{"columns":[{"alerts":[],"column":"id","extras":{"histogram":{"counts":[743,469,305,306,268,202,198,176,119,81,89,146,254,215,191,105,77,85,98,91,113,90,90,84,71,80,10,33,70,92,18,78,47,65,42,8,33,45,50,74],"edges":[60.0,2051.275,4042.55,6033.825000000001,8025.1,10016.375,12007.650000000001,13998.925000000001,15990.2,17981.475000000002,19972.75,21964.025,23955.300000000003,25946.575,27937.850000000002,29929.125,31920.4,33911.675,35902.950000000004,37894.225,39885.5,41876.775,43868.05,45859.325000000004,47850.600000000006,49841.875,51833.15,53824.425,55815.700000000004,57806.975000000006,59798.25,61789.525,63780.8,65772.075,67763.35,69754.625,71745.90000000001,73737.175,75728.45,77719.725,79711.0]},"sample":[35293.0,39620.0,37094.0,3296.0,8679.0,75309.0,26604.0,1255.0,2917.0,1261.0,78863.0,55195.0,41981.0,36623.0,1028.0,1606.0,11549.0,47536.0,24818.0,3032.0,36178.0,62851.0,37010.0,62595.0,802.0,166.0,63033.0,1664.0,147.0,2960.0,69315.0,3798.0,2141.0,1665.0,11519.0,1794.0,6961.0,8345.0,8487.0,2182.0,27844.0,6854.0,1742.0,13287.0,22500.0,4886.0,8059.0,3421.0,2919.0,5160.0,2248.0,36070.0,27983.0,79711.0,2844.0,3027.0,6824.0,2861.0,5637.0,1792.0,6971.0,25009.0,14338.0,6706.0,13419.0,16722.0,23974.0,10980.0,4649.0,7676.0,2309.0,348.0,15273.0,23065.0,12802.0,880.0,6164.0,6782.0,7225.0,12904.0,2667.0,513.0,1368.0,6755.0,1370.0,1372.0,32905.0,76534.0,18333.0,28720.0,27076.0,13313.0,41503.0,27587.0,45137.0,18065.0,37203.0,721.0,38893.0,35940.0,246.0,42978.0,6992.0,1030.0,42726.0,33764.0,5369.0,8935.0,7627.0,43381.0,43162.0,19232.0,23570.0,19421.0,14525.0,7004.0,26822.0,8454.0,56061.0,18377.0,9465.0,78583.0,4987.0,28386.0,15416.0,24693.0,13768.0,8460.0,2062.0,3085.0,71863.0,65924.0,57765.0,4741.0,42150.0,30367.0,18059.0,2805.0,35427.0,40842.0,10879.0,29448.0,11295.0,15019.0,40314.0,37522.0,43348.0,23418.0,37697.0,49302.0,27042.0,3472.0,28533.0,24354.0,27374.0,13070.0,42794.0,50965.0,50502.0,57303.0,42140.0,19910.0,23537.0,292.0,2464.0,29674.0,29891.0,2470.0,15374.0,14845.0,44111.0,35883.0,6394.0,76464.0,5532.0,1311.0,25860.0,26790.0,2363.0,10765.0,2368.0,26605.0,5678.0,2425.0,3269.0,24413.0,1459.0,78973.0,75126.0,25137.0,7651.0,232.0,30789.0,23929.0,32924.0,908.0,29675.0,55598.0,44437.0,46534.0,58484.0,31860.0,46401.0,22802.0,35387.0,14828.0,21271.0,43519.0,26544.0,30090.0,30089.0,35868.0,34990.0,43588.0,7275.0,29409.0,57401.0,31025.0,17939.0,22973.0,2554.0,28023.0,2953.0,8351.0,77435.0,14493.0,1049.0,27991.0,18221.0,41411.0,23367.0,19655.0,59346.0,12122.0,27167.0,6775.0,42742.0,40087.0,6194.0,48339.0,16294.0,48530.0,5085.0,15610.0,1135.0,1136.0,14237.0,4116.0,4421.0,28080.0,18278.0,23836.0,65664.0,1530.0,15615.0,5909.0,48354.0,1428.0,63728.0,459.0,66051.0,16486.0,12825.0,45098.0,22192.0,28886.0,26460.0,3399.0,4986.0,1451.0,1453.0,43285.0,23856.0,5047.0,22561.0,12709.0,68896.0,5326.0,15144.0,11841.0,16540.0,20363.0,1601.0,9750.0,9212.0,3336.0,78751.0,77563.0,4201.0,26011.0,65305.0,12669.0,63981.0,51962.0,41232.0,30548.0,4952.0,4731.0,10925.0,27613.0,6330.0,4960.0,33979.0,10863.0,9537.0,6313.0,23980.0,4972.0,58458.0,10421.0,5267.0,23637.0,63286.0,27206.0,59235.0,24512.0,23733.0,24967.0,4532.0,26226.0,4081.0,71794.0,56829.0,6644.0,23628.0,26005.0,650.0,14841.0,659.0,9276.0,2900.0,1720.0,11886.0,412.0,666.0,9534.0,9109.0,8680.0,3050.0,65789.0,674.0,683.0,684.0,15067.0,116.0,25907.0,15746.0,64019.0,7148.0,856.0,2932.0,3122.0,3551.0,3565.0,3002.0,26888.0,48013.0,3572.0,8000.0,16734.0,789.0,13673.0,24235.0,78786.0,1445.0,29455.0,7215.0,29794.0,6478.0,10220.0,7326.0,10740.0,6418.0,77199.0,58593.0,20231.0,6445.0,11682.0,10783.0,29244.0,6461.0,77793.0,30430.0,1632.0,30570.0,638.0,27768.0,50045.0,26473.0,63243.0,40420.0,15627.0,7604.0,9385.0,6941.0,12314.0,41621.0,9036.0,10273.0,14376.0,10157.0,8547.0,39137.0,4143.0,57754.0,7670.0,6007.0,10591.0,9315.0,71803.0,16470.0,1949.0,396.0,14732.0,18623.0,17730.0,55306.0,36591.0,36072.0,30462.0,27682.0,79672.0,1109.0,6058.0,10091.0,1723.0,66120.0,20923.0,42448.0,9373.0,57781.0,945.0,51753.0,14350.0,70737.0,5136.0,9175.0,47107.0,24772.0,4737.0,24714.0,43823.0,45423.0,48777.0,30459.0,15135.0,13487.0,9392.0,23300.0,63900.0,12655.0,1685.0,24310.0,72287.0,11930.0,59331.0,8456.0,38224.0,391.0,1671.0,39858.0,10354.0,20435.0,1917.0,62354.0,63451.0,17539.0,12997.0,33908.0,47225.0,34043.0,25989.0,23762.0,16204.0,20863.0,50469.0,20101.0,19841.0,79117.0,75925.0,43211.0,43915.0,50982.0,41062.0,2804.0,25470.0,45418.0,59659.0,19472.0,1240.0,1244.0,798.0,43994.0,2448.0,17142.0,2423.0,15141.0,15343.0,1486.0,1293.0]},"kind":"numeric","n":5411,"n_null":0,"n_unique":5411,"null_rate":0.0,"stats":{"iqr":31464.0,"kurtosis":-0.15101399407349625,"max":79711.0,"mean":23288.121604139717,"median":16598.0,"min":60.0,"n_outliers":0,"outlier_rate":0.0,"q1":4898.5,"q3":36362.5,"skew":0.9108865161140566,"std":21383.079149017754,"zero_rate":0.0}},{"alerts":[],"column":"state","extras":{"singletons":0,"top_values":[["Washington",631],["California",431],["Ohio",317],["Florida",314],["Oregon",253],["Illinois",239],["Texas",238],["Michigan",217],["Missouri",161],["Georgia",135],["Colorado",128],["Pennsylvania",125],["British