Intro: A new a year means a new Year in Review to digest and synthesize the events. Here's my attempt creating a Data oriented Year in Review of The Economist Newspaper using all the articles from the past year.
Getting Data: I used Python to 'scrape' data from The Economist website. I've included the code, but not the actual articles. If you have access to the Economist then you too can use the code to download the articles from the past year.
LDA: First I wanted to know what kind of topics were written about so I made a topics model with 100 topics. Below are the top ten words of each topic in decreasing order of importance. In addition, some of topics displayed over time that I thought were interesting.
library(topicmodels)
load("/users/sweiss/google drive/ld100.Rda")
theta = posterior(ld.100)$topics
theta.average = colMeans(theta)
top.5.factors = names(sort(theta.average, decreasing = TRUE))
terms(ld.100, 10)[, as.numeric(top.5.factors)]
## Topic 50 Topic 16 Topic 62 Topic 90 Topic 83
## [1,] "price" "elect" "scienc" "bank" "minist"
## [2,] "rate" "parti" "cell" "financi" "govern"
## [3,] "economist" "vote" "research" "loan" "polit"
## [4,] "index" "polit" "found" "capit" "prime"
## [5,] "market" "voter" "technolog" "lend" "parti"
## [6,] "econom" "poll" "one" "credit" "parliament"
## [7,] "exchang" "seat" "human" "deposit" "opposit"
## [8,] "commod" "candid" "brain" "financ" "leader"
## [9,] "interest" "win" "look" "asset" "elect"
## [10,] "job" "campaign" "univers" "regul" "coalit"
## Topic 46 Topic 64 Topic 52 Topic 66 Topic 30
## [1,] "market" "number" "billion" "presid" "republican"
## [2,] "firm" "year" "compani" "polit" "obama"
## [3,] "product" "sinc" "firm" "elect" "senat"
## [4,] "industri" "increas" "share" "power" "democrat"
## [5,] "sale" "rise" "busi" "presidenti" "congress"
## [6,] "manufactur" "rate" "profit" "year" "hous"
## [7,] "make" "fall" "deal" "govern" "state"
## [8,] "profit" "accord" "buy" "constitut" "polit"
## [9,] "busi" "quarter" "sharehold" "last" "barack"
## [10,] "cost" "averag" "stake" "countri" "presid"
## Topic 20 Topic 24 Topic 54 Topic 67 Topic 27 Topic 74
## [1,] "economi" "rate" "group" "syria" "will" "use"
## [2,] "growth" "inflat" "govern" "rebel" "may" "system"
## [3,] "econom" "bank" "armi" "war" "year" "can"
## [4,] "gdp" "polici" "peac" "assad" "hope" "work"
## [5,] "invest" "central" "pakistan" "regim" "alreadi" "one"
## [6,] "year" "currenc" "kill" "weapon" "get" "make"
## [7,] "account" "market" "polit" "iraq" "next" "way"
## [8,] "quarter" "fed" "violenc" "syrian" "expect" "machin"
## [9,] "export" "economi" "war" "libya" "think" "design"
## [10,] "spend" "reserv" "attack" "forc" "far" "problem"
## Topic 49 Topic 22 Topic 96 Topic 48 Topic 78 Topic 25
## [1,] "citi" "parti" "fund" "firm" "one" "polic"
## [2,] "local" "polit" "investor" "compani" "may" "crime"
## [3,] "mayor" "leader" "return" "busi" "might" "prison"
## [4,] "town" "power" "invest" "consult" "like" "drug"
## [5,] "area" "member" "asset" "industri" "way" "say"
## [6,] "council" "politician" "equiti" "big" "can" "crimin"
## [7,] "resid" "call" "manag" "servic" "whether" "jail"
## [8,] "centr" "nation" "share" "client" "even" "sentenc"
