education education by county

saturn notebook · generated 2026-05-01 Report Notebook

Overview

Source: /home/coolhand/datasets/us-inequality-atlas/education/education_by_county.csv

Saturn profiled 3,222 rows across 6 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).

[2]:

!pip install saturn-dissect
import subprocess
subprocess.run([
    "saturn", "analyze", "/home/coolhand/datasets/us-inequality-atlas/education/education_by_county.csv",
    "--findings", "education-education_by_county.json",
    "--llm", "anthropic:claude-opus-4-7",
])

Summary confidence: high

This dataset contains 3,222 US county-level education records with 6 columns covering county identifiers (county_name, fips, state) and educational attainment metrics (pct_hs_or_higher, pct_bachelors_or_higher, total_25_plus). The bachelor's degree rate averages 23.5% but ranges from 0% to nearly 79%, suggesting wide regional disparities worth investigating. The total_25_plus population column is heavily skewed (skew=13.5) with 440 outliers and a max of nearly 6.9 million, so any analysis using it should consider log transforms or per-capita normalization. State coverage is fairly even across 52 entries, with TX, GA, and VA contributing the most counties.

citing: row_count · column_count · columns.pct_bachelors_or_higher.stats · columns.pct_hs_or_higher.stats · columns.total_25_plus.stats · columns.state.top_values · columns.county_name.top_values

Out[4]:

saturn.schema() · 6 columns

column	kind	n	null%	unique	alerts
fips	numeric	3,222	0.0%	3,222
county_name	text	3,222	0.0%	1,960	short_text duplicates
state	categorical	3,222	0.0%	52
total_25_plus	numeric	3,222	0.0%	3,140	high_skew outliers
pct_hs_or_higher	numeric	3,222	0.0%	1,612
pct_bachelors_or_higher	numeric	3,222	0.0%	1,982

Fig 1.

pct_bachelors_or_higher · Shows the wide spread of college attainment across counties, from 0% to nearly 79%.

Show data table

Histogram bins for pct_bachelors_or_higher (median: 21.07).
bin	count
0 – 1.972	1
1.972 – 3.944	0
3.944 – 5.915	4
5.915 – 7.887	9
7.887 – 9.859	32
9.859 – 11.83	135
11.83 – 13.8	169
13.8 – 15.77	317
15.77 – 17.75	328
17.75 – 19.72	376
19.72 – 21.69	345
21.69 – 23.66	262
23.66 – 25.63	232
25.63 – 27.6	189
27.6 – 29.58	123
29.58 – 31.55	116
31.55 – 33.52	118
33.52 – 35.49	96
35.49 – 37.46	60
37.46 – 39.44	68
39.44 – 41.41	40
41.41 – 43.38	34
43.38 – 45.35	34
45.35 – 47.32	24
47.32 – 49.29	21
49.29 – 51.27	19
51.27 – 53.24	15
53.24 – 55.21	10
55.21 – 57.18	11
57.18 – 59.15	10
59.15 – 61.12	9
61.12 – 63.1	6
63.1 – 65.07	5
65.07 – 67.04	1
67.04 – 69.01	0
69.01 – 70.98	1
70.98 – 72.95	0
72.95 – 74.93	0
74.93 – 76.9	1
76.9 – 78.87	1

Fig 2.

pct_hs_or_higher · Most counties cluster near 88-89% high school completion, with a long left tail of low-attainment counties.

Show data table

Histogram bins for pct_hs_or_higher (median: 89.39).
bin	count
33.33 – 34.99	1
34.99 – 36.65	0
36.65 – 38.31	0
38.31 – 39.97	0
39.97 – 41.62	0
41.62 – 43.28	0
43.28 – 44.94	0
44.94 – 46.6	0
46.6 – 48.26	0
48.26 – 49.92	0
49.92 – 51.58	0
51.58 – 53.24	0
53.24 – 54.9	0
54.9 – 56.56	1
56.56 – 58.22	1
58.22 – 59.87	1
59.87 – 61.53	3
61.53 – 63.19	3
63.19 – 64.85	3
64.85 – 66.51	2
66.51 – 68.17	6
68.17 – 69.83	7
69.83 – 71.49	15
71.49 – 73.15	30
73.15 – 74.81	30
74.81 – 76.46	46
76.46 – 78.12	60
78.12 – 79.78	88
79.78 – 81.44	131
81.44 – 83.1	174
83.1 – 84.76	189
84.76 – 86.42	256
86.42 – 88.08	289
88.08 – 89.74	360
89.74 – 91.39	429
91.39 – 93.05	460
93.05 – 94.71	389
94.71 – 96.37	192
96.37 – 98.03	47
98.03 – 99.69	9

Fig 3.

total_25_plus · Highly skewed population distribution; consider log-scaling to see the bulk of small/medium counties.

