{"columns":[{"alerts":[],"column":"latitude","extras":{"histogram":{"counts":[3,0,0,0,0,0,0,0,0,0,2,0,0,2,0,75,19,10,22,270,522,1240,2165,2333,1803,1901,2226,1382,515,232,0,0,0,5,6,15,11,8,2,1],"edges":[-14.3236,-12.2123375,-10.101075000000002,-7.989812500000001,-5.878550000000001,-3.7672875,-1.6560250000000014,0.4552374999999991,2.5664999999999996,4.677762499999998,6.7890250000000005,8.9002875,11.011549999999998,13.1228125,15.234074999999999,17.3453375,19.4566,21.567862500000004,23.679125,25.7903875,27.901650000000004,30.0129125,32.124175,34.2354375,36.3467,38.4579625,40.569225,42.680487500000005,44.79175,46.9030125,49.014275000000005,51.12553750000001,53.2368,55.3480625,57.45932500000001,59.5705875,61.68185,63.79311250000001,65.904375,68.0156375,70.1269]},"sample":[35.6,45.12,30.37,34.7,30.5,35.47,46.5,35.75,35.58,43.93,34.7,34.32,33.83,32.35,34.6,44.5,39.97,41.53,40.72,40.9,41.4,40.55,38.7,34.73,43.02,31.83,31.43,34.78,33.13,42.03,29.85,35.47,31.42,41.8,41.43,35.92,33.62,34.83,34.45,33.02,40.95,34.98,35.57,39.98,39.75,38.7,37.57,31.37,36.05,39.48,40.82,31.83,33.52,39.32,30.2,43.82,43.65,34.32,40.07,31.98,36.72,33.42,43.07,32.58,29.2,32.78,28.07,40.6,30.1,36.72,40.67,26.17,32.25,37.2,41.88,40.35,33.62,37.9,37.02,40.52,38.15,38.78,30.93,39.3,29.42,40.63,29.9,32.37,36.23,34.92,40.48,34.33,35.12,35.47,44.67,37.05,34.75,42.02,35.75,32.13,39.72,31.52,31.43,42.42,41.13,34.17,41.25,29.43,34.6,38.78,34.27,34.38,38.15,38.93,39.55,38.67,41.03,38.25,39.48,37.82,39.43,40.6,40.12,28.02,38.12,32.73,32.4,45.55,30.13,40.28,32.33,46.8,43.93,41.13,35.98,35.82,31.1,32.45,32.38,32.42,31.58,41.45,28.1,35.68,30.82,25.68,37.43,35.9,43.92,43.07,41.52,43.1,44.55,32.42,36.53,40.43,42.3,41.52,40.88,46.37,43.73,41.62,24.7,33.42,33.4,38.48,41.82,44.03,46.8,34.65,34.7,32.75,41.23333,30.9,35.26667,35.91667,33.51667,39.45,35.06667,32.38333,31.11667,32.18333,32.55,44.26667,40.83333,41.16667,32.55,42.0,43.38333,36.05,40.3,30.45,31.05,31.78333,32.05,40.7,40.51667,18.28333,48.08333,18.21667,32.3,45.5,31.25,43.21667,29.83333,34.4,33.38333,34.2,38.36667,44.31667,45.45,39.06667,45.2,47.75,29.71,40.87,35.4891,30.3,32.8378,46.55,46.5355,35.0502,31.4493,32.87,41.5004,41.32,40.75,34.5259,38.83,39.85,43.67,34.73,33.6952,43.45,26.35,43.9604,43.02,34.01,34.07,34.97,33.4139,37.501,45.0,39.0204,38.1939,35.3097,37.3964,34.98,32.79,35.3321,35.2677,35.2114,37.5642,34.0936,38.6597,34.236,42.7188,34.6111,39.3205,33.644,43.4988,43.5107,37.9503,41.7304,26.6241,40.43,30.2374,33.7934,35.8441,32.42,40.6612,31.64,34.43,46.8554,39.6597,42.36,39.9555,41.72,38.9228,46.8778,35.323,33.38,37.6046,39.78,32.9456,42.13,34.254,39.9408,45.008,43.49,44.1627,35.65,40.8436,43.9137,41.1045,43.5675,29.1216,42.21,34.8924,35.9657,48.98,48.98,42.8418,44.0964,36.9665,41.6739,41.8763,42.484,38.2393,42.2185,35.3632,34.74,34.939,33.5328,36.5972,34.8055,36.9736,40.55,39.27,60.468,61.225,30.18,33.49,39.95,38.4,37.1,43.52,42.8247,17.9757,39.0832,37.548,34.1784,48.0489,43.4889,38.665,43.7461,33.44,32.46,29.3482,38.818,38.7405,34.697,44.87,39.8967,38.3073,30.4,26.45,43.1613,42.0908,41.56,47.8,35.94,38.1975,30.27,39.8137,39.8394,40.7198,43.65,40.9711,39.7257,42.61,44.3595,37.9371,35.1508,38.3381,34.21,34.1733,34.3878,32.4866,33.5646,34.3402,38.97,33.7163,36.6589,26.57,32.4685,32.2478,34.2232,30.4907,33.1,33.1002,33.8585,33.8197,34.3425,32.7203,43.1925,43.2857,31.2634,30.2113,34.69,18.011,34.2492,34.7207,39.9408,36.6323,29.8193,18.2757,18.3044,18.4862,33.4156,31.9255,36.75,34.9474,37.7238,36.148,37.6547,37.4477,40.8668,35.58,36.4869,43.57,43.05,40.3459,33.4474,35.2907,37.3787,43.848,41.0587,39.4266,35.8649,35.14,30.65,30.6149,35.4601,33.7467,45.6629,36.62,35.17,33.8827,29.9071,43.5023,36.7669,41.65,33.5304,26.172,32.8685,32.7475,46.75,35.18,47.1226,33.51,35.414,28.9908,36.77,37.9683,40.87,30.5288,39.6399,39.1498,30.4003,34.3551,39.0723,36.352,29.9398,33.3905,36.817,47.6393,39.5649,43.018,39.3696,46.8681,36.0214,37.368,17.9376,29.9275,37.1,30.05,41.0615,36.95,46.4126,37.3501,39.6409,34.32,34.464,41.6534,41.28,36.8286,39.94,36.5683,42.4357,38.8016,33.489,30.9102,37.02,27.6233,37.59,33.5414,37.3905,35.4,18.3615,35.95,31.845,36.8669,36.0951,36.005,46.6294,36.3635,41.14,43.2789,41.7313]},"kind":"numeric","n":14770,"n_null":0,"n_unique":7810,"null_rate":0.0,"stats":{"iqr":7.4986999999999995,"kurtosis":3.3406489774886445,"max":70.1269,"mean":37.27773758287068,"median":37.12,"min":-14.3236,"n_outliers":159,"outlier_rate":0.010765064319566689,"q1":33.63,"q3":41.1287,"skew":-0.1786765983590032,"std":5.247184183716053,"zero_rate":0.0}},{"alerts":[],"column":"longitude","extras":{"histogram":{"counts":[4,33,28,4,11,305,466,544,3693,5377,3281,941,79,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,1,0,1],"edges":[-170.7316,-162.17658749999998,-153.62157499999998,-145.06656249999997,-136.51155,-127.95653749999998,-119.40152499999999,-110.84651249999999,-102.29149999999998,-93.73648749999998,-85.18147499999998,-76.62646249999999,-68.07144999999998,-59.51643749999998,-50.96142499999999,-42.40641249999999,-33.851399999999984,-25.29638749999998,-16.741374999999977,-8.186362499999973,0.3686500000000308,8.923662500000006,17.47867500000001,26.033687500000013,34.58870000000002,43.14371250000002,51.698725000000024,60.25373750000003,68.80875,77.3637625,85.91877500000001,94.47378750000004,103.02880000000002,111.5838125,120.13882500000003,128.6938375,137.24885000000003,145.8038625,154.35887500