## [9,] "street" "offici" "stock" "work" "question" "murder"
## [10,] "build" "chief" "money" "say" "littl" "gun"
## Topic 31 Topic 21 Topic 26 Topic 77 Topic 61 Topic 40
## [1,] "euro" "investig" "labour" "mobil" "year" "year"
## [2,] "zone" "charg" "britain" "technolog" "day" "last"
## [3,] "spain" "alleg" "cameron" "phone" "week" "two"
## [4,] "european" "claim" "tori" "appl" "april" "ago"
## [5,] "bail" "case" "parti" "comput" "month" "five"
## [6,] "europ" "trial" "conserv" "servic" "last" "past"
## [7,] "greec" "report" "miliband" "oper" "may" "month"
## [8,] "countri" "scandal" "mps" "googl" "time" "four"
## [9,] "ireland" "accus" "david" "network" "said" "three"
## [10,] "cyprus" "former" "polit" "softwar" "june" "end"
## Topic 33 Topic 5 Topic 11 Topic 23 Topic 15 Topic 80 Topic 29
## [1,] "can" "cut" "court" "money" "britain" "china" "long"
## [2,] "make" "spend" "law" "cost" "british" "chines" "time"
## [3,] "world" "budget" "case" "pay" "london" "offici" "term"
## [4,] "peopl" "billion" "legal" "billion" "england" "beij" "like"
## [5,] "argu" "year" "right" "fee" "kingdom" "hong" "big"
## [6,] "think" "deficit" "rule" "year" "unit" "kong" "run"
## [7,] "one" "govern" "judg" "use" "briton" "shanghai" "also"
## [8,] "like" "fiscal" "lawyer" "paid" "english" "even" "less"
## [9,] "good" "will" "suprem" "charg" "scotland" "also" "even"
## [10,] "idea" "tax" "justic" "payment" "servic" "yuan" "well"
## Topic 65 Topic 98 Topic 34 Topic 56 Topic 1 Topic 35
## [1,] "measur" "european" "law" "histori" "space" "road"
## [2,] "data" "europ" "rule" "mani" "one" "line"
## [3,] "suggest" "union" "regul" "yet" "mar" "car"
## [4,] "also" "countri" "bill" "war" "scienc" "train"
## [5,] "may" "commiss" "pass" "day" "technolog" "transport"
## [6,] "can" "nation" "requir" "never" "field" "rail"
## [7,] "chang" "dutch" "ban" "father" "light" "railway"
## [8,] "base" "brussel" "new" "centuri" "though" "speed"
## [9,] "differ" "germani" "propos" "old" "earth" "drive"
## [10,] "point" "franc" "control" "much" "orbit" "say"
## Topic 73 Topic 12 Topic 28 Topic 2 Topic 82 Topic 58
## [1,] "will" "project" "protest" "school" "bond" "women"
## [2,] "octob" "build" "street" "educ" "debt" "children"
## [3,] "month" "plan" "govern" "student" "rate" "age"
## [4,] "next" "will" "call" "univers" "yield" "famili"
## [5,] "novemb" "water" "polic" "teacher" "govern" "young"
## [6,] "one" "say" "day" "year" "interest" "men"
## [7,] "year" "river" "demonstr" "colleg" "market" "old"
## [8,] "first" "construct" "support" "teach" "investor" "parent"
## [9,] "said" "built" "peopl" "children" "financ" "sex"
## [10,] "septemb" "billion" "thousand" "pupil" "borrow" "child"
## Topic 86 Topic 70 Topic 97 Topic 19 Topic 95 Topic 4
## [1,] "say" "reform" "polici" "first" "use" "work"
## [2,] "mani" "will" "visit" "second" "onlin" "worker"
## [3,] "one" "chang" "also" "back" "data" "job"
## [4,] "can" "polici" "diplomat" "two" "internet" "labour"
## [5,] "peopl" "system" "leader" "canada" "can" "employ"
## [6,] "see" "plan" "presid" "time" "social" "wage"
## [7,] "languag" "new" "foreign" "made" "user" "unemploy"
## [8,] "still" "need" "two" "place" "applic" "skill"