Show data table

Histogram bins for total_25_plus (median: 18313.5).
bin	count
50 – 1.728e+05	2948
1.728e+05 – 3.455e+05	135
3.455e+05 – 5.183e+05	53
5.183e+05 – 6.91e+05	37
6.91e+05 – 8.638e+05	13
8.638e+05 – 1.036e+06	10
1.036e+06 – 1.209e+06	7
1.209e+06 – 1.382e+06	4
1.382e+06 – 1.555e+06	2
1.555e+06 – 1.727e+06	5
1.727e+06 – 1.9e+06	1
1.9e+06 – 2.073e+06	1
2.073e+06 – 2.246e+06	1
2.246e+06 – 2.418e+06	1
2.418e+06 – 2.591e+06	0
2.591e+06 – 2.764e+06	0
2.764e+06 – 2.937e+06	0
2.937e+06 – 3.109e+06	2
3.109e+06 – 3.282e+06	0
3.282e+06 – 3.455e+06	0
3.455e+06 – 3.628e+06	0
3.628e+06 – 3.8e+06	1
3.8e+06 – 3.973e+06	0
3.973e+06 – 4.146e+06	0
4.146e+06 – 4.319e+06	0
4.319e+06 – 4.491e+06	0
4.491e+06 – 4.664e+06	0
4.664e+06 – 4.837e+06	0
4.837e+06 – 5.01e+06	0
5.01e+06 – 5.182e+06	0
5.182e+06 – 5.355e+06	0
5.355e+06 – 5.528e+06	0
5.528e+06 – 5.7e+06	0
5.7e+06 – 5.873e+06	0
5.873e+06 – 6.046e+06	0
6.046e+06 – 6.219e+06	0
6.219e+06 – 6.391e+06	0
6.391e+06 – 6.564e+06	0
6.564e+06 – 6.737e+06	0
6.737e+06 – 6.91e+06	1

Fig 4.

state · Counties per state — TX, GA, and VA contribute the highest counts.

Show data table

Top values for state (20 unique shown, of 52 total).
value	count	share
TX	254	7.9%
GA	159	4.9%
VA	133	4.1%
KY	120	3.7%
MO	115	3.6%
KS	105	3.3%
IL	102	3.2%
NC	100	3.1%
IA	99	3.1%
TN	95	2.9%
NE	93	2.9%
IN	92	2.9%
OH	88	2.7%
MN	87	2.7%
MI	83	2.6%
MS	82	2.5%
PR	78	2.4%
OK	77	2.4%
AR	75	2.3%
WI	72	2.2%

Fig 5.

Per-column null rate across the corpus. Columns are ordered by input position.

Show data table

Per-column null rate across the corpus.
column	kind	null %
fips	numeric	0.0%
county_name	text	0.0%
state	categorical	0.0%
total_25_plus	numeric	0.0%
pct_hs_or_higher	numeric	0.0%
pct_bachelors_or_higher	numeric	0.0%

Fig 6.

Pearson correlation across numeric columns (sampled, bounded).

Show data table

Pearson correlation across 4 numeric columns (values clipped to 2 decimals).
	fips	total_25_plus	pct_hs_or_higher	pct_bachelors_or_higher
fips	+1.00	-0.07	-0.09	+0.03
total_25_plus	-0.07	+1.00	+0.08	+0.34
pct_hs_or_higher	-0.09	+0.08	+1.00	+0.57
pct_bachelors_or_higher	+0.03	+0.34	+0.57	+1.00

fips numeric identifier

This column holds U.S. FIPS county/state codes: every one of the 3222 rows is unique, no nulls, and values span 1001 to 72153, consistent with state-prefixed county identifiers. The distribution is roughly symmetric (skew 0.16, kurtosis -0.63) with no outliers, which is expected for an enumerated geographic key rather than a measured quantity. Treat the numeric stats as incidental — these are categorical identifiers, not magnitudes.

Treatment: Cast to zero-padded string and use as a join key to county/state geographies; do not model as a number.

anthropic:claude-opus-4-7 · confidence high

Out[12]:

saturn.columns["fips"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	3,222
min	1,001
max	72,153
mean	3.138e+04
median	30,022
std	1.63e+04
q1	1.903e+04
q3	4.61e+04
iqr	27,075
skew	0.1574
kurtosis	-0.6314
n_outliers	0
outlier_rate	0
zero_rate	0

Fig 7.

