What does Completing Preferences from Sparse Purchases conclude, in numbers, about “Eastern and Western Sources: "Things of a Kind Gather Together" and Spearman's General Factor”?

Answer: Chapter 7 examines "things of a kind gather together, creatures divide into groups" from the Great Commentary of the Book of Changes and Spearman's general factor of 1904, showing that pure groups and mixed membership each favour a different model.

Scope of the numbers: Marked boxes separate published evidence, runnable Python calculations (23 programs), classical sources and the author's hypotheses.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python only

RMSE on unobserved cells against the noise-free taste
customersblock meanslow rank (ALS, r = 4)
pure0.03790.2428
mixed0.40920.2971
Show the full program
# Chapter 7. p72: "like gathers with like" as a block model.
# Model: 60 customers x 24 products, 4 customer groups x 4 product
# categories, group-by-category taste table G (Gaussian sd 2, plus 3).
# Pure: each customer belongs to one group. Mixed: each customer
# blends the groups with random weights. Scores carry noise sd 0.2;
# 40 percent observed (illustrative). Block model: mean of observed
# scores in the customer's main group x the product's category.
# Low rank: ALS rank 4 (ridge 0.3, spectral start) on centred scores.
import math
import random


def dot(a, b):
    return math.fsum(x * y for x, y in zip(a, b))


def solve(A, b):
    # Gaussian elimination with partial pivoting for a small system
    n = len(b)
    M = [list(A[i]) + [b[i]] for i in range(n)]
    for k in range(n):
        p = max(range(k, n), key=lambda i: abs(M[i][k]))
        M[k], M[p] = M[p], M[k]
        for i in range(k + 1, n):
            f = M[i][k] / M[k][k]
            M[i] = [M[i][j] - f * M[k][j] for j in range(n + 1)]
    x = [0.0] * n
    for i in range(n - 1, -1, -1):
        s = math.fsum(M[i][j] * x[j] for j in range(i + 1, n))
        x[i] = (M[i][n] - s) / M[i][i]
    return x


def update(trip, F, r, lam, prior=None):
    # weighted ridge step for one row: minimise
    # sum w (y - f.x)^2 + lam |x - prior|^2 over x
    pr = prior if prior is not None else [0.0] * r
    A = [[math.fsum(w * F[j][a] * F[j][b] for j, _, w in trip)
          + (lam if a == b else 0.0) for b in range(r)]
         for a in range(r)]
    y = [math.fsum(w * F[j][a] * v for j, v, w in trip) + lam * pr[a]
         for a in range(r)]
    return solve(A, y)


def als(nu, ni, obs, r, lam, iters, seed, V=None, trace=None):
    # alternating least squares on (u, i, value, weight) tuples
    rng = random.Random(seed)
    if V is None:
        V = [[rng.gauss(0.0, 1.0) for _ in range(r)] for _ in range(ni)]
    bu = [[] for _ in range(nu)]
    bi = [[] for _ in range(ni)]
    for u, i, x, w in obs:
        bu[u].append((i, x, w))
        bi[i].append((u, x, w))
    U = None
    for t in range(iters):
        U = [update(bu[u], V, r, lam) for u in range(nu)]
        V = [update(bi[i], U, r, lam) for i in range(ni)]
        if trace is not None:
            trace.append((t + 1, U, V))
    return U, V


def factors(n, r, rng):
    return [[rng.gauss(0.0, 1.0) for _ in range(r)] for _ in range(n)]


def product(A, B):
    return [[dot(a, b) for b in B] for a in A]


def mask(nu, ni, p, rng):
    return [(u, i) for u in range(nu) for i in range(ni)
            if rng.random() < p]


def relerr(M, U, V, cells):
    num = math.fsum((dot(U[u], V[i]) - M[u][i]) ** 2 for u, i in cells)
    den = math.fsum(M[u][i] ** 2 for u, i in cells)
    return math.sqrt(num / den)