Columbia",122],["New York",116],["Kentucky",115],["Arkansas",104],["Tennessee",104],["West Virginia",104],["Oklahoma",101],["Idaho",99]]},"kind":"categorical","n":5411,"n_null":0,"n_unique":53,"null_rate":0.0,"stats":{"cardinality":53,"entropy":5.025141117002036,"entropy_ratio":0.8773063726816794,"top_rate":0.11661430419515802,"top_value":"Washington"}},{"alerts":[],"column":"state_code","extras":{"singletons":0,"top_values":[["wa",631],["ca",431],["oh",317],["fl",314],["or",253],["il",239],["tx",238],["mi",217],["mo",161],["ga",135],["co",128],["pa",125],["ca-bc",122],["ny",116],["ky",115],["ar",104],["tn",104],["wv",104],["ok",101],["id",99]]},"kind":"categorical","n":5411,"n_null":0,"n_unique":53,"null_rate":0.0,"stats":{"cardinality":53,"entropy":5.025141117002036,"entropy_ratio":0.8773063726816794,"top_rate":0.11661430419515802,"top_value":"wa"}},{"alerts":[{"code":"one_word","level":"warn","message":"100.0% rows are a single word"},{"code":"short_text","level":"info","message":"95th-percentile length under 20 chars"},{"code":"duplicates","level":"warn","message":"81.1% duplicate strings"}],"column":"county","extras":{"language_counts":{},"language_sample_size":5000,"length_histogram":{"counts":[338,0,0,0,0,28,457,0,640,0,1110,0,802,916,0,608,0,301,0,62,94,0,5,0,24,0,16,3,0,3,0,0,0,3,0,0,0,0,0,1],"edges":[0.0,0.575,1.15,1.7249999999999999,2.3,2.875,3.4499999999999997,4.0249999999999995,4.6,5.175,5.75,6.324999999999999,6.8999999999999995,7.475,8.049999999999999,8.625,9.2,9.774999999999999,10.35,10.924999999999999,11.5,12.075,12.649999999999999,13.225,13.799999999999999,14.374999999999998,14.95,15.524999999999999,16.099999999999998,16.674999999999997,17.25,17.825,18.4,18.974999999999998,19.549999999999997,20.125,20.7,21.275,21.849999999999998,22.424999999999997,23.0]},"near_unique":false,"sample":["Bibb","Houston","Lewis","Cowlitz","Montmorency","","Cass","Skamania","Ferry","Navajo","Portage","Madison","Edgar","Clay","Logan","Dade","Los+Angeles","King","","Chippewa","Saline","Yavapai","San+Juan","Mono","Jefferson","Palo+Pinto","Montgomery","Hernando","El+Dorado","","Grant","","Josephine","Berkshire","Lee","","Pendleton","Passaic","St.+Louis","Essex","Clallam","Barbour","Cook","Yakima","Polk","","Jackson","Essex","Park","Pierce"],"top_values":[["",338],["Pierce",80],["Jefferson",57],["Lewis",55],["Washington",52],["Snohomish",51],["Humboldt",50],["Skamania",49],["Jackson",48],["Polk",42],["King",41],["Marion",39],["Madison",38],["Montgomery",38],["Grays+Harbor",37],["Lake",36],["Tuolumne",36],["Coconino",33],["Siskiyou",31],["Mason",31]],"top_words":[["pierce",80],["jefferson",57],["lewis",55],["washington",52],["snohomish",51],["humboldt",50],["skamania",49],["jackson",48],["polk",42],["king",41],["marion",39],["madison",38],["montgomery",38],["grays+harbor",37],["lake",36],["tuolumne",36],["coconino",33],["siskiyou",31],["mason",31],["warren",30],["monroe",28],["shasta",28],["douglas",28],["clackamas",28],["el+dorado",26]],"vocab_skipped":null,"word_histogram":{"counts":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,5411,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"edges":[0.5,0.5333333333333333,0.5666666666666667,0.6,0.6333333333333333,0.6666666666666666,0.7,0.7333333333333334,0.7666666666666666,0.8,0.8333333333333333,0.8666666666666667,0.9,0.9333333333333333,0.9666666666666667,1.0,1.0333333333333332,1.0666666666666667,1.1,1.1333333333333333,1.1666666666666665,1.2,1.2333333333333334,1.2666666666666666,1.3,1.3333333333333335,1.3666666666666667,1.4,1.4333333333333333,1.4666666666666668,1.5]}},"kind":"text","n":5411,"n_null":0,"n_unique":1022,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.0,"duplicate_rate":0.8111254851228978,"emoji_rate":0.0,"len_max":23,"len_mean":6.620957309184994,"len_median":7.0,"len_min":0,"len_p95":10.0,"n_duplicates":4389,"n_empty":338,"one_word_rate":1.0,"readability_flesch_mean":16.89670000000003,"url_rate":0.0,"vocab_size":1020,"word_mean":1.0,"word_median":1.0}},{"alerts":[{"code":"near_unique","level":"info","message":"100.0% of