{"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":"short_text","level":"info","message":"95th-percentile length under 20 chars"},{"code":"duplicates","level":"warn","message":"39.2% duplicate strings"}],"column":"county_name","extras":{"language_counts":{},"language_sample_size":3222,"length_histogram":{"counts":[29,255,465,682,588,493,291,219,67,0,49,23,16,14,8,4,5,2,1,0,1,0,0,2,1,1,1,1,0,0,0,0,0,2,1,0,0,0,0,1],"edges":[10.0,10.9,11.8,12.7,13.6,14.5,15.4,16.3,17.2,18.1,19.0,19.9,20.8,21.700000000000003,22.6,23.5,24.4,25.3,26.2,27.1,28.0,28.900000000000002,29.8,30.7,31.6,32.5,33.400000000000006,34.3,35.2,36.1,37.0,37.900000000000006,38.8,39.7,40.6,41.5,42.4,43.300000000000004,44.2,45.1,46.0]},"near_unique":false,"sample":["Bibb County","Cheatham County","Piute County","Lamb County","Martin County","Sheridan County","Chickasaw County","Rockingham County","Liberty County","Clark County","Moore County","Lancaster County","Chase County","DeKalb County","Linn County","Washington County","Saguache County","Pecos County","Patillas Municipio","Ogemaw County","Washington County","Greene County","Toombs County","Alachua County","Cambria County","Jefferson County","Hunterdon County","DuPage County","Baca County","Lincoln County","Scioto County","Blaine County","Greene County","Iosco County","Vernon Parish","Bolivar County","Mineral County","Silver Bow County","Lincoln County","Knox County","Hood County","Spokane County","Decatur County","San Juan County","La Crosse County","Aguas Buenas Municipio","Bienville Parish","Lapeer County","Upson County","Essex County"],"top_values":[["Washington County",30],["Jefferson County",25],["Franklin County",24],["Jackson County",23],["Lincoln County",23],["Madison County",19],["Clay County",18],["Montgomery County",18],["Marion County",17],["Monroe County",17],["Union County",17],["Wayne County",16],["Greene County",14],["Grant County",14],["Warren County",14],["Carroll County",13],["Lee County",12],["Marshall County",12],["Clark County",12],["Johnson County",12]],"top_words":[["county",2999],["municipio",78],["parish",64],["city",47],["washington",31],["jefferson",28],["franklin",26],["st.",26],["jackson",24],["lincoln",24],["san",21],["madison",20],["clay",18],["montgomery",18],["lake",18],["union",18],["marion",17],["monroe",17],["borough",17],["wayne",16],["carroll",15],["grant",15],["greene",14],["warren",14],["clark",13]],"vocab_skipped":null,"word_histogram":{"counts":[2987,0,0,0,0,0,0,207,0,0,0,0,0,0,0,23,0,0,0,0,0,0,4,0,0,0,0,0,0,1],"edges":[2.0,2.1333333333333333,2.2666666666666666,2.4,2.533333333333333,2.6666666666666665,2.8,2.9333333333333336,3.0666666666666664,3.2,3.333333333333333,3.466666666666667,3.6,3.7333333333333334,3.8666666666666667,4.0,4.133333333333333,4.266666666666667,4.4,4.533333333333333,4.666666666666666,4.8,4.933333333333334,5.066666666666666,5.2,5.333333333333334,5.466666666666667,5.6,5.733333333333333,5.866666666666667,6.0]}},"kind":"text","n":3222,"n_null":0,"n_unique":1960,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.0,"duplicate_rate":0.39168218497827434,"emoji_rate":0.0,"len_max":46,"len_mean":14.172253258845437,"len_median":14.0,"len_min":10,"len_p95":18.0,"n_duplicates":1262,"n_empty":0,"one_word_rate":0.0,"readability_flesch_mean":33.35860000000002,"url_rate":0.0,"vocab_size":1963,"word_mean":2.0834885164494104,"word_median":2.0}},