## [9,] "want" "propos" "want" "chang" "search" "young"
## [10,] "main" "polit" "might" "now" "peopl" "low"
## Topic 44 Topic 92 Topic 69 Topic 63 Topic 81 Topic 43
## [1,] "countri" "time" "state" "chief" "govern" "peopl"
## [2,] "foreign" "test" "unit" "manag" "state" "kill"
## [3,] "world" "ask" "feder" "boss" "privat" "fire"
## [4,] "global" "experi" "governor" "execut" "public" "mani"
## [5,] "intern" "suggest" "california" "offic" "sector" "miss"
## [6,] "develop" "person" "year" "also" "offici" "now"
## [7,] "rich" "control" "texa" "job" "own" "bad"
## [8,] "emerg" "word" "san" "board" "say" "least"
## [9,] "import" "show" "one" "head" "privatis" "disast"
## [10,] "abroad" "think" "counti" "need" "local" "die"
## Topic 99 Topic 84 Topic 13 Topic 94 Topic 47
## [1,] "like" "start" "media" "america" "deal"
## [2,] "class" "busi" "televis" "american" "talk"
## [3,] "middl" "firm" "news" "unit" "negoti"
## [4,] "still" "new" "advertis" "state" "agreement"
## [5,] "well" "entrepreneur" "newspap" "washington" "two"
## [6,] "just" "ventur" "video" "nation" "agre"
## [7,] "much" "small" "show" "long" "sign"
## [8,] "better" "big" "year" "see" "side"
## [9,] "half" "founder" "time" "obama" "want"
## [10,] "part" "capit" "watch" "action" "will"
## Topic 88 Topic 89 Topic 75 Topic 18 Topic 59 Topic 45
## [1,] "secur" "forc" "africa" "shop" "poor" "muslim"
## [2,] "agenc" "militari" "african" "retail" "peopl" "egypt"
## [3,] "govern" "defenc" "south" "store" "help" "islamist"
## [4,] "secret" "armi" "countri" "busi" "poverti" "islam"
## [5,] "attack" "arm" "east" "custom" "social" "saudi"
## [6,] "say" "war" "kenya" "sell" "work" "brother"
## [7,] "intellig" "afghanistan" "nigeria" "open" "give" "morsi"
## [8,] "offici" "secur" "middl" "sale" "incom" "arab"
## [9,] "inform" "soldier" "region" "onlin" "benefit" "brotherhood"
## [10,] "spi" "drone" "say" "say" "money" "arabia"
## Topic 32 Topic 10 Topic 36 Topic 9 Topic 71 Topic 7
## [1,] "hous" "right" "new" "univers" "music" "climat"
## [2,] "price" "group" "york" "paper" "art" "chang"
## [3,] "properti" "gay" "one" "research" "film" "carbon"
## [4,] "home" "campaign" "will" "publish" "one" "warm"
## [5,] "land" "marriag" "year" "public" "show" "environment"
## [6,] "mortgag" "support" "old" "book" "man" "tree"
## [7,] "rent" "member" "two" "author" "can" "emiss"
## [8,] "new" "among" "bloomberg" "work" "now" "model"
## [9,] "valu" "liber" "boston" "studi" "cultur" "water"
## [10,] "rise" "debat" "post" "journal" "first" "global"
## Topic 8 Topic 14 Topic 79 Topic 87 Topic 51 Topic 42
## [1,] "asia" "germani" "game" "health" "trade" "immigr"
## [2,] "ship" "german" "sport" "drug" "market" "mexico"
## [3,] "australia" "mrs" "footbal" "hospit" "exchang" "say"
## [4,] "island" "merkel" "club" "care" "import" "migrant"
## [5,] "south" "green" "play" "treatment" "financi" "border"
## [6,] "sea" "berlin" "team" "cancer" "goldman" "year"
## [7,] "region" "europ" "world" "patient" "deriv" "illeg"
## [8,] "port" "social" "player" "doctor" "econom" "countri"
## [9,] "countri" "coalit" "leagu" "medic" "world" "home"
## [10,] "indonesia" "left" "can" "also" "financ" "refuge"
