Source: /home/coolhand/html/datavis/data_trove/data/quirky/tornadoes.json
Saturn profiled 70,022 rows across 13 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/tornadoes.json",
"--findings", "quirky-tornadoes.json",
"--llm", "anthropic:claude-opus-4-7",
])This is a tornado event log with 70,022 rows and 13 columns covering dates, times, start/end coordinates, magnitudes, widths, fatalities, injuries, and U.S. state. Geographically it is a U.S.-centered dataset: starting longitudes average around -92.7 and latitudes around 37.1, with Texas (13.3% of records), Kansas, and Oklahoma leading the state counts. The severity fields are highly imbalanced — fatalities are 0 in 97.7% of events and injuries are 0 in 88.8% — so any analysis of harm should focus on the rare non-zero tail. Magnitude (mag) is a more usable categorical signal with 7 levels, dominated by 0 (46%) and 1 (34%). Note that the end-coordinate columns (elat, elon) are null in ~37.7% of rows, which matters if you plan to draw tornado tracks rather than just start points.
citing: row_count · column_count · columns.state.top_values · columns.state.top_rate · columns.fatalities.top_rate · columns.injuries.top_rate · columns.mag.top_values · columns.mag.top_rate · columns.elat.null_rate · columns.elon.null_rate · columns.slat.stats · columns.slon.stats
saturn.schema() · 13 columns
| column | kind | n | null% | unique | alerts |
|---|---|---|---|---|---|
| date | text | 70,022 | 0.0% | 12,639 | one_word allcaps short_text duplicates |
| time | text | 70,022 | 0.0% | 1,438 | one_word allcaps short_text duplicates |
| state | categorical | 70,022 | 0.0% | 53 | |
| mag | categorical | 70,022 | 0.0% | 7 | |
| injuries | categorical | 70,022 | 0.0% | 209 | |
| fatalities | categorical | 70,022 | 0.0% | 50 | imbalance |
| loss | text | 70,022 | 0.0% | 1,019 | one_word allcaps short_text duplicates |
| slat | numeric | 70,022 | 0.0% | 16,016 | |
| slon | numeric | 70,022 | 0.0% | 17,912 | |
| elat | numeric | 70,022 | 37.6% | 16,965 | null_rate |
| elon | numeric | 70,022 | 37.6% | 18,586 | null_rate |
| len | text | 70,022 | 0.0% | 3,663 | one_word allcaps short_text duplicates |
| wid | categorical | 70,022 | 0.0% | 419 |
| value | count | share |
|---|---|---|
| TX | 9345 | 13.3% |
| KS | 4474 | 6.4% |
| OK | 4221 | 6.0% |
| FL | 3620 | 5.2% |
| NE | 3056 | 4.4% |
| IA | 2887 | 4.1% |
| IL | 2835 | 4.0% |
| MS | 2657 | 3.8% |
| AL | 2529 | 3.6% |
| MO | 2462 | 3.5% |
| CO | 2425 | 3.5% |
| LA | 2305 | 3.3% |
| MN | 2118 | 3.0% |
| AR | 1981 | 2.8% |
| SD | 1917 | 2.7% |
| GA | 1898 | 2.7% |
| ND | 1640 | 2.3% |
| IN | 1610 | 2.3% |
| WI | 1515 | 2.2% |
| NC | 1472 | 2.1% |
| value | count | share |
|---|---|---|
| 0 | 32218 | 46.0% |
| 1 | 23782 | 34.0% |
| 2 | 9767 | 13.9% |
| 3 | 2585 | 3.7% |
| -9 | 1024 | 1.5% |
| 4 | 587 | 0.8% |
| 5 | 59 | 0.1% |
| value | count | share |
|---|---|---|
| 0 | 68423 | 97.7% |
| 1 | 830 | 1.2% |
| 2 | 277 | 0.4% |
| 3 | 134 | 0.2% |
| 4 | 77 | 0.1% |
| 5 | 46 | 0.1% |
| 6 | 45 | 0.1% |
| 7 | 32 | 0.0% |
| 9 | 15 | 0.0% |
| 10 | 15 | 0.0% |
| 11 | 14 | 0.0% |
| 8 | 13 | 0.0% |
| 16 | 12 | 0.0% |