{"alerts":[],"column":"state","extras":{"singletons":1,"top_values":[["TX",254],["GA",159],["VA",133],["KY",120],["MO",115],["KS",105],["IL",102],["NC",100],["IA",99],["TN",95],["NE",93],["IN",92],["OH",88],["MN",87],["MI",83],["MS",82],["PR",78],["OK",77],["AR",75],["WI",72]]},"kind":"categorical","n":3222,"n_null":0,"n_unique":52,"null_rate":0.0,"stats":{"cardinality":52,"entropy":5.314087905454926,"entropy_ratio":0.9322242086945259,"top_rate":0.07883302296710118,"top_value":"TX"}},{"alerts":[],"column":"gini_index","extras":{"histogram":{"counts":[1,1,1,0,1,3,6,10,29,66,123,202,277,365,375,402,370,299,227,162,104,80,37,26,22,14,6,5,2,3,2,0,0,0,0,0,0,0,0,1],"edges":[0.2744,0.28556499999999996,0.29673,0.307895,0.31905999999999995,0.330225,0.34138999999999997,0.35255499999999995,0.36372,0.37488499999999997,0.38605,0.397215,0.40837999999999997,0.41954499999999995,0.43071,0.44187499999999996,0.45304,0.464205,0.47536999999999996,0.48653499999999994,0.4977,0.5088649999999999,0.52003,0.531195,0.54236,0.553525,0.5646899999999999,0.575855,0.58702,0.598185,0.60935,0.6205149999999999,0.63168,0.6428449999999999,0.65401,0.665175,0.6763399999999999,0.687505,0.6986699999999999,0.709835,0.721]},"sample":[0.4488,0.5581,0.4441,0.4853,0.4664,0.4081,0.4578,0.3254,0.4693,0.4037,0.4208,0.4603,0.4622,0.4592,0.4502,0.4541,0.4555,0.4283,0.4723,0.4407,0.4694,0.4318,0.4581,0.4596,0.4434,0.4793,0.4207,0.4885,0.4427,0.4315,0.4385,0.4376,0.5034,0.4834,0.4666,0.4301,0.4454,0.4502,0.4181,0.4074,0.4201,0.421,0.4469,0.4887,0.4506,0.4722,0.4326,0.4811,0.5066,0.462,0.474,0.5128,0.4799,0.4227,0.4391,0.4409,0.4117,0.4989,0.476,0.425,0.3999,0.4106,0.4835,0.4122,0.445,0.3942,0.444,0.4646,0.4582,0.4099,0.4608,0.4413,0.4084,0.453,0.4468,0.6041,0.4369,0.5092,0.4853,0.5204,0.5026,0.4904,0.4942,0.4559,0.493,0.2744,0.499,0.4293,0.4649,0.4724,0.4269,0.4463,0.5048,0.3995,0.4102,0.4439,0.3955,0.5144,0.4275,0.4034,0.4553,0.4099,0.4517,0.4378,0.4118,0.4346,0.4544,0.4367,0.4265,0.4256,0.3807,0.4166,0.3712,0.4621,0.4948,0.4116,0.4066,0.4197,0.4244,0.4299,0.4389,0.3727,0.444,0.4294,0.4739,0.43,0.4779,0.4101,0.4209,0.3939,0.4187,0.4227,0.4536,0.4656,0.4206,0.4976,0.3966,0.3795,0.4026,0.3883,0.3674,0.3719,0.3944,0.431,0.4421,0.4135,0.4172,0.4844,0.4034,0.4614,0.5011,0.4405,0.4135,0.4272,0.5191,0.4755,0.3947,0.4816,0.4601,0.4101,0.4834,0.5194,0.4484,0.4178,0.5322,0.3978,0.428,0.4839,0.6062,0.4829,0.5244,0.4896,0.5112,0.4552,0.4906,0.4588,0.4219,0.3957,0.4071,0.491,0.4373,0.4705,0.3895,0.4452,0.4823,0.4505,0.4666,0.4801,0.4205,0.4367,0.4667,0.4414,0.4263,0.4141,0.4286,0.4903,0.4375,0.4152,0.4327,0.4267,0.4064,0.3857,0.4377,0.4003,0.4212,0.4532,0.4519,0.4596,0.4416,0.3882,0.4123,0.4401,0.4347,0.5003,0.5375,0.4597,0.5051,0.5244,0.5065,0.5734,0.4782,0.4888,0.4536,0.4443,0.4413,0.4824,0.489,0.4287,0.4815,0.4031,0.4455,0.5152,0.4504,0.4858,0.5319,0.4417,0.4269,0.4424,0.4333,0.4372,0.4731,0.4384,0.4305,0.4443,0.4628,0.4034,0.3969,0.4443,0.4587,0.4539,0.4563,0.4458,0.4496,0.4085,0.4074,0.3778,0.4579,0.422,0.436,0.4685,0.4303,0.4071,0.4442,0.4121,0.4141,0.3647,0.4821,0.4285,0.4331,0.4182,0.4431,0.4174,0.4733,0.4118,0.4415,0.4481,0.4347,0.4428,0.4479,0.4473,0.4229,0.4358,0.4411,0.4428,0.4414,0.526,0.4426,0.4534,0.4346,0.3509,0.4745,0.4358,0.4606,0.4589,0.4511,0.4022,0.4309,0.4571,0.4355,0.3959,0.4624,0.4679,0.3608,0.3971,0.4981,0.4281,0.4682,0.3777,0.457,0.4625,0.4744,0.3983