myprojects-hg-reborn

Fork

library(tidyverse)
library(stringdist)


jaccard <- function(a, b) {
    intersection = length(intersect(a, b))
    union = length(a) + length(b) - intersection
    return (intersection/union)
}


list_v1 <- list(structure(list(keyword = c("lieutenant army", "General army", 
"air force", "government establishment", "commander", "army", 
"lieutenant", "force officer", "force", "officer", "Air", "border", 
"employment", "equivalent", "example", "group", "job", "leadership", 
"management", "member", "occupations", "person", "rank", "service", 
"task", "unit", "variety"), ngram = c(2L, 2L, 2L, 2L, 1L, 1L, 
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 2L, 1L, 1L, 3L, 1L, 1L, 
4L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 
1L, 1L, 1L), rake = c(2.76190476190476, 2.42857142857143, 2.41666666666667, 
2, 1.5, 1.42857142857143, 1.33333333333333, 1.08333333333333, 
0.75, 0.333333333333333, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0)), row.names = c(NA, -27L), class = "data.frame"), 
    structure(list(keyword = c("government establishment", "force occupation", 
    "force officer", "warrant officer", "force", "rank", "officer", 
    "activity", "army", "border", "discipline", "employment", 
    "example", "flight", "group", "job", "member", "occupations", 
    "person", "service", "task", "variety"), ngram = c(2L, 2L, 
    2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L
    ), rake = c(2, 2, 1.66666666666667, 1.66666666666667, 1, 
    1, 0.666666666666667, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0)), row.names = c(NA, -22L), class = "data.frame"), 
    structure(list(keyword = c("government establishment", "air force", 
    "force example", "force occupation", "force", "Gunner", "army", 
    "border", "employment", "group", "job", "member", "navy", 
    "occupations", "officer", "person", "rank", "service", "task", 
    "variety"), ngram = c(2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 
    1L, 1L, 2L, 1L), rake = c(2, 1.75, 1.75, 1.75, 0.75, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -20L), class = "data.frame"), structure(list(keyword = c("assemblie b", 
    "committee e", "government Secretary", "government class", 
    "government department", "community function", "repeal law", 
    "interest group", "parliament councils", "government", "community", 
    "councils", "law", "parliament", "policy", "interest", "Legislator", 
    "administrator", "agency", "agreement", "amend", "amending", 
    "board", "body", "concern", "constituency", "framework", 
    "implementation", "information", "interpretation", "legislator", 
    "matter", "meeting", "member", "occupations", "official", 
    "opinion", "order", "presiding", "proceeding", "regulation", 
    "representative", "rule", "service", "state", "statutory"
    ), ngram = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 5L, 1L, 1L, 1L, 1L, 3L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 1L, 1L, 2L, 1L, 2L, 1L, 4L, 1L), rake = c(2, 2, 1.90909090909091, 
    1.90909090909091, 1.90909090909091, 1.5, 1.5, 1.33333333333333, 
    1, 0.909090909090909, 0.5, 0.5, 0.5, 0.5, 0.5, 0.333333333333333, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, -46L
    ), class = "data.frame"), structure(list(keyword = c("Police commissioner", 
    "government department", "policy matter", "government administration", 
    "government committee", "government e", "government policy", 
    "unit Group", "amendment class", "body tasnks", "document briefs", 
    "service commissioner", "commissioner inspector", "staff member", 
    "policy programme", "government official", "government manager", 
    "government legislation", "agency example", "government", 
    "budget", "control", "policy", "manager", "official", "agency", 
    "legislation", "Director", "accordance", "activity", "administrator", 
    "advising", "behalf", "commission", "conjunction", "consultation", 
    "country", "enterprise", "implementation", "interpretation", 
    "legislator", "objective", "occupations", "organization", 
    "preparation", "presentations", "procedure", "programm", 
    "regulation", "report", "state", "system", "task"), ngram = c(2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
    2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 4L, 1L, 1L, 1L, 
    1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 
    1L, 1L, 2L, 1L, 1L, 3L, 3L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 3L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 1L, 1L), rake = c(4, 3.02380952380952, 2.375, 2.19047619047619, 
    2.19047619047619, 2.19047619047619, 2.06547619047619, 2, 
    2, 2, 2, 2, 2, 2, 1.875, 1.69047619047619, 1.69047619047619, 
    1.44047619047619, 1.25, 1.19047619047619, 1, 1, 0.875, 0.5, 
    0.5, 0.25, 0.25, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, -53L
    ), class = "data.frame"), structure(list(keyword = c("councils g", 
    "custom e", "regulation example", "surplus production", "government rule", 
    "village b", "village care", "village chiefs", "chiefs", 
    "rule", "village", "allocating", "authority", "community", 
    "connection", "dispute", "division", "duty", "head", "household", 
    "land", "member", "occasion", "occupations", "resource", 
    "responsibility", "rights", "task", "tradition", "use", "variety", 
    "violation"), ngram = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 5L, 1L, 1L, 6L, 1L, 1L, 1L, 2L, 2L, 