## Topic 85 Topic 53 Topic 91 Topic 55 Topic 68 Topic 57
## [1,] "food" "power" "oil" "black" "itali" "tax"
## [2,] "say" "energi" "gas" "mani" "church" "rais"
## [3,] "hotel" "electr" "billion" "white" "italian" "revenu"
## [4,] "one" "plant" "energi" "may" "berlusconi" "pay"
## [5,] "meat" "nuclear" "price" "like" "left" "incom"
## [6,] "drink" "wind" "reserv" "race" "christian" "financ"
## [7,] "eat" "industri" "shale" "make" "one" "rate"
## [8,] "good" "generat" "year" "stop" "cathol" "govern"
## [9,] "may" "batteri" "invest" "less" "movement" "rich"
## [10,] "consum" "renew" "new" "becom" "hous" "money"
## Topic 72 Topic 60 Topic 76 Topic 41 Topic 93 Topic 39
## [1,] "air" "insur" "brazil" "pension" "french" "russia"
## [2,] "new" "health" "year" "pay" "franc" "russian"
## [3,] "airport" "will" "farmer" "scheme" "holland" "putin"
## [4,] "fli" "care" "farm" "public" "pari" "ukrain"
## [5,] "airlin" "plan" "latin" "benefit" "fran" "polit"
## [6,] "will" "obamacar" "say" "fund" "mali" "kremlin"
## [7,] "flight" "exchang" "govern" "will" "left" "moscow"
## [8,] "take" "like" "agricultur" "retir" "socialist" "soviet"
## [9,] "dubai" "cost" "land" "year" "now" "also"
## [10,] "plane" "mani" "brazilian" "detroit" "presid" "now"
## Topic 100 Topic 37 Topic 38 Topic 3 Topic 6 Topic 17
## [1,] "mine" "turkey" "india" "israel" "japan" "north"
## [2,] "make" "erdogan" "indian" "iran" "abe" "south"
## [3,] "gold" "yet" "say" "isra" "japanes" "korea"
## [4,] "world" "say" "state" "palestinian" "new" "park"
## [5,] "high" "includ" "year" "arab" "say" "korean"
## [6,] "year" "turkish" "delhi" "west" "tokyo" "nuclear"
## [7,] "wast" "smoke" "run" "middl" "minist" "kim"
## [8,] "miner" "may" "congress" "east" "countri" "regim"
## [9,] "steel" "world" "now" "iranian" "prime" "state"
## [10,] "littl" "troubl" "yet" "state" "now" "test"
As one can see in the most common topics; economics, finance, business, politics top the list.
econ.3 = read.csv("/users/sweiss/google drive/economistdata.csv")
respons.vars = paste(1:100)
theta.econ = cbind(econ.3[, 1:3], theta)
date.theta.agg = aggregate(x = theta.econ[respons.vars], by = theta.econ["Date"],
FUN = mean)
date.theta.agg$Month <- factor(date.theta.agg$Date, levels = date.theta.agg$Date[!duplicated(date.theta.agg$Date)])
date.theta.agg[, 1] = as.Date(date.theta.agg[, 1])
library(scales)
library(ggplot2)
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 68])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Syrian Civil War' Topic include words: syria,rebel,war,assad,regim") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
Syrian Civil War 'peaked' in May/June. Since then the percentage of articles attributed to this topic has declined. After it became clear that USA, France, and UK were not going to intervene militarily, there were fewer articles written on the topic.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 32])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Euro Crisis' Topic include words: euro,zone,spain,european,bail") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
Euro Crisis was with us the entire year…looks like this can continue on next year too!