,0.4209,0.4415,0.4532,0.424,0.4624,0.4588,0.4179,0.3729,0.416,0.4366,0.4126,0.421,0.4699,0.4387,0.4833,0.4369,0.4206,0.4846,0.4612,0.4525,0.4197,0.4682,0.4496,0.437,0.433,0.4332,0.4289,0.4422,0.483,0.3981,0.4197,0.4453,0.4446,0.4775,0.4329,0.4446,0.4541,0.421,0.4366,0.4236,0.4614,0.4306,0.4294,0.42,0.4792,0.4782,0.4662,0.4628,0.4942,0.4845,0.4721,0.4439,0.4517,0.4599,0.4898,0.4505,0.521,0.4052,0.4317,0.4533,0.4716,0.4527,0.3896,0.4644,0.4272,0.4473,0.4209,0.4229,0.4404,0.4852,0.432,0.4634,0.4785,0.4736,0.4294,0.4714,0.3626,0.4246,0.422,0.4161,0.3972,0.4704,0.4332,0.4741,0.4472,0.448,0.4223,0.5199,0.4556,0.4397,0.3038,0.3834,0.4571,0.4544,0.5296,0.4605,0.4123,0.3955,0.4421,0.3783,0.4127,0.5205,0.4565,0.3844,0.47,0.4389,0.4249,0.4089,0.47,0.5195,0.4553,0.3804,0.3859,0.4544,0.4051,0.4673,0.4374,0.4137,0.4128,0.4691,0.4617,0.4359,0.3759,0.4858,0.4477,0.4088,0.437,0.5002,0.4089,0.4549,0.3752,0.43,0.4671,0.4589,0.4513,0.4289,0.4368,0.4484,0.4518,0.466,0.5219,0.4477,0.4657,0.4239,0.4766,0.4366,0.4214,0.5388,0.4363,0.4042,0.4089,0.4837,0.4563,0.4014,0.4815,0.4684,0.4164,0.4447,0.3931,0.4289,0.4367,0.414,0.4491,0.4077,0.4575,0.4076,0.4529,0.4441,0.423,0.4547,0.442,0.3951,0.4389,0.439,0.5244,0.5173,0.5472,0.4633,0.4518,0.5073,0.4894,0.4778,0.5104,0.4873,0.4419,0.4795,0.4171,0.4863]},"kind":"numeric","n":3222,"n_null":0,"n_unique":1317,"null_rate":0.0,"stats":{"iqr":0.049375,"kurtosis":1.6339434161607498,"max":0.721,"mean":0.4481372439478585,"median":0.4457,"min":0.2744,"n_outliers":56,"outlier_rate":0.01738050900062073,"q1":0.422,"q3":0.471375,"skew":0.499853230300537,"std":0.03841051317977948,"zero_rate":0.0}}],"insights":{"errors":[],"insights":[{"confidence":"high","critiques":[],"evidence_keys":["row_count","column_count","columns.gini_index.stats","columns.state.top_values","columns.county_name.stats","columns.county_name.top_values"],"featured_charts":[{"caption":"Look at the right tail and the 56 flagged outliers to spot counties with unusually high inequality.","column":"gini_index","kind":"histogram"},{"caption":"Texas and Georgia dominate the county counts; weight any state comparisons accordingly.","column":"state","kind":"bar"},{"caption":"Top recurring county names like Washington, Jefferson, and Franklin drive the 39% duplicate rate.","column":"county_name","kind":"bar"},{"caption":"FIPS codes span 1,001 to 72,153 and act as a unique row identifier across states and territories.","column":"fips","kind":"histogram"}],"model":"anthropic:claude-opus-4-7","narrative":"This dataset contains 3,222 US county-level records with four fields: county name, FIPS code, Gini index, and state. The Gini index is the most analytically interesting column, with a mean of 0.448 and a max of 0.721, plus 56 outliers worth investigating for unusually high local inequality. The state distribution is broad (52 unique values), led by Texas (254 counties) and Georgia (159), so any state-level comparison should account for that imbalance. County names show a 39% duplicate rate, reflecting common names like Washington, Jefferson, and Franklin County that recur across states.","scope":"dataset","target":"__global__"},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.min","stats.max","stats.mean","stats.std","stats.skew"],"model":"anthropic:claude-opus-4-7","narrative":"This is the U.S. county FIPS code: a 5-digit numeric identifier