关于OIerDB部署与迁移到ACM的一些笔记

Posted 2023-01-22 小哈里

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了关于OIerDB部署与迁移到ACM的一些笔记相关的知识，希望对你有一定的参考价值。

文章目录

1、项目地址

https://github.com/OIerDb-ng/OIerDb
https://github.com/OIerDb-ng/OIerDb-data-generator

2、运行项目

OIerDb NG
项目主要基于Typescript，环境为node和yarn。

# 环境安装
nvm install 16.0.0
nvm ls
nvm use 16.0.0

# linux 需要 -g 才可以加到环境变量中
npm i -g yarn 

# npm修改代理
npm config get registry
npm config set registry https://registry.npm.taobao.org
npm config list
npm update

#查看代理 #删除代理 #更换淘宝镜像
yarn config list
yarn config delete proxy
yarn config set registry https://registry.npm.taobao.org

# 本地部署
yarn install --frozen-lockfile

yarn build
npm run dev

# Linux 服务器云端部署
# https://blog.csdn.net/qq_41664096/article/details/118961381
# 使用以下命令运行才能外网访问
npx vite --host 0.0.0.0

代码修改：

新增public中的文件夹，编译前将编译好的数据文件导入
修改数据来源为本地数据
src\\libs\\OIerDb.ts
```
http://localhost:3000/acmdb
```
其他网页的部分看着改
都在src，pages里，稍微学了一点点ts和react语法

OIerDb-data-generator
本项目主要基于python

# 环境安装
pip install pypinyin requests tqdm  -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
conda activate nowcoder

# 1
:= 海象运算符，py>=3.8
conda activate nowcoder

# 2 utils.py, main.py修改
open(class_file_name, 'r', encoding='utf-8') 
compute_sha512不用改

# 3 windows 需要修改执行命令
node ./update_static.js

# 生成数据
python main.py

数据生成器的代码修改
static静态文件夹里的几个json看着改下以外
oier.py和utils.py里涉及奖牌，相关方面的也要再改下，因为是写在代码里的，没有独立出来特判

3、更换数据

XCPC Board
https://board.xcpcio.com/
目标格式为：ACMDb-data-generator的相关格式。主要共3个文件。
核心部分，pandas数据处理

# 目标数据
import pandas as pd
df = pd.read_csv('OIerDb-data-generator\\data\\\\raw.txt', sep = ',')
df

# 打星队，导出的数据中没有特殊标注
# 因此之后只导出正式队名单

# 原始数据
import pandas as pd
import numpy as np
import json
# df = pd.read_json('data/board_47_xian.json')
# df

# 数据读入
competition = 'ICPC2022沈阳'
with open('data/ICPC2022沈阳.txt','r', encoding='utf-8') as f:
    data = json.loads(f.read())
data2 = pd.json_normalize(
    data, 
    record_path =['teams','members'], 
    meta=[
        # 'contestName',
        ['teams','organization'],
        ['teams','name'],
        ['teams','place','all']
    ]
)
# 数据清洗
data2 = pd.DataFrame(data2)
data2.columns = ['name', 'school', 'teams','rank']
data2['contest'] = competition
data2['sex'] = '男' 
data2['age'] = '大学' 
data2['other'] = None
data2['medal'] = None
data2.loc[data2['rank']>210 , 'medal'] = '铁牌'
data2.loc[data2['rank']<=210, 'medal'] = '铜牌'
data2.loc[data2['rank']<=105, 'medal'] = '银牌' 
data2.loc[data2['rank']<=36, 'medal'] = '金牌'
area = pd.read_csv('ACMDb-data-generator\\data\\\\school.txt', sep = ',', header=None)
del area[1]
area.columns = ['area','school']
data2 = pd.merge(data2, area, on='school', how='left')  # 类似于vlookup
data2 = data2[['contest', 'medal', 'name', 'age', 'school','rank','area','teams', 'sex','other']] # 排序
del data2['teams']  # 删除teams
data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
mx_value = data2[:1]['rank'].values[0]
data2['rank'] = mx_value-data2['rank']     # 折成分数
data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
data2.columns = ['contest', 'medal', 'name', 'age', 'school','score','area', 'sex','other'] # 改个名

data2
# print(data2)
# data2[data2['rank']<=210]
# data2[data2['teams']=='这么巧，你也是 ikun']


# 写入raw
# data2.to_csv('raw.txt',index=None)

# 批量生产，合规数据

import pandas as pd
import numpy as np
import json

def calc(competition):
    # 数据读入
    # competition = 'ICPC2022沈阳'
    with open('data/'+competition+'.txt','r', encoding='utf-8') as f:
        data = json.loads(f.read())
    data2 = pd.json_normalize(
        data, 
        record_path =['teams','members'], 
        meta=[
            # 'contestName',
            ['teams','organization'],
            ['teams','name'],
            ['teams','place','all']
        ]
    )
    # 数据清洗
    data2 = pd.DataFrame(data2)
    data2.columns = ['name', 'school', 'teams','rank']
    data2['contest'] = competition
    data2['sex'] = '男' 
    data2['age'] = '大学' 
    data2['other'] = None
    data2['medal'] = None
    data2.loc[data2['rank']>210 , 'medal'] = '铁牌'
    data2.loc[data2['rank']<=210, 'medal'] = '铜牌'
    data2.loc[data2['rank']<=105, 'medal'] = '银牌' 
    data2.loc[data2['rank']<=36, 'medal'] = '金牌'
    area = pd.read_csv('ACMDb-data-generator\\data\\\\school.txt', sep = ',', header=None)
    del area[1]
    area.columns = ['area','school']
    data2 = pd.merge(data2, area, on='school', how='left')  # 类似于vlookup
    data2 = data2[['contest', 'medal', 'name', 'age', 'school','rank','area','teams', 'sex','other']] # 排序
    del data2['teams']  # 删除teams
    data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
    mx_value = data2[:1]['rank'].values[0]
    data2['rank'] = mx_value-data2['rank']     # 折成分数
    data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
    data2.columns = ['contest', 'medal', 'name', 'age', 'school','score','area', 'sex','other'] # 改个名
    return data2