rows are unique strings"},{"code":"one_word","level":"warn","message":"100.0% rows are a single word"},{"code":"url_heavy","level":"info","message":"100.0% rows contain a URL"}],"column":"url","extras":{"language_counts":{},"language_sample_size":5000,"length_histogram":{"counts":[11,0,0,0,0,0,0,0,0,0,0,0,0,288,0,0,0,0,0,0,0,0,0,0,0,0,1789,0,0,0,0,0,0,0,0,0,0,0,0,3323],"edges":[46.0,46.075,46.15,46.225,46.3,46.375,46.45,46.525,46.6,46.675,46.75,46.825,46.9,46.975,47.05,47.125,47.2,47.275,47.35,47.425,47.5,47.575,47.65,47.725,47.8,47.875,47.95,48.025,48.1,48.175,48.25,48.325,48.4,48.475,48.55,48.625,48.7,48.775,48.85,48.925,49.0]},"near_unique":true,"sample":["https://www.bfro.net/GDB/show_report.asp?id=21714","https://www.bfro.net/GDB/show_report.asp?id=7604","https://www.bfro.net/GDB/show_report.asp?id=12803","https://www.bfro.net/GDB/show_report.asp?id=55658","https://www.bfro.net/GDB/show_report.asp?id=27009","https://www.bfro.net/GDB/show_report.asp?id=43994","https://www.bfro.net/GDB/show_report.asp?id=14942","https://www.bfro.net/GDB/show_report.asp?id=21473","https://www.bfro.net/GDB/show_report.asp?id=25722","https://www.bfro.net/GDB/show_report.asp?id=29358","https://www.bfro.net/GDB/show_report.asp?id=4969","https://www.bfro.net/GDB/show_report.asp?id=454","https://www.bfro.net/GDB/show_report.asp?id=33911","https://www.bfro.net/GDB/show_report.asp?id=42692","https://www.bfro.net/GDB/show_report.asp?id=30203","https://www.bfro.net/GDB/show_report.asp?id=1719","https://www.bfro.net/GDB/show_report.asp?id=14953","https://www.bfro.net/GDB/show_report.asp?id=26403","https://www.bfro.net/GDB/show_report.asp?id=71929","https://www.bfro.net/GDB/show_report.asp?id=25451","https://www.bfro.net/GDB/show_report.asp?id=13070","https://www.bfro.net/GDB/show_report.asp?id=12266","https://www.bfro.net/GDB/show_report.asp?id=32905","https://www.bfro.net/GDB/show_report.asp?id=65849","https://www.bfro.net/GDB/show_report.asp?id=1134","https://www.bfro.net/GDB/show_report.asp?id=19666","https://www.bfro.net/GDB/show_report.asp?id=15492","https://www.bfro.net/GDB/show_report.asp?id=22074","https://www.bfro.net/GDB/show_report.asp?id=6639","https://www.bfro.net/GDB/show_report.asp?id=20758","https://www.bfro.net/GDB/show_report.asp?id=7687","https://www.bfro.net/GDB/show_report.asp?id=1294","https://www.bfro.net/GDB/show_report.asp?id=6655","https://www.bfro.net/GDB/show_report.asp?id=49697","https://www.bfro.net/GDB/show_report.asp?id=27323","https://www.bfro.net/GDB/show_report.asp?id=77435","https://www.bfro.net/GDB/show_report.asp?id=13122","https://www.bfro.net/GDB/show_report.asp?id=10918","https://www.bfro.net/GDB/show_report.asp?id=35281","https://www.bfro.net/GDB/show_report.asp?id=10289","https://www.bfro.net/GDB/show_report.asp?id=10091","https://www.bfro.net/GDB/show_report.asp?id=13141","https://www.bfro.net/GDB/show_report.asp?id=39851","https://www.bfro.net/GDB/show_report.asp?id=1689","https://www.bfro.net/GDB/show_report.asp?id=45418","https://www.bfro.net/GDB/show_report.asp?id=12100","https://www.bfro.net/GDB/show_report.asp?id=38440","https://www.bfro.net/GDB/show_report.asp?id=6631","https://www.bfro.net/GDB/show_report.asp?id=35596","https://www.bfro.net/GDB/show_report.asp?id=1685"],"top_values":[],"top_words":[["https://www.bfro.net/gdb/show_report.asp?id=75577",1],["https://www.bfro.net/gdb/show_report.asp?id=71896",1],["https://www.bfro.net/gdb/show_report.asp?id=67423",1],["https://www.bfro.net/gdb/show_report.asp?id=1783",1],["https://www.bfro.net/gdb/show_report.asp?id=26513",1],["https://www.bfro.net/gdb/show_report.asp?id=27067",1],["https://www.bfro.net/gdb/show_report.asp?id=21714",1],["https://www.bfro.net/gdb/show_report.asp?id=43963",1],["https://www.bfro.net/gdb/show_report.asp?id=50178",1],["https://www.bfro.net/gdb/show_report.asp?id=8921",1],["https://www.bfro.net/gdb/show_report.asp?id=1830",1],["https://www.bfro.net/gdb/show_report.asp?id=45464",1],["https://www.bfro.net/gdb/show_report.asp?id=42939",1],["https://www.bfro.net/gdb/show_report.asp?id=26886",1],["https://www.bfro.net/gdb/show_report.asp?id=49238",1],["https://www.bfro.net/gdb/show_report.asp?id=24451",1],["https://www.bfro.net/gdb/show_report.asp?id=43402",1],["https://www.bfro.net/gdb/show_report.asp?id=1907",1],["https://www.bfro.net/gdb/show_report.asp?id=42692",1],["https://www.bfro.net/gdb/show_report.asp?id=22969",1],["https://www.bfro.net/gdb/show_report.asp?id=273",1],["https://www.bfro.net/gdb/show_report.asp?id=47975",1],["https://www.bfro.net/gdb/show_report.asp?id=44386",1],["https