000004,162.91388750000002,171.4689]},"sample":[-90.72,-93.08,-92.13,-87.7,-90.55,-100.0,-97.0,-96.65,-88.47,-88.97,-85.28,-86.98,-102.05,-95.32,-92.8,-107.55,-76.67,-85.42,-93.55,-81.4,-98.38,-98.37,-94.4,-88.62,-96.07,-86.63,-83.13,-90.97,-96.1,-87.85,-93.97,-76.7,-86.07,-72.53,-90.42,-85.5,-87.6,-86.78,-84.25,-80.18,-99.43,-90.78,-89.65,-88.23,-85.65,-95.97,-81.45,-84.17,-85.2,-84.12,-85.6,-99.43,-86.93,-94.0,-92.18,-88.73,-88.7,-90.42,-81.63,-90.42,-93.63,-92.33,-95.88,-94.8,-81.02,-95.52,-80.57,-79.55,-98.42,-84.47,-93.02,-80.17,-85.4,-89.72,-93.17,-91.45,-93.67,-93.87,-95.85,-88.88,-85.02,-90.7,-92.17,-90.27,-82.1,-95.67,-93.95,-86.4,-96.33,-78.92,-75.7,-90.53,-90.17,-91.05,-88.88,-93.13,-79.37,-79.57,-97.37,-100.12,-104.9,-90.37,-90.25,-96.38,-87.87,-87.38,-95.6,-98.52,-83.75,-99.55,-97.75,-97.58,-97.43,-96.48,-84.05,-86.65,-98.33,-88.47,-88.88,-95.45,-99.42,-96.4,-76.95,-82.78,-81.15,-97.12,-90.23,-88.93,-94.4,-86.52,-90.17,-100.77,-88.23,-104.82,-91.72,-92.35,-97.35,-85.13,-86.3,-87.23,-83.93,-75.38,-80.63,-82.02,-97.62,-80.52,-85.78,-92.63,-86.03,-77.0,-91.5,-84.87,-93.67,-99.85,-85.18,-79.7,-83.47,-82.95,-90.07,-94.2,-83.97,-91.62,-81.08,-111.82,-94.73,-100.9,-79.45,-92.47,-100.77,-112.35,-99.33,-97.35,-103.66667,-95.3,-89.0,-86.2,-88.05,-85.78333,-98.88333,-89.55,-94.76667,-90.31667,-101.05,-88.4,-99.26667,-83.4,-90.31667,-91.65,-97.13333,-89.81667,-81.91667,-85.05,-84.91667,-89.65,-81.08333,-99.08333,-98.06667,-66.51667,-99.85,-65.73333,-90.21667,-91.73333,-83.68333,-88.11667,-97.96667,-85.03333,-96.43333,-79.75,-81.66667,-93.56667,-94.53333,-76.55,-93.63333,-124.38,-85.0,-100.21,-114.05,-97.95,-91.9,-87.38,-87.38,-85.6855,-85.506,-97.37,-95.3773,-96.35,-74.88,-101.7822,-97.6,-95.53,-70.27,-92.4031,-111.8826,-90.73,-80.08,-91.8687,-91.18,-86.75,-84.3,-87.27,-80.31,-92.2247,-105.568,-86.9488,-87.8725,-89.7592,-92.9828,-93.3353,-96.77,-87.1979,-87.4027,-91.4832,-91.2167,-91.4365,-95.6002,-86.8635,-93.9304,-92.0297,-85.7591,-85.638,-91.648,-91.6754,-107.0308,-88.0307,-80.2348,-79.7,-92.0925,-84.75,-90.7185,-90.01,-75.2843,-93.64,-100.3,-102.8159,-86.2148,-93.1,-89.5611,-73.98,-76.45,-96.9276,-89.6526,-112.24,-114.0477,-97.89,-90.1539,-98.03,-96.432,-86.2367,-93.8562,-96.89,-92.5353,-97.58,-93.1129,-94.3451,-89.0723,-84.7918,-95.6492,-78.14,-85.423,-91.422,-102.25,-102.25,-85.9818,-102.5019,-91.4235,-72.9758,-87.6125,-70.869,-95.7604,-96.3817,-79.27,-80.18,-97.67,-89.153,-83.4922,-86.4641,-89.43,-82.62,-81.55,-150.5,-149.65,-93.58,-80.93,-82.02,-95.6,-76.53,-88.22,-102.68,-66.54,-82.7333,-97.348,-109.9434,-117.3422,-71.3451,-104.7677,-92.2092,-84.31,-84.99,-95.0186,-104.8316,-104.7458,-76.774,-88.63,-89.1125,-123.0501,-87.45,-81.95,-70.6446,-96.931,-85.24,-103.68,-79.0,-82.9471,-86.0,-75.4234,-75.6087,-74.7059,-83.93,-98.0,-86.3496,-83.51,-106.8055,-82.8799,-97.0142,-85.6392,-86.97,-101.7628,-97.3169,-97.4352,-116.1083,-90.1974,-90.45,-80.2181,-94.4463,-82.037,-88.8749,-92.9838,-83.9491,-87.2052,-96.68,-96.6288,-79.0687,-79.0829,-79.4344,-97.3554,-91.8536,-91.7242,-91.8498,-89.7614,-85.78,-65.9273,-77.9521,-79.0038,-79.7004,-87.6345,-96.7209,-66.1775,-67.2271,-66.8329,-89.5944,-93.7101,-90.4,-95.4836,-90.0055,-93.7322,-91.5341,-118.4093,-99.73,-78.83,-79.7452,-116.12,-86.24,-94.875,-94.6484,-90.4761,-79.162,-95.346,-80.5702,-77.4042,-79.0149,-79.121,-98.45,-98.3953,-94.3993,-116.9075,-118.8357,-88.32,-85.7823,-84.408,-96.9573,-97.1266,-93.175,-83.55,-90.9931,-97.9952,-96.9149,-93.9719,-118.32,-101.9,-104.7782,-89.92,-82.82,-90.194,-80.73,-83.6148,-98.0383,-103.8206,-75.7796,-77.2766,-88.5177,-86.4723,-77.1123,-88.522,-90.0672,-110.8224,-88.485,-122.4119,-99.4125,-83.235,-80.7593,-100.8664,-78.3321,-121.8806,-66.294,-90.0403,-92.92,-95.42,-92.3334,-88.61,-117.0225,-117.6781,-76.8703,-103.3,-88.789,-87.5248,-75.89,-119.3245,-75.91,-89.0403,-83.552,-81.3336,-97.487,-95.316,-92.66,-80.3957,-77.59,-111.4398,-91.1932,-97.242,-66.99,-81.944,-93.752,-88.3541,-94.8321,-114.967,-97.5341,-89.0436,-74.58,-88.0633,-87.9149]},"kind":"numeric","n":14770,"n_null":0,"n_unique":8828,"null_rate":0.0,"stats":{"iqr":12.170000000000002,"kurtosis":55.607955032539,"max":171.4689,"mean":-90.94044363452944,"median":-90.22,"min":-170.7316,"n_outliers":623,"outlier_rate":0.042180094786729856,"q1":-96.4,"q3":-84.23,"skew":1.2861616598782257,"std":11.695802025598638,"zero_rate":0.0}},{"alerts":[{"code":"multilingual","level":"info","message":"13 languages detected in sample"},{"code":"duplicates","level":"warn","message":"54.9% duplicate strings"}],"column":"name","extras":{"language_counts":{"__engine":"fasttext:5,000","de":25,"en":4796,"es":134,"eu":2,"fr":1,"id":6,"it":5,"ja":22,"pt":4,"ru":2,"sr":2,"zh":1},"language_sample_size":5000,"length_histogram":{"counts":[50,793,2165,3842,2969,1813,1442,915,493,153,45,4,3,4,6,9,5,7,3,10,7,5,6,3,3,3,1,5,3,0,0,0,0,0,1,0,0,0,1,1],"edges":[17.0,19.925,22.85,25.775,28.7,31.625,34.55,37.474999999999994,40.4,43.325,46.25,49.175,52.099999999999994,55.025,57.949999999999996,60.875,63.8,66.725,69.65,72.57499999999999,75.5,78.425,81.35,84.27499999999999,87.19999999999999,90.125,93.05,95.975,98.89999999999999,101.82499999999999,104.75,107.675,110.6,113.52499999999999,116.44999999999999,119.375,122.3,125.225,128.14999999999998,131.075,134.0]},"near_unique":false,"sample":["Tornado in LOUISIANA, CADDO","Flood in LOUISIANA, BEAUREGARD","Tornado in NORTH CAROLINA, ANSON","Thunderstorm