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 29])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Protests' Topic include words: protest,street,govern,call,police") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
Protest topic was very high in June/July because of the Brazillian Protests and Turkish Protests. Sharp increase in final weeks of year of this topic from Thailand and even (gasp!) Singapore.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 61])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Obama Care' Topic include words: insur,health,care,plan,obamaca") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
Obama Care topic increased in end of year due to botched introduction of healthcare website.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 96])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Internet' Topic include words: use,online,data,internet,social") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
Finally, the Internet topic showed a strong decline ovoer the past year despite events like Twitter IPO. Perhaps this is an indication that social networks and internet are becoming so ubiquitious, its simply not news anymore.
library(topicmodels)
load("/users/sweiss/google drive/ld100.Rda")
theta = posterior(ld.100)$topics
theta.average = colMeans(theta)
top.5.factors = names(sort(theta.average, decreasing = TRUE))
terms(ld.100, 10)[, as.numeric(top.5.factors)]
## Topic 50 Topic 16 Topic 62 Topic 90 Topic 83
## [1,] "price" "elect" "scienc" "bank" "minist"
## [2,] "rate" "parti" "cell" "financi" "govern"
## [3,] "economist" "vote" "research" "loan" "polit"
## [4,] "index" "polit" "found" "capit" "prime"
## [5,] "market" "voter" "technolog" "lend" "parti"
## [6,] "econom" "poll" "one" "credit" "parliament"
## [7,] "exchang" "seat" "human" "deposit" "opposit"
## [8,] "commod" "candid" "brain" "financ" "leader"
## [9,] "interest" "win" "look" "asset" "elect"
## [10,] "job" "campaign" "univers" "regul" "coalit"
## Topic 46 Topic 64 Topic 52 Topic 66 Topic 30
## [1,] "market" "number" "billion" "presid" "republican"
## [2,] "firm" "year" "compani" "polit" "obama"
## [3,] "product" "sinc" "firm" "elect" "senat"
## [4,] "industri" "increas" "share" "power" "democrat"
## [5,] "sale" "rise" "busi" "presidenti" "congress"
## [6,] "manufactur" "rate" "profit" "year" "hous"
## [7,] "make" "fall" "deal" "govern" "state"
## [8,] "profit" "accord" "buy" "constitut" "polit"
## [9,] "busi" "quarter" "sharehold" "last" "barack"
## [10,] "cost" "averag" "stake" "countri" "presid"
## Topic 20 Topic 24 Topic 54 Topic 67 Topic 27 Topic 74
## [1,] "economi" "rate" "group" "syria" "will" "use"
## [2,] "growth" "inflat" "govern" "rebel" "may" "system"
## [3,] "econom" "bank" "armi" "war" "year" "can"
## [4,] "gdp" "polici" "peac" "assad" "hope" "work"
## [5,] "invest" "central" "pakistan" "regim" "alreadi" "one"
## [6,] "year" "currenc" "kill" "weapon" "get" "make"
## [7,] "account" "market" "polit" "iraq" "next" "way"
## [8,] "quarter" "fed" "violenc" "syrian" "expect" "machin"
## [9,] "export" "economi" "war" "libya" "think" "design"
## [10,] "spend" "reserv" "attack" "forc" "far" "problem"
## Topic 49 Topic 22 Topic 96 Topic 48 Topic 78 Topic 25
## [1,] "citi" "parti" "fund" "firm" "one" "polic"
## [2,] "local" "polit" "investor" "compani" "may" "crime"
## [3,] "mayor" "leader" "return" "busi" "might" "prison"