://www.bfro.net/gdb/show_report.asp?id=27568",1],["https://www.bfro.net/gdb/show_report.asp?id=577",1]],"vocab_skipped":null,"word_histogram":{"counts":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,5411,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"edges":[0.5,0.5333333333333333,0.5666666666666667,0.6,0.6333333333333333,0.6666666666666666,0.7,0.7333333333333334,0.7666666666666666,0.8,0.8333333333333333,0.8666666666666667,0.9,0.9333333333333333,0.9666666666666667,1.0,1.0333333333333332,1.0666666666666667,1.1,1.1333333333333333,1.1666666666666665,1.2,1.2333333333333334,1.2666666666666666,1.3,1.3333333333333335,1.3666666666666667,1.4,1.4333333333333333,1.4666666666666668,1.5]}},"kind":"text","n":5411,"n_null":0,"n_unique":5411,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.0,"duplicate_rate":0.0,"emoji_rate":0.0,"len_max":49,"len_mean":48.55682868231381,"len_median":49.0,"len_min":46,"len_p95":49.0,"n_duplicates":0,"n_empty":0,"one_word_rate":1.0,"readability_flesch_mean":-301.7799999999999,"url_rate":1.0,"vocab_size":5411,"word_mean":1.0,"word_median":1.0}},{"alerts":[],"column":"month","extras":{"singletons":10,"top_values":[["August",634],["October",632],["July",618],["September",515],["June",468],["November",458],["May",303],["April",259],["December",233],["January",228],["Summer",217],["March",201],["February",163],["Fall",129],["Spring",96],["Winter",57],["Late",6],["about",6],["mid",5],["or",5]]},"kind":"categorical","n":5411,"n_null":160,"n_unique":32,"null_rate":0.029569395675475882,"stats":{"cardinality":32,"entropy":3.8072052455185728,"entropy_ratio":0.7614410491037146,"top_rate":0.12073890687488098,"top_value":"August"}},{"alerts":[],"column":"year","extras":{"histogram":{"counts":[1,0,0,0,0,1,0,0,0,1,1,0,2,2,2,2,4,2,5,4,15,13,18,24,53,120,158,331,307,257,224,195,380,610,679,622,616,355,220,130],"edges":[1870.0,1873.875,1877.75,1881.625,1885.5,1889.375,1893.25,1897.125,1901.0,1904.875,1908.75,1912.625,1916.5,1920.375,1924.25,1928.125,1932.0,1935.875,1939.75,1943.625,1947.5,1951.375,1955.25,1959.125,1963.0,1966.875,1970.75,1974.625,1978.5,1982.375,1986.25,1990.125,1994.0,1997.875,2001.75,2005.625,2009.5,2013.375,2017.25,2021.125,2025.0]},"sample":[1978.0,2013.0,2007.0,1993.0,1986.0,2022.0,2009.0,1998.0,1995.0,1990.0,2025.0,2021.0,2014.0,2013.0,2000.0,1981.0,1995.0,1972.0,2014.0,2000.0,1994.0,1973.0,1978.0,2011.0,2001.0,1977.0,1968.0,1983.0,2000.0,1995.0,1968.0,2003.0,2000.0,1999.0,1995.0,1992.0,1965.0,1961.0,1991.0,1980.0,1972.0,1989.0,2002.0,1992.0,1963.0,1978.0,1974.0,1984.0,2003.0,2003.0,1975.0,2019.0,1970.0,1970.0,1987.0,2002.0,1992.0,1998.0,1984.0,1966.0,1986.0,1980.0,1962.0,1994.0,2003.0,2007.0,2006.0,2006.0,2006.0,2001.0,1983.0,1963.0,2020.0,1971.0,2005.0,2003.0,2006.0,1987.0,2014.0,2008.0,2001.0,2005.0,1987.0,1991.0,2000.0,2004.0,1996.0,2024.0,1990.0,2010.0,2012.0,2015.0,1972.0,2006.0,2005.0,2006.0,1986.0,1997.0,2010.0,1998.0,1978.0,2018.0,1963.0,2001.0,2013.0,2012.0,1978.0,1985.0,1984.0,2010.0,2011.0,2005.0,2002.0,1999.0,1956.0,1993.0,2009.0,1985.0,1996.0,2013.0,1997.0,2018.0,1982.0,1983.0,2020.0,2006.0,1995.0,1995.0,1975.0,2021.0,2020.0,2017.0,1969.0,2008.0,1964.0,1998.0,1975.0,2012.0,1978.0,1975.0,1997.0,1984.0,2011.0,1983.0,2013.0,2012.0,1989.0,2008.0,1994.0,2017.0,2011.0,1977.0,2006.0,1975.0,1999.0,2009.0,2014.0,2010.0,1998.0,2014.0,2008.0,1970.0,1968.0,2004.0,2010.0,2009.0,1979.0,2000.0,1988.0,1985.0,1970.0,2012.0,2007.0,1970.0,1995.0,2014.0,1977.0,2018.0,1982.0,2014.0,1993.0,1973.0,1950.0,2012.0,2017.0,1980.0,2025.0,2016.0,2012.0,1999.0,2006.0,2007.0,1971.0,2008.0,2005.0,2016.0,1991.0,1965.0,2012.0,2014.0,1978.0,2006.0,1995.0,1986.0,1999.0,2009.0,2004.0,1983.0,2001.0,1950.0,1967.0,1992.0,2006.0,1993.0,1978.0,1977.0,2004.0,2001.0,2012.0,2022.0,1978.0,2010.0,2010.0,1978.0,2012.0,2007.0,2014.0,1997.0,2004.0,1982.0,1978.0,2002.0,2003.0,2015.0,1999.0,2016.0,2007.0,1961.0,1973.0,2019.0,2001.0,2012.0,1998.0,1983.0,2012.0,2018.0,1981.0,1974.0,2005.0,2001.0,1995.0,1952.0,1971.0,1969.0,1981.0,1989.0,1998.0,2015.0,2002.0,1996.0,1998.0,1985.0,2000.0,2002.0,1983.0,1969.0,2001.0,2006.0,1989.0,1969.0,1997.0,2003.0,2020.0,2009.0,2002.0,1999.0,2005.0,1965.0,1997.0,2024.0,2025.0,1999.0,2002.0,1994.0,2001.0,1976.0,2019.0,1979.0,2012.0,2002.0,1980.0,1981.0,2003.0,2021.0,1992.0,2017.0,2005.0,2004.0,2013.0,1974.0,2010.0,1978.0,2002.0,1986.0,2007.0,2001.0,1999.0,1995.0,2014.0,1942.0,2012.0,2012.0,2000.0,2020.0,2019.0,1996.0,1972.0,2011.0,1983.0,2018.0,1973.0,2008.0,2008.0,2004.0,1971.0,1989.0,1969.0,2012.0,1996.0,1963.0,1973.0,1994.0,1980.0,1968.0,1988.0,1996.0,1989