Wind in GEORGIA, NEWTON","Hail in WISCONSIN, DODGE","Flash Flood in MISSOURI, DENT","Tornado in PENNSYLVANIA, LUZERNE","Flash Flood in KENTUCKY, FRANKLIN","Lightning in FLORIDA, PALM BEACH","Tornado in SOUTH CAROLINA, DARLINGTON","Tornado in MISSISSIPPI, ATTALA","Tornado in LOUISIANA, CADDO","Hail in MICHIGAN, BRANCH","Tornado in KANSAS, STEVENS","Thunderstorm Wind in CALIFORNIA, FRESNO","Tornado in ALABAMA, MARSHALL","Tornado in ALABAMA, MADISON","Flash Flood in MISSOURI, LINCOLN","Flash Flood in TEXAS, HIDALGO","Tornado in MASSACHUSETTS, NORFOLK","Thunderstorm Wind in WISCONSIN, JEFFERSON","Tornado in KENTUCKY, LEE","Tornado in LOUISIANA, ST. LANDRY","Tornado in FLORIDA, HILLSBOROUGH","Flash Flood in OHIO, SUMMIT","Flood in WISCONSIN, VERNON","Flash Flood in IOWA, WAYNE","Thunderstorm Wind in NORTH CAROLINA, DAVIDSON","Tornado in KANSAS, ELLSWORTH","Tornado in GEORGIA, WHEELER","Thunderstorm Wind in TEXAS, LUBBOCK","Hail in COLORADO, ARAPAHOE","Thunderstorm Wind in OHIO, WASHINGTON","Thunderstorm Wind in MISSOURI, CASS","Tornado in MISSISSIPPI, WASHINGTON","Thunderstorm Wind in ILLINOIS, JEFFERSON","Hail in NEBRASKA, BUFFALO","Flood in MINNESOTA, HOUSTON","Lightning in UTAH, SUMMIT","Flood in WASHINGTON, WHATCOM","Flash Flood in VIRGINIA, HENRY","Thunderstorm Wind in TEXAS, HARRIS","Thunderstorm Wind in PENNSYLVANIA, UNION","Flood in MICHIGAN, IRON","Tornado in IOWA, POTTAWATTAMIE","Thunderstorm Wind in GEORGIA, LOWNDES","Tornado in KENTUCKY, TAYLOR","Tornado in NEW JERSEY, MERCER","Tornado in ARKANSAS, WHITE","Thunderstorm Wind in GEORGIA, CLAYTON"],"top_values":[["Hail in TEXAS, TARRANT",59],["Tornado in TEXAS, HARRIS",30],["Thunderstorm Wind in ARIZONA, MARICOPA",29],["Flash Flood in CALIFORNIA, SAN BERNARDINO",28],["Tornado in OKLAHOMA, OKLAHOMA",26],["Hail in TEXAS, DENTON",26],["Hail in TEXAS, COLLIN",24],["Flash Flood in ILLINOIS, COOK",23],["Tornado in ALABAMA, JEFFERSON",22],["Tornado in TEXAS, DALLAS",22],["Tornado in ARKANSAS, PULASKI",19],["Hail in TEXAS, LUBBOCK",19],["Hail in TEXAS, RANDALL",18],["Flash Flood in NEVADA, CLARK",18],["Tornado in LOUISIANA, CADDO",17],["Tornado in MISSISSIPPI, JONES",17],["Thunderstorm Wind in ILLINOIS, COOK",17],["Flash Flood in TEXAS, HARRIS",17],["Hail in TEXAS, DALLAS",17],["Tornado in LOUISIANA, BOSSIER",16]],"top_words":[["in",14773],["tornado",6334],["flood",4135],["flash",2358],["wind",2332],["thunderstorm",2282],["texas,",1450],["hail",1246],["new",685],["carolina,",657],["missouri,",648],["arkansas,",602],["lightning",575],["mississippi,",570],["north",568],["georgia,",562],["illinois,",560],["iowa,",527],["louisiana,",507],["tennessee,",499],["florida,",498],["oklahoma,",490],["nebraska,",486],["alabama,",469],["wisconsin,",463]],"vocab_skipped":null,"word_histogram":{"counts":[8215,5152,0,1215,89,0,11,15,0,5,8,0,18,8,0,9,11,0,4,3,0,1,4,0,0,1,0,0,0,1],"edges":[4.0,4.666666666666667,5.333333333333333,6.0,6.666666666666666,7.333333333333333,8.0,8.666666666666666,9.333333333333332,10.0,10.666666666666666,11.333333333333332,12.0,12.666666666666666,13.333333333333332,14.0,14.666666666666666,15.333333333333332,16.0,16.666666666666664,17.333333333333332,18.0,18.666666666666664,19.333333333333332,20.0,20.666666666666664,21.333333333333332,22.0,22.666666666666664,23.333333333333332,24.0]}},"kind":"text","n":14770,"n_null":0,"n_unique":6660,"null_rate":0.0,"stats":{"allcaps_rate":0.0,"boilerplate_rate":0.0,"duplicate_rate":0.5490859851049424,"emoji_rate":0.0,"len_max":134,"len_mean":30.219160460392686,"len_median":29.0,"len_min":17,"len_p95":41.0,"n_duplicates":8110,"n_empty":0,"one_word_rate":0.0,"readability_flesch_mean":31.163353571428587,"url_rate":0.0,"vocab_size":1980,"word_mean":4.587610020311442,"word_median":4.0}},{"alerts":[{"code":"multilingual","level":"info","message":"5 languages detected in sample"},{"code":"duplicates","level":"warn","message":"60.8% duplicate strings"}],"column":"description","extras":{"language_counts":{"__engine":"fasttext:5,000","en":4984,"fr":5,"ja":1,"no":10},"language_sample_size":5000,"length_histogram":{"counts":[4,13,3101,1689,2230,1186,572,1589,2168,902,7,6,14,10,15,25,30,30,34,47,71,64,52,77,60,74,66,65,54,69,82,70,72,78,64,29,20,11,12,8],"edges":[3.0,9.4,15.8,22.200000000000003,28.6,35.0,41.400000000000006,47.800000000000004,54.2,60.6,67.0,73.4,79.80000000000001,86.2,92.60000000000001,99.0,105.4,111.80000000000001,118.2,124.60000000000001,131.0,137.4,143.8,150.20000000000002,156.60000000000002,163.0,169.4,175.8,182.20000000000002,188.60000000000002,195.0,201.4,207.8,214.20000000000002,220.60000000000002,227.0,233.4,239.8,246.20000000000002,252.60000000000002,259.0]},"near_unique":false,"sample":["Magnitude 0; 40 injuries, 9 fatalities; $250K property damage","$40.00M property damage","$3.00M property damage","EG55.00; 1 injuries, 1 fatalities; $20.00K property damage; A weak upper-level wave moving across the state resulted in widespread strong to severe thunderstorms across north and central Georgia.","Magnitude 1.75; $3.17M property damage","$15.00M property damage","5 injuries, 0 fatalities; $1.00M property damage","0 injuries, 1 fatalities","1 injuries, 1 fatalities","Magnitude 0; 0 injuries, 1 fatalities; $25K property damage","2 injuries, 0 fatalities; $3.00M property damage","2 injuries, 0 fatalities; $10.00M property damage","Magnitude 1.75; $1M property damage","Magnitude 0; 5 