{"columns":[{"alerts":[],"column":"fips","extras":{"histogram":{"counts":[97,15,133,59,14,4,226,5,49,189,204,184,39,15,170,196,150,27,21,95,153,155,46,67,51,161,268,29,133,94,95,0,0,0,0,0,0,0,0,78],"edges":[1001.0,2779.8,4558.6,6337.4,8116.2,9895.0,11673.8,13452.6,15231.4,17010.199999999997,18789.0,20567.8,22346.6,24125.399999999998,25904.2,27683.0,29461.8,31240.6,33019.399999999994,34798.2,36577.0,38355.799999999996,40134.6,41913.4,43692.2,45471.0,47249.799999999996,49028.6,50807.4,52586.2,54365.0,56143.799999999996,57922.6,59701.4,61480.2,63259.0,65037.799999999996,66816.59999999999,68595.4,70374.2,72153.0]},"sample":[1033.0,1041.0,1059.0,1087.0,1113.0,1115.0,1131.0,2016.0,2105.0,2110.0,2188.0,4005.0,4015.0,5005.0,5019.0,5023.0,5053.0,5055.0,5111.0,5129.0,6001.0,6015.0,6047.0,6053.0,6077.0,6091.0,6095.0,6113.0,8007.0,8011.0,8015.0,8019.0,8023.0,8025.0,8029.0,8041.0,8055.0,8069.0,8075.0,8093.0,8123.0,8125.0,12007.0,12011.0,12015.0,12031.0,12047.0,12057.0,12061.0,12075.0,12079.0,12085.0,12107.0,12119.0,12121.0,13003.0,13011.0,13017.0,13051.0,13055.0,13061.0,13073.0,13081.0,13085.0,13109.0,13117.0,13125.0,13131.0,13137.0,13157.0,13159.0,13167.0,13179.0,13189.0,13191.0,13193.0,13229.0,13237.0,13245.0,13269.0,13271.0,13285.0,13293.0,13305.0,13319.0,15005.0,16003.0,16011.0,16013.0,16023.0,16053.0,16087.0,17031.0,17035.0,17047.0,17057.0,17063.0,17077.0,17149.0,17157.0,17185.0,17197.0,17201.0,18005.0,18041.0,18043.0,18083.0,18095.0,18099.0,18131.0,18133.0,18147.0,18159.0,18173.0,19003.0,19017.0,19023.0,19027.0,19035.0,19043.0,19047.0,19075.0,19107.0,19125.0,19137.0,19155.0,19169.0,19173.0,19175.0,19183.0,20003.0,20011.0,20023.0,20037.0,20047.0,20051.0,20057.0,20065.0,20069.0,20075.0,20083.0,20085.0,20113.0,20125.0,20133.0,20153.0,20157.0,20161.0,20171.0,20173.0,20181.0,20183.0,20201.0,20209.0,21011.0,21013.0,21029.0,21045.0,21053.0,21077.0,21085.0,21121.0,21151.0,21155.0,21193.0,21209.0,21223.0,21227.0,22035.0,22057.0,22061.0,22083.0,22111.0,22115.0,22127.0,23003.0,24003.0,24021.0,24025.0,25003.0,25011.0,25013.0,26003.0,26015.0,26033.0,26041.0,26049.0,26073.0,26091.0,26121.0,26125.0,26129.0,26137.0,26155.0,26159.0,26163.0,27007.0,27019.0,27021.0,27023.0,27031.0,27039.0,27041.0,27045.0,27049.0,27051.0,27083.0,27103.0,27107.0,27113.0,27129.0,27133.0,27169.0,28005.0,28007.0,28047.0,28063.0,28071.0,28075.0,28083.0,28085.0,28091.0,28095.0,28103.0,28109.0,28117.0,28133.0,28145.0,28163.0,29017.0,29031.0,29067.0,29087.0,29123.0,29153.0,29163.0,29173.0,29181.0,29187.0,29195.0,29201.0,29213.0,29227.0,30005.0,30009.0,30019.0,30021.0,30027.0,30029.0,30065.0,30077.0,30087.0,30089.0,30105.0,31027.0,31045.0,31075.0,31095.0,31105.0,31129.0,31135.0,31151.0,31161.0,31177.0,32007.0,32033.0,33003.0,33005.0,33007.0,34015.0,34033.0,34041.0,35025.0,35059.0,36003.0,36013.0,36057.0,36063.0,36071.0,36075.0,36083.0,36093.0,36097.0,36103.0,37009.0,37017.0,37019.0,37023.0,37025.0,37029.0,37047.0,37057.0,37065.0,37071.0,37089.0,37095.0,37105.0,37109.0,37141.0,37143.0,37149.0,37199.0,38011.0,38023.0,38041.0,38049.0,38053.0,38055.0,38063.0,38071.0,38095.0,39005.0,39045.0,39057.0,39067.0,39075.0,39093.0,39101.0,39109.0,39117.0,39125.0,39127.0,39159.0,39163.0,39167.0,40027.0,40039.0,40049.0,40051.0,40063.0,40095.0,40099.0,40149.0,41001.0,41005.0,41019.0,41025.0,41031.0,41047.0,41057.0,41065.0,41069.0,42005.0,42013.0,42017.0,42027.0,42033.0,42037.0,42051.0,42055.0,42073.0,42075.0,42077.0,42111.0,42113.0,42123.0,44