Рисование графика уклона в R с использованием ggplot, Ошибка: Эстетика должна быть либо длины 1, либо совпадать с данными
Я хочу создать график уклона в R, как это, используя ggplot https://rud.is/b/2013/01/11/slopegraphs-in-r/
после очистки данных и расплавления фрейма данных я столкнулся с ошибкой, подобной этой: Ошибка: эстетика должна быть либо длины 1, либо такой же, как данные (182): x, y, группа, цвет, метка
В моих данных нет NA. Есть идеи? Очень признателен!
Вот код
#Read file as numeric data
betterlife<-read.csv("betterlife.csv",skip=4,stringsAsFactors = F)
num_data <- data.frame(data.matrix(betterlife))
numeric_columns <- sapply(num_data,function(x){mean(as.numeric(is.na(x)))<0.5})
final_data <- data.frame(num_data[,numeric_columns],
betterlife[,!numeric_columns])
## rescale selected columns data frame
final_data <- data.frame(lapply(final_data[,c(3,4,5,6,7,10,11)], function(x) scale(x, center = FALSE, scale = max(x, na.rm = TRUE)/100)))
## Add country names as indicator
final_data["INDICATOR"] <- NA
final_data$INDICATOR <- betterlife$INDICATOR
employment.data <- final_data[5:30,]
indicator <- employment.data$INDICATOR
## Melt data to draw graph
employment.melt <- melt(employment.data)
#plot
sg = ggplot(employment.melt, aes(factor(variable), value,
group = indicator,
colour = indicator,
label = indicator)) +
theme(legend.position = "none",
axis.text.x = element_text(size=5),
axis.text.y=element_blank(),
axis.title.x=element_blank(),
axis.title.y=element_blank(),
axis.ticks=element_blank(),
axis.line=element_blank(),
panel.grid.major.x = element_line("black", size = 0.1),
panel.grid.major.y = element_blank(),
panel.grid.minor.y = element_blank(),
panel.background = element_blank())
sg1
Это данные, с которыми я работаю
dput(Betterlife)
structure(list(X = c("", "ISO3", "AUS", "AUT", "BEL", "CAN",
"CHL", "CZE", "DNK", "EST", "FIN", "FRA", "DEU", "GRC", "HUN",
"ISL", "IRL", "ISR", "ITA", "JPN", "KOR", "LUX", "MEX", "NLD",
"NZL", "NOR", "POL", "PRT", "SVK", "SVN", "ESP", "SWE", "CHE",
"TUR", "GBR", "USA", "OECD", "", ""),
INDICATOR = c("UNIT", "COUNTRY",
"Australia", "Austria", "Belgium", "Canada", "Chile", "Czech Republic",
"Denmark", "Estonia", "Finland", "France", "Germany", "Greece",
"Hungary", "Iceland", "Ireland", "Israel", "Italy", "Japan",
"Korea", "Luxembourg", "Mexico", "Netherlands", "New Zealand",
"Norway", "Poland", "Portugal", "Slovak Republic", "Slovenia",
"Spain", "Sweden", "Switzerland", "Turkey", "United Kingdom",
"United States", "OECD average", "", "n.a. : not available"),
Rooms.per.person = c("Average number of rooms shared per person in a dwelling",
"", "2.4", "1.7", "2.3", "2.5", "1.3", "1.3", "1.9", "1.2",
"1.9", "1.8", "1.7", "1.2", "1", "1.6", "2.1", "1.1", "1.4",
"1.8", "1.3", "1.9", "1.566666667", "2", "2.3", "1.9", "1",
"1.5", "1.1", "1.1", "1.9", "1.8", "1.7", "0.7", "1.8", "1.605208333",
"1.6", "", ""),
Dwelling.without.basic.facilities = c("% of people without indoor flushing toilets in their home",
"", "3.425714286", "1.3", "0.6", "2.722", "9.36", "0.7",
