{"columns":[{"alerts":[{"code":"long_tail","level":"info","message":"1000 singleton categories"}],"column":"unique_key","extras":{"singletons":1000,"top_values":[["67534607",1],["67540784",1],["67540752",1],["67537071",1],["67535886",1],["67543458",1],["67541950",1],["67537003",1],["67538353",1],["67543223",1],["67534550",1],["67537050",1],["67540783",1],["67535884",1],["67541981",1],["67540793",1],["67539537",1],["67534594",1],["67543236",1],["67535866",1]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":1000,"null_rate":0.0,"stats":{"cardinality":1000,"entropy":9.965784284662087,"entropy_ratio":1.0,"top_rate":0.001,"top_value":"67534607"}},{"alerts":[{"code":"long_tail","level":"info","message":"850 singleton categories"}],"column":"created_date","extras":{"singletons":850,"top_values":[["2026-01-19T22:01:09.000",9],["2026-01-19T22:38:46.000",7],["2026-01-19T23:17:18.000",6],["2026-01-19T23:57:16.000",5],["2026-01-19T22:05:00.000",5],["2026-01-19T23:31:38.000",4],["2026-01-19T23:10:44.000",3],["2026-01-19T23:07:39.000",3],["2026-01-19T23:04:06.000",3],["2026-01-19T23:01:05.000",3],["2026-01-19T22:48:53.000",3],["2026-01-19T22:15:33.000",3],["2026-01-20T02:00:04.000",2],["2026-01-20T01:04:29.000",2],["2026-01-20T00:41:14.000",2],["2026-01-20T00:12:00.000",2],["2026-01-19T23:58:19.000",2],["2026-01-19T23:57:12.000",2],["2026-01-19T23:43:00.000",2],["2026-01-19T23:41:00.000",2]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":910,"null_rate":0.0,"stats":{"cardinality":910,"entropy":9.746345094228523,"entropy_ratio":0.9915178033903309,"top_rate":0.009,"top_value":"2026-01-19T22:01:09.000"}},{"alerts":[],"column":"agency","extras":{"singletons":2,"top_values":[["NYPD",594],["HPD",232],["DSNY",82],["DOT",34],["DEP",24],["DOHMH",16],["TLC",12],["DPR",4],["DCWP",1],["OOS",1]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":10,"null_rate":0.0,"stats":{"cardinality":10,"entropy":1.7500754850296794,"entropy_ratio":0.5268252156701242,"top_rate":0.594,"top_value":"NYPD"}},{"alerts":[],"column":"agency_name","extras":{"singletons":2,"top_values":[["New York City Police Department",594],["Department of Housing Preservation and Development",232],["Department of Sanitation",82],["Department of Transportation",34],["Department of Environmental Protection",24],["Department of Health and Mental Hygiene",16],["Taxi and Limousine Commission",12],["Department of Parks and Recreation",4],["Department of Consumer and Worker Protection",1],["Office of the Sheriff",1]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":10,"null_rate":0.0,"stats":{"cardinality":10,"entropy":1.7500754850296794,"entropy_ratio":0.5268252156701242,"top_rate":0.594,"top_value":"New York City Police Department"}},{"alerts":[],"column":"complaint_type","extras":{"singletons":21,"top_values":[["Noise - Residential",234],["Illegal Parking",187],["HEAT/HOT WATER",170],["Snow or Ice",69],["Blocked Driveway",64],["Noise - Commercial",38],["Noise - Vehicle",22],["UNSANITARY CONDITION",21],["Noise - Street/Sidewalk",20],["Street Condition",14],["Noise",14],["Traffic Signal Condition",9],["Abandoned Vehicle",8],["Taxi Complaint",8],["DOOR/WINDOW",8],["Dirty Condition",7],["PLUMBING",7],["Non-Emergency Police Matter",6],["FLOORING/STAIRS",6],["Indoor Air Quality",5]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":61,"null_rate":0.0,"stats":{"cardinality":61,"entropy":3.7755237515892817,"entropy_ratio":0.6366027589312789,"top_rate":0.234,"top_value":"Noise - Residential"}},{"alerts":[],"column":"descriptor","extras":{"singletons":50,"top_values":[["Banging/Pounding",133],["Loud Music/Party",127],["ENTIRE BUILDING",112],["Blocked Hydrant",98],["Sidewalk",69],["APARTMENT ONLY",58],["No Access",50],["Loud Talking",31],["Commercial Overnight Parking",26],["Posted Parking Sign Violation",21],["Partial Access",14],["Engine Idling",12],["Pothole",11],["PESTS",11],["Double Parked Blocking Traffic",10],["Driver Complaint - Passenger",9],["Blocked Sidewalk",9],["With License Plate",8],["Trash",7],["Blocked Crosswalk",7]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":105,"null_rate":0.0,"stats":{"cardinality":105,"entropy":4.739343568816542,"entropy_ratio":0.7058639062790695,"top_rate":0.133,"top_value":"Banging/Pounding"}},{"alerts":[],"column":"location_type","extras":{"singletons":4,"top_values":[["Street/Sidewalk",306],["Residential Building/House",245],["RESIDENTIAL BUILDING",232],["Sidewalk",80],["Club/Bar/Restaurant",23],["Street",20],["Store/Commercial",15],["3+ Family Apartment Building",6],["Residential Building",5],["3+ Family Apt. Building",4],["Taxi",3],["Highway",3],["Yard",2],["Restaurant/Bar/Deli/Bakery",2],["Park/Playground",2],["Subway",1],["Business",1],["Subway Station",1],["Park",1]]},"kind":"categorical","n":1000,"n_null":48,"n_unique":19,"null_rate":0.048,"stats":{"cardinality":19,"entropy":2.437091030446133,"entropy_ratio":0.5737129512529048,"top_rate":0.32142857142857145,"top_value":"Street/Sidewalk"}},{"alerts":[],"column":"incident_zip","extras":{"singletons":23,"top_values":[["10461",29],["10462",25],["11226",23],["11214",20],["10034",19],["11373",19],["11385",18],["10473",17],["10029",16],["11103",16],["11230",16],["11225",16],["11204",15],["10040",15],["11366",14],["10468",14],["11212",13],["11208",13],["10457",13],["11233",13]]},"kind":"categorical","n":1000,"n_null":3,"n_unique":156,"null_rate":0.003,"stats":{"cardinality":156,"entropy":6.826486638225308,"entropy_ratio":0.9370088888917092,"top_rate":0.029087261785356068,"top_value":"10461"}},{"alerts":[{"code":"long_tail","level":"info","message":"681 singleton categories"}],"column":"incident_address","extras":{"singletons":681,"top_values":[["31 HARRISON AVENUE",9],["64 SOUTH 11 STREET",8],["41-72 JUDGE STREET",7],["170 VERMILYEA AVENUE",7],["JOHN F KENNEDY AIRPORT",6],["42-01 LAYTON STREET",6],["21 TRUXTON STREET",6],["LA GUARDIA AIRPORT",5],["ROCKAWAY BOULEVARD",5],["1790 STORY AVENUE",5],["9 EAST  193 STREET",5],["147-40 ARCHER AVENUE",5],["108-26 159 STREET",4],["239 OCEAN AVENUE",4],["66 WELDON STREET",4],["1365 5 AVENUE",4],["538 EAST 21 STREET",4],["2854 KINGSBRIDGE TERRACE",4],["67 DRIVE",4],["3990 BRONX BOULEVARD",4]]},"kind":"categorical","n":1000,"n_null":16,"n_unique":787,"null_rate":0.016,"stats":{"cardinality":787,"entropy":9.43059058883578,"entropy_ratio":0.9802884715618541,"top_rate":0.009146341463414634,"top_value":"31 HARRISON AVENUE"}},{"alerts":[{"code":"long_tail","level":"info","message":"401 singleton categories"}],"column":"street_name","extras":{"singletons":401,"top_values":[["OCEAN AVENUE",10],["EAST 21 STREET",9],["HARRISON AVENUE",9],["SOUTH 11 STREET",8],["66 STREET",8],["BROADWAY",8],["JUDGE STREET",8],["WASHINGTON AVENUE",7],["BAY PARKWAY",7],["VERMILYEA AVENUE",7],["RANDALL AVENUE",6],["JOHN F KENNEDY AIRPORT",6],["30 AVENUE",6],["WOODYCREST AVENUE",6],["RYER AVENUE",6],["ROCKAWAY BOULEVARD",6],["HERING AVENUE",6],["LAYTON STREET",6],["TRUXTON STREET",6],["LA GUARDIA AIRPORT",5]]},"kind":"categorical","n":1000,"n_null":16,"n_unique":592,"null_rate":0.016,"stats":{"cardinality":592,"entropy":8.885677191149341,"entropy_ratio":0.9648430627068498,"top_rate":0.01016260162601626,"top_value":"OCEAN AVENUE"}},{"alerts":[{"code":"long_tail","level":"info","message":"309 singleton categories"},{"code":"null_rate","level":"warn","message":"25.0% null"}],"column":"cross_street_1","extras":{"singletons":309,"top_values":[["BEND",10],["WYTHE AVENUE",8],["DORCHESTER ROAD",8],["75 AVENUE",8],["99 STREET",7],["ADAM CLAYTON POWELL JR BOULEVARD",7],["5 AVENUE",7],["3 AVENUE",6],["18 AVENUE",6],["DEAD END",6],["19 AVENUE",6],["94 STREET",6],["WEST 162 STREET",6],["36 STREET",5],["8 AVENUE",5],["EAST BURNSIDE AVENUE",5],["ST NICHOLAS AVENUE",5],["MYRTLE AVENUE",5],["ROSEDALE AVENUE",5],["108 AVENUE",4]]},"kind":"categorical","n":1000,"n_null":250,"n_unique":457,"null_rate":0.25,"stats":{"cardinality":457,"entropy":8.534004915705612,"entropy_ratio":0.9658166910310152,"top_rate":0.013333333333333334,"top_value":"BEND"}},{"alerts":[{"code":"long_tail","level":"info","message":"313 singleton categories"},{"code":"null_rate","level":"warn","message":"25.0% null"}],"column":"cross_street_2","extras":{"singletons":313,"top_values":[["BERRY STREET",8],["FREDERICK DOUGLASS BOULEVARD",8],["DITMAS AVENUE",8],["BOOTH STREET",7],["UNION TURNPIKE",7],["109 AVENUE",6],["AIRTRAIN-HOWARD BCH/JAMAICA LINE",6],["20 AVENUE",6],["DEAD END",6],["WEST 163 STREET",6],["BROADWAY",6],["102 STREET",6],["3 AVENUE",6],["10 AVENUE",6],["BEND",5],["19 AVENUE",5],["37 STREET",5],["18 AVENUE",5],["EAST 115 STREET",5],["GRAND CENTRAL PARKWAY ET 7 EB",5]]},"kind":"categorical","n":1000,"n_null":250,"n_unique":458,"null_rate":0.25,"stats":{"cardinality":458,"entropy":8.53558770371587,"entropy_ratio":0.9656511953271255,"top_rate":0.010666666666666666,"top_value":"BERRY