.0,1995.0,1970.0,1994.0,1998.0,1997.0,1993.0,1976.0,2016.0,2015.0,2022.0,1984.0,1996.0,1973.0,1978.0,2010.0,1998.0,2021.0,2003.0,2007.0,1987.0,1986.0,2003.0,2008.0,2004.0,1970.0,2007.0,2000.0,1981.0,2000.0,2008.0,2003.0,1987.0,1986.0,2006.0,2002.0,1994.0,2012.0,1979.0,1968.0,2014.0,1981.0,2017.0,2015.0,2001.0,1992.0,1991.0,1996.0,1996.0,2017.0,2005.0,1977.0,1978.0,2003.0,2021.0,1992.0,2019.0,1982.0,2022.0,2004.0,1980.0,1983.0,1990.0,2017.0,2021.0,1978.0,1996.0,1964.0,2005.0,2008.0,2021.0,2016.0,2004.0,1993.0,2010.0,1957.0,2003.0,2004.0,2004.0,2003.0,2009.0,2007.0,2010.0,2002.0,2016.0,1999.0,2012.0,2003.0,1973.0,2011.0,1998.0,2014.0,2006.0,2000.0,1998.0,1998.0,2001.0,2012.0,1996.0,2006.0,1986.0,1993.0,2020.0,2018.0,2002.0,1996.0,1983.0,1977.0,1973.0,2009.0,2004.0,2002.0,1999.0,1975.0,1971.0,2021.0,1984.0,2018.0,2014.0,2007.0,2005.0,1995.0,1984.0,1970.0,2014.0,2009.0,2008.0,1983.0,2009.0,2015.0,2010.0,2004.0,2023.0,2000.0,2012.0,2013.0,1992.0,1999.0,2014.0,2021.0,1996.0,1980.0,2007.0,2000.0,1970.0,2012.0,2004.0,2001.0,1999.0,1998.0,1995.0,1995.0,1995.0,1986.0,1986.0,1983.0,1977.0,1973.0,1994.0,1983.0,2007.0,1990.0,1990.0,1995.0]},"kind":"numeric","n":5411,"n_null":57,"n_unique":99,"null_rate":0.010534097209388284,"stats":{"iqr":22.0,"kurtosis":1.996502176474011,"max":2025.0,"mean":1997.8276055285767,"median":2001.0,"min":1870.0,"n_outliers":49,"outlier_rate":0.009152035861038476,"q1":1987.0,"q3":2009.0,"skew":-0.9738071931846934,"std":15.785219399352227,"zero_rate":0.0}},{"alerts":[],"column":"classification","extras":{"singletons":0,"top_values":[["Class B",2722],["Class A",2655],["Class C",34]]},"kind":"categorical","n":5411,"n_null":0,"n_unique":3,"null_rate":0.0,"stats":{"cardinality":3,"entropy":1.0486006898694666,"entropy_ratio":0.6615933748542029,"top_rate":0.5030493439290334,"top_value":"Class B"}},{"alerts":[{"code":"near_unique","level":"info","message":"99.9% of rows are unique strings"}],"column":"description","extras":{"language_counts":{},"language_sample_size":5000,"length_histogram":{"counts":[2,4,21,56,108,185,376,551,525,568,692,495,486,369,330,196,135,99,74,42,26,23,10,9,6,4,6,2,1,2,3,0,0,2,1,0,0,0,0,2],"edges":[10.0,15.275,20.55,25.825000000000003,31.1,36.375,41.650000000000006,46.925000000000004,52.2,57.475,62.75,68.025,73.30000000000001,78.575,83.85000000000001,89.125,94.4,99.67500000000001,104.95,110.22500000000001,115.5,120.775,126.05000000000001,131.325,136.60000000000002,141.875,147.15,152.425,157.70000000000002,162.97500000000002,168.25,173.525,178.8,184.07500000000002,189.35000000000002,194.625,199.9,205.175,210.45000000000002,215.72500000000002,221.0]},"near_unique":true,"sample":["Rescue workers describes possible stalking on the Cahaba River outside Montevallo","Possible bigfoot activity near Walker County line.","Hikers off Lewis River Trail find large footprint east of Cougar","Hunters on bikes have close encounter with a sasquatch near Randle","Woman recalls daylight sighting while driving and a possible incident at a home east of Gaylord","Possible sighting near Bowser on Vancouver Island","County workers find possible footprints near Bena","Man and girlfriend, camping, hear loud footsteps and tree knocking near Cispus, Washington","Possible reoccurring activity at a hunting spot near Republic","Brief daylight sighting within the city limits of Show Low","Silhouette seen protruding above brushline near Mogadore Reservoir.","Man recalls incident as a child in a swampy area near Cazenovia","Possible ongoing activity described and knocks recorded at a rural home near Paris","Daytime road crossing seen near Ashland","Nighttime sighting by motorists along I-55 near Lincoln","Possible collision with vehicle outside Homestead","Possible intimidation in the late afternoon reported by hikers in the Big Tujunga Canyon area.","Man sees large, hair-covered figure while riding on train near the Cascade Tunnel","Likely road crossing sighting of a sasquatch 20 miles southeast of Moncton, New Brunswick, Canada","Man witnesses the sillouette of a tall creature while boiling sap near Sault Ste. Marie","Youth has pre-dawn encounter on the way to deer stand near Mitchellville","Camping family glimpses a grey animal twice in three days","Hiker has a possible daytime sighting near Crater Lake","Possible sighting at Mono Lake at Sunrise","Three hunters see strange figure walking towards them in the pre-dawn woods.","Hunter hears very loud scream at short range near Brazos River","Road-crossing sighting by motorist on Hwy 220 north of Candor","Possible early morning encounter by