# df合并
# df1 = calc("ICPC2020南京")
# df2 = calc("ICPC2020沈阳")
# df3 = pd.concat([df1,df2])
# df3

# json写入
# dc1 = "fall_semester": True,"full_score": 1000,"name": "ICPC2022沈阳","type": "ICPC","year": 2022
# dc2 = "fall_semester": True,"full_score": 1000,"name": "ICPC2022沈阳","type": "ICPC","year": 2022
# dc2['name'] = "ICPC2022西安"
# dc = []
# dc.append(dc1)
# dc.append(dc2)
# print(dc)
# with open('contests.json', mode='w', encoding='utf-8') as f:
#     json.dump(dc, f, ensure_ascii=False)

# 批量合并
import os
dc = []
dfx = []
ok = 1
path = os.listdir(os.getcwd()+"\\data")
for p in path:
    if not os.path.isdir(p):
        print(p[:-4])
        dd = "fall_semester": True,"full_score": 1000,"name": "ICPC2022沈阳","type": "ICPC","year": 2022
        dd['name'] = p[:-4]
        dd['year'] = int(p[:-4][4:8])
        dc.append(dd)
        dfy = calc(p[:-4])
        if ok == 1: 
            dfx = dfy
            ok = 0
        else : 
            dfx = pd.concat([dfx,dfy])
        # print(dfx)

dfx = dfx.sort_values(by=['score'],ascending=False)  # 排名倒排
dfx = dfx[dfx['name'] != 'XXX']

# 写入文件
dfx.to_csv('raw.txt',index=None)
with open('contests.json', mode='w', encoding='utf-8') as f:
    json.dump(dc, f, ensure_ascii=False)

# 队伍质量判断，原始数据

import pandas as pd
import numpy as np
import json

def calc(competition):
    # 数据读入
    # competition = 'ICPC2022沈阳'
    with open('data/'+competition+'.txt','r', encoding='utf-8') as f:
        data = json.loads(f.read())
    data2 = pd.json_normalize(
        data, 
        record_path =['teams','members'], 
        meta=[
            # 'contestName',
            ['teams','organization'],
            ['teams','name'],
            ['teams','place','all']
        ]
    )
    # 数据清洗
    data2 = pd.DataFrame(data2)
    data2.columns = ['name', 'school', 'teams','rank']
    data2['contest'] = competition
    data2['sex'] = '男' 
    data2['age'] = '大学' 
    data2['other'] = None
    data2['medal'] = None
    data2.loc[data2['rank']>210 , 'medal'] = '铁牌'
    data2.loc[data2['rank']<=210, 'medal'] = '铜牌'
    data2.loc[data2['rank']<=105, 'medal'] = '银牌' 
    data2.loc[data2['rank']<=36, 'medal'] = '金牌'
    area = pd.read_csv('ACMDb-data-generator\\data\\\\school.txt', sep = ',', header=None)
    del area[1]
    area.columns = ['area','school']
    data2 = pd.merge(data2, area, on='school', how='left')  # 类似于vlookup
    data2 = data2[['contest', 'medal', 'name', 'age', 'school','rank','area','teams', 'sex','other']] # 排序
    # del data2['teams']  # 删除teams
    data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
    mx_value = data2[:1]['rank'].values[0]
    data2['rank'] = data2['rank']     # 折成分数
    data2['all'] = mx_value
    # data2.loc['all'] = mx_value
    # print(mx_value)
    # data2['all'] = mx_value
    # data2 = data2.sort_values(by=['rank'],ascending=False)  # 排名倒排
    # data2.columns = ['contest', 'medal', 'name', 'age', 'school', 'rank','area', 'sex','other','all'] # 改个名
    return data2
# 批量合并
import os
dc = []
dfx = []
ok = 1
path = os.listdir(os.getcwd()+"\\data")
for p in path:
    if not os.path.isdir(p):
        print(p[:-4])
        dd = "fall_semester": True,"full_score": 1000,"name": "ICPC2022沈阳","type": "ICPC","year": 2022
        dd['name'] = p[:-4]
        dd['year'] = int(p[:-4][4:8])
        dc.append(dd)
        dfy = calc(p[:-4])
        if ok == 1: 
            dfx = dfy
            ok = 0
        else : 
            dfx = pd.concat([dfx,dfy])
        # print(dfx)

dfx = dfx.sort_values(by=['rank'],ascending=True)  # 排名倒排
print(dfx)

# 写入文件
dfx.to_csv('raw.csv')

以上是关于关于OIerDB部署与迁移到ACM的一些笔记的主要内容，如果未能解决你的问题，请参考以下文章

在将项目部署到服务器之前重置所有迁移是一种好习惯吗？

蒟蒻ACMer回忆录 · 一段弱校ACM的奋斗史