Source: /home/coolhand/html/datavis/data_trove/data/quirky/global_sentiment.json
Saturn profiled 1 rows across 5 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/global_sentiment.json",
"--findings", "data-trove-global-sentiment-survey-pew-research.json",
"--llm", "anthropic:default",
])This dataset is a single-record metadata document titled 'How the World Sees America,' aggregating global favorability and presidential confidence data from Pew Research Center surveys covering 2020–2025. With only 1 row and 5 columns, it functions as a descriptor or wrapper rather than a traditional tabular dataset — the real analytical content is almost certainly nested inside the 'countries' and 'metrics' columns, which were skipped during profiling. Those two unknown-type columns are the most important things to examine next, as they likely contain the multi-country time-series data needed for any meaningful analysis. Until those nested structures are unpacked, no statistical patterns can be assessed from the surface-level profile alone.
citing: row_count · column_count · columns[0].stats.top_value · columns[1].stats.top_value · columns[2].stats.top_value · columns[3].alerts · columns[4].alerts
saturn.schema() · 5 columns
| column | kind | n | null% | unique | alerts |
|---|---|---|---|---|---|
| title | categorical | 1 | 0.0% | 1 | long_tail imbalance |
| description | categorical | 1 | 0.0% | 1 | long_tail imbalance |
| source | categorical | 1 | 0.0% | 1 | long_tail imbalance |
| metrics | unknown | 1 | 0.0% | — | skipped |
| countries | unknown | 1 | 0.0% | — | skipped |
| value | count | share |
|---|---|---|
| How the World Sees America | 1 | 100.0% |
| value | count | share |
|---|---|---|
| Aggregated from Pew Global Attitudes Survey summaries, 2020-2025 | 1 | 100.0% |
| value | count | share |
|---|---|---|
| Global favorability toward the United States and confidence in the US president, based on publicly reported survey trends from Pew Research Center and similar organizations. | 1 | 100.0% |
| column | kind | null % |
|---|---|---|
| title | categorical | 0.0% |
| description | categorical | 0.0% |
| source | categorical | 0.0% |
| metrics | unknown | 0.0% |
| countries | unknown | 0.0% |
This column contains a single article or document title — 'How the World Sees America' — and the dataset appears to consist of exactly one row. With n=1, cardinality=1, and top_rate=1.0, the column carries zero discriminative information. The 'long_tail' and 'imbalance' alerts are technically correct but trivially explained by the dataset having only one record.
Treatment: Drop from modelling; useless as a feature with a single row and zero entropy.
saturn.columns["title"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | 1 |
| top_value | How the World Sees America |
| top_rate | 1 |
| cardinality | 1 |
| entropy | 0 |
| entropy_ratio | 0 |
| alert: long_tail | 1 singleton categories |
| alert: imbalance | top value is 100.0% of rows |
title.
| value | count | share |
|---|---|---|
| How the World Sees America | 1 | 100.0% |
This column is a dataset-level description string — a single constant value repeated across all 1 row(s), explaining that the data covers global favorability toward the United States and confidence in the US president sourced from Pew Research Center and similar organizations. With cardinality of 1, entropy of 0.0, and top_rate of 1.0, it carries zero information variance and is purely metadata. The 'long_tail' and 'imbalance' alerts are technically correct but trivially explained by the constant nature of the field.
Treatment: Drop before modelling; retain only as dataset documentation.
saturn.columns["description"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | 1 |
| top_value | Global favorability toward the United States and confidence in the US president, based on publicly reported survey trends from Pew Research Center and similar organizations. |
| top_rate | 1 |
| cardinality | 1 |
| entropy | 0 |
| entropy_ratio | 0 |
| alert: long_tail | 1 singleton categories |
| alert: imbalance | top value is 100.0% of rows |
description.
| value | count | share |
|---|---|---|
| Global favorability toward the United States and confidence in the US president, based on publicly reported survey trends from Pew Research Center and similar organizations. | 1 | 100.0% |
This column records the data provenance or source citation for each row, and contains exactly one unique value across all 1 row(s): 'Aggregated from Pew Global Attitudes Survey summaries, 2020-2025'. With cardinality of 1 and top_rate of 1.0, it is a constant metadata field with zero discriminative power. The entropy of 0.0 confirms it adds no information variance whatsoever.
Treatment: Drop before modelling; retain only as dataset-level documentation.
saturn.columns["source"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | 1 |
| top_value | Aggregated from Pew Global Attitudes Survey summaries, 2020-2025 |
| top_rate | 1 |
| cardinality | 1 |
| entropy | 0 |
| entropy_ratio | 0 |
| alert: long_tail | 1 singleton categories |
| alert: imbalance | top value is 100.0% of rows |
source.
| value | count | share |
|---|---|---|
| Aggregated from Pew Global Attitudes Survey summaries, 2020-2025 | 1 | 100.0% |
This column contains only a single row (n=1) and was flagged as 'skipped' by the profiler, yielding no computable statistics. With n=1 and kind='unknown', no meaningful distributional or type inference is possible. The column cannot be assessed for role, skew, or cardinality.
Treatment: Investigate data pipeline — single-row column with unknown type warrants manual inspection before any downstream use.
saturn.columns["metrics"].stats
| stat | value |
|---|---|
| n | 1 |
| nulls | 0 (0.0%) |
| unique | — |
| alert: skipped | no profiler for kind=unknown |
This column contains only a single row with no null values, and the profiler skipped detailed analysis ('kind: unknown'), leaving no distributional statistics available. With n=1 and no uniqueness or value data, nothing meaningful can be inferred about the column's content or distribution. The name 'countries' suggests a categorical or list-type field, but this cannot be confirmed from the evidence.
Treatment: Inspect raw value manually; profiler skipped this column due to unknown type or single-row dataset — re-profile with a larger sample.
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-global-sentiment-survey-pew-research-2026,
author = {Steuber, Luke},
title = {Saturn reading: data trove global sentiment survey pew research},
year ={2026},
howpublished = {\url{https://dr.eamer.dev/saturn/view/data-trove-global-sentiment-survey-pew-research}},
note = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:default},
}
Steuber, L. (2026). Saturn reading: data trove global sentiment survey pew research. Source: /home/coolhand/html/datavis/data_trove/data/quirky/global_sentiment.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:default). Retrieved from https://dr.eamer.dev/saturn/view/data-trove-global-sentiment-survey-pew-research