Source: /home/coolhand/html/datavis/data_trove/data/attention/gdelt_timeline.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/data/attention/gdelt_timeline.json",
"--findings", "data-trove-gdelt-global-events.json",
"--llm", "anthropic:default",
])This dataset is a single-row JSON file (gdelt_timeline.json) containing two columns — 'countries' and 'metadata' — likely representing a GDELT event timeline snapshot. With only 1 row and both columns flagged as 'unknown' kind with no computable statistics, there is effectively no statistical signal to analyse at this stage. The file may contain nested or complex JSON structures (arrays, objects) that require unpacking before any meaningful exploration can begin. The immediate priority should be inspecting the raw structure of both columns to understand what nested data they contain.
citing: row_count · column_count · columns[0].alerts · columns[1].alerts · columns[0].null_rate · columns[1].null_rate
| column | kind | null % |
|---|---|---|
| metadata | unknown | 0.0% |
| countries | unknown | 0.0% |
This column contains a single row and was skipped by the profiler, yielding no distributional statistics. With n=1 and kind='unknown', nothing meaningful can be inferred about its content, type, or role beyond the column name 'metadata'. The complete absence of computed stats means any downstream assessment is premature.
Treatment: Inspect raw value manually before deciding whether to parse, drop, or expand into sub-fields.
saturn.columns["metadata"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | — |
| alert: skipped | no profiler for kind=unknown |
This column contains only 1 row and was skipped by the profiler, yielding no distributional statistics. With n=1 and no uniqueness or value-level evidence, nothing meaningful can be inferred about its content beyond the name suggesting it holds country identifiers or labels. The combination of a single record and a 'skipped' alert means all downstream assumptions are unsupported by data.
Treatment: Inspect raw value manually; re-profile with a larger sample before assigning a role or transformation.
saturn.columns["countries"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | — |
| alert: skipped | no profiler for kind=unknown |
click to copy
@misc{saturn-data-trove-gdelt-global-events-2026,
author = {Steuber, Luke},
title = {Saturn reading: data trove gdelt global events},
year ={2026},
howpublished = {\url{https://dr.eamer.dev/saturn/view/data-trove-gdelt-global-events}},
note = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:default},
}
Steuber, L. (2026). Saturn reading: data trove gdelt global events. Source: /home/coolhand/html/datavis/data_trove/data/attention/gdelt_timeline.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:default). Retrieved from https://dr.eamer.dev/saturn/view/data-trove-gdelt-global-events