Measured pairing · from 63,696 recipes

What goes with zucchini?

Measured across 63,696 recipes, the 8 ingredients that co-occur with zucchini most disproportionately are squash (×12.9 chance, n=149), chickpea (×4.0 chance, n=37), basil (×3.8 chance, n=314), romano cheese (×3.6 chance, n=21), mozzarella cheese (×3.2 chance, n=94), parmesan cheese (×3.1 chance, n=226), carrot (×3.1 chance, n=263) and oregano (×3.1 chance, n=209). The score behind the ranking is positive pointwise mutual information — how many times more often a pair shares a recipe than random combination would predict — and n is the number of recipes containing both ingredients. Nothing is published below a floor of 20 recipes per pair and 100 per ingredient. Co-occurrence records what recipe authors actually do — it conflates deliciousness with popularity and tradition — so read it as ethnography, not judgment.

The measured partners — PPMI · ×chance · n

  1. squash — PPMI 2.56 · ×12.9 chance · n=149 (squash itself appears in 583 recipes)
  2. chickpea — PPMI 1.39 · ×4.0 chance · n=37 (chickpea itself appears in 465 recipes)
  3. basil — PPMI 1.34 · ×3.8 chance · n=314 (basil itself appears in 4,153 recipes)
  4. romano cheese — PPMI 1.28 · ×3.6 chance · n=21 (romano cheese itself appears in 293 recipes)
  5. mozzarella cheese — PPMI 1.16 · ×3.2 chance · n=94 (mozzarella cheese itself appears in 1,484 recipes)
  6. parmesan cheese — PPMI 1.14 · ×3.1 chance · n=226 (parmesan cheese itself appears in 3,628 recipes)
  7. carrot — PPMI 1.13 · ×3.1 chance · n=263 (carrot itself appears in 4,268 recipes)
  8. oregano — PPMI 1.12 · ×3.1 chance · n=209 (oregano itself appears in 3,429 recipes)

Cook the pairing

Dishes in Palate's live corpus that use zucchini with one of its measured partners:

How this was measured

zucchini appears in 1,264 of the 63,696 recipes counted (5,296 parsed + 1,081 hand-curated + 57,319 from the dataset published with Ahn et al., 2011). PPMI = max(0, ln(count(A,B)·N / (count(A)·count(B)))), all counts over the same N; lift = e^PMI, which reads directly as "×chance." Staples (salt, sugar, flour, water) are excluded because sources under-record them, and pairs where one name contains the other are excluded as near-duplicates.

Read the numbers with their limits: the corpus is Western-skewed (90% of it is the largely North American and European recipe dataset published with Ahn et al.'s 2011 paper), so the absence of a pairing here proves nothing except who wrote the recipes down. PPMI favors the rare end even above the floor — a niche pair at n=22 can outrank a workhorse pair seen thousands of times, because common ingredients' huge counts divide the score down — so read PPMI and n together.

The full reference — 150 ingredients, top 8 partners each — lives at What actually goes with X.

Curious how these flavors fit your palate — take the short taste test →

Every number above is counted from recipes — pointwise mutual information over 63,696 of them — not chef interviews, model guesses, or reviews.