Add helper stuff for figures, cleanup

This commit is contained in:
2026-02-20 01:56:28 +01:00
parent 28823dc0b5
commit 101bd81ca1
20 changed files with 1862 additions and 1164 deletions

View File

@@ -0,0 +1,604 @@
{
"file": "../data/original/reviews.tab",
"rows_before_dedup": 56446,
"rows_after_dedup": 55662,
"distribution_word_length": {
"8": 1,
"9": 5,
"10": 10,
"11": 14,
"12": 20,
"13": 29,
"14": 37,
"15": 92,
"16": 163,
"17": 308,
"18": 482,
"19": 728,
"20": 859,
"21": 977,
"22": 944,
"23": 989,
"24": 937,
"25": 1032,
"26": 946,
"27": 927,
"28": 928,
"29": 920,
"30": 926,
"31": 879,
"32": 897,
"33": 856,
"34": 759,
"35": 829,
"36": 774,
"37": 708,
"38": 771,
"39": 717,
"40": 693,
"41": 737,
"42": 734,
"43": 655,
"44": 616,
"45": 630,
"46": 680,
"47": 609,
"48": 588,
"49": 586,
"50": 598,
"51": 562,
"52": 543,
"53": 563,
"54": 549,
"55": 551,
"56": 478,
"57": 522,
"58": 450,
"59": 515,
"60": 509,
"61": 461,
"62": 453,
"63": 451,
"64": 483,
"65": 403,
"66": 442,
"67": 404,
"68": 418,
"69": 389,
"70": 394,
"71": 355,
"72": 357,
"73": 389,
"74": 360,
"75": 356,
"76": 338,
"77": 330,
"78": 308,
"79": 327,
"80": 303,
"81": 302,
"82": 306,
"83": 273,
"84": 276,
"85": 265,
"86": 268,
"87": 263,
"88": 264,
"89": 229,
"90": 244,
"91": 239,
"92": 212,
"93": 267,
"94": 211,
"95": 226,
"96": 247,
"97": 219,
"98": 239,
"99": 201,
"100": 220,
"101": 213,
"102": 180,
"103": 194,
"104": 204,
"105": 201,
"106": 200,
"107": 149,
"108": 189,
"109": 196,
"110": 178,
"111": 140,
"112": 157,
"113": 150,
"114": 160,
"115": 130,
"116": 151,
"117": 159,
"118": 151,
"119": 118,
"120": 138,
"121": 115,
"122": 107,
"123": 121,
"124": 99,
"125": 135,
"126": 126,
"127": 125,
"128": 97,
"129": 99,
"130": 95,
"131": 92,
"132": 86,
"133": 108,
"134": 115,
"135": 101,
"136": 101,
"137": 103,
"138": 91,
"139": 81,
"140": 92,
"141": 91,
"142": 95,
"143": 76,
"144": 84,
"145": 91,
"146": 84,
"147": 87,
"148": 92,
"149": 73,
"150": 78,
"151": 71,
"152": 76,
"153": 87,
"154": 60,
"155": 67,
"156": 67,
"157": 88,
"158": 56,
"159": 66,
"160": 41,
"161": 56,
"162": 61,
"163": 68,
"164": 62,
"165": 67,
"166": 52,
"167": 62,
"168": 47,
"169": 41,
"170": 49,
"171": 47,
"172": 43,
"173": 39,
"174": 61,
"175": 56,
"176": 55,
"177": 47,
"178": 34,
"179": 44,
"180": 43,
"181": 37,
"182": 48,
"183": 47,
"184": 39,
"185": 38,
"186": 42,
"187": 42,
"188": 35,
"189": 43,
"190": 39,
"191": 38,
"192": 37,
"193": 27,
"194": 28,
"195": 40,
"196": 33,
"197": 36,
"198": 40,
"199": 35,
"200": 30,
"201": 28,
"202": 28,
"203": 26,
"204": 28,
"205": 32,
"206": 31,
"207": 36,
"208": 36,
"209": 24,
"210": 20,
"211": 34,
"212": 26,
"213": 31,
"214": 27,
"215": 25,
"216": 23,
"217": 26,
"218": 20,
"219": 20,
"220": 20,
"221": 28,
"222": 15,
"223": 18,
"224": 17,
"225": 22,
"226": 16,
"227": 29,
"228": 27,
"229": 23,
"230": 14,
"231": 23,
"232": 22,
"233": 21,
"234": 23,
"235": 16,
"236": 18,
"237": 14,
"238": 11,
"239": 17,
"240": 8,
"241": 16,
"242": 12,
"243": 18,
"244": 15,
"245": 11,
"246": 24,
"247": 14,
"248": 18,
"249": 15,
"250": 11,
"251": 17,
"252": 17,
"253": 15,
"254": 17,
"255": 18,
"256": 14,
"257": 21,
"258": 13,
"259": 16,
"260": 10,
"261": 20,
"262": 8,
"263": 9,
"264": 11,
"265": 16,
"266": 6,
"267": 14,
"268": 14,
"269": 12,
"270": 11,
"271": 12,
"272": 9,
"273": 5,
"274": 7,
"275": 4,
"276": 6,
"277": 10,
"278": 11,