005.0,45013.0,45025.0,45037.0,45039.0,45041.0,45045.0,45049.0,45061.0,45065.0,45079.0,45083.0,46007.0,46011.0,46013.0,46043.0,46045.0,46049.0,46093.0,46119.0,46135.0,47007.0,47009.0,47035.0,47053.0,47057.0,47083.0,47087.0,47137.0,47159.0,48001.0,48009.0,48011.0,48015.0,48021.0,48039.0,48059.0,48081.0,48085.0,48089.0,48119.0,48161.0,48165.0,48175.0,48221.0,48227.0,48261.0,48263.0,48265.0,48285.0,48299.0,48323.0,48341.0,48369.0,48373.0,48393.0,48397.0,48403.0,48439.0,48443.0,48445.0,48465.0,48475.0,48487.0,48499.0,48505.0,49019.0,49023.0,49041.0,50005.0,50011.0,50025.0,51035.0,51043.0,51047.0,51067.0,51081.0,51093.0,51101.0,51105.0,51109.0,51111.0,51115.0,51131.0,51137.0,51167.0,51179.0,51195.0,51197.0,51510.0,51595.0,51600.0,51650.0,51680.0,51730.0,51740.0,51760.0,51800.0,53003.0,53029.0,53033.0,53043.0,53047.0,53055.0,53059.0,54003.0,54009.0,54043.0,54055.0,54071.0,54087.0,54097.0,54105.0,55003.0,55011.0,55033.0,55037.0,55047.0,55053.0,55057.0,55063.0,55081.0,55085.0,55087.0,55099.0,55113.0,55133.0,56017.0,56027.0,56033.0,56035.0,72023.0,72033.0,72049.0,72054.0,72069.0,72081.0,72083.0,72085.0,72087.0,72093.0,72109.0,72147.0,72153.0]},"kind":"numeric","n":3222,"n_null":0,"n_unique":3222,"null_rate":0.0,"stats":{"iqr":27075.0,"kurtosis":-0.6313744123374883,"max":72153.0,"mean":31377.89044072005,"median":30022.0,"min":1001.0,"n_outliers":0,"outlier_rate":0.0,"q1":19029.5,"q3":46104.5,"skew":0.1573655534643171,"std":16299.548257647879,"zero_rate":0.0}},{"alerts":[{"code":"near_unique","level":"info","message":"100.0% of rows are unique strings"}],"column":"county_name","extras":{"language_counts":{},"language_sample_size":3222,"length_histogram":{"counts":[26,72,121,190,264,407,420,363,320,240,231,152,139,165,41,28,16,10,5,0,1,1,0,1,1,0,2,0,1,1,0,0,0,0,2,1,0,0,0,1],"edges":[16.0,17.075,18.15,19.225,20.3,21.375,22.45,23.525,24.6,25.674999999999997,26.75,27.825,28.9,29.975,31.049999999999997,32.125,33.2,34.275,35.349999999999994,36.425,37.5,38.575,39.65,40.724999999999994,41.8,42.875,43.95,45.025,46.099999999999994,47.175,48.25,49.324999999999996,50.4,51.475,52.55,53.625,54.699999999999996,55.775,56.85,57.925,59.0]},"near_unique":true,"sample":["Bibb County, Alabama","Cheatham County, Tennessee","Piute County, Utah","Lamb County, Texas","Martin County, Minnesota","Sheridan County, Wyoming","Chickasaw County, Mississippi","Rockingham County, Virginia","Liberty County, Texas","Clark County, Arkansas","Moore County, North Carolina","Lancaster County, Nebraska","Chase County, Kansas","DeKalb County, Alabama","Linn County, Kansas","Washington County, Idaho","Saguache County, Colorado","Pecos County, Texas","Patillas Municipio, Puerto Rico","Ogemaw County, Michigan","Washington County, Kansas","Greene County, Arkansas","Toombs County, Georgia","Alachua County, Florida","Cambria County, Pennsylvania","Jefferson County, Tennessee","Hunterdon County, New Jersey","DuPage County, Illinois","Baca County, Colorado","Lincoln County, Wyoming","Scioto County, Ohio","Blaine County, Oklahoma","Greene County, Alabama","Iosco County, Michigan","Vernon Parish, Louisiana","Bolivar County, Mississippi","Mineral County, West Virginia","Silver Bow County, Montana","Lincoln County, Mississippi","Knox County, Nebraska","Hood County, Texas","Spokane County, Washington","Decatur County, Kansas","San Juan County, Washington","La Crosse County, Wisconsin","Aguas Buenas Municipio, Puerto Rico","Bienville