Distribution of fips. Vertical dash marks the median.

Show data table

Histogram bins for fips (median: 30022.0).
bin	count
1001 – 2780	97
2780 – 4559	15
4559 – 6337	133
6337 – 8116	59
8116 – 9895	14
9895 – 1.167e+04	4
1.167e+04 – 1.345e+04	226
1.345e+04 – 1.523e+04	5
1.523e+04 – 1.701e+04	49
1.701e+04 – 1.879e+04	189
1.879e+04 – 2.057e+04	204
2.057e+04 – 2.235e+04	184
2.235e+04 – 2.413e+04	39
2.413e+04 – 2.59e+04	15
2.59e+04 – 2.768e+04	170
2.768e+04 – 2.946e+04	196
2.946e+04 – 3.124e+04	150
3.124e+04 – 3.302e+04	27
3.302e+04 – 3.48e+04	21
3.48e+04 – 3.658e+04	95
3.658e+04 – 3.836e+04	153
3.836e+04 – 4.013e+04	155
4.013e+04 – 4.191e+04	46
4.191e+04 – 4.369e+04	67
4.369e+04 – 4.547e+04	51
4.547e+04 – 4.725e+04	161
4.725e+04 – 4.903e+04	268
4.903e+04 – 5.081e+04	29
5.081e+04 – 5.259e+04	133
5.259e+04 – 5.436e+04	94
5.436e+04 – 5.614e+04	95
5.614e+04 – 5.792e+04	0
5.792e+04 – 5.97e+04	0
5.97e+04 – 6.148e+04	0
6.148e+04 – 6.326e+04	0
6.326e+04 – 6.504e+04	0
6.504e+04 – 6.682e+04	0
6.682e+04 – 6.86e+04	0
6.86e+04 – 7.037e+04	0
7.037e+04 – 7.215e+04	78

county_name text metadata

This is a US county-level place-name field: 2-word entries averaging 14 characters, with 'County' appearing 2999 times alongside 'Parish' (64, Louisiana) and 'Municipio' (78, Puerto Rico). Duplication is heavy at 39.2% (1262 rows) because common names like Washington County (30), Jefferson County (25), and Franklin County (24) recur across states — so this column is not unique on its own. With 1960 distinct values across 3222 rows, it needs a state qualifier to act as a key.

Treatment: Concatenate with a state/territory code before using as a join key; do not treat as unique.

anthropic:claude-opus-4-7 · confidence high

Out[15]:

saturn.columns["county_name"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	1,960
len_min	10
len_max	46
len_mean	14.17
len_median	14
len_p95	18
word_mean	2.083
word_median	2
n_empty	0
n_duplicates	1,262
duplicate_rate	0.3917
vocab_size	1,963
readability_flesch_mean	33.36
emoji_rate	0
url_rate	0
one_word_rate	0
allcaps_rate	0
boilerplate_rate	0
alert: short_text	95th-percentile length under 20 chars
alert: duplicates	39.2% duplicate strings

Fig 8.

Character-length distribution for county_name.

Show data table

Character-length distribution for county_name (mean: 14.172253258845437).
chars	count
10 – 11	29
11 – 12	255
12 – 13	465
13 – 14	682
14 – 14	588
14 – 15	493
15 – 16	291
16 – 17	219
17 – 18	67
18 – 19	0
19 – 20	49
20 – 21	23
21 – 22	16
22 – 23	14
23 – 24	8
24 – 24	4
24 – 25	5
25 – 26	2
26 – 27	1
27 – 28	0
28 – 29	1
29 – 30	0
30 – 31	0
31 – 32	2
32 – 32	1
32 – 33	1
33 – 34	1
34 – 35	1
35 – 36	0
36 – 37	0
37 – 38	0
38 – 39	0
39 – 40	0
40 – 41	2
41 – 42	1
42 – 42	0
42 – 43	0
43 – 44	0
44 – 45	0
45 – 46	1

state categorical feature

This is a US state code column with 52 distinct values, matching the 50 states plus likely DC and a territory. Distribution is fairly even (entropy ratio 0.93), with TX leading at 254 rows (7.88%) followed by GA, VA, and KY — consistent with county-level row counts where larger states contribute more records. No nulls.

Treatment: one-hot or target-encode for modelling; usable as a join key to state-level reference tables.

anthropic:claude-opus-4-7 · confidence high

Out[18]:

saturn.columns["state"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	52
top_value	TX
top_rate	0.07883
cardinality	52
entropy	5.314
entropy_ratio	0.9322

Fig 9.