STREET"}},{"alerts":[{"code":"long_tail","level":"info","message":"286 singleton categories"},{"code":"null_rate","level":"warn","message":"26.7% null"}],"column":"intersection_street_1","extras":{"singletons":286,"top_values":[["BEND",9],["WYTHE AVENUE",8],["DORCHESTER ROAD",8],["75 AVENUE",8],["99 STREET",7],["ADAM CLAYTON POWELL JR BOULEVARD",7],["5 AVENUE",7],["3 AVENUE",6],["18 AVENUE",6],["DEAD END",6],["19 AVENUE",6],["94 STREET",6],["WEST 162 STREET",6],["36 STREET",5],["8 AVENUE",5],["EAST BURNSIDE AVENUE",5],["ST NICHOLAS AVENUE",5],["AVENUE N",5],["MYRTLE AVENUE",5],["ROSEDALE AVENUE",5]]},"kind":"categorical","n":1000,"n_null":267,"n_unique":436,"null_rate":0.267,"stats":{"cardinality":436,"entropy":8.464509344760767,"entropy_ratio":0.9653662641240283,"top_rate":0.01227830832196453,"top_value":"BEND"}},{"alerts":[{"code":"long_tail","level":"info","message":"298 singleton categories"},{"code":"null_rate","level":"warn","message":"26.7% null"}],"column":"intersection_street_2","extras":{"singletons":298,"top_values":[["BERRY STREET",8],["FREDERICK DOUGLASS BOULEVARD",8],["DITMAS AVENUE",8],["BOOTH STREET",7],["UNION TURNPIKE",7],["AIRTRAIN-HOWARD BCH/JAMAICA LINE",6],["20 AVENUE",6],["DEAD END",6],["WEST 163 STREET",6],["BROADWAY",6],["102 STREET",6],["3 AVENUE",6],["10 AVENUE",6],["109 AVENUE",5],["19 AVENUE",5],["37 STREET",5],["18 AVENUE",5],["EAST 115 STREET",5],["GRAND CENTRAL PARKWAY ET 7 EB",5],["EAST 180 STREET",5]]},"kind":"categorical","n":1000,"n_null":267,"n_unique":443,"null_rate":0.267,"stats":{"cardinality":443,"entropy":8.48921163063558,"entropy_ratio":0.9656528650706109,"top_rate":0.010914051841746248,"top_value":"BERRY STREET"}},{"alerts":[],"column":"address_type","extras":{"singletons":0,"top_values":[["ADDRESS",939],["INTERSECTION",36],["PLACE",12],["BLOCKFACE",10]]},"kind":"categorical","n":1000,"n_null":3,"n_unique":4,"null_rate":0.003,"stats":{"cardinality":4,"entropy":0.3977951142012601,"entropy_ratio":0.19889755710063006,"top_rate":0.9418254764292878,"top_value":"ADDRESS"}},{"alerts":[],"column":"city","extras":{"singletons":6,"top_values":[["BROOKLYN",307],["BRONX",227],["NEW YORK",170],["JAMAICA",34],["ASTORIA",23],["STATEN ISLAND",21],["ELMHURST",19],["RIDGEWOOD",15],["FRESH MEADOWS",15],["QUEENS",13],["FLUSHING",12],["WOODSIDE",10],["FAR ROCKAWAY",9],["REGO PARK",9],["CORONA",8],["EAST ELMHURST",7],["MIDDLE VILLAGE",7],["JACKSON HEIGHTS",5],["SOUTH OZONE PARK",5],["FOREST HILLS",5]]},"kind":"categorical","n":1000,"n_null":29,"n_unique":40,"null_rate":0.029,"stats":{"cardinality":40,"entropy":3.2340719323673692,"entropy_ratio":0.6076880173323382,"top_rate":0.3161688980432544,"top_value":"BROOKLYN"}},{"alerts":[{"code":"long_tail","level":"info","message":"312 singleton categories"},{"code":"null_rate","level":"warn","message":"30.8% null"}],"column":"landmark","extras":{"singletons":312,"top_values":[["EAST 21 STREET",9],["SOUTH 11 STREET",8],["OCEAN AVENUE",8],["WASHINGTON AVENUE",7],["RANDALL AVENUE",6],["JOHN F KENNEDY AIRPORT",6],["30 AVENUE",6],["WOODYCREST AVENUE",6],["BROADWAY",6],["RYER AVENUE",6],["HERING AVENUE",6],["66 STREET",5],["LA GUARDIA AIRPORT",5],["YATES AVENUE",5],["KINGSBRIDGE TERRACE",5],["STORY AVENUE",5],["159 STREET",4],["BAY PARKWAY",4],["WELDON STREET",4],["5 AVENUE",4]]},"kind":"categorical","n":1000,"n_null":308,"n_unique":445,"null_rate":0.308,"stats":{"cardinality":445,"entropy":8.521810851301545,"entropy_ratio":0.9686450002945021,"top_rate":0.01300578034682081,"top_value":"EAST 21 STREET"}},{"alerts":[],"column":"status","extras":{"singletons":0,"top_values":[["In Progress",388],["Closed",336],["Open",276]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":3,"null_rate":0.0,"stats":{"cardinality":3,"entropy":1.5712466977690434,"entropy_ratio":0.9913462918233888,"top_rate":0.388,"top_value":"In Progress"}},{"alerts":[],"column":"community_board","extras":{"singletons":1,"top_values":[["12 MANHATTAN",44],["11 BROOKLYN",40],["09 BRONX",38],["14 BROOKLYN",33],["11 BRONX",33],["12 QUEENS",31],["10 BRONX",26],["05 QUEENS",26],["01 QUEENS",25],["10 MANHATTAN",25],["05 BROOKLYN",24],["12 BRONX",23],["04 QUEENS",23],["01 BROOKLYN",22],["08 QUEENS",22],["12 BROOKLYN",22],["16 BROOKLYN",22],["17 BROOKLYN",19],["03 BRONX",19],["10 QUEENS",19]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":64,"null_rate":0.0,"stats":{"cardinality":64,"entropy":5.729993782068641,"entropy_ratio":0.9549989636781069,"top_rate":0.044,"top_value":"12 MANHATTAN"}},{"alerts":[],"column":"council_district","extras":{"singletons":0,"top_values":[["13",46],["10",44],["18",43],["40",38],["34",29],["37",29],["09",29],["35",28],["15",28],["43",27],["17",26],["28",25],["14",24],["25",23],["08",23],["11",23],["22",23],["24",23],["42",22],["30",22]]},"kind":"categorical","n":1000,"n_null":13,"n_unique":51,"null_rate":0.013,"stats":{"cardinality":51,"entropy":5.49224483667193,"entropy_ratio":0.9682357202718261,"top_rate":0.04660587639311044,"top_value":"13"}},{"alerts":[],"column":"police_precinct","extras":{"singletons":2,"top_values":[["Precinct 62",40],["Precinct 43",38],["Precinct 34",36],["Precinct 70",33],["Precinct 49",33],["Precinct 104",29],["Precinct 114",28],["Precinct 45",26],["Precinct 75",24],["Precinct 47",23],["Precinct 110",23],["Precinct 107",22],["Precinct 66",22],["Precinct 73",22],["Precinct 67",19],["Precinct 113",19],["Precinct 42",19],["Precinct 106",19],["Precinct 71",19],["Precinct 90",18]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":76,"null_rate":0.0,"stats":{"cardinality":76,"entropy":5.883217470440643,"entropy_ratio":0.9416270367704811,"top_rate":0.04,"top_value":"Precinct 62"}},{"alerts":[{"code":"long_tail","level":"info","message":"636 singleton categories"}],"column":"bbl","extras":{"singletons":636,"top_values":[["5010780006",9],["3021600005",8],["4015070054",7],["1022280007",7],["4142600001",6],["2025110068",6],["4015080001",6],["3015420044",6],["4009260001",5],["2036370001",5],["2031910054",5],["4099987501",5],["4101460051",4],["3050260344",4],["2039730005",4],["3041640018",4],["1016180001",4],["3051840025",4],["2032530133",4],["2048200042",4]]},"kind":"categorical","n":1000,"n_null":59,"n_unique":744,"null_rate":0.059,"stats":{"cardinality":744,"entropy":9.342079546252284,"entropy_ratio":0.9793399744402772,"top_rate":0.009564293304994687,"top_value":"5010780006"}},{"alerts":[],"column":"borough","extras":{"singletons":0,"top_values":[["BROOKLYN",312],["QUEENS",261],["BRONX",230],["MANHATTAN",175],["STATEN ISLAND",22]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":5,"null_rate":0.0,"stats":{"cardinality":5,"entropy":2.0789231753744417,"entropy_ratio":0.8953434776692735,"top_rate":0.312,"top_value":"BROOKLYN"}},{"alerts":[{"code":"long_tail","level":"info","message":"679 singleton categories"}],"column":"x_coordinate_state_plane","extras":{"singletons":679,"top_values":[["946638",9],["993540",8],["1016981",7],["1006636",7],["1043001",6],["1016259",6],["1009589",6],["1018236",5],["1021634",5],["1012556",5],["1037889",5],["1041463",4],["994731",4],["1019629",4],["998703",4],["1025645",4],["995841",4],["1011173",4],["1025158",4],["1021852",4]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":788,"null_rate":0.012,"stats":{"cardinality":788,"entropy":9.432811962492773,"entropy_ratio":0.9803326919752242,"top_rate":0.009109311740890687,"top_value":"946638"}},{"alerts":[{"code":"long_tail","level":"info","message":"675 singleton categories"}],"column":"y_coordinate_state_plane","extras":{"singletons":675,"top_values":[["171301",9],["197050",8],["210691",7],["255285",7],["175548",6],["210546",6],["186419",6],["221443",5],["239284",5],["255017",5],["194669",5],["192497",4],["178635",4],["187056",4],["230311",4],["172790",4],["257790",4],["203433",4],["263320",4],["241935",4]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":788,"null_rate":0.012,"stats":{"cardinality":788,"entropy":9.436860545488724,"entropy_ratio":0.9807534528557429,"top_rate":0.009109311740890687,"top_value":"171301"}},{"alerts":[],"column":"open_data_channel_type","extras":{"singletons":0,"top_values":[["ONLINE",527],["MOBILE",234],["PHONE",214],["UNKNOWN",25]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":4,"null_rate":0.0,"stats":{"cardinality":4,"entropy":1.5863942275325447,"entropy_ratio":0.7931971137662723,"top_rate":0.527,"top_value":"ONLINE"}},{"alerts":[{"code":"long_tail","level":"info","message":"2 singleton categories"},{"code":"imbalance","level":"warn","message":"top value is 99.8% of rows"}],"column":"park_facility_name","extras":{"singletons":2,"top_values":[["Unspecified",998],["Marcus Garvey Park",1],["Forest