| 13 | 8 | 0.0% |
| 17 | 7 | 0.0% |
| 18 | 6 | 0.0% |
| 21 | 6 | 0.0% |
| 12 | 6 | 0.0% |
| 22 | 5 | 0.0% |
| 25 | 4 | 0.0% |
| bin | count |
|---|---|
| 17.72 – 18.8 | 33 |
| 18.8 – 19.89 | 6 |
| 19.89 – 20.97 | 8 |
| 20.97 – 22.05 | 26 |
| 22.05 – 23.13 | 1 |
| 23.13 – 24.22 | 0 |
| 24.22 – 25.3 | 76 |
| 25.3 – 26.38 | 487 |
| 26.38 – 27.46 | 748 |
| 27.46 – 28.55 | 1225 |
| 28.55 – 29.63 | 1468 |
| 29.63 – 30.71 | 3607 |
| 30.71 – 31.79 | 3441 |
| 31.79 – 32.88 | 5003 |
| 32.88 – 33.96 | 4775 |
| 33.96 – 35.04 | 5392 |
| 35.04 – 36.12 | 5164 |
| 36.12 – 37.21 | 4268 |
| 37.21 – 38.29 | 4028 |
| 38.29 – 39.37 | 4807 |
| 39.37 – 40.45 | 5498 |
| 40.45 – 41.54 | 5313 |
| 41.54 – 42.62 | 3995 |
| 42.62 – 43.7 | 3396 |
| 43.7 – 44.78 | 2407 |
| 44.78 – 45.87 | 1720 |
| 45.87 – 46.95 | 1257 |
| 46.95 – 48.03 | 1114 |
| 48.03 – 49.11 | 754 |
| 49.11 – 50.2 | 1 |
| 50.2 – 51.28 | 0 |
| 51.28 – 52.36 | 0 |
| 52.36 – 53.44 | 0 |
| 53.44 – 54.53 | 0 |
| 54.53 – 55.61 | 1 |
| 55.61 – 56.69 | 0 |
| 56.69 – 57.77 | 0 |
| 57.77 – 58.86 | 0 |
| 58.86 – 59.94 | 1 |
| 59.94 – 61.02 | 2 |
| bin | count |
|---|---|
| -163.5 – -161.1 | 2 |
| -161.1 – -158.6 | 9 |
| -158.6 – -156.1 | 25 |
| -156.1 – -153.6 | 8 |
| -153.6 – -151.2 | 0 |
| -151.2 – -148.7 | 0 |
| -148.7 – -146.2 | 0 |
| -146.2 – -143.8 | 1 |
| -143.8 – -141.3 | 0 |
| -141.3 – -138.8 | 0 |
| -138.8 – -136.4 | 0 |
| -136.4 – -133.9 | 0 |
| -133.9 – -131.4 | 0 |
| -131.4 – -128.9 | 0 |
| -128.9 – -126.5 | 0 |
| -126.5 – -124 | 15 |
| -124 – -121.5 | 231 |
| -121.5 – -119.1 | 241 |
| -119.1 – -116.6 | 282 |
| -116.6 – -114.1 | 174 |
| -114.1 – -111.7 | 399 |
| -111.7 – -109.2 | 323 |
| -109.2 – -106.7 | 325 |
| -106.7 – -104.2 | 1782 |
| -104.2 – -101.8 | 4689 |
| -101.8 – -99.3 | 6094 |
| -99.3 – -96.83 | 9665 |
| -96.83 – -94.36 | 8344 |
| -94.36 – -91.89 | 6626 |
| -91.89 – -89.42 | 6618 |
| -89.42 – -86.95 | 6086 |
| -86.95 – -84.48 | 5361 |
| -84.48 – -82.01 | 4363 |
| -82.01 – -79.54 | 3931 |
| -79.54 – -77.07 | 1885 |
| -77.07 – -74.6 | 1618 |
| -74.6 – -72.13 | 541 |
| -72.13 – -69.66 | 285 |
| -69.66 – -67.19 | 71 |
| -67.19 – -64.72 | 28 |
| column | kind | null % |
|---|---|---|
| date | text | 0.0% |
| time | text | 0.0% |
| state | categorical | 0.0% |
| mag | categorical | 0.0% |
| injuries | categorical | 0.0% |
| fatalities | categorical | 0.0% |
| loss | text | 0.0% |
| slat | numeric | 0.0% |
| slon | numeric | 0.0% |
| elat | numeric | 37.6% |
| elon | numeric | 37.6% |
| len | text | 0.0% |
| wid | categorical | 0.0% |
| slat | slon | elat | elon | |
|---|---|---|---|---|
| slat | +1.00 | -0.17 | -0.02 | -0.03 |
| slon | -0.17 | +1.00 | -0.04 | -0.04 |
| elat | -0.02 | -0.04 | +1.00 | -0.16 |
| elon | -0.03 | -0.04 | -0.16 | +1.00 |
This is a date column stored as ISO-formatted text (YYYY-MM-DD), with every value exactly 10 characters long and one token. Across 70,022 rows there are only 12,639 unique dates and an 81.9% duplicate rate, so many records share dates — top value 2011-04-27 appears 207 times. The range spans at least 1974-04-03 to 2023-03-31, suggesting it was misclassified as text rather than a date type.