    1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), rake = c(2, 
    2, 2, 2, 1.5, 1.375, 1.375, 0.875, 0.5, 0.5, 0.375, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -32L), class = "data.frame"), structure(list(keyword = c("interest group", 
    "of planning", "policy rule", "funding agency", "forum example", 
    "charity organization", "organization class", "employer organization", 
    "interest organization", "rights organization", "sport associations", 
    "board meeting", "party organization", "director", "interest", 
    "policy", "organization", "associations", "board", "party", 
    "act", "behalf", "body", "convention", "determining", "enterprise", 
    "functioning", "government", "hearing", "implementation", 
    "member", "membership", "negotiation", "objective", "occasion", 
    "occupations", "official", "operation", "performance", "procedure", 
    "regulation", "result", "section", "system"), ngram = c(2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 
    8L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L), rake = c(2.5, 
    2.5, 2.25, 2, 2, 1.72222222222222, 1.72222222222222, 1.72222222222222, 
    1.72222222222222, 1.72222222222222, 1.5, 1.5, 1.22222222222222, 
    1, 1, 0.75, 0.722222222222222, 0.5, 0.5, 0.5, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0)), row.names = c(NA, -44L), class = "data.frame"), structure(list(
        keyword = c("unit Group", "conventions seminar", "unit group", 
        "staff k", "subordinate staff", "body class", "government department", 
        "regulation example", "operation undertaken", "organization b", 
        "organization e", "interest organization", "manager note", 
        "board meeting", "objective", "sale manager", "body", 
        "example", "government", "operation", "policy", "sale", 
        "organization", "manager", "board", "Director", "activity", 
        "area", "budget", "consult", "coordinate", "director", 
        "directors", "enterprise", "enterprisis", "executive", 
        "expenditure", "forum", "function", "functioning", "guideline", 
        "hearing", "leadership", "legislation", "management", 
        "member", "negotiation", "occasion", "occupations", "performance", 
        "planning", "programme", "range", "recommendation", "report", 
        "resource", "responsibility", "result", "selection", 
        "support", "use"), ngram = c(2L, 2L, 2L, 2L, 2L, 2L, 
        2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 
        1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
        1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
        1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), 
        freq = c(3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
        1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 7L, 5L, 3L, 
        3L, 2L, 1L, 1L, 1L, 1L, 4L, 1L, 6L, 2L, 2L, 1L, 1L, 1L, 
        1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 
        1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L), rake = c(2, 2, 2, 2, 
        2, 1.5, 1.5, 1.5, 1.5, 1.3, 1.3, 1.3, 1.28571428571429, 
        1.25, 1, 0.785714285714286, 0.5, 0.5, 0.5, 0.5, 0.5, 
        0.5, 0.3, 0.285714285714286, 0.25, 0, 0, 0, 0, 0, 0, 
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -61L), class = "data.frame"), structure(list(keyword = c("management accountant", 
    "body example", "resource e", "staff h", "selection training", 
    "operation g", "Finance manager", "finance manager", "organization b", 
    "operation", "manager", "organization", "budget", "consultation", 
    "controller", "dealings", "departments", "enterprise", "enterprisis", 
    "expenditure", "occupations", "performance", "planning", 
    "procedure", "section", "service", "situation", "use"), ngram = c(2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 3L, 4L, 2L, 1L, 1L, 1L, 
    2L, 4L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L), rake = c(2, 
    2, 2, 2, 2, 1.75, 1.66666666666667, 1.66666666666667, 1.2, 
    0.75, 0.666666666666667, 0.2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, -28L), class = "data.frame"), 
    structure(list(keyword = c("resource manager", "manager", 
    "selection training", "relation", "activity e", "safety activity", 
    "body example", "organizing negotiation", "wage structure", 
    "safety health", "resource service", "procedure g", "health", 
    "management", "planning", "policy", "staff", "resource", 
    "safety", "organization", "procedure", "budget", "compliance", 
    "concern", "condition", "consult", "consultation", "dealings", 
    "departments", "determination", "development", "dismissal", 
    "employment", "enterprise", "enterprisis", "expenditure", 
    "implementation", "legislation", "level", "occupations", 
    "opportunity", "performance", "personnel", "practice", "programm", 
    "standard", "use", "worker"), ngram = c(2L, 1L, 2L, 1L, 2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 4L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 4L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 1L), rake = c(3.86666666666667, 3.2, 3, 2.33333333333333, 
    2.33333333333333, 2, 2, 2, 2, 1.66666666666667, 1.66666666666667, 
    1.33333333333333, 1, 1, 1, 1, 1, 0.666666666666667, 0.666666666666667, 
    0.4, 0.333333333333333, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -48L), class = "data.frame"))