Park",1]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":3,"null_rate":0.0,"stats":{"cardinality":3,"entropy":0.022814071335501035,"entropy_ratio":0.01439407640566932,"top_rate":0.998,"top_value":"Unspecified"}},{"alerts":[],"column":"park_borough","extras":{"singletons":0,"top_values":[["BROOKLYN",312],["QUEENS",261],["BRONX",230],["MANHATTAN",175],["STATEN ISLAND",22]]},"kind":"categorical","n":1000,"n_null":0,"n_unique":5,"null_rate":0.0,"stats":{"cardinality":5,"entropy":2.0789231753744417,"entropy_ratio":0.8953434776692735,"top_rate":0.312,"top_value":"BROOKLYN"}},{"alerts":[{"code":"long_tail","level":"info","message":"687 singleton categories"}],"column":"latitude","extras":{"singletons":687,"top_values":[["40.63677840515416",9],["40.7075286122006",8],["40.744914143624996",7],["40.86734453983834",7],["40.64832048620134",6],["40.74451879806252",6],["40.67831758601989",6],["40.77442086598845",5],["40.82337577056312",5],["40.866591963493335",5],["40.700835637070725",5],["40.694851633900804",4],["40.65698230332589",4],["40.680031571772965",4],["40.79881467021513",4],["40.64093766389099",4],["40.874207322276355",4],["40.72495870564602",4],["40.88934639713765",4],["40.83066324047387",4]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":794,"null_rate":0.012,"stats":{"cardinality":794,"entropy":9.449006294476579,"entropy_ratio":0.9809001355340707,"top_rate":0.009109311740890687,"top_value":"40.63677840515416"}},{"alerts":[{"code":"long_tail","level":"info","message":"687 singleton categories"}],"column":"longitude","extras":{"singletons":687,"top_values":[["-74.13551741527912",9],["-73.96649227605458",8],["-73.88187760396336",7],["-73.91906278851496",7],["-73.78828125130184",6],["-73.88448390553113",6],["-73.90864580709884",6],["-73.87729410513894",5],["-73.86492637415863",5],["-73.89766001179035",5],["-73.80655093855829",5],["-73.79367980321378",4],["-73.96222514965272",4],["-73.8724454944903",4],["-73.94779857268328",4],["-73.95823461385314",4],["-73.9026490846547",4],["-73.85241193799187",4],["-73.86400388206638",4],["-73.87487410501063",4]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":794,"null_rate":0.012,"stats":{"cardinality":794,"entropy":9.449006294476579,"entropy_ratio":0.9809001355340707,"top_rate":0.009109311740890687,"top_value":"-74.13551741527912"}},{"alerts":[{"code":"skipped","level":"info","message":"no profiler for kind=unknown"}],"column":"location","extras":{},"kind":"unknown","n":1000,"n_null":0,"n_unique":null,"null_rate":0.0,"stats":{}},{"alerts":[],"column":":@computed_region_f5dn_yrer","extras":{"singletons":1,"top_values":[["47",44],["1",40],["58",38],["60",33],["59",33],["41",31],["43",26],["54",26],["18",26],["39",25],["45",24],["29",23],["66",23],["36",22],["25",22],["2",22],["55",22],["61",19],["70",19],["34",19]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":62,"null_rate":0.012,"stats":{"cardinality":62,"entropy":5.698012602071721,"entropy_ratio":0.9569742589997828,"top_rate":0.044534412955465584,"top_value":"47"}},{"alerts":[],"column":":@computed_region_yeji_bk3q","extras":{"singletons":0,"top_values":[["2",312],["3",250],["5",229],["4",175],["1",22]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":5,"null_rate":0.012,"stats":{"cardinality":5,"entropy":2.080210681882834,"entropy_ratio":0.8958979765408049,"top_rate":0.3157894736842105,"top_value":"2"}},{"alerts":[],"column":":@computed_region_sbqj_enih","extras":{"singletons":3,"top_values":[["37",40],["26",38],["22",36],["43",33],["32",33],["72",27],["28",26],["62",26],["47",24],["30",23],["68",23],["65",22],["39",22],["46",22],["40",19],["71",19],["25",19],["44",19],["56",18],["61",18]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":75,"null_rate":0.012,"stats":{"cardinality":75,"entropy":5.86747160667506,"entropy_ratio":0.9419878629037356,"top_rate":0.04048582995951417,"top_value":"37"}},{"alerts":[],"column":":@computed_region_92fq_4b7q","extras":{"singletons":0,"top_values":[["12",46],["31",45],["39",41],["11",34],["36",32],["46",30],["22",29],["37",28],["35",27],["45",27],["48",27],["34",25],["28",24],["44",23],["5",23],["29",23],["4",22],["43",22],["24",22],["30",22]]},"kind":"categorical","n":1000,"n_null":12,"n_unique":51,"null_rate":0.012,"stats":{"cardinality":51,"entropy":5.497315121230435,"entropy_ratio":0.9691295680094048,"top_rate":0.0465587044534413,"top_value":"12"}},{"alerts":[{"code":"long_tail","level":"info","message":"42 singleton categories"},{"code":"null_rate","level":"warn","message":"59.6% null"}],"column":"descriptor_2","extras":{"singletons":42,"top_values":[["NO HEAT",117],["N/A",98],["NO HEAT AND NO HOT WATER",36],["NO HOT WATER",19],["NM1",6],["BROKEN OR MISSING",6],["ROACHES",6],["Operating Improperly",5],["NR5",5],["AT WALL OR CEILING",5],["Littering",4],["Fare/Tip Complaint - Credit Card",4],["Dog",4],["L10",4],["Blocking Driveway",3],["Not Cleaned by Property Owner",3],["Out",3],["MISSING OR INADEQUATE CANS/LID",3],["SAGGING OR SLOPING",3],["Other",2]]},"kind":"categorical","n":1000,"n_null":596,"n_unique":75,"null_rate":0.596,"stats":{"cardinality":75,"entropy":3.9947588994126653,"entropy_ratio":0.6413349140356243,"top_rate":0.2896039603960396,"top_value":"NO HEAT"}},{"alerts":[{"code":"null_rate","level":"warn","message":"41.2% null"}],"column":"resolution_description","extras":{"singletons":5,"top_values":[["The following complaint conditions are still open. HPD has already attempted to notify the property owner that the condition exists; the tenant should provide access for the owner to make the repair.  HPD may attempt to contact the tenant by phone to verify the correction of the condition or an HPD Inspector may attempt to conduct an inspection.",142],["The New York City Police Department responded to the complaint and with the information available observed no evidence of a criminal violation at that time. If the problem persists, please contact 311 to create another complaint. If possible, provide contact information so responding officers may reach out to you for more details. If necessary, your complaint may be referred to your local precinct's special operations units (Quality of Life, etc.). We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",120],["This complaint is a duplicate of a building-wide condition already reported by another tenant.  The original complaint is still open, and HPD may only need to confirm that the condition exists by inspecting one apartment.  If we cannot contact the tenant from the original complaint or get access to that apartment, HPD may attempt to contact the person who filed this complaint to verify the correction of the condition or may conduct an inspection of your unit. You can check HPDONLINE to see if a",89],["The New York City Police Department responded to the complaint and their investigation determined that no criminal violation existed. The condition was corrected without the need to issue a summons or effect an arrest. If the problem persists, please contact 311 to create another complaint. If possible, provide contact information so responding officers may reach out to you for more details. If necessary, your complaint may be referred to your local precinct's special operations units (Quality of Life, etc.). Thank you for your attention to this matter. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",67],["The New York City Police Department responded to the complaint and their investigation determined that a violation of law occurred. Police issued a summons in response to the complaint. Thank you for attention to this matter. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",41],["The New York City Police Department responded to the complaint but officers were unable to gain entry into the premises. If the problem persists, please contact 311 to create another complaint and ensure that contact information (e.g., buzzer number, phone number, etc.) is available to assist the responding officers in gaining entry to properly investigate the complaint.  We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",37],["The New York City Police Department responded to the complaint and their investigation determined that police action was not necessary. If the problem persists, please contact 311 to create another complaint. If possible, provide contact information so responding officers may reach out to you for more details. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",34],["The New York City Police Department responded to the complaint and observed no criminal violation upon their arrival. If the problem persists, please contact 311 to create another complaint. If possible, provide contact information so responding officers may reach out to you for more details. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",27],["The Department of Transportation referred this complaint to the appropriate Maintenance Unit for repair.",9],["Your complaint has been received by the New York City Police Department and assigned to a unit at your local precinct. The responding officers will conduct an assessment of the complaint and may contact you for further information, if you left contact information. Our team is committed to resolving this matter promptly, and we appreciate your contribution to maintaining the well-being of our community.",8],["The New York City Police Department responded to the complaint and observed no encampment at the noted location. If the problem persists, please contact 311 to create another complaint. If possible, provide contact information so responding officers may reach out to you for more details. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",3],["The Department of Transportation determined that this complaint is a duplicate of a previously filed complaint. The original complaint is being addressed.",2],["The Police Department reviewed your complaint and provided additional information below.",2],["The Department of Health and Mental Hygiene has sent official written notification to the Owner/Landlord warning them of potential violations and instructing them to correct the situation. If the situation persists 21 days after your initial complaint, please make a new complaint.",2],["The Department of Health and Mental Hygiene has received and processed your complaint. All restaurants and mobile food vendors are inspected annually. Restaurant inspection results can be found on WWW.NYC.GOV or a copy of the inspection can be requested from 311.",1],["The New York City Police Department responded to the complaint and their investigation determined that a violation of law occurred. Police made an arrest in response to the complaint. Thank you for attention to this matter. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",1],["Service Request status for this request is available on the Department of Transportation\u00e2\u0080\u0099s website. Please click the \u00e2\u0080\u009cLearn More\u00e2\u0080\u009d link below.",1],["This request required re-assignment to a new DOT unit.",1],["The New York City Police Department responded to the complaint and a report was prepared as part of their investigation. Thank you for attention to this matter. We count on New Yorkers like yourself to maintain a safe City, so please let us know if you see other conditions that require our attention.",1]]},"kind":"categorical","n":1000,"n_null":412,"n_unique":19,"null_rate":0.412,"stats":{"cardinality":19,"entropy":3.070576202059069,"entropy_ratio":0.7228410071361845,"top_rate":0.24149659863945577,"top_value":"The following complaint conditions are still open. HPD has already attempted to notify the property owner that the condition exists; the tenant should provide access for the owner to make the repair.  HPD may attempt to contact the tenant by phone to verify the correction of the condition or an HPD Inspector may attempt to conduct an inspection."}},{"alerts":[{"code":"long_tail","level":"info","message":"347 singleton categories"},{"code":"null_rate","level":"warn","message":"40.9% null"}],"column":"resolution_action_updated_date","extras":{"singletons":347,"top_values":[["2026-01-19T00:00:00.000",232],["2026-01-20T01:49:13.000",2],["2026-01-20T01:55:13.000",2],["2026-01-20T01:12:29.000",2],["2026-01-20T02:01:00.000",2],["2026-01-20T01:08:29.000",2],["2026-01-20T00:19:12.000",2],["2026-01-20T01:59:27.000",1],["2026-01-20T02:04:38.000",1],["2026-01-20T01:49:45.000",1],["2026-01-20T02:05:08.000",1],["2026-01-20T01:43:12.000",1],["2026-01-20T02:04:57.000",1],["2026-01-20T01:28:28.000",1],["2026-01-20T01:32:18.000",1],["2025-03-31T12:11:47.000",1],["2025-05-28T08:40:41.000",1],["2026-01-20T01:46:37.000",1],["2026-01-20T01:45:05.000",1],["2026-01-20T02:04:52.000",1]]},"kind":"categorical","n":1000,"n_null":409,"n_unique":354,"null_rate":0.409,"stats":{"cardinality":354,"entropy":6.102020088587688,"entropy_ratio":0.7206311220446349,"top_rate":0.3925549915397631,"top_value":"2026-01-19T00:00:00.000"}},{"alerts":[{"code":"null_rate","level":"warn","message":"98.8% null"}],"column":"taxi_pick_up_location","extras":{"singletons":1,"top_values":[["JOHN F KENNEDY AIRPORT, QUEENS (JAMAICA) ,NY, 11430",6],["LA GUARDIA AIRPORT, QUEENS (EAST ELMHURST) ,NY, 11369",5],["141 NAGLE AVENUE, MANHATTAN (NEW YORK), NY, 10040",1]]},"kind":"categorical","n":1000,"n_null":988,"n_unique":3,"null_rate":0.988,"stats":{"cardinality":3,"entropy":1.3250112108241772,"entropy_ratio":0.8359889967247166,"top_rate":0.5,"top_value":"JOHN F KENNEDY AIRPORT, QUEENS (JAMAICA) ,NY, 11430"}},{"alerts":[{"code":"null_rate","level":"warn","message":"95.7% null"}],"column":"vehicle_type","extras":{"singletons":0,"top_values":[["Car",28],["SUV",5],["Other",5],["Van",3],["Truck",2]]},"kind":"categorical","n":1000,"n_null":957,"n_unique":5,"null_rate":0.957,"stats":{"cardinality":5,"entropy":1.5988204228730278,"entropy_ratio":0.6885744767004025,"top_rate":0.6511627906976745,"top_value":"Car"}},{"alerts":[{"code":"long_tail","level":"info","message":"332 singleton categories"},{"code":"null_rate","level":"warn","message":"66.4% null"}],"column":"closed_date","extras":{"singletons":332,"top_values":[["2026-01-20T01:00:32.000",2],["2026-01-20T01:08:26.000",2],["2026-01-20T02:04:35.000",1],["2026-01-20T02:05:03.000",1],["2026-01-20T01:43:08.000",1],["2026-01-20T01:55:05.000",1],["2026-01-20T02:04:52.000",1],["2026-01-20T01:28:25.000",1],["2026-01-20T01:32:15.000",1],["2026-01-20T01:46:35.000",1],["2026-01-20T01:45:02.000",1],["2026-01-20T02:04:49.000",1],["2026-01-20T01:44:55.000",1],["2026-01-20T01:52:28.000",1],["2026-01-20T01:38:17.000",1],["2026-01-20T01:12:33.000",1],["2026-01-20T01:59:33.000",1],["2026-01-20T01:16:46.000",1],["2026-01-20T01:26:42.000",1],["2026-01-20T01:47:42.000",1]]},"kind":"categorical","n":1000,"n_null":664,"n_unique":334,"null_rate":0.664,"stats":{"cardinality":334,"entropy":8.380412660873999,"entropy_ratio":0.9996073774210992,"top_rate":0.005952380952380952,"top_value":"2026-01-20T01:00:32.000"}},{"alerts":[{"code":"long_tail","level":"info","message":"4 singleton categories"},{"code":"null_rate","level":"warn","message":"99.6% null"}],"column":"bridge_highway_name","extras":{"singletons":4,"top_values":[["J",1],["Cross Island Pkwy",1],["Long Island Expwy",1],["Nassau Expwy",1]]},"kind":"categorical","n":1000,"n_null":996,"n_unique":4,"null_rate":0.996,"stats":{"cardinality":4,"entropy":2.0,"entropy_ratio":1.0,"top_rate":0.25,"top_value":"J"}},{"alerts":[{"code":"long_tail","level":"info","message":"4 singleton categories"},{"code":"null_rate","level":"warn","message":"99.6% null"}],"column":"bridge_highway_segment","extras":{"singletons":4,"top_values":[["Mezzanine",1],["Hempstead Ave (NY 24) (Exit 26C)",1],["Van Dam St (Exit 15) - Queens Midtown Tunnel",1],["Belt Pkwy So Conduit Ave (Exit 2 N)",1]]},"kind":"categorical","n":1000,"n_null":996,"n_unique":4,"null_rate":0.996,"stats":{"cardinality":4,"entropy":2.0,"entropy_ratio":1.0,"top_rate":0.25,"top_value":"Mezzanine"}},{"alerts":[{"code":"null_rate","level":"warn","message":"95.9% null"},{"code":"imbalance","level":"warn","message":"top value is 100.0% of rows"}],"column":"facility_type","extras":{"singletons":0,"top_values":[["N/A",41]]},"kind":"categorical","n":1000,"n_null":959,"n_unique":1,"null_rate":0.959,"stats":{"cardinality":1,"entropy":-0.0,"entropy_ratio":0.0,"top_rate":1.0,"top_value":"N/A"}},{"alerts":[{"code":"long_tail","level":"info","message":"3 singleton categories"},{"code":"null_rate","level":"warn","message":"99.7% null"}],"column":"bridge_highway_direction","extras":{"singletons":3,"top_values":[["South/Long Island Bound",1],["West/Manhattan Bound",1],["Eastbound",1]]},"kind":"categorical","n":1000,"n_null":997,"n_unique":3,"null_rate":0.997,"stats":{"cardinality":3,"entropy":1.584962500721156,"entropy_ratio":1.0,"top_rate":0.3333333333333333,"top_value":"South/Long Island Bound"}},{"alerts":[{"code":"null_rate","level":"warn","message":"99.7% null"}],"column":"road_ramp","extras":{"singletons":1,"top_values":[["Ramp",2],["Roadway",1]]},"kind":"categorical","n":1000,"n_null":997,"n_unique":2,"null_rate":0.997,"stats":{"cardinality":2,"entropy":0.9182958340544896,"entropy_ratio":0.9182958340544896,"top_rate":0.6666666666666666,"top_value":"Ramp"}},{"alerts":[{"code":"long_tail","level":"info","message":"1 singleton categories"},{"code":"null_rate","level":"warn","message":"99.9% null"},{"code":"imbalance","level":"warn","message":"top value is 100.0% of rows"}],"column":"taxi_company_borough","extras":{"singletons":1,"top_values":[["BRONX",1]]},"kind":"categorical","n":1000,"n_null":999,"n_unique":1,"null_rate":0.999,"stats":{"cardinality":1,"entropy":-0.0,"entropy_ratio":0.0,"top_rate":1.0,"top_value":"BRONX"}}],"insights":{"errors":[],"insights":[{"confidence":"high","critiques":[],"evidence_keys":["agency","complaint_type","borough","status","open_data_channel_type","descriptor","facility_type","taxi_company_borough","vehicle_type"],"featured_charts":[{"caption":"NYPD