Treatment: Cast to a proper date type and use for temporal joins or time-based features.
saturn.columns["date"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 12,639 |
| len_min | 10 |
| len_max | 10 |
| len_mean | 10 |
| len_median | 10 |
| len_p95 | 10 |
| word_mean | 1 |
| word_median | 1 |
| n_empty | 0 |
| n_duplicates | 57,383 |
| duplicate_rate | 0.8195 |
| vocab_size | 7,831 |
| readability_flesch_mean | 121.2 |
| emoji_rate | 0 |
| url_rate | 0 |
| one_word_rate | 1 |
| allcaps_rate | 1 |
| boilerplate_rate | 0 |
| alert: one_word | 100.0% rows are a single word |
| alert: allcaps | 100.0% rows are all-caps |
| alert: short_text | 95th-percentile length under 20 chars |
| alert: duplicates | 81.9% duplicate strings |
date.
| chars | count |
|---|---|
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 70022 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 0 |
This column holds clock times stored as 8-character HH:MM:SS strings, with all 70,022 rows non-null and uniform length (len_min=len_max=8). Only 1,438 distinct values appear and 97.95% are duplicates, with afternoon/evening slots like 16:00:00 (978), 17:00:00 (971) and 15:00:00 (959) dominating — consistent with event start times rather than free text. It's mistyped as text: parse to a proper time type before use.
Treatment: Cast to a time type and bucket by hour for modelling.
saturn.columns["time"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 1,438 |
| len_min | 8 |
| len_max | 8 |
| len_mean | 8 |
| len_median | 8 |
| len_p95 | 8 |
| word_mean | 1 |
| word_median | 1 |
| n_empty | 0 |
| n_duplicates | 68,584 |
| duplicate_rate | 0.9795 |
| vocab_size | 1,352 |
| readability_flesch_mean | 121.2 |
| emoji_rate | 0 |
| url_rate | 0 |
| one_word_rate | 1 |
| allcaps_rate | 1 |
| boilerplate_rate | 0 |
| alert: one_word | 100.0% rows are a single word |
| alert: allcaps | 100.0% rows are all-caps |
| alert: short_text | 95th-percentile length under 20 chars |
| alert: duplicates | 97.9% duplicate strings |
time.
| chars | count |
|---|---|
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 70022 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
This is a US state code column with 53 distinct values, slightly more than the 50 states (likely including DC and territories like PR). TX dominates at 13.3% of 70,022 rows, followed by KS (4,474) and OK (4,221), giving a clear southern/plains skew rather than a uniform national distribution. Entropy ratio of 0.847 confirms the distribution is fairly spread but not flat, and there are no nulls.
Treatment: One-hot or target-encode; consider grouping low-frequency states into an 'Other' bucket.
saturn.columns["state"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 53 |
| top_value | TX |
| top_rate | 0.1335 |
| cardinality | 53 |
| entropy | 4.851 |
| entropy_ratio | 0.8468 |
state.
| value | count | share |
|---|---|---|
| TX | 9345 | 13.3% |
| KS | 4474 | 6.4% |
| OK | 4221 | 6.0% |
| FL | 3620 | 5.2% |
| NE | 3056 | 4.4% |
| IA | 2887 | 4.1% |
| IL | 2835 | 4.0% |
| MS | 2657 | 3.8% |
| AL | 2529 | 3.6% |
| MO | 2462 | 3.5% |
| CO | 2425 | 3.5% |
| LA | 2305 | 3.3% |
| MN | 2118 | 3.0% |
| AR | 1981 | 2.8% |
| SD | 1917 | 2.7% |
| GA | 1898 | 2.7% |
| ND | 1640 | 2.3% |
| IN | 1610 | 2.3% |
| WI | 1515 | 2.2% |
| NC | 1472 | 2.1% |
`mag` is a low-cardinality categorical with 7 distinct values dominated by '0' (46% of 70022 rows) and decreasing counts through '1','2','3','4','5'. The ordered integer levels suggest a magnitude or severity code rather than a free category, and the presence of '-9' (1024 rows) is the standout signal — almost certainly a sentinel for missing/unknown that is not being counted as null.