## [4,] "town" "power" "invest" "consult" "like" "drug"
## [5,] "area" "member" "asset" "industri" "way" "say"
## [6,] "council" "politician" "equiti" "big" "can" "crimin"
## [7,] "resid" "call" "manag" "servic" "whether" "jail"
## [8,] "centr" "nation" "share" "client" "even" "sentenc"
## [9,] "street" "offici" "stock" "work" "question" "murder"
## [10,] "build" "chief" "money" "say" "littl" "gun"
## Topic 31 Topic 21 Topic 26 Topic 77 Topic 61 Topic 40
## [1,] "euro" "investig" "labour" "mobil" "year" "year"
## [2,] "zone" "charg" "britain" "technolog" "day" "last"
## [3,] "spain" "alleg" "cameron" "phone" "week" "two"
## [4,] "european" "claim" "tori" "appl" "april" "ago"
## [5,] "bail" "case" "parti" "comput" "month" "five"
## [6,] "europ" "trial" "conserv" "servic" "last" "past"
## [7,] "greec" "report" "miliband" "oper" "may" "month"
## [8,] "countri" "scandal" "mps" "googl" "time" "four"
## [9,] "ireland" "accus" "david" "network" "said" "three"
## [10,] "cyprus" "former" "polit" "softwar" "june" "end"
## Topic 33 Topic 5 Topic 11 Topic 23 Topic 15 Topic 80 Topic 29
## [1,] "can" "cut" "court" "money" "britain" "china" "long"
## [2,] "make" "spend" "law" "cost" "british" "chines" "time"
## [3,] "world" "budget" "case" "pay" "london" "offici" "term"
## [4,] "peopl" "billion" "legal" "billion" "england" "beij" "like"
## [5,] "argu" "year" "right" "fee" "kingdom" "hong" "big"
## [6,] "think" "deficit" "rule" "year" "unit" "kong" "run"
## [7,] "one" "govern" "judg" "use" "briton" "shanghai" "also"
## [8,] "like" "fiscal" "lawyer" "paid" "english" "even" "less"
## [9,] "good" "will" "suprem" "charg" "scotland" "also" "even"
## [10,] "idea" "tax" "justic" "payment" "servic" "yuan" "well"
## Topic 65 Topic 98 Topic 34 Topic 56 Topic 1 Topic 35
## [1,] "measur" "european" "law" "histori" "space" "road"
## [2,] "data" "europ" "rule" "mani" "one" "line"
## [3,] "suggest" "union" "regul" "yet" "mar" "car"
## [4,] "also" "countri" "bill" "war" "scienc" "train"
## [5,] "may" "commiss" "pass" "day" "technolog" "transport"
## [6,] "can" "nation" "requir" "never" "field" "rail"
## [7,] "chang" "dutch" "ban" "father" "light" "railway"
## [8,] "base" "brussel" "new" "centuri" "though" "speed"
## [9,] "differ" "germani" "propos" "old" "earth" "drive"
## [10,] "point" "franc" "control" "much" "orbit" "say"
## Topic 73 Topic 12 Topic 28 Topic 2 Topic 82 Topic 58
## [1,] "will" "project" "protest" "school" "bond" "women"
## [2,] "octob" "build" "street" "educ" "debt" "children"
## [3,] "month" "plan" "govern" "student" "rate" "age"
## [4,] "next" "will" "call" "univers" "yield" "famili"
## [5,] "novemb" "water" "polic" "teacher" "govern" "young"
## [6,] "one" "say" "day" "year" "interest" "men"
## [7,] "year" "river" "demonstr" "colleg" "market" "old"
## [8,] "first" "construct" "support" "teach" "investor" "parent"
## [9,] "said" "built" "peopl" "children" "financ" "sex"
## [10,] "septemb" "billion" "thousand" "pupil" "borrow" "child"
## Topic 86 Topic 70 Topic 97 Topic 19 Topic 95 Topic 4
## [1,] "say" "reform" "polici" "first" "use" "work"
## [2,] "mani" "will" "visit" "second" "onlin" "worker"
## [3,] "one" "chang" "also" "back" "data" "job"
## [4,] "can" "polici" "diplomat" "two" "internet" "labour"
## [5,] "peopl" "system" "leader" "canada" "can" "employ"
## [6,] "see" "plan" "presid" "time" "social" "wage"