handles nearly 60% of requests; check how the long tail of smaller agencies splits the remainder.","column":"agency","kind":"bar"},{"caption":"Noise, Illegal Parking, and HEAT/HOT WATER lead \u2014 see how concentrated the top complaints are versus the 61-category tail.","column":"complaint_type","kind":"bar"},{"caption":"Brooklyn, Queens, and Bronx dominate; Staten Island barely registers at ~2%.","column":"borough","kind":"donut"},{"caption":"Roughly two-thirds of tickets are still In Progress or Open \u2014 a useful backlog indicator.","column":"status","kind":"donut"},{"caption":"Online intake (52.7%) outpaces Mobile and Phone, showing how residents are actually filing.","column":"open_data_channel_type","kind":"bar"}],"model":"anthropic:claude-opus-4-7","narrative":"This is a 1,000-row sample of NYC 311 service requests (47 columns), almost entirely categorical, capturing complaints by agency, location, and resolution status. NYPD dominates routing at 59.4% of requests, followed by HPD (23.2%) and DSNY (8.2%), and the top complaint types are Noise - Residential (23.4%), Illegal Parking (18.7%), and HEAT/HOT WATER (17.0%) \u2014 a good first place to look. Geographically, Brooklyn (31.2%), Queens (26.1%), and the Bronx (23.0%) account for most cases, while Staten Island is just 2.2%. Status is split across In Progress (38.8%), Closed (33.6%), and Open (27.6%), so a sizable share remains unresolved. Note that many specialized fields (taxi, bridge/highway, vehicle, facility_type) are >95% null and not informative, and `location` was skipped during profiling.","scope":"dataset","target":"__global__"},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.cardinality","stats.entropy_ratio","stats.top_rate","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is a row-level identifier: every one of the 1000 values is unique (n_unique=1000, entropy_ratio=1.0) and no nulls are present. The values are 8-digit numeric strings clustered around 6753xxxx\u20136754xxxx, consistent with a sequential record key. There is no predictive signal here, only joinability.","role":"identifier","scope":"column","target":"unique_key","treatment":"Drop from modelling; retain only as a join key."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_value","stats.top_rate","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"ISO-8601 datetime stamps stored as strings, with 910 unique values across 1000 rows and zero nulls. The top 10 timestamps all fall on 2026-01-19 between 22:01 and 23:57, suggesting the sample is concentrated in a roughly two-hour window rather than spread over time. Entropy ratio 0.9915 confirms near-unique values, but the column is typed as categorical instead of a proper timestamp.","role":"timestamp","scope":"column","target":"created_date","treatment":"Parse to datetime and derive features (hour, day, delta); do not use raw string as a category."},{"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 column records the NYC agency handling each record, drawn from 10 distinct codes with no nulls across 1000 rows. Distribution is heavily concentrated: NYPD alone accounts for 594 rows (top_rate 0.594) and HPD another 232, while DCWP and OOS appear just once each. Entropy ratio of 0.527 confirms the long tail is thin, which may starve models of signal for rare agencies.","role":"feature","scope":"column","target":"agency","treatment":"One-hot encode the top few agencies and bucket the rare codes (DPR, DCWP, OOS) into an 'other' category."},{"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 column names the NYC agency handling each record, with 10 distinct agencies and no nulls across 1000 rows. The distribution is highly concentrated: NYPD alone accounts for 59.4% of records, followed by Housing Preservation and Development at 232 and Sanitation at 82, while two agencies appear just once. The entropy ratio of 0.53 confirms the heavy skew toward a single dominant category.","role":"feature","scope":"column","target":"agency_name","treatment":"One-hot encode or group rare agencies into an 'Other' bucket before modelling."},{"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":"This is a categorical complaint-type field, almost certainly from a 311-style service request log, with 61 distinct categories across 1000 rows and no nulls. The distribution is moderately concentrated: 'Noise - Residential' leads at 23.4%, followed by 'Illegal Parking' (187) and 'HEAT/HOT WATER' (170), with entropy ratio 0.637 indicating a long tail. Worth noting the inconsistent casing (e.g., 'HEAT/HOT WATER' and 'UNSANITARY CONDITION' in caps vs. mixed-case neighbours), and that 'Noise' alone fragments across at least four sub-types.","role":"label","scope":"column","target":"complaint_type","treatment":"Normalise casing and consider grouping rare tail categories before one-hot or target encoding."},{"confidence":"high","critiques":[],"evidence_keys":["cardinality","entropy_ratio","top_rate","top_value","top_values","n","n_unique"],"model":"anthropic:claude-opus-4-7","narrative":"Categorical descriptor field detailing the specific nature of a complaint or issue, with values like 'Banging/Pounding', 'Loud Music/Party', and 'Blocked Hydrant' suggesting NYC 311-style service requests. Cardinality is moderate at 105 unique values across 1000 rows, with the top value covering 13.3% and entropy ratio of 0.71 indicating a reasonably spread distribution. Notably, casing is inconsistent ('ENTIRE BUILDING' and 'APARTMENT ONLY' in caps versus title-case elsewhere), hinting at multiple upstream sources or schemas merged together.","role":"feature","scope":"column","target":"descriptor","treatment":"Normalize casing and group rare levels before one-hot or target encoding."},{"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 descriptor of where an incident occurred, with 19 distinct values across 1000 rows and a 4.8% null rate. The top value 'Street/Sidewalk' covers 32.1% of records, but the vocabulary is clearly inconsistent: 'Residential Building/House' (245), 'RESIDENTIAL BUILDING' (232), and 'Residential Building' (5) appear as separate categories, as do 'Sidewalk' (80) vs 'Street/Sidewalk', and '3+ Family Apartment Building' vs '3+ Family Apt. Building'. Entropy ratio of 0.57 reflects this fragmentation rather than genuine diversity.","role":"feature","scope":"column","target":"location_type","treatment":"Normalize casing and merge synonymous labels into a controlled vocabulary before encoding."},{"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":"This is a US ZIP code field for incident locations, with 156 distinct codes across 1000 rows and only 0.3% nulls. The distribution is highly diffuse (entropy ratio 0.94) \u2014 the most frequent ZIP, 10461, accounts for just 2.9% of rows, and the top values (10461, 10462, 11226, 11214, 10034) are all NYC codes, suggesting a NYC-scoped dataset.","role":"feature","scope":"column","target":"incident_zip","treatment":"Treat as high-cardinality categorical: group by borough/region or target-encode rather than one-hot."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_value","stats.top_rate","top_values","alerts"],"model":"anthropic:claude-opus-4-7","narrative":"Street-level incident addresses, almost certainly NYC given entries like JOHN F KENNEDY AIRPORT and LA GUARDIA AIRPORT. Cardinality is extreme: 787 unique values across 1000 rows with entropy ratio 0.98, and the modal address '31 HARRISON AVENUE' appears just 9 times (0.9%). Null rate is low at 1.6%, but the long tail makes this unusable as a categorical feature without aggregation.","role":"metadata","scope":"column","target":"incident_address","treatment":"Geocode to borough/zip or coordinates rather than using raw strings."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values","alerts"],"model":"anthropic:claude-opus-4-7","narrative":"Street-name strings, almost certainly NYC thoroughfares given entries like OCEAN AVENUE, BROADWAY, and BAY PARKWAY. Cardinality is extreme: 592 unique values across 1000 rows with the top value covering only 1.0% and entropy_ratio of 0.96, so the distribution is essentially flat with a long tail. Null rate is low at 1.6%.","role":"feature","scope":"column","target":"street_name","treatment":"Group rare streets into an 'other' bucket or target/frequency-encode before modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Street-name field used as a cross-street reference, likely from NYC service or incident records given entries like 'WYTHE AVENUE', 'ADAM CLAYTON POWELL JR BOULEVARD', and numbered avenues. Cardinality is extreme (457 unique across 1000 rows, entropy ratio 0.97) and the top value 'BEND' covers only 1.3%, so no value dominates. A 25% null rate and presence of placeholder-like 'DEAD END' suggest inconsistent capture that should be reviewed before use.","role":"metadata","scope":"column","target":"cross_street_1","treatment":"Normalise street strings and treat as high-cardinality location metadata; do not one-hot encode directly."