injuries, 1 fatalities; $25K property damage","Magnitude 30; 15 injuries, 0 fatalities; $.15M property damage","Magnitude 0; 5 injuries, 0 fatalities; $2.5M property damage","Magnitude 0; 3 injuries, 2 fatalities; $2.5M property damage","$5.40M property damage; The Pin Oak Levee in Winfield, MO was breached during the afternoon hours of June 2nd, flooding eastern portions of Winfield east of Highway 79.","0 injuries, 3 fatalities","$1.5M property damage","8 injuries, 0 fatalities; $2.7M property damage","Magnitude 0; 25 injuries, 1 fatalities; $2.5M property damage","Magnitude 0; 7 injuries, 0 fatalities; $2.5M property damage","Magnitude 0; 53 injuries, 0 fatalities; $2.5M property damage","$1.50M property damage","0 injuries, 1 fatalities; $986.00K property damage","$2.50M property damage","Magnitude 0; 1 injuries, 1 fatalities; $0 property damage","Magnitude 0; $2.5M property damage","0 injuries, 2 fatalities","MG83.00; $5.00M property damage","Magnitude 2.50; $161.10M property damage","EG56.00; $3.00M property damage","EG61; 2 injuries, 1 fatalities; $150K property damage","12 injuries, 0 fatalities; $3.5M property damage","EG78; 5 injuries, 0 fatalities; $13M property damage","Magnitude 1.50; $8.00M property damage","$6.50M property damage","2 injuries, 1 fatalities; Showers and thunderstorms occurred across much of northern Utah, and a man was killed by a lightning strike.","$5.60M property damage","$9.20M property damage","EG50.00; 1 injuries, 1 fatalities; A cluster of severe thunderstorms moved across the area and produced hail, damaging winds and flash flooding.","$15M property damage; Strong winds knocked trees down along Rte. 80 near West Buffalo Township.","$3.10M property damage","3 injuries, 1 fatalities","EG65.00; $3.50M property damage","E50; $5K property damage","$1M property damage","Magnitude 0; 7 injuries, 0 fatalities; $2.5M property damage","EG45.00; 0 injuries, 1 fatalities; $15.00K property damage"],"top_values":[["Magnitude 0; $2.5M property damage",1055],["$1.00M property damage",660],["0 injuries, 1 fatalities",488],["$2.00M property damage",292],["$1.50M property damage",178],["Magnitude 0; 1 injuries, 0 fatalities; $2.5M property damage",162],["Magnitude 0; $25M property damage",159],["$5.00M property damage",159],["$3.00M property damage",157],["$1M property damage",146],["Magnitude 0; 2 injuries, 0 fatalities; $2.5M property damage",115],["$10.00M property damage",101],["$4.00M property damage",87],["Magnitude 0; 3 injuries, 0 fatalities; $2.5M property damage",86],["Magnitude 0; 0 injuries, 1 fatalities; $0 property damage",85],["0 injuries, 2 fatalities",77],["Magnitude 0; 4 injuries, 0 fatalities; $2.5M property damage",75],["$1.20M property damage",73],["$2.50M property damage",67],["$2M property damage",66]],"top_words":[["property",13178],["damage",12415],["injuries,",7098],["fatalities;",5949],["magnitude",5463],["0",4929],["1",4111],["0;",3863],["$2.5m",2278],["$1.00m",1306],["the",1290],["and",1278],["2",1219],["a",1198],["fatalities",1153],["of",1026],["damage;",890],["in",622],["3",581],["$2.00m",553],["thunderstorms",546],["$25m",530],["across",508],["$250k",471],["$1m",457]],"vocab_skipped":null,"word_histogram":{"counts":[17,3777,4389,41,2427,2803,13,8,21,26,21,67,54,115,61,75,133,78,113,83,130,43,75,94,39,37,13,14,1,2],"edges":[1.0,2.4333333333333336,3.8666666666666667,5.3,6.733333333333333,8.166666666666668,9.6,11.033333333333333,12.466666666666667,13.9,15.333333333333334,16.766666666666666,18.2,19.633333333333333,21.066666666666666,22.5,23.933333333333334,25.366666666666667,26.8,28.233333333333334,29.666666666666668,31.1,32.53333333333333,33.96666666666667,35.4,36.833333333333336,38.266666666666666,39.7,41.13333333333333,42.56666666666667,44.0]}},"kind":"text","n":14770,"n_null":0,"n_unique":5796,"null_rate":0.0,"stats":{"allcaps_rate":0.00027081922816519973,"boilerplate_rate":0.0,"duplicate_rate":0.6075829383886255,"emoji_rate":0.0,"len_max":259,"len_mean":50.085240352065,"len_median":36.0,"len_min":3,"len_p95":166.0,"n_duplicates":8974,"n_empty":0,"one_word_rate":0.00027081922816519973,"readability_flesch_mean":29.857567232767256,"url_rate":0.0,"vocab_size":4289,"word_mean":7.393026404874746,"word_median":5.0}},{"alerts":[{"code":"imbalance","level":"warn","message":"top value is 100.0% of rows"}],"column":"category","extras":{"singletons":0,"top_values":[["significant_us_storms",14770]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":1,"null_rate":0.0,"stats":{"cardinality":1,"entropy":-0.0,"entropy_ratio":0.0,"top_rate":1.0,"top_value":"significant_us_storms"}},{"alerts":[{"code":"one_word","level":"warn","message":"100.0% rows are a single word"},{"code":"allcaps","level":"info","message":"100.0% rows are all-caps"},{"code":"short_text","level":"info","message":"95th-percentile length under 20 chars"},{"code":"duplicates","level":"warn","message":"65.8% duplicate