Parish, Louisiana","Lapeer County, Michigan","Upson County, Georgia","Essex County, Virginia"],"top_values":[],"top_words":[["county,",2999],["texas",256],["virginia",189],["georgia",159],["north",155],["carolina",147],["new",131],["dakota",121],["kentucky",120],["missouri",115],["south",113],["kansas",105],["illinois",102],["iowa",101],["tennessee",95],["indiana",93],["nebraska",93],["ohio",91],["minnesota",87],["mississippi",84],["michigan",83],["oklahoma",78],["municipio,",78],["puerto",78],["rico",78]],"vocab_skipped":null,"word_histogram":{"counts":[2492,0,0,0,0,0,0,667,0,0,0,0,0,0,0,57,0,0,0,0,0,0,5,0,0,0,0,0,0,1],"edges":[3.0,3.1333333333333333,3.2666666666666666,3.4,3.533333333333333,3.6666666666666665,3.8,3.9333333333333336,4.066666666666666,4.2,4.333333333333333,4.466666666666667,4.6,4.733333333333333,4.866666666666667,5.0,5.133333333333333,5.266666666666667,5.4,5.533333333333333,5.666666666666666,5.8,5.933333333333334,6.066666666666666,6.2,6.333333333333334,6.466666666666667,6.6,6.733333333333333,6.866666666666667,7.0]}},"kind":"text","n":3222,"n_null":0,"n_unique":3222,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.0,"duplicate_rate":0.0,"emoji_rate":0.0,"len_max":59,"len_mean":24.324022346368714,"len_median":24.0,"len_min":16,"len_p95":31.0,"n_duplicates":0,"n_empty":0,"one_word_rate":0.0,"readability_flesch_mean":10.283900000000026,"url_rate":0.0,"vocab_size":1990,"word_mean":3.2482929857231535,"word_median":3.0}},{"alerts":[{"code":"high_skew","level":"info","message":"skew=-17.87"},{"code":"outliers","level":"warn","message":"7.3% rows beyond 1.5 IQR"}],"column":"median_gross_rent","extras":{"histogram":{"counts":[10,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3212],"edges":[-666666666.0,-649999929.225,-633333192.45,-616666455.675,-599999718.9,-583332982.125,-566666245.35,-549999508.575,-533332771.8,-516666035.025,-499999298.25,-483332561.475,-466665824.7,-449999087.92499995,-433332351.15,-416665614.375,-399998877.6,-383332140.825,-366665404.05,-349998667.275,-333331930.5,-316665193.72499996,-299998456.95,-283331720.175,-266664983.39999998,-249998246.625,-233331509.84999996,-216664773.075,-199998036.3,-183331299.52499998,-166664562.75,-149997825.97499996,-133331089.19999999,-116664352.42499995,-99997615.64999998,-83330878.875,-66664142.100000024,-49997405.32499993,-33330668.549999952,-16663931.774999976,2805.0]},"sample":[810.0,595.0,596.0,688.0,908.0,1044.0,787.0,1672.0,996.0,1464.0,1386.0,1353.0,976.0,810.0,690.0,844.0,802.0,808.0,642.0,611.0,2229.0,1146.0,1200.0,1873.0,1542.0,1184.0,1981.0,1655.0,1184.0,778.0,1330.0,1201.0,691.0,988.0,933.0,1507.0,735.0,1584.0,854.0,1788.0,1351.0,866.0,902.0,1683.0,1206.0,1293.0,778.0,1413.0,1183.0,798.0,832.0,1374.0,844.0,1185.0,760.0,566.0,776.0,668.0,1284.0,753.0,383.0,1295.0,735.0,1360.0,715.0,1779.0,779.0,806.0,861.0,1007.0,1009.0,590.0,1178.0,834.0,760.0,627.0,764.0,934.0,1024.0,730.0,644.0,956.0,778.0,805.0,715.0,1297.0,763.0,787.0,1238.0,573.0,834.0,881.0,1318.0,683.0,710.0,782.0,1126.0,757.0,641.0,740.0,728.0,1342.0,941.0,1063.0,763.0,943.0,746.0,888.0,882.0,702.0,866.0,715.0,842.0,964.0,787.0,783.0,749.0,697.0,655.0,738.0,732.0,742.0,744.0,845.0,718.0,956.0,991.0,636.0,712.0,849.0,778.0,774.0,673.0,821.0,715.0,864.0,948.0,696.0,802.0,900.0,854.0,821.0,871.0,747.0,623.0,695.0,656.0,1016.0,642.0,937.0,827.0,564.0,540.0,1043.0,566.0,608.0,947.0,618.0,605.0,815.0,636.0,623.0,826.0,687.0,735.0,1098.0,894.