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is a free-text street name field, almost certainly the second cross-street bounding an incident or location record. Cardinality is extreme (458 unique across 750 non-null rows, entropy ratio 0.97) and the modal value 'BERRY STREET' covers just 1.07% of rows, so no street dominates. A quarter of values are null and oddities like 'DEAD END' and 'AIRTRAIN-HOWARD BCH/JAMAICA LINE' appear alongside normal street names, suggesting inconsistent free-text entry.","role":"feature","scope":"column","target":"cross_street_2","treatment":"Normalise casing/synonyms and bucket rare values, or drop in favour of geocoded coordinates."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Cross-street name for an incident location, judging from values like 'WYTHE AVENUE', 'ADAM CLAYTON POWELL JR BOULEVARD', and 'DEAD END'. The field is sparse and highly diverse: 26.7% null and 436 distinct values across 1000 rows, with the most common ('BEND') appearing only 9 times and entropy ratio 0.965 indicating an almost-flat long tail. Note the presence of non-street tokens like 'BEND' and 'DEAD END', which suggest mixed semantics rather than clean street names.","role":"feature","scope":"column","target":"intersection_street_1","treatment":"Normalize street names and bucket the long tail; treat nulls as a separate category before encoding."},{"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":"This column holds the second cross-street of an intersection, drawn from NYC street names like BERRY STREET, FREDERICK DOUGLASS BOULEVARD, and DITMAS AVENUE. It is extremely high-cardinality (443 unique values across 1000 rows, entropy ratio 0.97) with a long flat tail \u2014 the top value covers only 1.1% of rows. Notably, 26.7% of rows are null, and oddities like 'DEAD END' and 'AIRTRAIN-HOWARD BCH/JAMAICA LINE' appear alongside conventional street names.","role":"feature","scope":"column","target":"intersection_street_2","treatment":"Normalize street strings and group rare values or geocode to coordinates before modelling; impute or flag the 26.7% nulls."},{"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 tag describing the kind of geolocation reference, with four levels: ADDRESS, INTERSECTION, PLACE, and BLOCKFACE. The distribution is highly imbalanced \u2014 ADDRESS covers 94.2% of 1000 rows, leaving the other three categories with 36, 12, and 10 occurrences respectively. Entropy ratio is just 0.199, and 0.3% of rows are null.","role":"feature","scope":"column","target":"address_type","treatment":"One-hot encode, but expect the non-ADDRESS levels to contribute little signal given the severe imbalance."},{"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 column listing NYC-area city/neighborhood names, dominated by the five boroughs with BROOKLYN top at 307/1000 (31.6%), followed by BRONX (227) and NEW YORK (170). Cardinality is modest (40 unique) and null rate is low (2.9%), but the mix conflates borough names (BROOKLYN, BRONX, QUEENS) with neighborhood names (ASTORIA, ELMHURST, RIDGEWOOD), so granularity is inconsistent. Entropy ratio of 0.61 confirms the heavy concentration in a few labels.","role":"feature","scope":"column","target":"city","treatment":"Normalize to a consistent geographic level (e.g., map neighborhoods to boroughs) and one-hot or target-encode."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","stats.cardinality","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds landmark or street-name references, dominated by NYC thoroughfares like EAST 21 STREET, OCEAN AVENUE, and JOHN F KENNEDY AIRPORT. It's sparsely populated (30.8% null) and extremely long-tailed \u2014 445 unique values across only 692 non-null rows, with the top value covering just 1.3% and entropy ratio at 0.969. No single landmark carries signal on its own.","role":"metadata","scope":"column","target":"landmark","treatment":"Treat as high-cardinality free text: drop or bucket into broad categories rather than one-hot encode."},{"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":"A 3-level categorical status field (In Progress, Closed, Open) with no nulls across 1000 rows. The distribution is nearly uniform \u2014 entropy_ratio of 0.991 and a modest top_rate of 0.388 \u2014 so no class dominates, which is unusual for status fields that often skew heavily to one state.","role":"label","scope":"column","target":"status","treatment":"One-hot or ordinal encode for modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This column encodes NYC community board assignments, formatted as a zero-padded board number plus borough name (e.g., '12 MANHATTAN'). With 64 unique values across 1000 rows, no nulls, and a near-uniform distribution (entropy ratio 0.955, top value only 4.4%), no single board dominates. The composite format mixes two facts (board id + borough) into one string, which is worth splitting before analysis.","role":"metadata","scope":"column","target":"community_board","treatment":"Split into borough and board-number fields, then treat as a categorical geographic key."},{"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":"Categorical column holding council district codes as zero-padded strings (e.g. '09', '13'), with 51 distinct values across 1000 rows and a 1.3% null rate. The distribution is nearly uniform: entropy ratio is 0.968 and the top district '13' accounts for only 4.7% of rows, so no single district dominates. Treat the codes as discrete labels rather than numbers since they are stored as strings with leading zeros.","role":"feature","scope":"column","target":"council_district","treatment":"Keep as string categorical and one-hot or target-encode before modelling."},{"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":"This column identifies the police precinct associated with each record, using labels like 'Precinct 62' across 76 distinct values with no nulls. The distribution is nearly uniform: the top value appears in only 4% of rows and entropy ratio is 0.94, so no precinct dominates. Treat it as a high-cardinality categorical feature rather than a meaningful ranking.","role":"feature","scope":"column","target":"police_precinct","treatment":"Target- or frequency-encode before modelling; avoid one-hot given 76 levels."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values","alerts"],"model":"anthropic:claude-opus-4-7","narrative":"This column holds NYC Borough-Block-Lot (BBL) parcel identifiers \u2014 10-digit codes where the leading digit encodes the borough (values 1\u20135 appear in the top entries). With 744 unique values across 1000 rows and entropy ratio 0.979, it is near-unique but has mild repetition (top BBL '5010780006' appears 9 times), suggesting multiple records per parcel rather than a primary key. Null rate is 5.9%, and the long_tail alert confirms most BBLs occur only once or twice.","role":"foreign_key","scope":"column","target":"bbl","treatment":"left-join on this id to a parcel/property reference table; do not use as a model feature directly."},{"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":"This is a NYC borough categorical with all 5 expected values present and no nulls across 1000 rows. Distribution is fairly balanced (entropy ratio 0.895) with BROOKLYN leading at 31.2% and QUEENS at 26.1%; STATEN ISLAND is notably underrepresented at just 22 rows.","role":"feature","scope":"column","target":"borough","treatment":"one-hot encode for modelling."},{"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":"This column holds X coordinates in a state plane projection, stored as strings rather than numerics \u2014 values like \"946638\" and \"1016981\" are typical NYC-area easting values. Cardinality is extremely high (788 unique across 1000 rows, entropy ratio 0.98) with the modal value appearing only 9 times (0.9%), so it behaves as a near-continuous spatial measurement. Null rate is low at 1.2%.","role":"feature","scope":"column","target":"x_coordinate_state_plane","treatment":"Cast to numeric and pair with the Y coordinate for spatial features rather than treating as categorical."