strings"}],"column":"date","extras":{"language_counts":{},"language_sample_size":5000,"length_histogram":{"counts":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,14770,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"edges":[9.5,9.525,9.55,9.575,9.6,9.625,9.65,9.675,9.7,9.725,9.75,9.775,9.8,9.825,9.85,9.875,9.9,9.925,9.95,9.975,10.0,10.025,10.05,10.075,10.1,10.125,10.15,10.175,10.2,10.225,10.25,10.275,10.3,10.325,10.35,10.375,10.4,10.425,10.45,10.475,10.5]},"near_unique":false,"sample":["1950-02-12","2016-03-10","2020-04-13","2018-06-25","2006-04-13","2024-11-05","2006-12-01","2021-12-11","2018-07-10","1961-04-12","2011-01-01","2009-04-09","1996-04-12","1951-06-23","1997-05-19","1985-04-05","1974-04-03","2019-06-02","2025-03-27","2004-08-21","1998-05-31","1961-06-09","1983-02-09","1974-02-19","2014-05-12","2016-09-22","2009-08-26","1985-05-15","1970-03-02","2024-09-26","2012-04-29","2012-06-07","2012-06-29","2003-08-21","2001-11-24","2006-07-21","2023-05-05","2008-06-08","2007-10-13","2009-01-07","2018-05-18","2023-05-08","1996-06-20","2023-04-13","2024-04-26","2024-03-27","2000-05-23","2003-09-23","1982-12-02","2021-03-01"],"top_values":[["1974-04-03",126],["2011-04-27",105],["2011-08-28",59],["2011-05-01",59],["2008-03-18",57],["2021-09-01",56],["1990-03-13",52],["1965-04-11",49],["2011-09-07",49],["2012-06-29",45],["2019-03-13",45],["2006-04-13",42],["1984-06-07",41],["1992-11-22",40],["2016-10-08",40],["1984-03-28",38],["2008-06-08",37],["2009-05-08",37],["1985-05-31",35],["2012-03-02",35]],"top_words":[["1974-04-03",126],["2011-04-27",105],["2011-08-28",59],["2011-05-01",59],["2008-03-18",57],["2021-09-01",56],["1990-03-13",52],["1965-04-11",49],["2011-09-07",49],["2012-06-29",45],["2019-03-13",45],["2006-04-13",42],["1984-06-07",41],["1992-11-22",40],["2016-10-08",40],["1984-03-28",38],["2008-06-08",37],["2009-05-08",37],["1985-05-31",35],["2012-03-02",35],["2024-09-27",35],["1998-05-31",34],["2003-05-04",34],["2011-04-26",34],["1990-06-02",32]],"vocab_skipped":null,"word_histogram":{"counts":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,14770,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"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":14770,"n_null":0,"n_unique":5058,"null_rate":0.0,"stats":{"allcaps_rate":1.0,"boilerplate_rate":0.0,"duplicate_rate":0.657549085985105,"emoji_rate":0.0,"len_max":10,"len_mean":10.0,"len_median":10.0,"len_min":10,"len_p95":10.0,"n_duplicates":9712,"n_empty":0,"one_word_rate":1.0,"readability_flesch_mean":121.22000000000004,"url_rate":0.0,"vocab_size":5058,"word_mean":1.0,"word_median":1.0}},{"alerts":[{"code":"imbalance","level":"warn","message":"top value is 100.0% of rows"}],"column":"country","extras":{"singletons":0,"top_values":[["USA",14770]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":1,"null_rate":0.0,"stats":{"cardinality":1,"entropy":-0.0,"entropy_ratio":0.0,"top_rate":1.0,"top_value":"USA"}},{"alerts":[],"column":"event_type","extras":{"singletons":4,"top_values":[["Tornado",6334],["Flash Flood",2358],["Thunderstorm Wind",2257],["Flood",1777],["Hail",1246],["Lightning",574],["Heavy Rain",99],["Marine Strong Wind",43],["Debris Flow",43],["Marine Thunderstorm Wind",25],["Marine High Wind",5],["Dust Devil",3],["Waterspout",2],["Tropical Storm",1],["High Wind",1],["Heat",1],["Marine Lightning",1]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":17,"null_rate":0.0,"stats":{"cardinality":17,"entropy":2.336076472984396,"entropy_ratio":0.5715223755452659,"top_rate":0.4288422477995938,"top_value":"Tornado"}},{"alerts":[],"column":"state","extras":{"singletons":3,"top_values":[["TEXAS",1450],["MISSOURI",648],["ARKANSAS",602],["MISSISSIPPI",570],["GEORGIA",562],["ILLINOIS",560],["IOWA",527],["LOUISIANA",507],["TENNESSEE",499],["FLORIDA",498],["OKLAHOMA",490],["NEBRASKA",486],["ALABAMA",469],["WISCONSIN",463],["OHIO",441],["MICHIGAN",426],["NORTH CAROLINA",422],["KANSAS",418],["INDIANA",408],["KENTUCKY",383]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":65,"null_rate":0.0,"stats":{"cardinality":65,"entropy":5.182276527947146,"entropy_ratio":0.8605048195057264,"top_rate":0.0981719702098849,"top_value":"TEXAS"}},{"alerts":[{"code":"null_rate","level":"warn","message":"51.8% null"}],"column":"magnitude","extras":{"singletons":48,"top_values":[["0",3863],["1.75",383],["2.75",220],["70.00",162],["50.00",151],["2.00",150],["2.50",123],["61.00",122],["65.00",104],["52.00",95],["78.00",80],["70",79],["3.00",77],["56.00",76],["87.00",65],["60.00",63],["50",59],["60",54],["1.50",50],["61",47]]},"kind":"categorical","n":14770,"n_null":7648,"n_unique":170,"null_rate":0.5178063642518619,"stats":{"cardinality":170,"entropy":3.586498005507387,"entropy_ratio":0.4840476142262948,"top_rate":0.5424038191519236,"top_value":"0"}},{"alerts":[],"column":"injuries","extras":{"singletons":69,"top_values":[["0",10064],["1",893],["2",552],["3",343],["4",236],["5",234],["10",219],["6",196],["12",158],["7",134],["8",121],["20",114],["15",111],["11",90],["9",85],["13",70],["14",69],["30",68],["25",56],["16",48]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":178,"null_rate":0.0,"stats":{"cardinality":178,"entropy":2.468064058708073,"entropy_ratio":0.33014340084475474,"top_rate":0.6813811780636425,"top_value":"0"}},{"alerts":[],"column":"fatalities","extras":{"singletons":18,"top_values":[["0",10209],["1",3208],["2",649],["3",222],["4",112],["5",74],["6",66],["7",38],["9",25],["10",24],["8",21],["11",20],["13",11],["16",10],["12",9],["14",8],["17",6],["20",6],["25",4],["23",3]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":49,"null_rate":0.0,"stats":{"cardinality":49,"entropy":1.4234519366880767,"entropy_ratio":0.2535219051755631,"top_rate":0.691198375084631,"top_value":"0"}},{"alerts":[{"code":"one_word","level":"warn","message":"100.0% rows are a single