Source: /home/coolhand/html/datavis/data_trove/data/quirky/insects_by_form.json
Saturn profiled 7 rows across 2 columns. The stats below are deterministic and machine-readable; the prose is a language-model interpretation of those stats (opt-in, added after the fact, never sees raw rows).
!pip install saturn-dissect
import subprocess
subprocess.run([
"saturn", "analyze", "/home/coolhand/html/datavis/data_trove/data/quirky/insects_by_form.json",
"--findings", "data-trove-edible-insects-database.json",
"--llm", "anthropic:default",
])This tiny dataset categorises insect-based food products into 7 form types and records how many products fall into each category. With only 7 rows, the big story is the extreme skew in counts: most form types have just 1–6 products, but one outlier category reaches 57, pulling the mean (10.7) far above the median (3.0). That dominant category is worth identifying immediately, as it likely represents the most commercially developed segment of the edible-insect market. The high standard deviation (20.6) confirms the distribution is anything but uniform.
citing: mean · median · max · std · n_outliers · outlier_rate · skew · top_value · n_unique
| bin | count |
|---|---|
| 1 – 12.2 | 6 |
| 12.2 – 23.4 | 0 |
| 23.4 – 34.6 | 0 |
| 34.6 – 45.8 | 0 |
| 45.8 – 57 | 1 |
| value | count | share |
|---|---|---|
| Whole Insects | 1 | 14.3% |
| Flour/Powder | 1 | 14.3% |
| Protein Products | 1 | 14.3% |
| Snack Bars | 1 | 14.3% |
| Confectionery | 1 | 14.3% |
| Whole Snacks | 1 | 14.3% |
| Crackers | 1 | 14.3% |
| value | count | share |
|---|---|---|
| Whole Insects | 1 | 14.3% |
| Flour/Powder | 1 | 14.3% |
| Protein Products | 1 | 14.3% |
| Snack Bars | 1 | 14.3% |
| Confectionery | 1 | 14.3% |
| Whole Snacks | 1 | 14.3% |
| Crackers | 1 | 14.3% |
| column | kind | null % |
|---|---|---|
| name | categorical | 0.0% |
| count | numeric | 0.0% |
This column contains product category names for what appears to be an insect-based food product taxonomy, with 7 distinct categories such as 'Whole Insects', 'Flour/Powder', 'Snack Bars', and 'Crackers'. Every category appears exactly once (top_rate = 0.143, equal to 1/7), yielding a perfectly uniform distribution and maximum entropy ratio of 1.0. The 'long_tail' alert is a statistical artefact of this uniformity rather than a genuine skew signal. With only 7 rows and 7 unique values, this is likely a small reference/lookup table rather than a transactional dataset.
Treatment: Use as a categorical label or join key against a larger fact table; no encoding needed at this cardinality.
saturn.columns["name"].stats
| stat | value |
|---|---|
| n | 7 |
| nulls | 0 (0.0%) |
| unique | 7 |
| top_value | Whole Insects |
| top_rate | 0.1429 |
| cardinality | 7 |
| entropy | 2.807 |
| entropy_ratio | 1 |
| alert: long_tail | 7 singleton categories |
name.
| value | count | share |
|---|---|---|
| Whole Insects | 1 | 14.3% |
| Flour/Powder | 1 | 14.3% |
| Protein Products | 1 | 14.3% |
| Snack Bars | 1 | 14.3% |
| Confectionery | 1 | 14.3% |
| Whole Snacks | 1 | 14.3% |
| Crackers | 1 | 14.3% |
This column appears to be a frequency or occurrence count, likely recording how many times something was observed across 7 rows with only 4 distinct values. The distribution is severely right-skewed (skew = 1.96) with one outlier: the max of 57.0 sits far above the median of 3.0 and mean of 10.71, pulling the standard deviation to 20.61 — an unusually high spread for such a small dataset. With only 7 rows total, this column provides very limited statistical signal.
Treatment: Investigate the outlier row (value 57.0) for data quality issues; if retained, log-transform before modelling to reduce skew.
saturn.columns["count"].stats
| stat | value |
|---|---|
| n | 7 |
| nulls | 0 (0.0%) |
| unique | 4 |
| min | 1 |
| max | 57 |
| mean | 10.71 |
| median | 3 |
| std | 20.61 |
| q1 | 1 |
| q3 | 6 |
| iqr | 5 |
| skew | 1.965 |
| kurtosis | 1.987 |
| n_outliers | 1 |
| outlier_rate | 0.1429 |
| zero_rate | 0 |
| alert: outliers | 14.3% rows beyond 1.5 IQR |
count. Vertical dash marks the median.
| bin | count |
|---|---|
| 1 – 12.2 | 6 |
| 12.2 – 23.4 | 0 |
| 23.4 – 34.6 | 0 |
| 34.6 – 45.8 | 0 |
| 45.8 – 57 | 1 |
click to copy
@misc{saturn-data-trove-edible-insects-database-2026,
author = {Steuber, Luke},
title = {Saturn reading: data trove edible insects database},
year ={2026},
howpublished = {\url{https://dr.eamer.dev/saturn/view/data-trove-edible-insects-database}},
note = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:default},
}
Steuber, L. (2026). Saturn reading: data trove edible insects database. Source: /home/coolhand/html/datavis/data_trove/data/quirky/insects_by_form.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:default). Retrieved from https://dr.eamer.dev/saturn/view/data-trove-edible-insects-database