pydata

Keep Looking, Don't Settle

2019-04-20 Week 16

Shares From Internet

  1. code-of-learn-deep-learning-with-pytorch

  2. 从信用卡欺诈模型看不平衡数据分类:这个作者总结了kaggle上面不同的人使用不同的抽样办法,不同的模型,以及异常值检验的办法。我以前也做过这个project,还是挺有意思的一个项目。

  3. 何用Deep Autoencoder实现信用卡欺诈侦测建模:这是另外一个办法,使用autoencoder来压缩数据

  4. The Syncthing Project: 一个开源软件用来备份文件夹

  5. PyTorch中文文档

How to keep alive ssh sessions

1. On AWS to connect with ServerAliveInterval=100

ssh -i ~/.ssh/xxxx.pem ubuntu@hithere.amazonaws.com -o ServerAliveInterval=100

2. General Setup

Many NAT firewalls time out idle sessions after a certain period of time to keep their trunks clean. Sometimes the interval between session drops is 24 hours ...

2019-02-23 Week 8

Shares From Internet

  1. Handling Categorical Data in Python
    • Categorical features may have a very large number of levels, known as high cardinality, (for example, cities or URLs), where most of the levels appear in a relatively small number of instances.
    • Many machine learning models, such as regression or SVM or ...