word"},{"code":"allcaps","level":"info","message":"87.2% rows are all-caps"},{"code":"short_text","level":"info","message":"95th-percentile length under 20 chars"},{"code":"duplicates","level":"warn","message":"93.1% duplicate strings"}],"column":"damage_property","extras":{"language_counts":{},"language_sample_size":5000,"length_histogram":{"counts":[368,0,0,0,0,264,0,0,0,0,1252,0,0,0,0,1172,0,0,0,0,3414,0,0,0,0,6075,0,0,0,0,1450,0,0,0,0,514,0,0,0,261],"edges":[0.0,0.2,0.4,0.6000000000000001,0.8,1.0,1.2000000000000002,1.4000000000000001,1.6,1.8,2.0,2.2,2.4000000000000004,2.6,2.8000000000000003,3.0,3.2,3.4000000000000004,3.6,3.8000000000000003,4.0,4.2,4.4,4.6000000000000005,4.800000000000001,5.0,5.2,5.4,5.6000000000000005,5.800000000000001,6.0,6.2,6.4,6.6000000000000005,6.800000000000001,7.0,7.2,7.4,7.6000000000000005,7.800000000000001,8.0]},"near_unique":false,"sample":["250K","40.00M","3.00M","20.00K","3.17M","15.00M","1.00M","0.00K","0.00K","25K","3.00M","10.00M","1M","25K",".15M","2.5M","2.5M","5.40M","0.00K","1.5M","2.7M","2.5M","2.5M","2.5M","1.50M","986.00K","2.50M","0","2.5M","","5.00M","161.10M","3.00M","150K","3.5M","13M","8.00M","6.50M","0.00K","5.60M","9.20M","0.00K","15M","3.10M","","3.50M","5K","1M","2.5M","15.00K"],"top_values":[["2.5M",2278],["1.00M",1306],["0.00K",1229],["2.00M",553],["25M",530],["250K",471],["1M",457],["",368],["1.50M",334],["5.00M",325],["3.00M",297],["0",264],["2M",231],["10.00M",212],["5M",182],["25K",178],["4.00M",155],["2.50M",136],["1.5M",123],["10.00K",113]],"top_words":[["2.5m",2278],["1.00m",1306],["0.00k",1229],["2.00m",553],["25m",530],["250k",471],["1m",457],["1.50m",334],["5.00m",325],["3.00m",297],["0",264],["2m",231],["10.00m",212],["5m",182],["25k",178],["4.00m",155],["2.50m",136],["1.5m",123],["10.00k",113],["0k",111],["3m",109],["1.20m",109],["1000.00k",102],["10m",92],["50.00m",78]],"vocab_skipped":null,"word_histogram":{"counts":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,14770,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"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":14770,"n_null":0,"n_unique":1014,"null_rate":0.0,"stats":{"allcaps_rate":0.872444143534191,"boilerplate_rate":0.0,"duplicate_rate":0.9313473256601219,"emoji_rate":0.0,"len_max":8,"len_mean":4.380568720379147,"len_median":5.0,"len_min":0,"len_p95":7.0,"n_duplicates":13756,"n_empty":368,"one_word_rate":1.0,"readability_flesch_mean":116.97730000000003,"url_rate":0.0,"vocab_size":1013,"word_mean":1.0,"word_median":1.0}},{"alerts":[{"code":"imbalance","level":"warn","message":"top value is 100.0% of rows"}],"column":"source","extras":{"singletons":0,"top_values":[["NOAA Storm Events Database",14770]]},"kind":"categorical","n":14770,"n_null":0,"n_unique":1,"null_rate":0.0,"stats":{"cardinality":1,"entropy":-0.0,"entropy_ratio":0.0,"top_rate":1.0,"top_value":"NOAA Storm Events Database"}}],"insights":{"errors":[],"insights":[{"confidence":"high","critiques":[],"evidence_keys":["row_count","column_count","columns.event_type.top_values","columns.event_type.stats.top_rate","columns.state.top_values","columns.magnitude.null_rate","columns.fatalities.stats.top_rate","columns.injuries.stats.top_rate","columns.country.stats.top_value","columns.source.stats.top_value","columns.latitude.stats","columns.longitude.stats"],"featured_charts":[{"caption":"Tornadoes account for ~43% of events; check how steeply the distribution drops to Flash Flood and Thunderstorm Wind.","column":"event_type","kind":"bar"},{"caption":"Texas leads at nearly 10% of records \u2014 see how concentrated events are in the southern/midwestern tornado belt.","column":"state","kind":"bar"},{"caption":"Heavy zero-inflation (69% are 0 fatalities) means the tail of deadly events is what matters analytically.","column":"fatalities","kind":"bar"},{"caption":"Damage values cluster on a few round figures like 2.5M and 1.00M, hinting at coded or estimated reporting rather than precise amounts.","column":"damage_property","kind":"bar"},{"caption":"Most events fall between 33\u00b0 and 41\u00b0 N, with a few outliers extending toward Alaska and the tropics.","column":"latitude","kind":"histogram"}],"model":"anthropic:claude-opus-4-7","narrative":"This dataset contains 14,770 records of significant U.S. storm events sourced entirely from the NOAA Storm Events Database, with each row describing a weather incident's location, type, magnitude, and damages. Tornadoes dominate the event mix at roughly 43% of records, followed by Flash Floods and Thunderstorm Winds, so the event_type distribution is the first thing to inspect. Geographically the data skews toward Texas (1,450 events) and other tornado-belt states like Missouri, Arkansas, and Mississippi, which is worth confirming on the latitude/longitude spread. Two caveats deserve attention: the magnitude field is missing for 51.8% of rows, and category/country/source are constants (single value) so they carry no analytical signal. Fatalities and injuries are heavily zero-inflated (about 69% and 68% zeros respectively), meaning summary stats will be driven by a small tail of severe events.","scope":"dataset","target":"__global__"},{"confidence":"high","critiques":[],"evidence_keys":["min","max","mean","median","q1","q3","std","iqr","skew","kurtosis","n_outliers","outlier_rate","null_rate"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds geographic latitudes, ranging from -14.3236 to 70.1269 with a mean of 37.28 and median of 37.12, consistent with degrees north/south. The distribution is tightly clustered (IQR 7.50, std 5.25) around the mid-30s to low-40s, suggesting most records sit in northern temperate zones. Skew is mild (-0.18) but kurtosis of 3.34 plus 159 outliers (1.08%) hints at a long southern tail extending into the southern hemisphere.","role":"feature","scope":"column","target":"latitude","treatment":"Pair with longitude as a geospatial feature; consider binning or projecting rather than treating as a plain scalar."