Top values for state.

Show data table

Top values for state (20 unique shown, of 52 total).
value	count	share
TX	254	7.9%
GA	159	4.9%
VA	133	4.1%
KY	120	3.7%
MO	115	3.6%
KS	105	3.3%
IL	102	3.2%
NC	100	3.1%
IA	99	3.1%
TN	95	2.9%
NE	93	2.9%
IN	92	2.9%
OH	88	2.7%
MN	87	2.7%
MI	83	2.6%
MS	82	2.5%
PR	78	2.4%
OK	77	2.4%
AR	75	2.3%
WI	72	2.2%

total_25_plus numeric feature

A heavily right-skewed count of population (or units) aged 25 and over per row, ranging from 50 to 6,909,650 with a median of 18,313.5 but a mean of 71,074.3. Skew of 13.5 and kurtosis of 306.9 indicate a long heavy tail, and 440 rows (13.7%) flag as outliers. No nulls or zeros, and 3,140 of 3,222 values are unique, consistent with geographic aggregates of varying size.

Treatment: log-transform before any regression or distance-based modelling.

anthropic:claude-opus-4-7 · confidence high

Out[21]:

saturn.columns["total_25_plus"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	3,140
min	50
max	6.91e+06
mean	7.107e+04
median	1.831e+04
std	2.266e+05
q1	7696
q3	4.649e+04
iqr	3.879e+04
skew	13.51
kurtosis	306.9
n_outliers	440
outlier_rate	0.1366
zero_rate	0
alert: high_skew	skew=+13.51
alert: outliers	13.7% rows beyond 1.5 IQR

Fig 10.

Distribution of total_25_plus. Vertical dash marks the median.

Show data table

Histogram bins for total_25_plus (median: 18313.5).
bin	count
50 – 1.728e+05	2948
1.728e+05 – 3.455e+05	135
3.455e+05 – 5.183e+05	53
5.183e+05 – 6.91e+05	37
6.91e+05 – 8.638e+05	13
8.638e+05 – 1.036e+06	10
1.036e+06 – 1.209e+06	7
1.209e+06 – 1.382e+06	4
1.382e+06 – 1.555e+06	2
1.555e+06 – 1.727e+06	5
1.727e+06 – 1.9e+06	1
1.9e+06 – 2.073e+06	1
2.073e+06 – 2.246e+06	1
2.246e+06 – 2.418e+06	1
2.418e+06 – 2.591e+06	0
2.591e+06 – 2.764e+06	0
2.764e+06 – 2.937e+06	0
2.937e+06 – 3.109e+06	2
3.109e+06 – 3.282e+06	0
3.282e+06 – 3.455e+06	0
3.455e+06 – 3.628e+06	0
3.628e+06 – 3.8e+06	1
3.8e+06 – 3.973e+06	0
3.973e+06 – 4.146e+06	0
4.146e+06 – 4.319e+06	0
4.319e+06 – 4.491e+06	0
4.491e+06 – 4.664e+06	0
4.664e+06 – 4.837e+06	0
4.837e+06 – 5.01e+06	0
5.01e+06 – 5.182e+06	0
5.182e+06 – 5.355e+06	0
5.355e+06 – 5.528e+06	0
5.528e+06 – 5.7e+06	0
5.7e+06 – 5.873e+06	0
5.873e+06 – 6.046e+06	0
6.046e+06 – 6.219e+06	0
6.219e+06 – 6.391e+06	0
6.391e+06 – 6.564e+06	0
6.564e+06 – 6.737e+06	0
6.737e+06 – 6.91e+06	1

pct_hs_or_higher numeric feature

This column reports the percentage of a population with at least a high school education, ranging from 33.33 to 99.69 with a mean of 88.08 and median of 89.39. The distribution is left-skewed (skew -1.33) with heavy tails (kurtosis 3.74), and 86 low-end outliers (2.67%) pull below the bulk concentrated between Q1 84.9 and Q3 92.47. With 1612 unique values across 3222 rows and no nulls, it looks like a clean geographic feature (likely county- or tract-level).

Treatment: Use as-is or apply a reflected log/Box-Cox to address the left skew before linear modelling.

anthropic:claude-opus-4-7 · confidence high

Out[24]:

saturn.columns["pct_hs_or_higher"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	1,612
min	33.33
max	99.69
mean	88.08
median	89.39
std	5.97
q1	84.9
q3	92.47
iqr	7.567
skew	-1.328
kurtosis	3.742
n_outliers	86
outlier_rate	0.02669
zero_rate	0

Fig 11.

