Plotting multiple variables using ggplot2
Duc Nguyen | Chuyên đào tạo kỹ năng R |
www.tuhocr.com
May 26, 2023
Để có dataset minh họa việc plotting line chart cho trường hợp nhiều biến, mình sẽ subset dữ liệu lúa gạo và dân số cho Việt Nam và Thái Lan từ database FAOSTAT và World Bank.
library(ggpubr)
library(ggplot2)
library(tidyr)
library(reshape2)
rice_full <- readRDS(file = "rice_ready.rds")
vietnam_rice <- rice_full |> subset(area == "Viet Nam")
thailand_rice <- rice_full |> subset(area == "Thailand")
vietnam_rice$yield <- vietnam_rice$production / vietnam_rice$area_harvested
vietnam_rice$production / 1000000 -> vietnam_rice$production
vietnam_rice$area_harvested / 1000000 -> vietnam_rice$area_harvested
thailand_rice$yield <- thailand_rice$production / thailand_rice$area_harvested
thailand_rice$production / 1000000 -> thailand_rice$production
thailand_rice$area_harvested / 1000000 -> thailand_rice$area_harvested
########
# install.packages('WDI')
# library(WDI)
# dat <- WDI(indicator = 'SP.POP.TOTL', country = c('all'))
# saveRDS(dat, file = "population_all.rds")
readRDS(file = "population_all.rds") -> dat
###################
vietnam_population <- subset(dat, country == "Vietnam")
row.names(vietnam_population) <- NULL
vietnam_population_ok <- vietnam_population[-c(1, 63), c(1, 4, 5)]
thailand_population <- subset(dat, country == "Thailand")
thailand_population_ok <- thailand_population[-c(1, 63), c(1, 4, 5)]
#########################
vietnam_rice$population <- vietnam_population_ok$SP.POP.TOTL / 1000000
thailand_rice$population <- thailand_population_ok$SP.POP.TOTL / 1000000
rbind(vietnam_rice, thailand_rice) -> df_big
df_big[, c(1, 3, 4, 5, 6, 7)] -> df_big
row.names(df_big) <- NULLTa có dataset như sau. Khi bạn muốn vẽ tương tự mình thì cũng áp dụng cùng cấu trúc dataset này.
print(df_big)## area year production area_harvested yield population
## 1 Viet Nam 2021 43.85273 7.219797 6.073956 97.46803
## 2 Viet Nam 2020 42.76500 7.222403 5.921159 96.64869
## 3 Viet Nam 2019 43.49549 7.451544 5.837111 95.77672
## 4 Viet Nam 2018 44.04625 7.570741 5.817958 94.91433
## 5 Viet Nam 2017 42.76368 7.708534 5.547577 94.03305
## 6 Viet Nam 2016 43.11201 7.734722 5.573828 93.12653
## 7 Viet Nam 2015 45.09056 7.828607 5.759717 92.19140
## 8 Viet Nam 2014 44.97421 7.816476 5.753770 91.23550
## 9 Viet Nam 2013 44.03910 7.902813 5.572585 90.26774
## 10 Viet Nam 2012 43.73760 7.761314 5.635334 89.30133
## 11 Viet Nam 2011 42.39834 7.655440 5.538329 88.34912
## 12 Viet Nam 2010 40.00560 7.489400 5.341630 87.41101
## 13 Viet Nam 2009 38.95020 7.437200 5.237213 86.48292
## 14 Viet Nam 2008 38.72980 7.400200 5.233615 85.59724
## 15 Viet Nam 2007 35.94270 7.207400 4.986916 84.76227
## 16 Viet Nam 2006 35.84950 7.324800 4.894263 83.95180
## 17 Viet Nam 2005 35.83290 7.329200 4.889060 83.14209
## 18 Viet Nam 2004 36.14890 7.445300 4.855264 82.31123
## 19 Viet Nam 2003 34.56880 7.452200 4.638738 81.47583
## 20 Viet Nam 2002 34.44720 