},{"confidence":"high","critiques":[],"evidence_keys":["kind","n","n_unique","null_rate","stats.entropy_ratio","stats.top_value","stats.top_rate","top_values","alerts"],"model":"anthropic:claude-opus-4-7","narrative":"This is a State Plane Y-coordinate (northing), stored as strings rather than numerics \u2014 788 unique values across 1000 rows with only a 1.2% null rate. The distribution is essentially flat (entropy ratio 0.98, top value '171301' appearing just 9 times), consistent with continuous spatial coordinates rather than a true category. The categorical typing is the surprise here; it should be a numeric geo-feature.","role":"feature","scope":"column","target":"y_coordinate_state_plane","treatment":"Cast to numeric and pair with the X-coordinate as a geospatial feature; do not one-hot encode."},{"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 a low-cardinality categorical recording the intake channel for a request, with only 4 distinct values and no nulls. ONLINE dominates at 52.7% (527/1000), followed by MOBILE (234) and PHONE (214), while UNKNOWN appears 25 times and may warrant treatment as missing. Entropy ratio of 0.79 indicates a fairly balanced spread across the top three channels.","role":"feature","scope":"column","target":"open_data_channel_type","treatment":"One-hot encode and consider mapping UNKNOWN to null."},{"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":"Categorical column for a park or facility name, but it is effectively a constant: 998 of 1000 rows are 'Unspecified', with single occurrences of 'Marcus Garvey Park' and 'Forest Park'. Entropy ratio is 0.014 and top_rate is 0.998, so this column carries virtually no signal despite having no nulls.","role":"feature","scope":"column","target":"park_facility_name","treatment":"Drop; near-constant with 99.8% 'Unspecified'."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This column records one of New York City's five boroughs (likely the borough of an associated park), with no missing values across 1000 rows. Distribution is fairly even \u2014 entropy ratio 0.8953 \u2014 but Staten Island is sharply underrepresented at just 22 rows versus Brooklyn's 312.","role":"feature","scope":"column","target":"park_borough","treatment":"One-hot encode the five borough levels before modelling."},{"confidence":"high","critiques":[],"evidence_keys":["n","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Latitude coordinates stored as strings rather than floats, with 794 unique values across 988 non-null rows (1.2% nulls). All top values cluster in the 40.6-40.87 range, consistent with the New York City area. The near-maximum entropy ratio (0.98) and 0.9% top rate confirm this is effectively continuous geospatial data miscast as categorical.","role":"feature","scope":"column","target":"latitude","treatment":"cast to float and pair with longitude for geospatial features rather than treating as categorical."},{"confidence":"high","critiques":[],"evidence_keys":["column","kind","n","n_unique","null_rate","stats.cardinality","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values","alerts"],"model":"anthropic:claude-opus-4-7","narrative":"This is a longitude coordinate column, almost certainly geographic points in the New York City area given values clustered around -73.8 to -74.1. It has been ingested as categorical text rather than numeric, with 794 unique values across 1000 rows and a top value frequency of just 0.9%, indicating a long tail of near-unique floats. Null rate is low at 1.2%, and entropy ratio of 0.98 confirms values are spread very evenly.","role":"feature","scope":"column","target":"longitude","treatment":"Cast to float and use as a numeric geospatial feature, optionally paired with latitude for distance or grid encoding."},{"confidence":"low","critiques":[],"evidence_keys":["alerts","column","kind","n","null_rate","stats"],"model":"anthropic:claude-opus-4-7","narrative":"The column is named \"location\" but saturn skipped detailed profiling, so its kind is unknown and no value statistics are available. We can only confirm there are 1000 rows with a 0.0 null rate; uniqueness, cardinality, and value distribution are all missing. The name suggests geographic or place data, but without evidence we cannot verify format (string, coordinates, codes) or quality.","role":"metadata","scope":"column","target":"location","treatment":"Re-profile with an appropriate parser before deciding; do not use as-is."},{"confidence":"high","critiques":[],"evidence_keys":["column","kind","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","stats.cardinality"],"model":"anthropic:claude-opus-4-7","narrative":"This is a Socrata-style computed region column (`:@computed_region_f5dn_yrer`), almost certainly a spatial join key mapping each row to one of 62 geographic regions. Distribution is remarkably flat \u2014 entropy ratio 0.957 and the top value '47' covers only 4.5% of rows \u2014 so no single region dominates. Null rate is low at 1.2%.","role":"foreign_key","scope":"column","target":":@computed_region_f5dn_yrer","treatment":"Treat as a categorical region id; one-hot or target-encode, or left-join to a region lookup."},{"confidence":"high","critiques":[],"evidence_keys":["column","kind","n_unique","null_rate","stats.cardinality","stats.entropy_ratio","stats.top_rate","stats.top_value","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This appears to be an auto-generated Socrata computed region column (`:@computed_region_yeji_bk3q`), holding a small geographic or administrative bucket id encoded as strings. Cardinality is just 5 with a fairly balanced spread (top value '2' at 31.6%, entropy ratio 0.896), though category '1' is rare at only 22 occurrences and 1.2% of rows are null.","role":"metadata","scope":"column","target":":@computed_region_yeji_bk3q","treatment":"Treat as a low-cardinality categorical region code; one-hot encode or drop if the region mapping is not needed."},{"confidence":"high","critiques":[],"evidence_keys":["column","n_unique","null_rate","stats.entropy_ratio","stats.top_rate","stats.top_value","stats.cardinality","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"This is a Socrata-style computed region column (`:@computed_region_sbqj_enih`), almost certainly a spatial-join key assigning each row to one of 75 region polygons. The distribution is very flat \u2014 entropy ratio 0.94 of the maximum, top value '37' covers only 4.05% of rows \u2014 so no single region dominates. Null rate is low at 1.2%, consistent with rows that fell outside any polygon.","role":"foreign_key","scope":"column","target":":@computed_region_sbqj_enih","treatment":"Treat as a categorical region id; left-join to the region lookup or drop if spatial context isn't needed."},{"confidence":"high","critiques":[],"evidence_keys":["column","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":"This is a Socrata-style computed region column (`:@computed_region_92fq_4b7q`) holding 51 distinct integer-coded region IDs across 1000 rows, with only 1.2% nulls. The distribution is remarkably flat \u2014 entropy ratio 0.969, and the top value '12' covers just 4.66% \u2014 suggesting a near-uniform spread across regions rather than a dominant one. No single region drives the data, so this behaves like a geographic foreign key into an external boundary lookup.","role":"foreign_key","scope":"column","target":":@computed_region_92fq_4b7q","treatment":"Left-join on this id to a region lookup, or treat as a high-cardinality categorical (target-encode) for modelling."},{"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":"Secondary descriptor for service complaints, dominated by heating issues \u2014 \"NO HEAT\" leads at 28.9% of non-null rows, with \"NO HOT WATER\" variants and pest/structural codes filling the tail across 75 distinct values. Nearly 60% of rows are null (null_rate 0.596) and \"N/A\" appears as a literal value 98 times, so missingness is encoded inconsistently. Entropy ratio 0.64 confirms a long tail beyond the heat-related top categories.","role":"feature","scope":"column","target":"descriptor_2","treatment":"Normalize \"N/A\" to null, then group rare levels before one-hot or target encoding."},{"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":"Canned resolution narratives attached to 311-style complaints, drawn from a fixed template library of 19 distinct strings covering HPD, NYPD, and DOT outcomes. 41.2% of rows are null (likely still-open cases), and the top template alone covers 24.1% of populated rows, with entropy ratio 0.72 indicating moderate concentration across the small vocabulary. The text is boilerplate agency response language rather than free-form notes, so it behaves as a high-cardinality categorical disposition code.","role":"label","scope":"column","target":"resolution_description","treatment":"Map the 19 templates to short disposition codes (agency + outcome) and treat nulls as an explicit 'open/unresolved' category."