## [7,] "languag" "new" "foreign" "made" "user" "unemploy"
## [8,] "still" "need" "two" "place" "applic" "skill"
## [9,] "want" "propos" "want" "chang" "search" "young"
## [10,] "main" "polit" "might" "now" "peopl" "low"
## Topic 44 Topic 92 Topic 69 Topic 63 Topic 81 Topic 43
## [1,] "countri" "time" "state" "chief" "govern" "peopl"
## [2,] "foreign" "test" "unit" "manag" "state" "kill"
## [3,] "world" "ask" "feder" "boss" "privat" "fire"
## [4,] "global" "experi" "governor" "execut" "public" "mani"
## [5,] "intern" "suggest" "california" "offic" "sector" "miss"
## [6,] "develop" "person" "year" "also" "offici" "now"
## [7,] "rich" "control" "texa" "job" "own" "bad"
## [8,] "emerg" "word" "san" "board" "say" "least"
## [9,] "import" "show" "one" "head" "privatis" "disast"
## [10,] "abroad" "think" "counti" "need" "local" "die"
## Topic 99 Topic 84 Topic 13 Topic 94 Topic 47
## [1,] "like" "start" "media" "america" "deal"
## [2,] "class" "busi" "televis" "american" "talk"
## [3,] "middl" "firm" "news" "unit" "negoti"
## [4,] "still" "new" "advertis" "state" "agreement"
## [5,] "well" "entrepreneur" "newspap" "washington" "two"
## [6,] "just" "ventur" "video" "nation" "agre"
## [7,] "much" "small" "show" "long" "sign"
## [8,] "better" "big" "year" "see" "side"
## [9,] "half" "founder" "time" "obama" "want"
## [10,] "part" "capit" "watch" "action" "will"
## Topic 88 Topic 89 Topic 75 Topic 18 Topic 59 Topic 45
## [1,] "secur" "forc" "africa" "shop" "poor" "muslim"
## [2,] "agenc" "militari" "african" "retail" "peopl" "egypt"
## [3,] "govern" "defenc" "south" "store" "help" "islamist"
## [4,] "secret" "armi" "countri" "busi" "poverti" "islam"
## [5,] "attack" "arm" "east" "custom" "social" "saudi"
## [6,] "say" "war" "kenya" "sell" "work" "brother"
## [7,] "intellig" "afghanistan" "nigeria" "open" "give" "morsi"
## [8,] "offici" "secur" "middl" "sale" "incom" "arab"
## [9,] "inform" "soldier" "region" "onlin" "benefit" "brotherhood"
## [10,] "spi" "drone" "say" "say" "money" "arabia"
## Topic 32 Topic 10 Topic 36 Topic 9 Topic 71 Topic 7
## [1,] "hous" "right" "new" "univers" "music" "climat"
## [2,] "price" "group" "york" "paper" "art" "chang"
## [3,] "properti" "gay" "one" "research" "film" "carbon"
## [4,] "home" "campaign" "will" "publish" "one" "warm"
## [5,] "land" "marriag" "year" "public" "show" "environment"
## [6,] "mortgag" "support" "old" "book" "man" "tree"
## [7,] "rent" "member" "two" "author" "can" "emiss"
## [8,] "new" "among" "bloomberg" "work" "now" "model"
## [9,] "valu" "liber" "boston" "studi" "cultur" "water"
## [10,] "rise" "debat" "post" "journal" "first" "global"
## Topic 8 Topic 14 Topic 79 Topic 87 Topic 51 Topic 42
## [1,] "asia" "germani" "game" "health" "trade" "immigr"
## [2,] "ship" "german" "sport" "drug" "market" "mexico"
## [3,] "australia" "mrs" "footbal" "hospit" "exchang" "say"
## [4,] "island" "merkel" "club" "care" "import" "migrant"
## [5,] "south" "green" "play" "treatment" "financi" "border"
## [6,] "sea" "berlin" "team" "cancer" "goldman" "year"
## [7,] "region" "europ" "world" "patient" "deriv" "illeg"
## [8,] "port" "social" "player" "doctor" "econom" "countri"
## [9,] "countri" "coalit" "leagu" "medic" "world" "home"
## [10,] "indonesia" "left" "can" "also" "financ" "refuge"
## Topic 85 Topic 53 Topic 91 Topic 55 Topic 68 Topic 57
## [1,] "food" "power" "oil" "black" "itali" "tax"