Treatment: Recode '-9' as missing, then treat as an ordinal feature.
saturn.columns["mag"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 7 |
| top_value | 0 |
| top_rate | 0.4601 |
| cardinality | 7 |
| entropy | 1.772 |
| entropy_ratio | 0.6312 |
mag.
| value | count | share |
|---|---|---|
| 0 | 32218 | 46.0% |
| 1 | 23782 | 34.0% |
| 2 | 9767 | 13.9% |
| 3 | 2585 | 3.7% |
| -9 | 1024 | 1.5% |
| 4 | 587 | 0.8% |
| 5 | 59 | 0.1% |
Counts of injuries stored as strings, with 209 distinct values across 70,022 rows and no nulls. The distribution is severely zero-inflated: '0' accounts for 88.8% of records, and entropy ratio is just 0.123. Tail values like '1' through '10' decay quickly but 209 unique tokens suggests very long tails or non-integer entries worth inspecting.
Treatment: Cast to integer and model as a zero-inflated count (e.g., hurdle or ZIP regression).
saturn.columns["injuries"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 209 |
| top_value | 0 |
| top_rate | 0.888 |
| cardinality | 209 |
| entropy | 0.9454 |
| entropy_ratio | 0.1227 |
injuries.
| value | count | share |
|---|---|---|
| 0 | 62177 | 88.8% |
| 1 | 2480 | 3.5% |
| 2 | 1388 | 2.0% |
| 3 | 770 | 1.1% |
| 4 | 484 | 0.7% |
| 5 | 385 | 0.5% |
| 6 | 300 | 0.4% |
| 7 | 194 | 0.3% |
| 8 | 171 | 0.2% |
| 10 | 141 | 0.2% |
| 12 | 120 | 0.2% |
| 9 | 117 | 0.2% |
| 11 | 80 | 0.1% |
| 20 | 71 | 0.1% |
| 15 | 69 | 0.1% |
| 13 | 66 | 0.1% |
| 14 | 55 | 0.1% |
| 30 | 46 | 0.1% |
| 25 | 44 | 0.1% |
| 16 | 43 | 0.1% |
This is a fatality count per event, stored as a categorical/string field with 50 distinct integer values and no nulls across 70,022 rows. The distribution is extremely imbalanced: '0' accounts for 97.72% of records, giving an entropy ratio of just 0.039, with '1' at 830 rows and a long thin tail (2 → 277, 3 → 134, down to single-digit counts at higher values). Despite being typed as categorical, the values are numeric and ordered, so the current encoding is likely a load artifact.
Treatment: Cast to integer and model as a zero-inflated count rather than a categorical.
saturn.columns["fatalities"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 50 |
| top_value | 0 |
| top_rate | 0.9772 |
| cardinality | 50 |
| entropy | 0.2174 |
| entropy_ratio | 0.03852 |
| alert: imbalance | top value is 97.7% of rows |
fatalities.
| value | count | share |
|---|---|---|
| 0 | 68423 | 97.7% |
| 1 | 830 | 1.2% |
| 2 | 277 | 0.4% |
| 3 | 134 | 0.2% |
| 4 | 77 | 0.1% |
| 5 | 46 | 0.1% |
| 6 | 45 | 0.1% |
| 7 | 32 | 0.0% |
| 9 | 15 | 0.0% |
| 10 | 15 | 0.0% |
| 11 | 14 | 0.0% |
| 8 | 13 | 0.0% |
| 16 | 12 | 0.0% |
| 13 | 8 | 0.0% |
| 17 | 7 | 0.0% |
| 18 | 6 | 0.0% |
| 21 | 6 | 0.0% |
| 12 | 6 | 0.0% |
| 22 | 5 | 0.0% |
| 25 | 4 | 0.0% |
Numeric loss values stored as text strings, with all 70,022 entries being single tokens (one_word_rate 1.0) and lengths of 1-10 characters. The distribution is heavily concentrated: '0.0' alone accounts for 22,764 rows and the duplicate_rate is 0.985 across only 1,019 unique values. Mixed formatting is a hazard — '0' and '0.0' appear as separate tokens, so a naive cast will collapse them but string-based grouping won't.