list_v2 <- list(structure(list(keyword = c("user journey", "market data", 
"logistic firm", "management tool", "rights offence", "other shine", 
"usability testing", "user experience", "business requirement", 
"end journey", "health service", "house team", "stakeholder interest", 
"bank design", "design process", "constraint ability", "service design", 
"product designer", "product design", "experience", "business", 
"designer", "end", "interest", "service", "team", "design", "product", 
"ability", "action", "aesthetic", "agency", "app", "artefact", 
"attitude", "blueprint", "client", "consultant", "core", "curiosity", 
"define", "deliverable", "developer", "discipline", "eye", "flow", 
"future", "idea", "insight", "kind", "life", "lot", "mind", "mindset", 
"mockup", "money", "need", "opportunity", "output", "passion", 
"persona", "practice", "prototype", "reporting", "research", 
"role", "sense", "story", "strategy", "thing", "travel", "trend", 
"wireframe", "workshop"), ngram = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 5L, 1L, 
5L, 4L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 2L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L
), rake = c(2.25, 2, 2, 2, 2, 2, 2, 1.91666666666667, 1.5, 1.5, 
1.5, 1.5, 1.5, 1.44444444444444, 1.44444444444444, 1.16666666666667, 
0.944444444444444, 0.833333333333333, 0.777777777777778, 0.666666666666667, 
0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.444444444444444, 0.333333333333333, 
0.166666666666667, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, -74L), class = "data.frame"), 
    structure(list(keyword = c("employment Business", "employment agency", 
    "bank holiday", "construction environment", "pension contribution", 
    "minimising disruption", "home projects", "home scheme", 
    "property information", "market leader", "site operation", 
    "training opportunity", "roofing renewal", "communication skill", 
    "literacy skill", "principal contractor", "housing sector", 
    "job type", "site team", "ability", "opportunity", "client team", 
    "skill", "role", "contractor", "housing", "job", "team", 
    "client", "CV", "Cladding", "FTC", "access", "appointment", 
    "appreciation", "benefit", "candidate", "complaint", "customer", 
    "detail", "experience", "initiative", "issue", "leave", "level", 
    "location", "mixture", "offer", "party", "phone", "process", 
    "project", "recruitment", "refurbishment", "relation", "relationship", 
    "resident", "supply", "survey", "today", "touch", "units", 
    "vacancy", "value", "view", "worker", "year"), ngram = c(2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
    2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L), rake = c(2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1.75, 
    1.75, 1.5, 1.5, 1.5, 1.5, 1, 1, 0.833333333333333, 0.75, 
    0.666666666666667, 0.5, 0.5, 0.5, 0.5, 0.333333333333333, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -67L), class = "data.frame"), structure(list(keyword = c("department standard", 
    "Package Benefits", "Wells area", "household name", "stock package", 
    "customer base", "business objective", "quality plant", "manager", 
    "product offer", "customer service", "retail business", "day", 
    "job", "business", "customer", "plant", "service", "role", 
    "retail", "product", "Assistants", "Tn2", "accessory", "advice", 
    "aspect", "belief", "candidate", "client", "company", "condition", 
    "confidence", "desire", "example", "experience", "garden", 
    "gardener", "gardening", "hand", "horticulturist", "individual", 
    "interview", "knowledge", "layout", "location", "love", "management", 
    "order", "passion", "people", "plenty", "position", "purveyor", 
    "recruit", "reputation", "responsibility", "sale", "sundry", 
    "support", "team", "thing", "training", "update", "willingness"
    ), ngram = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 