hunters in the Green Swamp","Couple have night sighting near Lake Tahoe","Strange, tall creature seen crossing the road at Kennedy Lake","Lone camper hears vocalization","Brushfire fighters find and photograph large track in remote area on the northside of Lac Seul","Couple hears repetitive calls near Oregon Caves N. M","Daytime sighting while traveling on US-7 North of Williamstown","Possible harrassment at a secluded cabin near Zachariah","EXPEDITION REPORT for incidents on Spring 2024 MN trip","Possible repeat approaches outside Circleville","Hunter has early morning encounter 8 miles north of Riverdale","Unknown nighttime visitor at a campsite on Lake Jeannette","Two people in canoe see creature on shoreline","Series of vocalizations around the town of Joyce","Possible vocalizations heard by camper near Tygart Valley River","Motorists have possible nighttime sighting in Green Belt Forest Preserve","A tall black creature covered with hair and very muscular was seen walking quickly across a clearing","Campers hear possible vocalization and have trailer shaken at Interstate State Park","Possible rock-knocking heard by hikers near Pitt Lake","Woman driving at night hits a man-like animal near Mayetta","Essex County, April 1978, Encounter with Creature","Early evening sighting by two women hiking in Bailey","Skydivers witness creature while flying over mountain"],"top_values":[],"top_words":[["near",2283],["a",1937],["of",1503],["sighting",1436],["in",1286],["possible",1117],["by",1013],["the",972],["and",899],["on",855],["at",739],["encounter",521],["while",491],["has",483],["night",437],["outside",422],["lake",421],["creature",414],["daylight",410],["two",410],["vocalizations",398],["road",373],["heard",357],["man",344],["hunter",339]],"vocab_skipped":null,"word_histogram":{"counts":[17,62,429,476,613,1292,620,509,710,220,258,70,40,40,20,10,7,8,2,2,2,1,0,0,1,0,0,0,1,1],"edges":[2.0,3.3666666666666667,4.733333333333333,6.1,7.466666666666667,8.833333333333334,10.2,11.566666666666666,12.933333333333334,14.3,15.666666666666668,17.03333333333333,18.4,19.766666666666666,21.133333333333333,22.5,23.866666666666667,25.233333333333334,26.6,27.96666666666667,29.333333333333336,30.7,32.06666666666666,33.43333333333334,34.8,36.166666666666664,37.53333333333333,38.9,40.266666666666666,41.63333333333333,43.0]}},"kind":"text","n":5411,"n_null":0,"n_unique":5407,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.00018480872297172427,"duplicate_rate":0.0007392348918868971,"emoji_rate":0.0,"len_max":221,"len_mean":67.04213638883755,"len_median":65.0,"len_min":10,"len_p95":101.5,"n_duplicates":4,"n_empty":0,"one_word_rate":0.0,"readability_flesch_mean":55.70520615200523,"url_rate":0.0,"vocab_size":7169,"word_mean":10.620772500462023,"word_median":10.0}}],"insights":{"errors":[],"insights":[{"confidence":"high","critiques":[],"evidence_keys":["row_count","column_count","state.top_values","state.n_unique","year.median","year.min","year.max","year.skew","classification.top_values","month.top_value","month.top_values","county.n_unique"],"featured_charts":[{"caption":"Look for the outsized lead of Washington state and the Pacific Northwest/Midwest cluster in reported sightings.","column":"state","kind":"bar"},{"caption":"Notice the strong skew toward post-1980 reports, with a long sparse tail stretching back to 1870.","column":"year","kind":"histogram"},{"caption":"Class A and Class B sightings are nearly equal halves, with Class C barely registering.","column":"classification","kind":"donut"},{"caption":"Summer months (July\u2013October) peak sharply, likely reflecting increased outdoor activity rather than Bigfoot seasonality.","column":"month","kind":"bar"},{"caption":"Pierce, Jefferson, and Lewis counties lead \u2014 check whether these align with the dominant Washington state concentration.","column":"county","kind":"bar"}],"model":"anthropic:default","narrative":"This dataset contains 5,411 Bigfoot sighting reports sourced from the Bigfoot Field Researchers Organization (BFRO), covering sightings across 53 U.S. states and territories with attributes including location, date, classification, and a short description. Washington state dominates with 631 reports (about 12% of all sightings), followed by California and Ohio, suggesting strong geographic clustering worth examining. The temporal distribution is skewed toward more recent decades \u2014 median year is 2001 with records stretching back to 1870 \u2014 raising questions about whether sightings are truly increasing or simply better reported. Sighting