Treatment: Cast to float (normalising '0' vs '0.0') before any modelling or aggregation.
saturn.columns["loss"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 1,019 |
| len_min | 1 |
| len_max | 10 |
| len_mean | 3.181 |
| len_median | 3 |
| len_p95 | 5 |
| word_mean | 1 |
| word_median | 1 |
| n_empty | 0 |
| n_duplicates | 69,003 |
| duplicate_rate | 0.9854 |
| vocab_size | 503 |
| readability_flesch_mean | 121.2 |
| emoji_rate | 0 |
| url_rate | 0 |
| one_word_rate | 1 |
| allcaps_rate | 0.9251 |
| boilerplate_rate | 0 |
| alert: one_word | 100.0% rows are a single word |
| alert: allcaps | 92.5% rows are all-caps |
| alert: short_text | 95th-percentile length under 20 chars |
| alert: duplicates | 98.5% duplicate strings |
loss.
| chars | count |
|---|---|
| 1 – 1 | 5248 |
| 1 – 1 | 0 |
| 1 – 2 | 0 |
| 2 – 2 | 0 |
| 2 – 2 | 0 |
| 2 – 2 | 0 |
| 2 – 3 | 0 |
| 3 – 3 | 0 |
| 3 – 3 | 50873 |
| 3 – 3 | 0 |
| 3 – 3 | 0 |
| 3 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 7040 |
| 4 – 4 | 0 |
| 4 – 5 | 0 |
| 5 – 5 | 0 |
| 5 – 5 | 4912 |
| 5 – 5 | 0 |
| 5 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 1581 |
| 6 – 6 | 0 |
| 6 – 7 | 0 |
| 7 – 7 | 0 |
| 7 – 7 | 292 |
| 7 – 7 | 0 |
| 7 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 58 |
| 8 – 8 | 0 |
| 8 – 9 | 0 |
| 9 – 9 | 0 |
| 9 – 9 | 16 |
| 9 – 9 | 0 |
| 9 – 10 | 0 |
| 10 – 10 | 0 |
| 10 – 10 | 2 |
Values range from 17.72 to 61.02 with a mean of 37.14 and median of 37.03, consistent with a starting latitude (slat) field in decimal degrees, likely covering the contiguous US. The distribution is essentially symmetric (skew 0.04, kurtosis -0.58) with a tight IQR of 7.74 and only 70 outliers (0.10%). No nulls and no zeros, and 16,016 unique values across 70,022 rows suggest repeated coordinates rather than free-form noise.
Treatment: Use as-is for geospatial features; optionally pair with a longitude column for distance or region encoding.
saturn.columns["slat"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 16,016 |
| min | 17.72 |
| max | 61.02 |
| mean | 37.14 |
| median | 37.03 |
| std | 5.09 |
| q1 | 33.19 |
| q3 | 40.93 |
| iqr | 7.74 |
| skew | 0.03792 |
| kurtosis | -0.5825 |
| n_outliers | 70 |
| outlier_rate | 0.0009997 |
| zero_rate | 0 |
slat. Vertical dash marks the median.
| bin | count |
|---|---|
| 17.72 – 18.8 | 33 |
| 18.8 – 19.89 | 6 |
| 19.89 – 20.97 | 8 |
| 20.97 – 22.05 | 26 |
| 22.05 – 23.13 | 1 |
| 23.13 – 24.22 | 0 |
| 24.22 – 25.3 | 76 |
| 25.3 – 26.38 | 487 |
| 26.38 – 27.46 | 748 |
| 27.46 – 28.55 | 1225 |
| 28.55 – 29.63 | 1468 |
| 29.63 – 30.71 | 3607 |
| 30.71 – 31.79 | 3441 |
| 31.79 – 32.88 | 5003 |
| 32.88 – 33.96 | 4775 |
| 33.96 – 35.04 | 5392 |
| 35.04 – 36.12 | 5164 |
| 36.12 – 37.21 | 4268 |
| 37.21 – 38.29 | 4028 |
| 38.29 – 39.37 | 4807 |
| 39.37 – 40.45 | 5498 |
| 40.45 – 41.54 | 5313 |
| 41.54 – 42.62 | 3995 |
| 42.62 – 43.7 | 3396 |
| 43.7 – 44.78 | 2407 |
| 44.78 – 45.87 | 1720 |
| 45.87 – 46.95 | 1257 |
| 46.95 – 48.03 | 1114 |
| 48.03 – 49.11 | 754 |
| 49.11 – 50.2 | 1 |
| 50.2 – 51.28 | 0 |
| 51.28 – 52.36 | 0 |
| 52.36 – 53.44 | 0 |
| 53.44 – 54.53 | 0 |
| 54.53 – 55.61 | 1 |
| 55.61 – 56.69 | 0 |
| 56.69 – 57.77 | 0 |
| 57.77 – 58.86 | 0 |
| 58.86 – 59.94 | 1 |
| 59.94 – 61.02 | 2 |
Values are negative decimal degrees ranging from -163.53 to -64.7151 with a median of -93.5, consistent with western-hemisphere longitudes (the 'slon' name suggests starting longitude). The distribution is mildly left-skewed (-0.32) and concentrated within an IQR of ~11.7 degrees around the central US longitude band. Only 951 outliers (1.36%) fall outside that range, and there are no nulls or zeros.