7.504300 4.590328 80.64231
## 21 Viet Nam 2001 32.10840 7.492700 4.285291 79.81778
## 22 Viet Nam 2000 32.52950 7.666300 4.243181 79.00114
## 23 Viet Nam 1999 31.39380 7.653600 4.101834 78.12371
## 24 Viet Nam 1998 29.40814 7.350801 4.000672 77.12842
## 25 Viet Nam 1997 27.52390 7.099700 3.876769 76.05860
## 26 Viet Nam 1996 26.39670 7.003800 3.768911 74.94645
## 27 Viet Nam 1995 24.96370 6.765600 3.689798 73.75911
## 28 Viet Nam 1994 23.52830 6.598600 3.565650 72.50109
## 29 Viet Nam 1993 22.83660 6.559400 3.481507 71.17641
## 30 Viet Nam 1992 21.59030 6.475400 3.334204 69.78875
## 31 Viet Nam 1991 19.62190 6.302700 3.113254 68.35882
## 32 Viet Nam 1990 19.22510 6.042800 3.181489 66.91261
## 33 Viet Nam 1989 18.99630 5.911200 3.213612 65.46636
## 34 Viet Nam 1988 17.00000 5.740800 2.961260 64.03751
## 35 Viet Nam 1987 15.10260 5.603100 2.695401 62.63079
## 36 Viet Nam 1986 16.00290 5.703100 2.806000 61.22111
## 37 Viet Nam 1985 15.87480 5.718300 2.776140 59.81131
## 38 Viet Nam 1984 15.50560 5.675000 2.732264 58.40686
## 39 Viet Nam 1983 14.74330 5.611700 2.627243 57.01144
## 40 Viet Nam 1982 14.39020 5.711700 2.519425 55.63215
## 41 Viet Nam 1981 12.41520 5.651900 2.196642 54.28039
## 42 Viet Nam 1980 11.64740 5.600200 2.079819 52.96827
## 43 Viet Nam 1979 11.36290 5.485200 2.071556 51.83139
## 44 Viet Nam 1978 9.78990 5.462500 1.792201 50.70146
## 45 Viet Nam 1977 10.59710 5.468700 1.937773 49.41815
## 46 Viet Nam 1976 11.82720 5.297300 2.232685 48.16357
## 47 Viet Nam 1975 10.29360 4.855900 2.119813 46.96962
## 48 Viet Nam 1974 11.02329 5.111920 2.156389 45.89870
## 49 Viet Nam 1973 11.12500 5.030000 2.211730 44.89128
## 50 Viet Nam 1972 10.74820 4.900000 2.193510 43.90602
## 51 Viet Nam 1971 10.44700 4.692100 2.226508 42.91662
## 52 Viet Nam 1970 10.17330 4.724400 2.153353 41.92885
## 53 Viet Nam 1969 8.81500 4.930000 1.788032 41.01586
## 54 Viet Nam 1968 8.36615 4.893800 1.709541 40.14529
## 55 Viet Nam 1967 9.18840 4.795800 1.915926 39.28256
## 56 Viet Nam 1966 8.46350 4.681300 1.807938 38.38821
## 57 Viet Nam 1965 9.36970 4.826300 1.941384 37.46608
## 58 Viet Nam 1964 9.69703 4.987800 1.944150 36.50917
## 59 Viet Nam 1963 9.62267 4.496520 2.140026 35.52673
## 60 Viet Nam 1962 9.74704 4.888860 1.993725 34.53389
## 61 Viet Nam 1961 8.99740 4.744000 1.896585 33.62198
## 62 Thailand 2021 33.58200 11.244000 2.986660 71.60110
## 63 Thailand 2020 30.23102 10.401653 2.906367 71.47566
## 64 Thailand 2019 28.61795 9.812614 2.916445 71.30776
## 65 Thailand 2018 32.34811 10.647941 3.037969 71.12780
## 66 Thailand 2017 32.89890 10.719698 3.069014 70.89820
## 67 Thailand 2016 31.85700 10.734279 2.967782 70.60704
## 68 Thailand 2015 27.70219 9.717975 2.850614 70.29440
## 69 Thailand 2014 32.62016 10.664923 3.058640 69.96094
## 70 Thailand 2013 36.76228 11.684315 3.146293 69.57860
## 71 Thailand 2012 38.10019 11.956781 3.186492 69.15702
## 72 Thailand 2011 38.10272 11.956638 3.186742 68.71285
## 73 Thailand 2010 