Embedding Recipes

import numpy as np
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
import umap

Z = StandardScaler().fit_transform(X)
if Z.shape[1] > 50:
    Z = PCA(n_components=50, random_state=0).fit_transform(Z)
Y_pca = PCA(n_components=2).fit_transform(Z)
Y_tsne = TSNE(perplexity=30, init="pca", learning_rate="auto", max_iter=1000, random_state=0).fit_transform(Z)
Y_umap = umap.UMAP(n_neighbors=15, min_dist=0.1, random_state=0).fit_transform(Z)

from sklearn.preprocessing import normalize
E = normalize(embeddings)                               # unit vectors
Y = umap.UMAP(n_neighbors=30, min_dist=0.05, metric="cosine", random_state=0).fit_transform(E)

from sklearn.cluster import HDBSCAN
U = umap.UMAP(n_components=10, n_neighbors=30, min_dist=0.0, metric="cosine", random_state=0).fit_transform(E)
labels = HDBSCAN(min_cluster_size=25).fit_predict(U)
Y2 = umap.UMAP(n_components=2, n_neighbors=30, min_dist=0.1, metric="cosine", random_state=0).fit_transform(E)
# plot Y2 coloured by labels; the clustering itself happened in 10-D

reducer = umap.UMAP(n_neighbors=15, random_state=0).fit(Z_train)
Y_new = reducer.transform(Z_new)                       # same scaler / PCA applied to Z_new first

Y_sup = umap.UMAP(random_state=0).fit_transform(Z, y=labels)          # -1 for unlabelled points

import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(6, 6))
for lv in np.unique(labels):
    m = labels == lv
    ax.scatter(Y[m, 0], Y[m, 1], s=4, alpha=0.7, label=str(lv))
ax.set_xticks([]); ax.set_yticks([]); ax.legend(markerscale=4)
ax.set_title("UMAP (n_neighbors=15, min_dist=0.1, seed 0) - sizes/distances not to scale")

from sklearn.manifold import trustworthiness
trustworthiness(Z, Y, n_neighbors=10)            # same as embedding_trust.py