where the first two digits encode state and the last three encode county. With 3222 unique values across 3222 rows, no nulls, and a range from 1001 to 72153 spanning the standard FIPS state prefixes, every row corresponds to a distinct county. Distribution stats (mean 31377, std 16299, near-zero skew) are artifacts of the prefix encoding and not meaningful as a numeric feature.","role":"identifier","scope":"column","target":"fips","treatment":"Treat as a categorical key; left-join on this to bring in county-level attributes rather than using as a numeric feature."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.duplicate_rate","stats.n_duplicates","stats.len_min","stats.len_max","stats.len_mean","stats.word_mean","top_values","top_words"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds US county-level place names: nearly every value ends in 'County' (2999 of 3222 rows), with smaller contingents of 'Parish' (64, Louisiana), 'Municipio' (78, Puerto Rico), and 'City' (47). Heavy duplication is expected and present \u2014 39.2% duplicate rate with 1262 repeats \u2014 because common names like Washington, Jefferson, and Franklin County recur across states. Lengths are tight (10\u201346 chars, mean 14.2, ~2 words) and there are no nulls or empties.","role":"metadata","scope":"column","target":"county_name","treatment":"Pair with a state column to form a unique geographic key before joining or grouping."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.cardinality","stats.entropy","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is a US state code field with 52 distinct values across 3222 rows and no nulls, consistent with the 50 states plus DC and likely a territory. Distribution closely tracks county counts: TX leads at 254 (7.88%), followed by GA (159) and VA (133), and entropy is high at 5.31 (ratio 0.93), indicating broad spread rather than concentration. The 52-value cardinality is the only mild surprise\u2014worth confirming whether the extras are DC, PR, or stray codes.","role":"feature","scope":"column","target":"state","treatment":"One-hot or target-encode for modelling; verify the two codes beyond the 50 states."},{"confidence":"high","critiques":[],"evidence_keys":["n","null_rate","zero_rate","min","max","mean","median","std","iqr","skew","kurtosis","n_outliers","outlier_rate"],"model":"anthropic:claude-opus-4-7","narrative":"Numeric column holding Gini index values, all within the plausible 0.2744\u20130.721 range with no nulls or zeros across 3222 rows. The distribution is tight (IQR 0.049, std 0.038) and centred near 0.448, but a mild right skew (0.50) and 56 high-end outliers (1.7%) suggest a handful of unusually unequal observations.","role":"feature","scope":"column","target":"gini_index","treatment":"Use as-is as a numeric feature; consider winsorising the upper outliers if downstream models are sensitive."}],"providers":["anthropic:claude-opus-4-7"],"total_usage":{"completion_tokens":1690,"prompt_tokens":5373,"total_tokens":7063}},"language_counts":{},"meta":{"generated_at":"2026-05-01T17:00:58+00:00","mode":"full","row_count":3222,"sampled_rows":3222,"seed":42,"source":"/home/coolhand/datasets/us-inequality-atlas/economic/gini_by_county.csv"},"notes":[],"saturn_version":"0.2.0","schema":{"county_name":"text","fips":"numeric","gini_index":"numeric","state":"categorical"}}