classifications split almost evenly between Class A (direct sightings, 2,655) and Class B (indirect evidence, 2,722), with Class C being rare at just 34 reports.","scope":"dataset","target":"__global__"},{"confidence":"high","critiques":[],"evidence_keys":["column","n","n_unique","null_rate","stats.duplicate_rate","stats.n_duplicates","stats.n_empty","top_values","alerts"],"model":"anthropic:default","narrative":"This column contains US county names, functioning as a categorical geographic label with 1,022 unique values across 5,411 rows. The duplicate rate is high at 81.1%, which is expected for a county field where many records share the same geography. Notably, 338 rows (6.2%) have empty strings rather than nulls, masking true missingness since null_rate reports 0.0. The top counties \u2014 Pierce, Jefferson, Lewis, Washington, Snohomish \u2014 suggest a Pacific Northwest-heavy dataset, but the presence of Humboldt and Polk hints at multi-state coverage.","role":"label","scope":"column","target":"county","treatment":"Replace empty strings with NaN, then encode as categorical (ordinal or target-encode) for modelling or use as a group-by key for geographic aggregation."},{"confidence":"high","critiques":[],"evidence_keys":["url_rate","duplicate_rate","n_unique","n","len_mean","len_median","len_min","len_max","top_words","alerts"],"model":"anthropic:default","narrative":"This column contains unique URLs pointing to individual report pages on bfro.net (the Bigfoot Field Researchers Organization database), all following the pattern `https://www.bfro.net/gdb/show_report.asp?id=<integer>`. Every one of the 5,411 rows holds a distinct URL (duplicate_rate: 0.0, n_unique: 5411), with lengths tightly clustered between 46 and 49 characters (len_mean: 48.56, len_median: 49.0), reflecting only variation in the numeric report ID. This column is effectively a primary or foreign key into the BFRO report database \u2014 not a content feature \u2014 and carries no modelling signal on its own.","role":"identifier","scope":"column","target":"url","treatment":"Retain as a row identifier or use to left-join additional scraped report metadata; drop from any feature matrix."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","duplicate_rate","n_duplicates","top_words","len_mean","word_mean","readability_flesch_mean","vocab_size"],"model":"anthropic:default","narrative":"This column contains short free-text descriptions of reported sightings \u2014 most likely UFO or wildlife sighting reports, inferred from the high-frequency terms 'sighting', 'near', and 'possible'. With 5,407 unique values out of 5,411 rows and zero nulls, entries are nearly all distinct; the 4 duplicates (duplicate_rate 0.00074) are negligible. Mean length of ~67 characters and ~10 words per entry suggests structured-but-natural one-line summaries rather than long narratives. Flesch readability of 55.7 indicates plain, accessible prose with a vocabulary of 7,169 unique tokens across the corpus.","role":"free_text","scope":"column","target":"description","treatment":"Tokenize and embed (e.g., TF-IDF or sentence transformer) before modelling; near-uniqueness makes direct encoding unusable."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","zero_rate","stats.min","stats.max","stats.mean","stats.median","stats.skew","stats.kurtosis","stats.n_outliers"],"model":"anthropic:default","narrative":"This column is a numeric row identifier: all 5,411 values are unique, there are no nulls, and the zero rate is 0.0, consistent with a primary key or surrogate ID. The IDs are not sequential (range 60\u201379,711 with a mean of ~23,288 and median of ~16,598), suggesting they originate from a larger parent table or were assigned non-contiguously. Mild positive skew (0.91) indicates more records cluster in lower ID ranges, but the near-zero kurtosis (\u22120.15) and absence of outliers confirm a broadly spread, roughly uniform-ish distribution rather than a tightly clustered one.","role":"identifier","scope":"column","target":"id","treatment":"Retain as row key for joins/lookups; exclude from any predictive model as a feature."