    2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 4L, 
    2L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L
    ), rake = c(2.5, 2, 2, 2, 2, 1.66666666666667, 1.66666666666667, 
    1.5, 1.33333333333333, 1.25, 1.16666666666667, 1, 1, 1, 0.666666666666667, 
    0.666666666666667, 0.5, 0.5, 0.4, 0.333333333333333, 0.25, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0)), row.names = c(NA, -64L), class = "data.frame"), 
    structure(list(keyword = c("conduct work", "document responsibility", 
    "industry health", "Groundworkers", "duty", "experience", 
    "qualification", "reference", "site", "skills", "week"), 
        ngram = c(2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), 
        freq = c(1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L), 
        rake = c(2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0)), row.names = c(NA, 
    -11L), class = "data.frame"), structure(list(keyword = c("Pension scheme", 
    "transportation allowances", "job career", "employment condition", 
    "hour contract", "university degree", "holiday payment", 
    "hour week", "risk manager", "market risk", "Mrcp team", 
    "communication skill", "risk team", "team work", "trading activity", 
    "life balance", "vacation day", "work environment", "programme knowledge", 
    "portfolio self", "month salary", "it skill", "experience", 
    "risk", "market", "skill", "team", "management", "day", "environment", 
    "knowledge", "life", "portfolio", "trading", "it", "salary", 
    "13th", "Fluent", "ability", "addition", "ambition", "analysis", 
    "atmosphere", "attention", "attitude", "audit", "business", 
    "candidate", "capital", "challenge", "change", "choice", 
    "coach", "colleague", "competence", "concept", "coordinating", 
    "course", "demand", "departments", "detail", "development", 
    "difference", "econometric", "economics", "finance", "focus", 
    "gross", "guideline", "home", "idea", "impact", "initiative", 
    "instrument", "interest", "listen", "measure", "measurement", 
    "method", "mindset", "monitoring", "motivat", "other", "part", 
    "party", "passion", "performance", "personality", "policy", 
    "possibility", "professional", "profile", "project", "publication", 
    "regulation", "regulator", "regulatory", "responsibility", 
    "result", "role", "scope", "stakeholder", "starter", "subject", 
    "supervisor", "support", "technique", "thing", "think", "thinking", 
    "time", "understanding", "way"), ngram = c(2L, 2L, 2L, 2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
    2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 1L, 1L), freq = c(1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 
    1L, 3L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 
    1L, 3L, 3L, 3L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 
    1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 
    2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 
    1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L
    ), rake = c(2, 2, 2, 2, 2, 2, 2, 2, 2, 1.875, 1.71428571428571, 
    1.71428571428571, 1.71428571428571, 1.71428571428571, 1.5, 
    1.5, 1.5, 1.5, 1.5, 1.5, 1.33333333333333, 1.04761904761905, 
    1, 1, 0.875, 0.714285714285714, 0.714285714285714, 0.666666666666667, 
    0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.333333333333333, 0.333333333333333, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0)), row.names = c(NA, -113L), class = "data.frame"))


## see what they look like

list_v1[[5]] |> glimpse()

list_v2[[5]] |> glimpse()

## sapply solution

mm <- sapply(list_v2, \(y) sapply(list_v1, \(x) jaccard(x$keyword, y$keyword)))

mm

## map solution

mm2 <- map_df(list_v1, ~data.frame(t(map_dbl(list_v2, ~jaccard(.x[[1]],.y[[1]]), .y=.x))))

mm2


## outer solution
mm3 <- outer(
    list_v1,
    list_v2,
    Vectorize(\(x, y) jaccard(x$keyword, y$keyword))
)


sessionInfo()