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.min","stats.max","stats.median","stats.mean","stats.iqr","stats.kurtosis","stats.skew","stats.n_outliers","stats.outlier_rate","stats.q1","stats.q3"],"model":"anthropic:claude-opus-4-7","narrative":"Geographic longitude coordinates, with 8828 unique values across 14770 rows and no nulls. Values span -170.73 to 171.47 (full global range), but the distribution is tightly concentrated around a median of -90.22 with an IQR of just 12.17, indicating most records cluster in the Americas. Heavy kurtosis (55.6) and 623 outliers (4.2%) reflect a small set of points scattered far from this North/Central American core.","role":"feature","scope":"column","target":"longitude","treatment":"Pair with latitude for geospatial features; do not standardize as a plain scalar."},{"confidence":"high","critiques":[],"evidence_keys":["alerts","n","n_unique","stats.duplicate_rate","stats.n_duplicates","stats.len_mean","stats.word_mean","top_values","top_words","language_counts"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds short structured event labels of the form '<Event Type> in <STATE>, <COUNTY>' describing US severe weather incidents (tornadoes, floods, hail, thunderstorm winds). It is highly repetitive: 8110 of 14770 rows are duplicates (54.9% duplicate_rate) with only 6660 unique values, and 'Hail in TEXAS, TARRANT' alone appears 59 times. The 'multilingual' alert is largely a false positive driven by place names \u2014 4796 rows classify as English versus tiny counts like 134 Spanish and 25 German.","role":"label","scope":"column","target":"name","treatment":"Parse into structured fields (event_type, state, county) rather than treating as free text."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","stats.duplicate_rate","stats.n_duplicates","top_values","top_words","language_counts","stats.len_mean","stats.readability_flesch_mean"],"model":"anthropic:claude-opus-4-7","narrative":"This is a templated event-summary field describing storm or disaster impacts (magnitude, injuries, fatalities, property damage in dollars), not free-form prose. With 14,770 rows but only 5,796 unique values and a 60.8% duplicate rate, the text is highly formulaic \u2014 the single string 'Magnitude 0; $2.5M property damage' alone appears 1,055 times. Language detection flags 5 French, 1 Japanese, and 10 Norwegian rows against 4,984 English, almost certainly false positives from numeric/currency tokens rather than real multilingual content; mean Flesch of 29.9 reflects the terse template, not difficult prose.","role":"metadata","scope":"column","target":"description","treatment":"Parse with regex into structured fields (magnitude, injuries, fatalities, damage_usd) rather than treating as free text."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","stats.cardinality","stats.entropy","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This column is a constant categorical tag identifying the dataset source: every one of the 14770 rows holds the single value \"significant_us_storms\". With cardinality 1, entropy 0, and top_rate 1.0, it carries no information for modelling and only serves as a provenance marker.","role":"metadata","scope":"column","target":"category","treatment":"Drop before modelling; retain only as a source tag if merging with other datasets."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.len_min","stats.len_max","stats.word_mean","stats.duplicate_rate","stats.n_duplicates","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is a date column stored as ISO-formatted text (YYYY-MM-DD), with every one of 14770 rows exactly 10 characters and a single token. Values span at least 1965 to 2021, and duplicates are heavy: 9712 rows (65.8%) repeat, with 1974-04-03 appearing 126 times and 2011-04-27 appearing 105 times, suggesting clustering around specific event dates rather than a uniform timeline. The 'allcaps' flag is a false positive since digits and hyphens trigger it.","role":"timestamp","scope":"column","target":"date","treatment":"parse to date dtype and use for temporal grouping or joins."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","stats.cardinality","stats.entropy","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This column records the country of origin for each record, but every one of the 14770 rows holds the value \"USA\". Cardinality is 1 and entropy is 0, so the field carries no information.","role":"metadata","scope":"column","target":"country","treatment":"Drop; constant column with zero variance."