Distribution of pct_hs_or_higher. Vertical dash marks the median.

Show data table

Histogram bins for pct_hs_or_higher (median: 89.39).
bin	count
33.33 – 34.99	1
34.99 – 36.65	0
36.65 – 38.31	0
38.31 – 39.97	0
39.97 – 41.62	0
41.62 – 43.28	0
43.28 – 44.94	0
44.94 – 46.6	0
46.6 – 48.26	0
48.26 – 49.92	0
49.92 – 51.58	0
51.58 – 53.24	0
53.24 – 54.9	0
54.9 – 56.56	1
56.56 – 58.22	1
58.22 – 59.87	1
59.87 – 61.53	3
61.53 – 63.19	3
63.19 – 64.85	3
64.85 – 66.51	2
66.51 – 68.17	6
68.17 – 69.83	7
69.83 – 71.49	15
71.49 – 73.15	30
73.15 – 74.81	30
74.81 – 76.46	46
76.46 – 78.12	60
78.12 – 79.78	88
79.78 – 81.44	131
81.44 – 83.1	174
83.1 – 84.76	189
84.76 – 86.42	256
86.42 – 88.08	289
88.08 – 89.74	360
89.74 – 91.39	429
91.39 – 93.05	460
93.05 – 94.71	389
94.71 – 96.37	192
96.37 – 98.03	47
98.03 – 99.69	9

pct_bachelors_or_higher numeric feature

This column reports the percentage of residents with a bachelor's degree or higher across 3,222 rows, ranging from 0.0 to 78.87 with a median of 21.07 and mean of 23.50. The distribution is right-skewed (skew 1.36, kurtosis 2.31) with 141 high-end outliers (4.4%) reflecting a long tail of highly-educated areas. Near-zero zero_rate (0.0003) and no nulls suggest clean coverage.

Treatment: Consider a log or sqrt transform to tame the right skew before linear modelling.

anthropic:claude-opus-4-7 · confidence high

Out[27]:

saturn.columns["pct_bachelors_or_higher"].stats

stat	value
n	3,222
nulls	0 (0.0%)
unique	1,982
min	0
max	78.87
mean	23.5
median	21.07
std	9.983
q1	16.59
q3	27.85
iqr	11.26
skew	1.357
kurtosis	2.306
n_outliers	141
outlier_rate	0.04376
zero_rate	0.0003104

Fig 12.

Distribution of pct_bachelors_or_higher. Vertical dash marks the median.

Show data table

Histogram bins for pct_bachelors_or_higher (median: 21.07).
bin	count
0 – 1.972	1
1.972 – 3.944	0
3.944 – 5.915	4
5.915 – 7.887	9
7.887 – 9.859	32
9.859 – 11.83	135
11.83 – 13.8	169
13.8 – 15.77	317
15.77 – 17.75	328
17.75 – 19.72	376
19.72 – 21.69	345
21.69 – 23.66	262
23.66 – 25.63	232
25.63 – 27.6	189
27.6 – 29.58	123
29.58 – 31.55	116
31.55 – 33.52	118
33.52 – 35.49	96
35.49 – 37.46	60
37.46 – 39.44	68
39.44 – 41.41	40
41.41 – 43.38	34
43.38 – 45.35	34
45.35 – 47.32	24
47.32 – 49.29	21
49.29 – 51.27	19
51.27 – 53.24	15
53.24 – 55.21	10
55.21 – 57.18	11
57.18 – 59.15	10
59.15 – 61.12	9
61.12 – 63.1	6
63.1 – 65.07	5
65.07 – 67.04	1
67.04 – 69.01	0
69.01 – 70.98	1
70.98 – 72.95	0
72.95 – 74.93	0
74.93 – 76.9	1
76.9 – 78.87	1

How to cite

click to copy

BibTeX

@misc{saturn-education-education-by-county-2026,
  author       = {Steuber, Luke},
  title        = {Saturn reading: education education by county},
  year         ={2026},
  howpublished = {\url{https://dr.eamer.dev/saturn/view/education-education_by_county}},
  note         = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:claude-opus-4-7},
}

APA

Steuber, L. (2026). Saturn reading: education education by county. Source: /home/coolhand/datasets/us-inequality-atlas/education/education_by_county.csv. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:claude-opus-4-7). Retrieved from https://dr.eamer.dev/saturn/view/education-education_by_county