"0", "12.2", "0.8", "0.8", "1.2", "1.8", "7.1", "0.3", "0.3",
"2.52", "0.2", "6.4", "7.46", "0.8", "6.6", "0", "2.984285714",
"0.1", "4.8", "2.4", "1.1", "0.6", "0", "0", "0.1", "17.1",
"0.5", "0", "2.82", "", ""),
Household.disposable.income = c("USD (PPPs adjusted)",
"", "27,039", "27,670", "26,008", "27,015", "8,712", "16,690",
"22,929", "13,486", "24,246", "27,508", "27,665", "21,499",
"13,858", "19,621", "24,313", "22,539", "24,383", "23,210",
"16,254", "19,621", "12,182", "25,977", "18,819", "29,366",
"13,811", "18,540", "15,490", "19,890", "22,972", "26,543",
"27,542", "21,030", "27,208", "37,685", "22,284", "", ""),
Employment.rate = c("% of the working age population (15-64)",
"", "72.3", "71.73", "62.01", "71.68", "59.32", "65", "73.44",
"61.02", "68.15", "63.99", "71.1", "59.55", "55.4", "78.17",
"59.96", "59.21", "56.89", "70.11", "63.31", "65.21", "60.39",
"74.67", "72.34", "75.31", "59.26", "65.55", "58.76", "66.2",
"58.55", "72.73", "78.59", "46.29", "69.51", "66.71", "64.52",
"", ""),
Long.term.unemployment.rate = c("% of people, aged 15-64, who are not working but have been actively seeking a job for over a year",
"", "1", "1.13", "4.07", "0.97", "2.98375", "3.19", "1.44",
"7.84", "2.01", "3.75", "3.4", "5.73", "5.68", "1.35", "6.74",
"1.85", "4.13", "1.99", "0.01", "1.29", "0.13", "1.24", "0.6",
"0.34", "2.49", "5.97", "8.56", "3.21", "9.1", "1.42", "1.49",
"3.11", "2.59", "2.85", "2.74", "", ""),
Quality.of.support.network = c("% of people who have friends or relatives to rely on in case of need",
"", "95.4", "94.6", "92.6", "95.3", "85.2", "88.9", "96.8",
"84.6", "93.4", "93.9", "93.5", "86.1", "88.6", "97.6", "97.3",
"93", "86", "89.7", "79.8", "95", "87.1", "94.8", "97.1",
"93.1", "92.2", "83.3", "89.6", "90.7", "94.1", "96.2", "93.2",
"78.8", "94.9", "92.3", "91.1", "", ""),
Educational.attainment = c("% of people, aged 15-64, having at least an upper-secondary (high-school) degree",
"", "69.72", "81.04", "69.58", "87.07", "67.97", "90.9",
"74.56", "88.48", "81.07", "69.96", "85.33", "61.07", "79.7",
"64.13", "69.45", "81.23", "53.31", "87", "79.14", "67.94",
"33.55", "73.29", "72.05", "80.7", "87.15", "28.25", "89.93",
"82.04", "51.23", "85.04", "86.81", "30.31", "69.63", "88.7",
"72.95", "", ""),
Students.reading.skills = c("Average reading performance of students aged 15, according to PISA",
"", "515", "470", "506", "524", "449", "478", "495", "501",
"536", "496", "497", "483", "494", "500", "496", "474", "486",
"520", "539", "472", "425", "508", "521", "503", "500", "489",
"477", "483", "481", "497", "501", "464", "494", "500", "493",
"", ""),
Air.pollution = c("Average concentration of particulate matter (PM10) in cities with population larger than 100 000, measured in micrograms per cubic meter",
"", "14.28", "29.03", "21.27", "15", "61.55", "18.5", "16.26",
"12.62", "14.87", "12.94", "16.21", "32", "15.6", "14.47",
"12.54", "27.57", "23.33", "27.14", "30.76", "12.63", "32.69",
"30.76", "11.93", "15.85", "35.07", "21", "13.14", "29.03",
"27.56", "10.52", "22.36", "37.06", "12.67", "19.4", "21.99",