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.top_value","stats.top_rate","stats.entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Categorical label of severe-weather event types across 14,770 rows with no nulls and 17 distinct categories. Tornado dominates at 42.9% (6,334 rows), followed by Flash Flood, Thunderstorm Wind, Flood, and Hail; entropy ratio of 0.57 confirms the distribution is concentrated in a few classes. The long tail (Heavy Rain, Marine Strong Wind, Debris Flow, Marine Thunderstorm Wind) has very thin support, which will hurt per-class modelling.","role":"label","scope":"column","target":"event_type","treatment":"Use as categorical target or feature; consider grouping rare classes given the heavy Tornado skew."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.cardinality","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"US state names in uppercase, with 65 distinct values across 14,770 complete rows \u2014 more than the 50 states, suggesting territories, military codes, or 'UNKNOWN'-style entries are mixed in. Distribution is broad (entropy ratio 0.86) with Texas leading at 9.8% (1,450 rows), followed by Missouri, Arkansas, Mississippi, and Georgia, indicating a southern/central US tilt.","role":"feature","scope":"column","target":"state","treatment":"Normalize to standard state codes and one-hot or target-encode; investigate the 15 extra categories beyond 50 states."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","stats.top_value","stats.top_rate","stats.entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Numeric magnitudes stored as strings, with 170 distinct values ranging from '0' to two-decimal figures like '70.00'. Over half the rows (51.78%) are null, and of the non-nulls the value '0' dominates at 54.24%, leaving real magnitudes in a minority of records. Entropy ratio of 0.48 confirms most signal is concentrated in a few buckets.","role":"feature","scope":"column","target":"magnitude","treatment":"Cast to numeric, treat '0' and nulls as likely missing/sentinel, and consider a presence flag before modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.top_value","stats.top_rate","stats.entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is an injury count per record, stored as strings but numeric in nature (top values are '0' through '12'). The distribution is dominated by zeros: 68.1% of 14,770 rows report '0' injuries, with 893 at '1' and a long tail spanning 178 distinct values. Entropy ratio of 0.33 confirms heavy concentration at the low end.","role":"feature","scope":"column","target":"injuries","treatment":"Cast to integer and consider log1p or zero-inflated modelling given the heavy zero mass."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.top_rate","stats.top_value","stats.entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Counts of fatalities per event, stored as strings with 49 distinct values across 14,770 rows and no nulls. The distribution is heavily zero-inflated: 69.1% of records are \"0\" and the next bucket \"1\" covers 3,208 rows, leaving a long thin tail (e.g., 25 rows at \"9\", 24 at \"10\"). Low entropy ratio (0.25) confirms most variance lives in the 0/1 split.","role":"numeric_target","scope":"column","target":"fatalities","treatment":"Cast to integer and consider modelling as a count (Poisson/negative binomial) or binarise to any-fatality given the zero inflation."},{"confidence":"high","critiques":[],"evidence_keys":["stats.len_max","stats.one_word_rate","stats.duplicate_rate","stats.n_empty","top_values","n_unique"],"model":"anthropic:claude-opus-4-7","narrative":"This column encodes property damage as short magnitude strings with a K/M suffix (e.g., '2.5M', '250K', '0.00K'), not free text \u2014 every value is one word and max length is 8. Formatting is inconsistent: '1M' and '1.00M' coexist, and '0.00K' appears 1229 times alongside 368 empty entries, conflating true zeros with missingness. With 93.1% duplicate rate across only 1013 unique tokens, this is a coarse categorical-looking encoding of a numeric quantity.","role":"feature","scope":"column","target":"damage_property","treatment":"Parse the K/M suffix into a numeric dollar amount and treat empty strings as missing (distinct from 0.00K)."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","stats.cardinality","stats.entropy","stats.top_rate","stats.top_value"],"model":"anthropic:claude-opus-4-7","narrative":"This column records the data provenance, holding the constant string \"NOAA Storm Events Database\" for all 14770 rows. With cardinality of 1 and entropy of 0.0, it carries no information for modelling and only serves as a dataset-level annotation.","role":"metadata","scope":"column","target":"source","treatment":"Drop before modelling; retain in documentation as a provenance tag."}],"providers":["anthropic:claude-opus-4-7"],"total_usage":{"completion_tokens":4660,"prompt_tokens":19014,"total_tokens":23674}},"language_counts":{"de":25,"en":9780,"es":134,"eu":2,"fr":6,"id":6,"it":5,"ja":23,"no":10,"pt":4,"ru":2,"sr":2,"zh":1},"meta":{"generated_at":"2026-05-01T18:38:10+00:00","mode":"full","row_count":14770,"sampled_rows":14770,"seed":42,"source":"/home/coolhand/html/datavis/data_trove/data/natural_hazards/storms.json"},"notes":[],"saturn_version":"0.2.0","schema":{"category":"categorical","country":"categorical","damage_property":"text","date":"text","description":"text","event_type":"categorical","fatalities":"categorical","injuries":"categorical","latitude":"numeric","longitude":"numeric","magnitude":"categorical","name":"text","source":"categorical","state":"categorical"}}