35.70295 11.932320 2.992121 68.27049
## 74 Thailand 2009 32.39786 11.141447 2.907868 67.81365
## 75 Thailand 2008 32.02299 10.683549 2.997411 67.32824
## 76 Thailand 2007 32.47703 10.668905 3.044083 66.82675
## 77 Thailand 2006 29.99060 10.165155 2.950334 66.31952
## 78 Thailand 2005 30.64825 10.224967 2.997393 65.82136
## 79 Thailand 2004 28.87398 9.992868 2.889458 65.31117
## 80 Thailand 2003 29.82027 10.163878 2.933946 64.77696
## 81 Thailand 2002 28.32114 9.653534 2.933758 64.22258
## 82 Thailand 2001 29.09991 10.125424 2.873945 63.64989
## 83 Thailand 2000 25.84388 9.891200 2.612815 63.06660
## 84 Thailand 1999 24.17141 9.969920 2.424434 62.44265
## 85 Thailand 1998 22.99841 9.511520 2.417954 61.74522
## 86 Thailand 1997 23.58008 9.912790 2.378753 60.98911
## 87 Thailand 1996 22.33164 9.267200 2.409750 60.21110
## 88 Thailand 1995 22.01548 9.112951 2.415845 59.42483
## 89 Thailand 1994 21.11071 8.975229 2.352109 58.61001
## 90 Thailand 1993 18.44726 9.000000 2.049696 57.77608
## 91 Thailand 1992 19.91730 9.159680 2.174454 56.93902
## 92 Thailand 1991 20.40000 9.052960 2.253407 56.09987
## 93 Thailand 1990 17.19322 8.791885 1.955578 55.22841
## 94 Thailand 1989 20.60101 9.879040 2.085325 54.32400
## 95 Thailand 1988 21.26290 9.905932 2.146481 53.41096
## 96 Thailand 1987 18.42827 9.147076 2.014663 52.47918
## 97 Thailand 1986 18.86816 9.194021 2.052221 51.54209
## 98 Thailand 1985 20.26387 9.833074 2.060787 50.59494
## 99 Thailand 1984 19.90482 9.629710 2.067021 49.63672
## 100 Thailand 1983 19.54894 9.606013 2.035074 48.67057
## 101 Thailand 1982 16.87851 8.940017 1.887973 47.70034
## 102 Thailand 1981 17.77432 9.105026 1.952144 46.72729
## 103 Thailand 1980 17.36810 9.200080 1.887820 45.73775
## 104 Thailand 1979 15.75800 8.654000 1.820892 44.76009
## 105 Thailand 1978 17.47000 8.935000 1.955232 43.80671
## 106 Thailand 1977 13.92100 8.750000 1.590971 42.84380
## 107 Thailand 1976 15.06800 8.167000 1.844986 41.88213
## 108 Thailand 1975 15.30000 8.357000 1.830801 40.90847
## 109 Thailand 1974 13.38600 7.333000 1.825447 39.90096
## 110 Thailand 1973 14.89900 7.743000 1.924190 38.87306
## 111 Thailand 1972 12.41300 6.780000 1.830826 37.83438
## 112 Thailand 1971 13.74400 7.096000 1.936866 36.80800
## 113 Thailand 1970 13.85000 6.854000 2.020718 35.79173
## 114 Thailand 1969 13.41000 7.259000 1.847362 34.78758
## 115 Thailand 1968 12.41000 6.940000 1.788184 33.80736
## 116 Thailand 1967 11.19800 6.400000 1.749688 32.83934
## 117 Thailand 1966 13.50000 7.353000 1.835985 31.88375
## 118 Thailand 1965 11.16400 6.270000 1.780542 30.94027
## 119 Thailand 1964 11.60000 6.310000 1.838352 30.01357
## 120 Thailand 1963 12.17100 6.500000 1.872462 29.11412
## 121 Thailand 1962 11.25000 6.540000 1.720183 28.24217
## 122 Thailand 1961 10.15000 6.120000 1.658497 27.39996Xử lý dataset để thành dạng phù hợp vẽ đồ thị. Code vẽ đồ thị này mình cũng tham khảo mỗi nguồn một ít để tổng hợp thành file hoàn chỉnh như bạn đã thấy.