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","stats.top_value","stats.top_rate","top_values","stats.entropy_ratio"],"model":"anthropic:claude-opus-4-7","narrative":"ISO-8601 datetimes recording when a resolution action was last updated, stored as strings rather than parsed timestamps. 40.9% of rows are null and a single value, 2026-01-19T00:00:00.000, accounts for 39.3% of non-null entries (232 of 1000) \u2014 likely a default or batch-stamped backfill at midnight, since all other timestamps cluster on 2026-01-20 with second-level precision. The remaining 353 unique values appear at most twice, giving high entropy (ratio 0.72) among the long tail.","role":"timestamp","scope":"column","target":"resolution_action_updated_date","treatment":"Parse to datetime, treat the midnight 2026-01-19 spike as a sentinel/default, and engineer null-flag plus recency features rather than using the raw string."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n","n_unique","top_values","stats.top_value","stats.top_rate","stats.cardinality"],"model":"anthropic:claude-opus-4-7","narrative":"This is a free-text taxi pickup address, populated for only 12 of 1000 rows (null_rate 0.988). Among the 12 non-null entries, just 3 distinct addresses appear, dominated by JFK Airport (6) and LaGuardia Airport (5), suggesting the field is only filled for airport-related trips. With near-total nullity, this column carries almost no signal as-is.","role":"metadata","scope":"column","target":"taxi_pick_up_location","treatment":"Drop or collapse to a binary 'pickup_address_present' flag given 98.8% nulls."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","stats.cardinality","stats.top_rate","stats.top_value","stats.entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"Categorical descriptor of vehicle class with five levels (Car, SUV, Other, Van, Truck), almost certainly a feature describing involved vehicles. The column is essentially empty: 95.7% of rows are null, leaving only 43 populated values, of which 65% are 'Car'. With such severe missingness any modelling signal is fragile despite reasonable entropy ratio (0.69) across the observed sample.","role":"feature","scope":"column","target":"vehicle_type","treatment":"Drop or encode missingness as its own level; do not rely on this column given 95.7% nulls."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","n","top_value","top_rate","entropy_ratio","top_values"],"model":"anthropic:claude-opus-4-7","narrative":"ISO-8601 timestamps recording when a record was closed, stored as strings rather than parsed datetimes. 66.4% of rows are null, consistent with most records still being open. Among the 336 non-null entries there are 334 unique values, and the visible top values all fall within a narrow window on 2026-01-20, suggesting closures cluster tightly in time rather than spreading across the dataset.","role":"timestamp","scope":"column","target":"closed_date","treatment":"Parse to datetime and derive features (e.g., time-to-close); treat nulls as 'still open' rather than imputing."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","top_values","stats.top_rate","stats.cardinality"],"model":"anthropic:claude-opus-4-7","narrative":"This column appears to record the bridge or highway name associated with each row, but it is essentially empty \u2014 99.6% of values are null and only 4 distinct strings appear across 1000 rows. The four observed values (\"J\", \"Cross Island Pkwy\", \"Long Island Expwy\", \"Nassau Expwy\") each occur exactly once, with one entry (\"J\") looking like a stray code or data-entry artifact rather than a real road name.","role":"metadata","scope":"column","target":"bridge_highway_name","treatment":"Drop or retain only as a sparse flag; too null-heavy to model directly."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","top_values","cardinality","entropy_ratio"],"model":"anthropic:claude-opus-4-7","narrative":"Categorical field naming a bridge or highway segment, but 99.6% of rows are null with only 4 non-null values observed across 1000 records. Each of the 4 surviving entries is unique (Mezzanine, Hempstead Ave, Van Dam St, Belt Pkwy), suggesting this attribute applies to a rare subset of incidents tied to specific NYC roadway infrastructure.","role":"metadata","scope":"column","target":"bridge_highway_segment","treatment":"Drop or convert to a binary 'has_segment' flag given the 99.6% null rate."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","stats.cardinality","stats.entropy","stats.top_value","stats.top_rate","top_values","n"],"model":"anthropic:claude-opus-4-7","narrative":"This column is meant to record facility_type but is effectively empty: 95.9% of rows are null and the only non-null value across all 1000 rows is the literal string \"N/A\" (41 occurrences). Cardinality is 1 and entropy is 0, so the field carries no information as-is.","role":"metadata","scope":"column","target":"facility_type","treatment":"Drop; zero entropy and 95.9% nulls leave nothing to model."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n_unique","top_values","stats.cardinality","stats.top_value"],"model":"anthropic:claude-opus-4-7","narrative":"Almost certainly a directional descriptor for bridge or highway traffic, with values like \"South/Long Island Bound\", \"West/Manhattan Bound\", and \"Eastbound\". The column is effectively empty: 99.7% of rows are null, leaving only 3 populated rows each with a distinct value. With such sparse coverage, the cardinality and entropy stats describe three observations rather than a meaningful distribution.","role":"metadata","scope":"column","target":"bridge_highway_direction","treatment":"Drop or retain only as a contextual flag; too sparse (99.7% null) for modelling."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","n","n_unique","top_values","stats.top_value","stats.top_rate"],"model":"anthropic:claude-opus-4-7","narrative":"A categorical flag distinguishing 'Ramp' vs 'Roadway' segments, but it is effectively empty: 997 of 1000 rows are null, leaving only 3 observed values (2 'Ramp', 1 'Roadway'). With such sparse signal the entropy and top-rate stats are computed on just 3 records and carry no real information.","role":"feature","scope":"column","target":"road_ramp","treatment":"Drop; null rate of 0.997 leaves no usable signal."},{"confidence":"high","critiques":[],"evidence_keys":["null_rate","stats.cardinality","stats.entropy","stats.top_value","stats.top_rate","n_unique"],"model":"anthropic:claude-opus-4-7","narrative":"This column appears to be the borough associated with a taxi company, but it is effectively empty: 99.9% of rows are null and the single non-null value is 'BRONX'. With cardinality of 1 and entropy of 0, the field carries no information in this sample.","role":"metadata","scope":"column","target":"taxi_company_borough","treatment":"Drop; the column is 99.9% null with only one observed category."}],"providers":["anthropic:claude-opus-4-7"],"total_usage":{"completion_tokens":13258,"prompt_tokens":56183,"total_tokens":69441}},"language_counts":{},"meta":{"generated_at":"2026-05-01T18:06:43+00:00","mode":"full","row_count":1000,"sampled_rows":1000,"seed":42,"source":"/home/coolhand/html/datavis/data_trove/cache/wild/nyc_311_sample_20260121.json"},"notes":[],"saturn_version":"0.2.0","schema":{":@computed_region_92fq_4b7q":"categorical",":@computed_region_f5dn_yrer":"categorical",":@computed_region_sbqj_enih":"categorical",":@computed_region_yeji_bk3q":"categorical","address_type":"categorical","agency":"categorical","agency_name":"categorical","bbl":"categorical","borough":"categorical","bridge_highway_direction":"categorical","bridge_highway_name":"categorical","bridge_highway_segment":"categorical","city":"categorical","closed_date":"categorical","community_board":"categorical","complaint_type":"categorical","council_district":"categorical","created_date":"categorical","cross_street_1":"categorical","cross_street_2":"categorical","descriptor":"categorical","descriptor_2":"categorical","facility_type":"categorical","incident_address":"categorical","incident_zip":"categorical","intersection_street_1":"categorical","intersection_street_2":"categorical","landmark":"categorical","latitude":"categorical","location":"unknown","location_type":"categorical","longitude":"categorical","open_data_channel_type":"categorical","park_borough":"categorical","park_facility_name":"categorical","police_precinct":"categorical","resolution_action_updated_date":"categorical","resolution_description":"categorical","road_ramp":"categorical","status":"categorical","street_name":"categorical","taxi_company_borough":"categorical","taxi_pick_up_location":"categorical","unique_key":"categorical","vehicle_type":"categorical","x_coordinate_state_plane":"categorical","y_coordinate_state_plane":"categorical"}}