Treatment: Use as a geographic coordinate; pair with the matching latitude column for spatial features rather than treating as a standalone scalar.
saturn.columns["slon"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 17,912 |
| min | -163.5 |
| max | -64.72 |
| mean | -92.74 |
| median | -93.5 |
| std | 8.677 |
| q1 | -98.4 |
| q3 | -86.69 |
| iqr | 11.71 |
| skew | -0.3229 |
| kurtosis | 2.156 |
| n_outliers | 951 |
| outlier_rate | 0.01358 |
| zero_rate | 0 |
slon. Vertical dash marks the median.
| bin | count |
|---|---|
| -163.5 – -161.1 | 2 |
| -161.1 – -158.6 | 9 |
| -158.6 – -156.1 | 25 |
| -156.1 – -153.6 | 8 |
| -153.6 – -151.2 | 0 |
| -151.2 – -148.7 | 0 |
| -148.7 – -146.2 | 0 |
| -146.2 – -143.8 | 1 |
| -143.8 – -141.3 | 0 |
| -141.3 – -138.8 | 0 |
| -138.8 – -136.4 | 0 |
| -136.4 – -133.9 | 0 |
| -133.9 – -131.4 | 0 |
| -131.4 – -128.9 | 0 |
| -128.9 – -126.5 | 0 |
| -126.5 – -124 | 15 |
| -124 – -121.5 | 231 |
| -121.5 – -119.1 | 241 |
| -119.1 – -116.6 | 282 |
| -116.6 – -114.1 | 174 |
| -114.1 – -111.7 | 399 |
| -111.7 – -109.2 | 323 |
| -109.2 – -106.7 | 325 |
| -106.7 – -104.2 | 1782 |
| -104.2 – -101.8 | 4689 |
| -101.8 – -99.3 | 6094 |
| -99.3 – -96.83 | 9665 |
| -96.83 – -94.36 | 8344 |
| -94.36 – -91.89 | 6626 |
| -91.89 – -89.42 | 6618 |
| -89.42 – -86.95 | 6086 |
| -86.95 – -84.48 | 5361 |
| -84.48 – -82.01 | 4363 |
| -82.01 – -79.54 | 3931 |
| -79.54 – -77.07 | 1885 |
| -77.07 – -74.6 | 1618 |
| -74.6 – -72.13 | 541 |
| -72.13 – -69.66 | 285 |
| -69.66 – -67.19 | 71 |
| -67.19 – -64.72 | 28 |
Almost certainly an event latitude in decimal degrees, with values spanning 17.72 to 61.02 — consistent with locations across North America. The distribution is roughly symmetric (skew 0.03, kurtosis -0.41) and centered near 37.26, with only 78 mild outliers. The standout concern is that 37.65% of rows are null, so coverage is partial.
Treatment: Pair with the matching longitude and impute or filter the 37.65% nulls before any spatial modelling.
saturn.columns["elat"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 26,363 (37.6%) |
| unique | 16,965 |
| min | 17.72 |
| max | 61.02 |
| mean | 37.26 |
| median | 37.13 |
| std | 4.942 |
| q1 | 33.49 |
| q3 | 40.91 |
| iqr | 7.42 |
| skew | 0.03404 |
| kurtosis | -0.4085 |
| n_outliers | 78 |
| outlier_rate | 0.001787 |
| zero_rate | 0 |
| alert: null_rate | 37.6% null |
elat. Vertical dash marks the median.