## [2,] "say" "energi" "gas" "mani" "church" "rais"
## [3,] "hotel" "electr" "billion" "white" "italian" "revenu"
## [4,] "one" "plant" "energi" "may" "berlusconi" "pay"
## [5,] "meat" "nuclear" "price" "like" "left" "incom"
## [6,] "drink" "wind" "reserv" "race" "christian" "financ"
## [7,] "eat" "industri" "shale" "make" "one" "rate"
## [8,] "good" "generat" "year" "stop" "cathol" "govern"
## [9,] "may" "batteri" "invest" "less" "movement" "rich"
## [10,] "consum" "renew" "new" "becom" "hous" "money"
## Topic 72 Topic 60 Topic 76 Topic 41 Topic 93 Topic 39
## [1,] "air" "insur" "brazil" "pension" "french" "russia"
## [2,] "new" "health" "year" "pay" "franc" "russian"
## [3,] "airport" "will" "farmer" "scheme" "holland" "putin"
## [4,] "fli" "care" "farm" "public" "pari" "ukrain"
## [5,] "airlin" "plan" "latin" "benefit" "fran" "polit"
## [6,] "will" "obamacar" "say" "fund" "mali" "kremlin"
## [7,] "flight" "exchang" "govern" "will" "left" "moscow"
## [8,] "take" "like" "agricultur" "retir" "socialist" "soviet"
## [9,] "dubai" "cost" "land" "year" "now" "also"
## [10,] "plane" "mani" "brazilian" "detroit" "presid" "now"
## Topic 100 Topic 37 Topic 38 Topic 3 Topic 6 Topic 17
## [1,] "mine" "turkey" "india" "israel" "japan" "north"
## [2,] "make" "erdogan" "indian" "iran" "abe" "south"
## [3,] "gold" "yet" "say" "isra" "japanes" "korea"
## [4,] "world" "say" "state" "palestinian" "new" "park"
## [5,] "high" "includ" "year" "arab" "say" "korean"
## [6,] "year" "turkish" "delhi" "west" "tokyo" "nuclear"
## [7,] "wast" "smoke" "run" "middl" "minist" "kim"
## [8,] "miner" "may" "congress" "east" "countri" "regim"
## [9,] "steel" "world" "now" "iranian" "prime" "state"
## [10,] "littl" "troubl" "yet" "state" "now" "test"
econ.3 = read.csv("/users/sweiss/google drive/economistdata.csv")
respons.vars = paste(1:100)
theta.econ = cbind(econ.3[, 1:3], theta)
date.theta.agg = aggregate(x = theta.econ[respons.vars], by = theta.econ["Date"],
FUN = mean)
date.theta.agg$Month <- factor(date.theta.agg$Date, levels = date.theta.agg$Date[!duplicated(date.theta.agg$Date)])
date.theta.agg[, 1] = as.Date(date.theta.agg[, 1])
library(scales)
library(ggplot2)
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 68])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Syrian Civil War' Topic include words: syria,rebel,war,assad,regim") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 32])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Euro Crisis' Topic include words: euro,zone,spain,european,bail") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 29])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Protests' Topic include words: protest,street,govern,call,police") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 61])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Obama Care' Topic include words: insur,health,care,plan,obamaca") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
ggplot(data = date.theta.agg, aes(x = as.Date(Date), y = date.theta.agg[, 96])) +
geom_line() + geom_smooth() + scale_x_date(breaks = "months", labels = date_format("%b-%Y")) +
ggtitle("'Internet' Topic include words: use,online,data,internet,social") +
xlab("Date (By Month)") + ylab("Average Percentage of Articles Attributed to Factor")
## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.
No comments:
Post a Comment