https://github.com/duruii/contest-dingtalkcup2023-a

🗑️2023年第二届“钉钉杯”大学生大数据挑战赛——智能手机用户监测数据分析
https://github.com/duruii/contest-dingtalkcup2023-a

data-mining machine-learning pandas scikit-learn xgboost

Last synced: about 1 year ago
JSON representation

🗑️2023年第二届“钉钉杯”大学生大数据挑战赛——智能手机用户监测数据分析

• Host: GitHub
• URL: https://github.com/duruii/contest-dingtalkcup2023-a
• Owner: DURUII
• License: mit
• Created: 2023-07-13T13:04:48.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2023-09-07T04:15:24.000Z (almost 3 years ago)
• Last Synced: 2025-06-14T16:06:14.868Z (about 1 year ago)
• Topics: data-mining, machine-learning, pandas, scikit-learn, xgboost
• Language: Jupyter Notebook
• Homepage: http://www.nmmcm.org.cn/ad_detail/194
• Size: 36.8 MB
• Stars: 6
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Contest-DingTalkCup2-A

## 依赖

```shell

pip install -r requirements.txt

```

## 数据

下载解压初赛数据集，将app_class.csv、dayxx.txt放至Datasets中，在Visual Studio Code 或 Terminal 中运行 `dr/preprocessing.py`的`generate_pickle_origin`，获得pickle格式的粗处理数据，对应2.1、2.2、2.3、2.4小节。

## 成绩

初赛本科组三等奖，未晋级复赛，可作为反面教材供参考。