},{"confidence":"high","critiques":[],"evidence_keys":["min","max","mean","median","iqr","q1","q3","skew","n_unique","n_outliers","outlier_rate","null_rate"],"model":"anthropic:default","narrative":"This column represents calendar years for records in the dataset, spanning 1870 to 2025 with 99 distinct values. The distribution is left-skewed (skew = -0.974) with a mean of ~1998 and IQR of 22 years (1987\u20132009), meaning the bulk of records cluster in the late 20th to early 21st century while a thin tail extends back to 1870. The 49 outliers (0.9%) likely correspond to those historically distant records, and analysts should verify whether pre-20th-century entries are genuine or data quality issues.","role":"timestamp","scope":"column","target":"year","treatment":"Treat as an ordinal temporal feature; investigate the 49 outlier records (pre-~1960s) for validity before modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","top_value","top_rate","top_values","entropy_ratio"],"model":"anthropic:default","narrative":"This column is a three-level ordinal or nominal classification label applied to all 5,411 rows with no nulls. The distribution is nearly balanced between 'Class B' (2,722; 50.3%) and 'Class A' (2,655; 49.1%), but 'Class C' is severely underrepresented with only 34 instances (~0.6%), which would surprise any analyst expecting a balanced multi-class target and will require oversampling or class-weight adjustments if used as a target variable.","role":"label","scope":"column","target":"classification","treatment":"Use as classification target; apply class-weighting or oversampling to address severe 'Class C' imbalance (34 of 5411 rows)."},{"confidence":"high","critiques":[],"evidence_keys":["n_unique","null_rate","top_value","top_rate","top_values","entropy_ratio"],"model":"anthropic:default","narrative":"This column contains US state names, with all 50 states likely represented plus Washington D.C. and possibly territories (53 unique values, 0 nulls across 5,411 rows). Washington dominates at 11.7% (631 records), roughly 1.5\u00d7 California's share (431), suggesting a dataset with geographic bias toward the Pacific Northwest. Entropy ratio of 0.877 indicates reasonably broad distribution across states, though concentration in a handful of large/coastal states is apparent.","role":"feature","scope":"column","target":"state","treatment":"One-hot encode for tree models or ordinal-encode by region grouping; investigate the Washington overrepresentation relative to population before modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n_unique","top_value","top_rate","n","top_values","entropy_ratio"],"model":"anthropic:default","narrative":"This column contains US state abbreviations (plus possibly DC and territories, explaining the 53 distinct values vs. 50 states). Washington ('wa') is notably over-represented at 11.7% of 5,411 rows \u2014 roughly 1.5\u00d7 California ('ca') and nearly 2\u00d7 Ohio ('oh') \u2014 suggesting a geographic skew toward the Pacific Northwest rather than a nationally representative sample. Entropy ratio of 0.877 indicates reasonably broad distribution across states, but the top-heavy concentration in 'wa' is worth flagging.","role":"feature","scope":"column","target":"state_code","treatment":"One-hot encode or target-encode for modelling; investigate why 'wa' is over-represented relative to population share before training."},{"confidence":"medium","critiques":[],"evidence_keys":["n_unique","cardinality","top_value","top_rate","top_values","entropy_ratio","null_rate"],"model":"anthropic:default","narrative":"This column represents calendar month names, but with a cardinality of 32 instead of the expected 12, there are clearly duplicate or variant entries beyond the standard month labels \u2014 likely encoding errors, alternate spellings, or appended year/year-month combinations. The distribution is notably skewed toward summer and early-autumn months (August 634, October 632, July 618), with winter months dramatically underrepresented (December 233, January 228), suggesting seasonal bias in data collection. The entropy_ratio of 0.761 across 32 unique values rather than 12 is a strong flag that this field is dirty and needs normalisation before use.","role":"feature","scope":"column","target":"month","treatment":"Audit and collapse the 32 distinct values down to 12 canonical month names, then encode as an ordered cyclic feature."}],"providers":["anthropic:default"],"total_usage":{"completion_tokens":2902,"prompt_tokens":9825,"total_tokens":12727}},"language_counts":{},"meta":{"generated_at":"2026-06-22T00:50:12+00:00","mode":"full","row_count":5411,"sampled_rows":5411,"seed":42,"source":"/home/coolhand/html/datavis/data_trove/data/wild/bigfoot_sightings.json"},"notes":[],"saturn_version":"0.2.0","schema":{"classification":"categorical","county":"text","description":"text","id":"numeric","month":"categorical","state":"categorical","state_code":"categorical","url":"text","year":"numeric"}}