AS7-0A ggplot2 繪圖套件

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

package 'maps' was built under R version 3.4.4

library(ggmap)

package 'ggmap' was built under R version 3.4.4Google Maps API Terms of Service: http://developers.google.com/maps/terms.
Please cite ggmap if you use it: see citation('ggmap') for details.

---

7.1 ggplot2 繪圖套件

7.1.1 基本點狀圖

WHO = read.csv("data/WHO.csv")

# 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))

# Add the geom_point geometry
scatterplot + geom_point() 

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

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

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

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

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

Warning message:
In scan(file = file, what = what, sep = sep, quote = quote, dec = dec,  :
  EOF within quoted string

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")
pdf("MyPlot.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()

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

# 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()

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

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)

# 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()

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()

---