0,942.0,724.0,873.0,817.0,772.0,698.0,1020.0,624.0,681.0,1908.0,1633.0,1475.0,1003.0,1109.0,1051.0,716.0,966.0,785.0,655.0,893.0,840.0,924.0,915.0,1243.0,782.0,865.0,851.0,843.0,1043.0,935.0,1384.0,874.0,788.0,874.0,901.0,847.0,724.0,895.0,778.0,718.0,901.0,717.0,935.0,746.0,788.0,803.0,677.0,693.0,1034.0,411.0,1092.0,865.0,688.0,705.0,625.0,724.0,582.0,909.0,656.0,650.0,855.0,829.0,752.0,854.0,704.0,658.0,825.0,636.0,724.0,777.0,699.0,748.0,718.0,798.0,873.0,355.0,597.0,900.0,530.0,791.0,815.0,1029.0,1035.0,752.0,641.0,731.0,675.0,681.0,887.0,917.0,681.0,807.0,614.0,756.0,763.0,756.0,926.0,1077.0,983.0,1138.0,1139.0,825.0,1435.0,1165.0,1292.0,1031.0,587.0,735.0,759.0,867.0,823.0,1494.0,899.0,1141.0,1092.0,808.0,2113.0,730.0,731.0,1187.0,768.0,1185.0,1151.0,738.0,822.0,779.0,1005.0,1032.0,917.0,923.0,928.0,1039.0,1033.0,984.0,757.0,862.0,1032.0,852.0,753.0,1192.0,766.0,539.0,663.0,622.0,815.0,1042.0,1027.0,682.0,749.0,886.0,837.0,906.0,895.0,718.0,695.0,1144.0,675.0,794.0,1073.0,732.0,791.0,841.0,604.0,761.0,824.0,752.0,765.0,1605.0,957.0,665.0,940.0,1228.0,1148.0,925.0,730.0,777.0,838.0,1461.0,1118.0,737.0,862.0,754.0,1019.0,787.0,1023.0,1259.0,704.0,688.0,728.0,1544.0,1435.0,796.0,786.0,830.0,871.0,1122.0,808.0,753.0,736.0,1142.0,960.0,621.0,870.0,748.0,763.0,839.0,775.0,1109.0,935.0,765.0,751.0,957.0,786.0,756.0,648.0,719.0,777.0,720.0,809.0,972.0,718.0,942.0,1046.0,1195.0,1333.0,888.0,681.0,1689.0,892.0,875.0,785.0,711.0,788.0,1255.0,981.0,-666666666.0,921.0,1048.0,871.0,974.0,757.0,879.0,839.0,920.0,554.0,1779.0,725.0,1352.0,-666666666.0,763.0,913.0,1061.0,795.0,882.0,557.0,1020.0,969.0,791.0,919.0,1125.0,1031.0,643.0,1260.0,1383.0,809.0,979.0,1223.0,1239.0,651.0,1137.0,802.0,966.0,763.0,1085.0,668.0,1828.0,715.0,668.0,1983.0,960.0,1972.0,1255.0,972.0,1082.0,1225.0,1227.0,1376.0,941.0,1517.0,1950.0,839.0,862.0,1279.0,1019.0,1154.0,591.0,734.0,777.0,666.0,605.0,744.0,490.0,658.0,808.0,908.0,571.0,781.0,749.0,820.0,984.0,919.0,876.0,941.0,759.0,670.0,1235.0,824.0,951.0,919.0,985.0,544.0,570.0,458.0,649.0,509.0,479.0,305.0,486.0,459.0,394.0,486.0,441.0,495.0]},"kind":"numeric","n":3222,"n_null":0,"n_unique":984,"null_rate":0.0,"stats":{"iqr":260.0,"kurtosis":317.2031132877657,"max":2805.0,"mean":-2068220.0580384855,"median":817.5,"min":-666666666.0,"n_outliers":235,"outlier_rate":0.0729360645561763,"q1":718.0,"q3":978.0,"skew":-17.866256274579687,"std":37088473.49143141,"zero_rate":0.0}}],"insights":{"errors":[],"insights":[{"confidence":"high","critiques":[],"evidence_keys":["median_gross_rent.stats.median","median_gross_rent.stats.mean","median_gross_rent.stats.min","median_gross_rent.stats.max","median_gross_rent.stats.q1","median_gross_rent.stats.q3","median_gross_rent.stats.skew","median_gross_rent.stats.kurtosis","median_gross_rent.stats.n_outliers","median_gross_rent.stats.outlier_rate","fips.stats.min","fips.stats.max","row_count","column_count"],"featured_charts":[{"caption":"Expect an extreme left tail from the -666,666,666 sentinel; filter it out to see the real distribution centered near $817.","column":"median_gross_rent","kind":"histogram"},{"caption":"Should spread fairly evenly across state FIPS prefixes, confirming nationwide county coverage.","column":"fips","kind":"histogram"},{"caption":"County name lengths cluster tightly around 24 characters; useful as a sanity check that no rows are truncated or malformed.","column":"county_name","kind":"length"}],"model":"anthropic:claude-opus-4-7","narrative":"This