| bin | count |
|---|---|
| 17.72 – 18.8 | 33 |
| 18.8 – 19.89 | 6 |
| 19.89 – 20.97 | 8 |
| 20.97 – 22.05 | 26 |
| 22.05 – 23.13 | 1 |
| 23.13 – 24.22 | 0 |
| 24.22 – 25.3 | 41 |
| 25.3 – 26.38 | 262 |
| 26.38 – 27.46 | 369 |
| 27.46 – 28.55 | 534 |
| 28.55 – 29.63 | 668 |
| 29.63 – 30.71 | 1952 |
| 30.71 – 31.79 | 2190 |
| 31.79 – 32.88 | 3083 |
| 32.88 – 33.96 | 3018 |
| 33.96 – 35.04 | 3496 |
| 35.04 – 36.12 | 3427 |
| 36.12 – 37.21 | 2899 |
| 37.21 – 38.29 | 2790 |
| 38.29 – 39.37 | 3133 |
| 39.37 – 40.45 | 3414 |
| 40.45 – 41.54 | 3272 |
| 41.54 – 42.62 | 2540 |
| 42.62 – 43.7 | 2078 |
| 43.7 – 44.78 | 1428 |
| 44.78 – 45.87 | 1122 |
| 45.87 – 46.95 | 745 |
| 46.95 – 48.03 | 676 |
| 48.03 – 49.11 | 443 |
| 49.11 – 50.2 | 1 |
| 50.2 – 51.28 | 0 |
| 51.28 – 52.36 | 0 |
| 52.36 – 53.44 | 0 |
| 53.44 – 54.53 | 0 |
| 54.53 – 55.61 | 1 |
| 55.61 – 56.69 | 0 |
| 56.69 – 57.77 | 0 |
| 57.77 – 58.86 | 0 |
| 58.86 – 59.94 | 1 |
| 59.94 – 61.02 | 2 |
This is almost certainly longitude (east coordinate), with values bounded between -163.53 and -64.7151 and a median of -92.47, consistent with points across North America. The distribution is moderately left-skewed (-0.60) with kurtosis 3.77 and a tight IQR of 11.26 around the median. Notably, 37.65% of rows are null, which will materially shrink any geo-based analysis.
Treatment: Pair with the matching latitude column and filter out the ~38% null rows before spatial analysis.
saturn.columns["elon"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 26,363 (37.6%) |
| unique | 18,586 |
| min | -163.5 |
| max | -64.72 |
| mean | -92.19 |
| median | -92.47 |
| std | 8.545 |
| q1 | -97.73 |
| q3 | -86.47 |
| iqr | 11.26 |
| skew | -0.5954 |
| kurtosis | 3.766 |
| n_outliers | 647 |
| outlier_rate | 0.01482 |
| zero_rate | 0 |
| alert: null_rate | 37.6% null |
elon. Vertical dash marks the median.
| bin | count |
|---|---|
| -163.5 – -161.1 | 2 |
| -161.1 – -158.6 | 9 |
| -158.6 – -156.1 | 25 |
| -156.1 – -153.6 | 8 |
| -153.6 – -151.2 | 0 |
| -151.2 – -148.7 | 0 |
| -148.7 – -146.2 | 0 |
| -146.2 – -143.8 | 1 |
| -143.8 – -141.3 | 0 |
| -141.3 – -138.8 | 0 |
| -138.8 – -136.4 | 0 |
| -136.4 – -133.9 | 0 |
| -133.9 – -131.4 | 0 |
| -131.4 – -128.9 | 0 |
| -128.9 – -126.5 | 0 |
| -126.5 – -124 | 8 |
| -124 – -121.5 | 157 |
| -121.5 – -119.1 | 158 |
| -119.1 – -116.6 | 142 |
| -116.6 – -114.1 | 82 |
| -114.1 – -111.7 | 173 |
| -111.7 – -109.2 | 176 |
| -109.2 – -106.7 | 177 |
| -106.7 – -104.2 | 774 |
| -104.2 – -101.8 | 2464 |
| -101.8 – -99.3 | 3415 |
| -99.3 – -96.83 | 5507 |
| -96.83 – -94.36 | 5157 |
| -94.36 – -91.89 | 4463 |
| -91.89 – -89.42 | 4668 |
| -89.42 – -86.95 | 4417 |
| -86.95 – -84.48 | 3706 |
| -84.48 – -82.01 | 2739 |
| -82.01 – -79.54 | 2302 |
| -79.54 – -77.07 | 1344 |
| -77.07 – -74.6 | 1056 |
| -74.6 – -72.13 | 303 |
| -72.13 – -69.66 | 152 |
| -69.66 – -67.19 | 47 |
| -67.19 – -64.72 | 27 |
Despite being typed as text, `len` holds short numeric tokens (length 3-8, one word each) like '0.1', '0.5', '1.0' — almost certainly a length or size measurement stored as strings. Values are highly concentrated: '0.1' alone covers 15,456 of 70,022 rows and the duplicate rate is 94.8% across only 3,663 unique tokens. The allcaps and one_word alerts are artefacts of numeric strings rather than real text signal.
