**The most important metric is `petal_length`.** It separates the three species better than any other measure here. **Why petal length** - The per-species ranges (from the `iris_by_species` gold table) show setosa's petal lengths run 1.0–1.9, with a mean of 1.46. - Versicolor runs 3.0–5.1 (mean 4.26), and virginica runs 4.5–6.9 (mean 5.55). - Setosa has no overlap with the other two species, because its maximum of 1.9 is below versicolor's minimum of 3.0. - Versicolor and virginica overlap only in a narrow band of 4.5–5.1. - Sepal width is the weakest separator. Its species means sit within about 0.65 of each other, and its ranges overlap heavily (setosa 2.3–4.4, versicolor 2.0–3.4, virginica 2.2–3.8). - This pick rests on the ranges and means alone. I did not run a formal feature-importance test, and petal width looks nearly as discriminating. **Highest and lowest records by petal length** - **Highest:** a virginica specimen with petal length 6.9, petal width 2.3, sepal length 7.7 and sepal width 2.6. - **Lowest:** a setosa specimen with petal length 1.0, petal width 0.2, sepal length 4.6 and sepal width 3.6. The two extremes come from opposite species. They also differ far more in petal length (6.9 vs 1.0) than in sepal width (2.6 vs 3.6). This is why petal length is a strong feature for classifying new specimens.