"", ""),
Consultation.on.rule.making = c("Composite index, increasing with the number of key elements of formal consultation processes",
"", "10.5", "7.13", "4.5", "10.5", "2", "6.75", "7", "3.25",
"9", "3.5", "4.5", "6.5", "7.88", "5.13", "9", "2.5", "5",
"7.25", "10.38", "6", "9", "6.13", "10.25", "8.13", "10.75",
"6.5", "6.63", "10.25", "7.25", "10.88", "8.38", "5.5", "11.5",
"8.25", "7.28", "", ""),
Voter.turnout = c("Number of people voting as % of the registered population ",
"", "95", "82", "91", "60", "88", "64", "87", "62", "74",
"84", "78", "74", "64", "84", "67", "65", "81", "67", "63",
"57", "59", "80", "79", "77", "54", "64", "55", "63", "75",
"82", "48", "84", "61", "90", "72", "", ""),
Life.expectancy = c("Average number of years a person can expect to live",
"", "81.5", "80.5", "79.8", "80.7", "77.8", "77.3", "78.8",
"73.9", "79.9", "81", "80.2", "80", "73.8", "81.3", "79.9",
"81.1", "81.5", "82.7", "79.9", "80.6", "75.1", "80.2", "80.4",
"80.6", "75.6", "79.3", "74.8", "78.8", "81.2", "81.2", "82.2",
"73.6", "79.7", "77.9", "79.2", "", ""),
Self.reported.health = c("% of people reporting their health to be \"good or very good\"",
"", "84.9", "69.6", "76.7", "88.1", "56.2", "68.2", "74.3",
"56.3", "67.7", "72.4", "64.7", "76.4", "55.2", "80.6", "84.4",
"79.7", "63.4", "32.7", "43.7", "74", "65.5", "80.6", "89.7",
"80", "57.7", "48.6", "31.1", "58.8", "69.8", "79.1", "80.95",
"66.8", "76", "88", "69", "", ""),
Life.Satisfaction = c("Average self-evaluation of life satisfaction, on a scale from 0 to 10",
"", "7.5", "7.3", "6.9", "7.7", "6.6", "6.2", "7.8", "5.1",
"7.4", "6.8", "6.7", "5.8", "4.7", "6.9", "7.3", "7.4", "6.4",
"6.1", "6.1", "7.1", "6.8", "7.5", "7.2", "7.6", "5.8", "4.9",
"6.1", "6.1", "6.2", "7.5", "7.5", "5.5", "7", "7.2", "6.7",
"", ""),
Homicide.rate = c("Average number of reported homicides per 100 000 people",
"", "1.2", "0.5", "1.8", "1.7", "8.1", "2", "1.4", "6.3",
"2.5", "1.4", "0.8", "1.1", "1.5", "0", "2", "2.4", "1.2",
"0.5", "2.3", "1.5", "11.6", "1", "1.3", "0.6", "1.2", "1.2",
"1.7", "0.5", "0.9", "0.9", "0.7", "2.9", "2.6", "5.2", "2.1",
"", ""),
Assault.rate = c("% of people who report having been assaulted in the previous year",
"", "2.1", "3", "7.3", "1.4", "9.5", "3.5", "3.9", "6.2",
"2.4", "4.9", "3.6", "3.8", "3.8", "2.7", "2.7", "3.1", "4.7",
"1.6", "2.1", "4.3", "14.8", "5", "2.3", "3.3", "2.2", "6.2",
"3.5", "3.9", "4.2", "5.2", "4.2", "6", "1.9", "1.6", "4.1",
"", "")),
.Names = c("X", "INDICATOR", "Rooms.per.person", "Dwelling.without.basic.facilities",
"Household.disposable.income", "Employment.rate",
"Long.term.unemployment.rate", "Quality.of.support.network",
"Educational.attainment", "Students.reading.skills", "Air.pollution",
"Consultation.on.rule.making", "Voter.turnout", "Life.expectancy",
"Self.reported.health", "Life.Satisfaction", "Homicide.rate",
"Assault.rate"), class = "data.frame", row.names = c(NA, -39L))
Я неправильно переплавил фрейм данных? так как индекс каждой строки не в правильном порядке