names(df_big) <- c("area", "year", "d_production", "c_area_harvested", "b_yield", "a_population")
# df_big
###########################
# https://scc.ms.unimelb.edu.au/resources/tips-for-using-r/r-scripts
# https://waterdata.usgs.gov/blog/beyond-basic-plotting/
# https://www.datanovia.com/en/blog/how-to-change-ggplot-facet-labels/
longer_data <- df_big %>%
pivot_longer(d_production:a_population, names_to = "value_data", values_to = "response")
longer_data$note_1 <- "Khủng hoảng\nkinh tế 1997"
clean_1 <- longer_data |> subset(value_data == "a_population")
clean_1$note_1 <- ""
clean_2 <- longer_data |> subset(value_data == "b_yield")
clean_2$note_1 <- ""
clean_3 <- longer_data |> subset(value_data == "c_area_harvested")
clean_3$note_1 <- ""
clean_4 <- longer_data |> subset(value_data == "d_production")
gop_lai <- rbind(clean_1, clean_2, clean_3, clean_4)
gop_lai -> longer_data
longer_data$area <- factor(longer_data$area,
levels = c("Viet Nam", "Thailand"),
labels = c("Việt Nam", "Thái Lan"))
supp.labs <- c("Sản lượng \n(triệu tấn)", "Diện tích canh tác \n(triệu ha)", "Năng suất \n(tấn/ha)",
"Dân số \n(triệu người)")
names(supp.labs) <- names(df_big)[3:6]
rice_plot <- ggplot(data = na.omit(longer_data), aes(x = year, y = response,
color = area, group = area)) +
geom_point(aes(color = area, shape = area), size = 1.5) +
scale_shape_manual(values = c(19, 22)) +
scale_x_continuous(breaks = c(1961, 1970, 1980, 1990, 1997, 1999, 2010, 2021)) +
geom_line(aes(color = area)) +
scale_color_manual(values=c("#ff4b66", "#0b3173")) +
facet_grid(scales = "free_y",
# cols = vars(value_data),
rows = vars(value_data),
labeller = labeller(value_data = supp.labs),
switch = "both"
) +
labs(x = "", y = "", title = "Tình hình sản xuất lúa gạo ở Việt Nam và Thái Lan | Dữ liệu FAOSTAT | Đồ thị: tuhocr.com") +
theme_bw() +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank()) +
theme(strip.background = element_blank(), # remove the background
strip.placement = "outside") +
theme(legend.position="top",
legend.title = element_blank(),
legend.text = element_text(size = 11, colour = "#261d3b", face = "bold")) +
theme(
# strip.text.x = element_text(
# size = 9, color = "red", face = "bold"
# ),
strip.text.y = element_text(
size = 10, color = "darkgreen", face = "bold"
)
) +
# coord_flip() +
theme(axis.text = element_text(colour = "black",
size = 8,
face = "bold"),
plot.title = element_text(size = 12, colour = "black", face = "bold", hjust = 0.5)) +
theme(plot.margin = margin(t = 0.5, r = 0.5, b = 0.5, l = 0.5, "cm")) +
annotate("rect", xmin = 1997, xmax = 1999,
ymin = -Inf,
ymax = +Inf,
alpha = 0.1,
fill = "blue")
############
# https://stackoverflow.com/questions/26371307/add-text-to-individual-facets-in-ggplot
# rice_plot + geom_text(aes(x = 1997, y = 30, label = note_1),
# show.legend = FALSE, size = 4)
rice_plot + geom_text(data = longer_data,
mapping = aes(x = 1997, y = Inf, label = note_1),
hjust = "middle",
vjust = 1.5,
show.legend = FALSE,
color = "#a10800")
# ggsave("four_plot_rice_v11.png", width = 30, height = 20, units = "cm", dpi = 300)Sơ kết
Trên đây là hướng dẫn vẽ đồ thị đa biến sử dụng package ggplot2. Để học R bài bản từ A đến Z, thân mời Bạn tham gia khóa học “HDSD R để xử lý dữ liệu” để có nền tảng vững chắc về R nhằm tự tay làm các câu chuyện dữ liệu của riêng mình!
ĐĂNG KÝ NGAY:
https://www.tuhocr.com/register
