AS7-0A ggplot2 繪圖套件

Sys.setlocale("LC_ALL","C")

[1] "C/C/C/C/C/en_US.UTF-8"

packages = c(
  "dplyr","ggplot2","d3heatmap","googleVis","devtools","plotly", "xgboost",
  "magrittr","caTools","ROCR","corrplot", "rpart", "rpart.plot",
  "doParallel", "caret", "glmnet", "Matrix", "e1071", "randomForest",
  "flexclust", "FactoMineR", "factoextra", "maps", "ggmap", "igraph", "rgl",
  "tm", "SnowballC", "wordcloud", "slam", "Matrix", "RColorBrewer"
  )
existing = as.character(installed.packages()[,1])
for(pkg in packages[!(packages %in% existing)]) install.packages(pkg)

rm(list=ls(all=T))
options(digits=4, scipen=12)
library(dplyr)
library(ggplot2)
library(maps)
library(ggmap)

---

7.1 ggplot2 繪圖套件

7.1.1 基本點狀圖

WHO <- read.csv("data/WHO.csv")
str(WHO)

'data.frame':   194 obs. of  13 variables:
 $ Country                      : Factor w/ 194 levels "Afghanistan",..: 1 2 3 4 5 6 7 8 9 10 ...
 $ Region                       : Factor w/ 6 levels "Africa","Americas",..: 3 4 1 4 1 2 2 4 6 4 ...
 $ Population                   : int  29825 3162 38482 78 20821 89 41087 2969 23050 8464 ...
 $ Under15                      : num  47.4 21.3 27.4 15.2 47.6 ...
 $ Over60                       : num  3.82 14.93 7.17 22.86 3.84 ...
 $ FertilityRate                : num  5.4 1.75 2.83 NA 6.1 2.12 2.2 1.74 1.89 1.44 ...
 $ LifeExpectancy               : int  60 74 73 82 51 75 76 71 82 81 ...
 $ ChildMortality               : num  98.5 16.7 20 3.2 163.5 ...
 $ CellularSubscribers          : num  54.3 96.4 99 75.5 48.4 ...
 $ LiteracyRate                 : num  NA NA NA NA 70.1 99 97.8 99.6 NA NA ...
 $ GNI                          : num  1140 8820 8310 NA 5230 ...
 $ PrimarySchoolEnrollmentMale  : num  NA NA 98.2 78.4 93.1 91.1 NA NA 96.9 NA ...
 $ PrimarySchoolEnrollmentFemale: num  NA NA 96.4 79.4 78.2 84.5 NA NA 97.5 NA ...

# Basic Plot in R 
plot(WHO$GNI, WHO$FertilityRate)

library(ggplot2)
# Create the ggplot object with the data and the aesthetic mapping:
scatterplot <- ggplot(WHO, aes(x = GNI, y = FertilityRate))
# ggplot2的建置方式：先建好原始模型，後續可疊加成不同類型的圖表

# Add the geom_point geometry
scatterplot + geom_point()   # 點圖

# geopoint: 畫點圖的指令
# 底圖scatterplot都不要動

# Make a line graph instead:
scatterplot + geom_line()   # 折線圖

# Switch back to our points:
scatterplot + geom_point()   # 點圖

# Redo the plot with blue triangles instead of circles:
scatterplot + geom_point(color = "blue", size = 3, shape = 21)

# 點圖+顏色/大小/形狀

# Another option:
scatterplot + geom_point(color = "darkred", size = 3, shape = 8)

# 點圖+顏色(暗紅色)/大小/形狀

# Add a title to the plot:
scatterplot + 
  geom_point(colour = "blue", size = 3, shape = 17) + 
  ggtitle("Fertility Rate vs. Gross National Income")

7.1.2 儲存圖檔

# Save our plot:
fertilityGNIplot <- scatterplot + 
  geom_point(colour = "blue", size = 3, shape = 17) + 
  ggtitle("Fertility Rate vs. Gross National Income")      # 加標題
# 儲存所做的圖片到fertilityGNIplot
pdf("MyPlot.pdf")
# 將圖片存成pdf
print(fertilityGNIplot)
dev.off()

null device 
          1 

7.1.3 圖形元件屬性

# Color the points by region:
ggplot(WHO, aes(x = GNI, y = FertilityRate, color = Region)) + 
  geom_point()

# 點的「大小」、「形狀」...都可以當成一個繪圖的屬性

# Color the points according to life expectancy:
ggplot(WHO, aes(x = GNI, y = FertilityRate, color = LifeExpectancy)) + 
  geom_point()

# LifeExpectancy：連續變數，可用顏色深淺表示

# Is the fertility rate of a country was a good predictor of the 
# percentage of the population under 15?
ggplot(WHO, aes(x = FertilityRate, y = Under15)) + geom_point()

7.1.4 數值尺度比例轉換

# Let's try a log transformation:
ggplot(WHO, aes(x = log(FertilityRate), y = Under15)) + geom_point()

# 有點歪、不是線性的圖形  >>  可以取log，這樣變數之間就會變成線性關係

7.1.5 回歸趨勢線

# Simple linear regression model to predict the percentage of the 
# population under 15, using the log of the fertility rate:
mod <- lm(Under15 ~ log(FertilityRate), data = WHO)
summary(mod)

Call:
lm(formula = Under15 ~ log(FertilityRate), data = WHO)

Residuals:
    Min      1Q  Median      3Q     Max 
-10.313  -1.774   0.045   1.744   7.717 

Coefficients:
                   Estimate Std. Error t value Pr(>|t|)    
(Intercept)           7.654      0.448    17.1   <2e-16 ***
log(FertilityRate)   22.055      0.418    52.8   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 2.65 on 181 degrees of freedom
  (11 observations deleted due to missingness)
Multiple R-squared:  0.939, Adjusted R-squared:  0.939 
F-statistic: 2.79e+03 on 1 and 181 DF,  p-value: <2e-16

# Add this regression line to our plot:
ggplot(WHO, aes(x = log(FertilityRate), y = Under15)) + 
  geom_point() + stat_smooth(method = "lm")

# ggplot的原則：有一張底圖，想要什麼再加上去就可以了

7.1.6 趨勢線的信賴區間

# 99% confidence interval
ggplot(WHO, aes(x = log(FertilityRate), y = Under15)) + 
  geom_point() + stat_smooth(method = "lm", level = 0.99)

# Level:信賴區間（Confidence Interval）族群平均有99％會掉在CI」範圍內

# No confidence interval in the plot
ggplot(WHO, aes(x = log(FertilityRate), y = Under15)) + 
  geom_point() + stat_smooth(method = "lm", se = FALSE)

# Change the color of the regression line:
ggplot(WHO, aes(x = log(FertilityRate), y = Under15)) + 
  geom_point() + stat_smooth(method = "lm", colour = "orange")

7.1.7 分群點狀圖

# quiz-1:
ggplot(WHO, aes(x = FertilityRate, y = Under15, col=Region)) + 
  scale_color_brewer(palette="Accent") +
  geom_point()

# 所有資料化成一張圖（藉由這樣的方式可以看出變數之間的關係）

7.1.8 分格點狀圖

# quiz-1:
ggplot(WHO, aes(x = log(Population), y = GNI, color=Region)) + 
  geom_point() + 
  stat_smooth(method='lm') +
  facet_wrap(~Region) + theme_bw()

# facet_wrap(~Region)：每個region各自畫成一張圖
# 資料視覺化：很精緻很厲害的瞭解變數之間的關聯性（不需要做其他分析也可以）

---