"279": 13,
"280": 7,
"281": 9,
"282": 6,
"283": 9,
"284": 10,
"285": 9,
"286": 11,
"287": 8,
"288": 5,
"289": 6,
"290": 8,
"291": 4,
"292": 11,
"293": 6,
"294": 11,
"295": 11,
"296": 7,
"297": 4,
"298": 7,
"299": 13,
"300": 7,
"301": 15,
"302": 10,
"303": 7,
"304": 11,
"305": 3,
"306": 7,
"307": 8,
"308": 6,
"309": 4,
"310": 7,
"311": 4,
"312": 8,
"313": 5,
"314": 1,
"315": 8,
"316": 8,
"317": 9,
"318": 8,
"319": 6,
"320": 8,
"321": 2,
"322": 8,
"323": 6,
"324": 9,
"325": 6,
"326": 8,
"327": 3,
"328": 8,
"329": 7,
"330": 5,
"331": 8,
"332": 7,
"333": 2,
"334": 1,
"335": 9,
"336": 4,
"337": 6,
"338": 4,
"339": 3,
"340": 6,
"341": 5,
"342": 3,
"343": 4,
"344": 3,
"345": 5,
"346": 3,
"347": 5,
"348": 3,
"349": 3,
"350": 3,
"351": 2,
"352": 8,
"353": 4,
"354": 4,
"355": 4,
"356": 3,
"357": 4,
"358": 3,
"359": 3,
"360": 8,
"361": 6,
"362": 5,
"363": 8,
"364": 4,
"365": 6,
"366": 3,
"367": 7,
"368": 4,
"369": 8,
"370": 2,
"371": 2,
"372": 7,
"373": 5,
"374": 4,
"375": 1,
"376": 1,
"377": 3,
"378": 1,
"379": 2,
"380": 2,
"381": 2,
"382": 3,
"383": 2,
"384": 1,
"385": 1,
"386": 2,
"387": 4,
"388": 6,
"389": 4,
"390": 4,
"391": 3,
"392": 3,
"393": 2,
"394": 2,
"395": 7,
"396": 6,
"397": 2,
"398": 2,
"401": 1,
"402": 5,
"403": 1,
"404": 3,
"405": 4,
"406": 1,
"407": 1,
"409": 3,
"410": 2,
"411": 1,
"412": 1,
"413": 2,
"414": 3,
"415": 4,
"416": 2,
"417": 2,
"418": 3,
"419": 1,
"420": 2,
"421": 4,
"422": 1,
"424": 3,
"425": 4,
"426": 4,
"427": 1,
"428": 1,
"429": 2,
"430": 2,
"431": 4,
"433": 1,
"434": 1,
"436": 1,
"437": 1,
"438": 5,
"439": 1,
"440": 2,
"441": 1,
"443": 4,
"444": 3,
"445": 1,
"446": 5,
"448": 1,
"449": 4,
"451": 2,
"452": 1,
"455": 3,
"456": 1,
"457": 1,
"458": 1,
"459": 1,
"463": 2,
"464": 1,
"465": 2,
"466": 2,
"467": 2,
"469": 1,
"470": 1,
"474": 1,
"475": 5,
"476": 1,
"477": 1,
"478": 1,
"479": 3,
"481": 1,
"482": 1,
"484": 1,
"485": 2,
"489": 1,
"490": 1,
"494": 3,
"495": 1,
"497": 1,
"499": 1,
"501": 1,
"502": 1,
"503": 1,
"504": 1,
"505": 1,
"506": 1,
"508": 3,
"510": 2,
"511": 4,
"518": 1,
"519": 2,
"520": 1,
"522": 1,
"523": 1,
"524": 1,
"525": 1,
"526": 1,
"527": 1,
"537": 1,
"540": 1,
"541": 1,
"543": 1,
"545": 2,
"546": 3,
"554": 1,
"555": 1,
"557": 2,
"558": 1,
"559": 1,
"562": 1,
"564": 3,
"566": 1,
"568": 1,
"573": 1,
"578": 2,
"580": 2,
"581": 1,
"583": 1,
"584": 1,
"585": 1,
"586": 1,
"588": 1,
"592": 1,
"594": 2,
"595": 1,
"597": 2,
"598": 1,
"601": 1,
"609": 1,
"610": 1,
"612": 1,
"613": 2,
"615": 1,
"618": 2,
"620": 2,
"622": 1,
"623": 1,
"624": 1,
"626": 1,
"635": 1,
"637": 1,
"639": 1,
"643": 2,
"645": 1,
"649": 2,
"651": 1,
"654": 1,
"658": 1,
"661": 1,
"667": 1,
"670": 1,
"671": 1,
"672": 1,
"673": 1,
"676": 1,
"679": 2,
"686": 1,
"691": 1,
"694": 2,
"698": 1,
"701": 1,
"708": 1,
"710": 1,
"711": 1,
"715": 1,
"719": 1,
"723": 1,
"729": 2,
"737": 1,
"739": 1,
"745": 1,
"747": 1,
"753": 1,
"755": 1,
"756": 1,
"765": 1,
"786": 1,
"794": 1,
"799": 1,
"810": 1,
"813": 1,
"816": 2,
"822": 1,
"873": 1,
"880": 1,
"891": 1,
"912": 1,
"945": 1,
"957": 1,
"960": 1,
"987": 1,
"992": 1,
"1005": 1,
"1035": 1,
"1046": 1,
"1073": 1,
"1096": 1,
"1099": 1,
"1196": 2,
"1233": 1,
"1263": 1,
"1329": 1,
"1597": 1,
"1699": 1,
"1893": 1,
"2244": 1,
"2537": 1
},
"summary": {
"min_words": 8,
"max_words": 2537,
"mean_words": 72.6454133879487,
"median_words": 53.0
}
}