Starting this site: six projects in high-dimensional data
This site records a learning project. Over the next few months I will build one project in each of six sectors, using public datasets, and write up what I learn.
The plan
- Marketing: customer segmentation
- Industry: fault detection from sensor data
- Finance: portfolio construction with many assets
- Healthcare: gene expression analysis
- Text and AI: semantic search with embeddings
- Education: automated answer evaluation
How each project is documented
- A repository with a notebook and a short README.
- A write-up here covering the problem, method, results and limitations.
- A theory note in my own words.
Writing maths
Inline maths uses ( x^2 ). Display maths uses double dollar signs:
\[\hat{\beta} = \arg\min_{\beta} \; \|y - X\beta\|_2^2 + \lambda \|\beta\|_1\]Writing code
from sklearn.decomposition import PCA
pca = PCA(n_components=2).fit(X_scaled)
print(pca.explained_variance_ratio_)