程-CSDN博客

本文链接：https://blog.csdn.net/m0_74187997/article/details/147049011

一、系统架构设计

技术选型矩阵

功能模块	技术方案	依赖库
数据读取	Excel/CSV解析	pandas
基础可视化	静态图表生成	matplotlib
地理可视化	交互式地图	pyecharts
文本分析	中文分词与词云	jieba+wordcloud
关系网络	图结构可视化	networkx
人脸识别	云API调用	tencentcloud-sdk-python
界面交互	可视化看板	streamlit（可选）

二、开发环境搭建

2.1 环境配置

# 创建虚拟环境
python -m venv student_analysis
source student_analysis/bin/activate  # Linux/Mac
student_analysis\Scripts\activate     # Windows

# 安装核心依赖
pip install pandas matplotlib pyecharts jieba wordcloud networkx pillow python-dotenv

# 腾讯云SDK
pip install tencentcloud-sdk-python

2.2 配置文件(.env)

TENCENT_SECRET_ID=your_secret_id
TENCENT_SECRET_KEY=your_secret_key
DATA_PATH=./students.xlsx

三、核心功能实现

3.1 数据加载模块

import pandas as pd
from dotenv import load_dotenv

load_dotenv()

def load_data():
    df = pd.read_excel(os.getenv('DATA_PATH'))
    
    # 数据预处理
    df['成绩'] = pd.to_numeric(df['成绩'], errors='coerce')
    df['省份'] = df['省份'].str.replace('省|市', '')  # 标准化地名
    
    return df.dropna(subset=['性别', '省份', '成绩'])

3.2 可视化模块

性别分布饼图

def plot_gender(df):
    gender_count = df['性别'].value_counts()
    plt.figure(figsize=(8,6))
    plt.pie(gender_count, labels=gender_count.index, 
           autopct='%1.1f%%', colors=['#ff9999','#66b3ff'])
    plt.title("Gender Distribution")
    plt.savefig('gender_pie.png')

中国省份分布地图

from pyecharts.charts import Map

def plot_province_map(df):
    province_dist = df['省份'].value_counts().to_dict()
    
    map_chart = Map()
    map_chart.add("学生分布", 
                 [list(z) for z in province_dist.items()], 
                 "china")
    map_chart.set_global_opts(title_opts=opts.TitleOpts(title="生源地分布"))
    map_chart.render("province_map.html")

城市分布柱状图

def plot_city_bar(df):
    plt.figure(figsize=(12,6))
    city_top20 = df['城市'].value_counts()[:20]
    city_top20.plot(kind='bar', color='#2ca02c')
    plt.title("Top 20 Cities")
    plt.xticks(rotation=45)
    plt.tight_layout()
    plt.savefig('city_bar.png')

签名词云

from wordcloud import WordCloud
import jieba

def generate_wordcloud(df):
    text = ' '.join(df['签名'].dropna())
    wordlist = jieba.cut(text)
    word_str = ' '.join(wordlist)
    
    wc = WordCloud(font_path='msyh.ttc',
                  background_color='white',
                  max_words=200)
    wc.generate(word_str)
    wc.to_file('wordcloud.png')

成绩分布折线图

def plot_score_dist(df):
    plt.figure(figsize=(10,6))
    bins = range(0, 101, 5)
    df['成绩区间'] = pd.cut(df['成绩'], bins)
    score_dist = df.groupby('成绩区间').size()
    
    plt.plot(score_dist.index.astype(str), 
            score_dist.values, 
            marker='o', 
            color='#d62728')
    plt.title("Score Distribution")
    plt.xticks(rotation=45)
    plt.savefig('score_line.png')

3.3 高级功能模块

宿舍关系网络图

import networkx as nx

def plot_dorm_network(df):
    G = nx.Graph()
    
    # 添加宿舍节点
    dorms = df['宿舍号'].unique()
    G.add_nodes_from(dorms, node_type='dorm')
    
    # 添加学生节点并建立关联
    for _, row in df.iterrows():
        G.add_node(row['学号'], node_type='student')
        G.add_edge(row['学号'], row['宿舍号'])
    
    plt.figure(figsize=(15,10))
    pos = nx.spring_layout(G)
    nx.draw(G, pos, with_labels=True, node_size=500)
    plt.savefig('dorm_network.png')

腾讯云人脸识别

from tencentcloud.common import credential
from tencentcloud.iai.v20200303 import iai_client, models

def detect_faces(image_path):
    cred = credential.Credential(
        os.getenv('TENCENT_SECRET_ID'),
        os.getenv('TENCENT_SECRET_KEY'))
    
    client = iai_client.IaiClient(cred, "ap-guangzhou")
    
    with open(image_path, "rb") as f:
        image = f.read()
    
    req = models.DetectFaceRequest()
    req.Image = image
    req.NeedFaceAttributes = 1
    
    return client.DetectFace(req)

四、系统集成与运行

4.1 主程序

import os
import matplotlib.pyplot as plt

if __name__ == "__main__":
    df = load_data()
    
    # 基础可视化
    plot_gender(df)
    plot_city_bar(df)
    generate_wordcloud(df)
    plot_score_dist(df)
    
    # 高级可视化
    plot_province_map(df)
    plot_dorm_network(df)
    
    # 人脸识别示例
    result = detect_faces("sample_face.jpg")
    print("人脸特征：", result.FaceInfos[0].FaceAttributesInfo)

4.2 运行指令

python main.py

4.3 输出结果

生成文件列表：
- gender_pie.png # 性别饼图
- city_bar.png # 城市柱状图
- wordcloud.png # 签名词云
- score_line.png # 成绩分布
- province_map.html # 交互式地图
- dorm_network.png # 宿舍关系图

五、设计思想与优化建议

5.1 核心设计原则

模块化设计：每个可视化功能独立实现
数据驱动：采用pandas统一处理数据源
渐进增强：基础功能先行，高级功能可选
云原生：敏感操作通过API实现

5.2 性能优化方向

# 内存优化示例：分块处理大数据
chunk_size = 1000
for chunk in pd.read_csv('big_data.csv', chunksize=chunk_size):
    process_chunk(chunk)

5.3 安全建议

# 敏感数据处理
from cryptography.fernet import Fernet

key = Fernet.generate_key()
cipher = Fernet(key)

encrypted_data = cipher.encrypt(b"Sensitive Info")
decrypted_data = cipher.decrypt(encrypted_data)