diff --git a/app/__init__.py b/app/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/app/demo/__init__.py b/app/demo/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/app/demo/index.html b/app/demo/index.html new file mode 100644 index 0000000..c01efa5 --- /dev/null +++ b/app/demo/index.html @@ -0,0 +1,526 @@ + + + + + +Input dataset · Dimension Reduction Sandbox + + + + +
+
§1
+

Select input dataset

+
+
Demo · picker
+
+ +

+ Three candidate generators for the embedding pipeline. Drag to rotate, scroll to zoom, + 1 2 3 to select. +

+ +
+ + + 500 +
+ + + +
+
+ generator + — +
+ +
+ + + + + diff --git a/app/demo/main.py b/app/demo/main.py new file mode 100644 index 0000000..d6b6d94 --- /dev/null +++ b/app/demo/main.py @@ -0,0 +1,64 @@ +from functools import lru_cache +from pathlib import Path + +from fastapi import FastAPI +from fastapi.staticfiles import StaticFiles +from sklearn.datasets import make_blobs, make_s_curve, make_swiss_roll + +app = FastAPI() +HERE = Path(__file__).parent + + +@lru_cache(maxsize=1) +def _datasets(): + s, sl = make_s_curve(n_samples=5000, noise=0.03, random_state=0) + sr, srl = make_swiss_roll(n_samples=5000, noise=0.15, random_state=0) + b, bl = make_blobs( + n_samples=5000, n_features=3, centers=5, cluster_std=1.0, random_state=0 + ) + return { + "s_curve": { + "name": "S-Curve", + "path": "sklearn.datasets.make_s_curve", + "description": ( + "A 2-D manifold warped into R³. Continuous label encodes position " + "along the curve — a good test of whether a reducer unrolls the " + "sheet without tearing." + ), + "kind": "continuous", + "points": s.tolist(), + "labels": sl.tolist(), + }, + "swiss_roll": { + "name": "Swiss Roll", + "path": "sklearn.datasets.make_swiss_roll", + "description": ( + "A rolled-up plane. The canonical hard case for linear methods: " + "PCA collapses the spiral, non-linear methods should recover the " + "unroll." + ), + "kind": "continuous", + "points": sr.tolist(), + "labels": srl.tolist(), + }, + "blobs": { + "name": "Gaussian Blobs", + "path": "sklearn.datasets.make_blobs", + "description": ( + "Five isotropic Gaussian clusters in R³. Discrete class labels. " + "Tests whether a reducer preserves cluster separation when " + "projected to 2-D." + ), + "kind": "categorical", + "points": b.tolist(), + "labels": bl.tolist(), + }, + } + + +@app.get("/data.json") +def data(): + return _datasets() + + +app.mount("/", StaticFiles(directory=str(HERE), html=True), name="static")