def rmse(M, U, V, cells):
    num = math.fsum((dot(U[u], V[i]) - M[u][i]) ** 2 for u, i in cells)
    return math.sqrt(num / len(cells))


def orthonormal(cols):
    # Gram-Schmidt on a list of column vectors
    out = []
    for c in cols:
        v = list(c)
        for q in out:
            h = dot(q, v)
            v = [a - h * b for a, b in zip(v, q)]
        nv = math.sqrt(dot(v, v))
        out.append([a / nv for a in v])
    return out


def spectral(nu, ni, cells, r, rng, iters=30):
    # top-r right singular subspace of the rescaled observed matrix:
    # Y[u][i] = x / p for observed cells, 0 elsewhere
    Y = [[0.0] * ni for _ in range(nu)]
    for u, i, x, p in cells:
        Y[u][i] = x / p
    Yt = [list(c) for c in zip(*Y)]
    Q = orthonormal([[rng.gauss(0, 1) for _ in range(ni)]
                     for _ in range(r)])
    for _ in range(iters):
        Q = orthonormal([[dot(row, [dot(y, q) for y in Y]) for row in Yt]
                         for q in Q])
    return [[Q[k][i] for k in range(r)] for i in range(ni)]

nu, ni, K = 60, 24, 4
res = []
for kind in ("pure", "mixed"):
    rng = random.Random(20261113)
    G = [[2 * rng.gauss(0, 1) for _ in range(K)] for _ in range(K)]
    ct = [i % K for i in range(ni)]
    W = []
    for u in range(nu):
        if kind == "pure":
            W.append([1.0 if g == u % K else 0.0 for g in range(K)])
        else:
            x = [rng.expovariate(1.0) for _ in range(K)]
            W.append([v / math.fsum(x) for v in x])
    T = [[3.0 + math.fsum(W[u][g] * G[g][ct[i]] for g in range(K))
          for i in range(ni)] for u in range(nu)]
    seen = mask(nu, ni, 0.4, rng)
    ss = set(seen)
    rest = [(u, i) for u in range(nu) for i in range(ni)
            if (u, i) not in ss]
    y = {c: T[c[0]][c[1]] + rng.gauss(0, 0.2) for c in seen}
    main = [max(range(K), key=lambda g: W[u][g]) for u in range(nu)]
    blk = {}
    for (u, i), v in y.items():
        blk.setdefault((main[u], ct[i]), []).append(v)
    bm = {key: math.fsum(v) / len(v) for key, v in blk.items()}
    e1 = math.sqrt(math.fsum((bm[(main[u], ct[i])] - T[u][i]) ** 2
                             for u, i in rest) / len(rest))
    g0 = math.fsum(y.values()) / len(y)
    obs = [(u, i, y[(u, i)] - g0, 1.0) for u, i in seen]
    V0 = spectral(nu, ni, [(u, i, x, 0.4) for u, i, x, _ in obs], K, rng)
    U, V = als(nu, ni, obs, K, 0.3, 100, 8, V=V0)
    e2 = math.sqrt(math.fsum((g0 + dot(U[u], V[i]) - T[u][i]) ** 2
                             for u, i in rest) / len(rest))
    res.append((kind, e1, e2))
print("RMSE on unobserved cells against the noise-free taste")
print(" customers    block means   low rank (ALS, r = 4)")
for kind, a, b in res:
    print(" {:9s}      {:.4f}        {:.4f}".format(kind, a, b))

Single source and citation

Fan, Y. (2026). Low-Rank Matrix Completion and Alternating Least Squares: Inferring Unstated Preferences from Sparse Purchase Records (Version 1.0.0), Chapter 7: Eastern and Western Sources: "Things of a Kind Gather Together" and Spearman's General Factor. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-328 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026328,
  author    = {Fan, Yafu},
  title     = {Low-Rank Matrix Completion and Alternating Least Squares: Inferring Unstated Preferences from Sparse Purchase Records},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book