dataset contains 3,222 rows of U.S. county-level median gross rent figures, keyed by county name and FIPS code. The standout issue is the median_gross_rent column: while the median is a plausible $817.50 and the IQR runs $718 to $978, the minimum is -666,666,666, dragging the mean to roughly -2.07M and producing extreme skew (-17.87) and kurtosis (317.2). That sentinel-style negative value and the 235 flagged outliers (7.3%) should be cleaned or filtered before any analysis. The fips column is well-behaved and unique per row, and county_name is essentially an identifier (3,222 unique values), so neither needs deep inspection beyond confirming coverage.","scope":"dataset","target":"__global__"},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.min","stats.max","stats.mean","stats.median","stats.skew"],"model":"anthropic:claude-opus-4-7","narrative":"This is the county-level FIPS code: an integer geographic identifier where every one of the 3222 rows is unique and non-null. The range (1001 to 72153) and distribution (mean 31377, median 30022, low skew 0.16) are consistent with the standard 5-digit state+county FIPS scheme covering US states and territories. There is nothing anomalous here \u2014 it behaves as a clean primary key rather than a numeric feature.","role":"identifier","scope":"column","target":"fips","treatment":"Treat as a categorical key for joins; do not use as a numeric feature."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.len_min","stats.len_max","stats.len_median","stats.duplicate_rate","top_words"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds fully-qualified US county names (e.g. 'X County, Texas'), with the word 'county,' appearing in 2999 of 3222 rows and state names like Texas (256), Virginia (189) and Georgia (159) dominating the remaining tokens. Every one of the 3222 values is unique with zero nulls or duplicates, so it functions as a row identifier rather than a categorical feature. String lengths are tight (16-59 chars, median 24) and there is no boilerplate, URL or emoji noise.","role":"identifier","scope":"column","target":"county_name","treatment":"Split into county and state fields, or use as a join key against county-level reference data."},{"confidence":"high","critiques":[],"evidence_keys":["min","median","mean","q1","q3","iqr","skew","kurtosis","std","n_outliers","outlier_rate","null_rate","max"],"model":"anthropic:claude-opus-4-7","narrative":"Median gross rent in dollars, with a healthy interquartile range of 718 to 978 around a median of 817.5. The minimum of -666666666 is clearly a sentinel for missing data, dragging the mean to -2068220 and producing extreme skew (-17.87) and kurtosis (317.20). 235 outliers (7.3%) flag this contamination even though null_rate is 0.","role":"feature","scope":"column","target":"median_gross_rent","treatment":"Replace the -666666666 sentinel with NA before any modelling or aggregation."}],"providers":["anthropic:claude-opus-4-7"],"total_usage":{"completion_tokens":1395,"prompt_tokens":3885,"total_tokens":5280}},"language_counts":{},"meta":{"generated_at":"2026-05-01T16:53:40+00:00","mode":"full","row_count":3222,"sampled_rows":3222,"seed":42,"source":"/home/coolhand/html/datavis/data_trove/cache/median_rents.parquet"},"notes":[],"saturn_version":"0.2.0","schema":{"county_name":"text","fips":"numeric","median_gross_rent":"numeric"}}