Source: /home/coolhand/html/datavis/data_trove/cache/accessibility/census_disability_states_2021.json
Saturn profiled 1 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/cache/accessibility/census_disability_states_2021.json",
"--findings", "data-trove-acs-disability-statistics.json",
"--llm", "anthropic:default",
])This dataset appears to be a JSON file containing 2021 US Census disability data by state, but it contains only 1 row with two opaque columns ('data' and 'metadata') that were skipped during profiling. The profiler was unable to parse the internal structure of either column, meaning the actual disability statistics are likely nested within those fields. Before any analysis can proceed, the dataset will need to be unpacked or flattened so that state-level disability metrics become accessible as individual columns.
citing: row_count · column_count · columns[0].alerts · columns[1].alerts · columns[0].kind · columns[1].kind
| column | kind | null % |
|---|---|---|
| metadata | unknown | 0.0% |
| data | unknown | 0.0% |
This column contains a single row with no nulls, but saturn skipped profiling it entirely, leaving kind as 'unknown' and all statistics absent. With n=1 and no uniqueness or value distribution data, almost nothing can be inferred about its content or structure. The 'metadata' name suggests it may hold structured or semi-structured ancillary information, but this is speculation beyond the evidence.
Treatment: Inspect raw value manually; determine if it is JSON/structured data that should be parsed and exploded before any downstream use.
saturn.columns["metadata"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | — |
| alert: skipped | no profiler for kind=unknown |
This column contains only a single row and was skipped during profiling, yielding no distributional statistics. With n=1 and no uniqueness or type information available, nothing meaningful can be inferred about its content or role. The 'unknown' kind flag indicates the profiler could not determine a data type.
Treatment: Inspect raw value manually; re-profile with a larger sample before any downstream use.
saturn.columns["data"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | — |
| alert: skipped | no profiler for kind=unknown |
click to copy
@misc{saturn-data-trove-acs-disability-statistics-2026,
author = {Steuber, Luke},
title = {Saturn reading: data trove acs disability statistics},
year ={2026},
howpublished = {\url{https://dr.eamer.dev/saturn/view/data-trove-acs-disability-statistics}},
note = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:default},
}
Steuber, L. (2026). Saturn reading: data trove acs disability statistics. Source: /home/coolhand/html/datavis/data_trove/cache/accessibility/census_disability_states_2021.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:default). Retrieved from https://dr.eamer.dev/saturn/view/data-trove-acs-disability-statistics