Treatment: Cast to float and treat as a numeric feature rather than text.
saturn.columns["len"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 3,663 |
| len_min | 3 |
| len_max | 8 |
| len_mean | 3.626 |
| len_median | 3 |
| len_p95 | 6 |
| word_mean | 1 |
| word_median | 1 |
| n_empty | 0 |
| n_duplicates | 66,359 |
| duplicate_rate | 0.9477 |
| vocab_size | 2,204 |
| readability_flesch_mean | 121.2 |
| emoji_rate | 0 |
| url_rate | 0 |
| one_word_rate | 1 |
| allcaps_rate | 1 |
| boilerplate_rate | 0 |
| alert: one_word | 100.0% rows are a single word |
| alert: allcaps | 100.0% rows are all-caps |
| alert: short_text | 95th-percentile length under 20 chars |
| alert: duplicates | 94.8% duplicate strings |
len.
| chars | count |
|---|---|
| 3 – 3 | 47630 |
| 3 – 3 | 0 |
| 3 – 3 | 0 |
| 3 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 11687 |
| 4 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 4 | 0 |
| 4 – 5 | 0 |
| 5 – 5 | 0 |
| 5 – 5 | 0 |
| 5 – 5 | 0 |
| 5 – 5 | 795 |
| 5 – 5 | 0 |
| 5 – 5 | 0 |
| 5 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 9118 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 6 | 0 |
| 6 – 7 | 0 |
| 7 – 7 | 0 |
| 7 – 7 | 0 |
| 7 – 7 | 0 |
| 7 – 7 | 789 |
| 7 – 7 | 0 |
| 7 – 7 | 0 |
| 7 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 0 |
| 8 – 8 | 3 |
wid is a categorical column with 419 distinct values, all numeric-looking strings like '10', '50', '100', '30' — almost certainly a width or weight parameter stored as text rather than a true category. The distribution is heavily concentrated on round numbers: '10' alone covers 20.6% of 70022 rows and the top ten values are all multiples of 5 or 25, giving an entropy ratio of 0.51. No nulls, but the string encoding of clearly numeric quanta is the surprise.
Treatment: cast to numeric and consider binning or log-transform given the round-number concentration.
saturn.columns["wid"].stats
| stat | value |
|---|---|
| n | 70,022 |
| nulls | 0 (0.0%) |
| unique | 419 |
| top_value | 10 |
| top_rate | 0.2059 |
| cardinality | 419 |
| entropy | 4.463 |
| entropy_ratio | 0.5124 |
wid.
| value | count | share |
|---|---|---|
| 10 | 14417 | 20.6% |
| 50 | 10366 | 14.8% |
| 100 | 7067 | 10.1% |
| 30 | 4772 | 6.8% |
| 20 | 4368 | 6.2% |
| 200 | 2946 | 4.2% |
| 25 | 2452 | 3.5% |
| 150 | 2101 | 3.0% |
| 40 | 1967 | 2.8% |
| 75 | 1906 | 2.7% |
| 300 | 1430 | 2.0% |
| 33 | 1160 | 1.7% |
| 17 | 1037 | 1.5% |
| 400 | 944 | 1.3% |
| 23 | 812 | 1.2% |
| 250 | 765 | 1.1% |
| 60 | 737 | 1.1% |
| 440 | 677 | 1.0% |
| 500 | 636 | 0.9% |
| 80 | 573 | 0.8% |
click to copy
@misc{saturn-quirky-tornadoes-2026,
author = {Steuber, Luke},
title = {Saturn reading: quirky tornadoes},
year ={2026},
howpublished = {\url{https://dr.eamer.dev/saturn/view/quirky-tornadoes}},
note = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:claude-opus-4-7},
}
Steuber, L. (2026). Saturn reading: quirky tornadoes. Source: /home/coolhand/html/datavis/data_trove/data/quirky/tornadoes.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:claude-opus-4-7). Retrieved from https://dr.eamer.dev/saturn/view/quirky-tornadoes