Where does your data come from? In this video of Machine Learning Explained Simply, we explore every way to load data in scikit-learn: toy dataset loaders, real-world fetchers, synthetic data generators, OpenML, the svmlight format, and storage formats for large data like HDF5.
We then open a notebook and code it live, one line at a time: load the wine dataset, then create fake classification and regression data. We finish with how to choose the right tool and the most common beginner mistake.
Code from this video (open and run it in your browser, no setup needed):
https://molab.marimo.io/notebooks/nb_bLXr61CW52nd2EkoZbTAgB/app
Chapters:
0:00 Intro
0:22 Recap
0:44 The dataset API
1:18 Toy dataset loaders
2:10 Real-world fetchers
2:42 Synthetic data generators
3:26 Live code: toy loaders
4:37 Live code: synthetic data
5:56 External datasets with OpenML
6:26 The svmlight format
7:04 Storage for large data
7:40 Which one should you use
8:10 Common mistake
8:44 Quick check
9:10 Recap and outro
Previous video: Introduction to scikit-learn, Explained Simply https://www.youtube.com/watch?v=scM7KBdlE_4
Next video: Transformers and Feature Extraction
Full playlist, Machine Learning Explained Simply:
https://www.youtube.com/playlist?list=PLe1RZInMUKM8
If this helped, like, follow, and tell me in the comments what topic you want next. Stay curious!
#machinelearning #scikitlearn #python
ข้อเสนอแนะ
รายงาน
ห้ามทำซ้ำหรือดัดแปลงโดยไม่ได้รับอนุญาตจากครีเอเตอร์
ข้อเสนอแนะ
รายงาน