R Lecture 3
Gallon
2019年2月12日
7. dplyr
arrange 排列
filter 對列做篩選 (row)
select 對欄做篩選 (column)
mutate 更改欄或新增欄
group_by + summarise 分類
以下以上次 Lecture 2 的台灣死亡資料為例。
library(magrittr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionsetwd("C:/Users/User/Google 雲端硬碟/政治大學ECO/R")
dead<-read.csv("2012-2017dead.csv",stringsAsFactors = F)
7.1 資料排序 arrange
表示方式：arrange(dataframe, 要進行排序的項目,….)
排序預設是由小到大。
head(arrange(.data = dead,pop))## year county sex age cause pop num
## 1 2014 Lienchiang County 2 21 1 0 0
## 2 2014 Lienchiang County 2 21 2 0 0
## 3 2014 Lienchiang County 2 21 3 0 0
## 4 2014 Lienchiang County 2 21 4 0 0
## 5 2014 Lienchiang County 2 21 5 0 0
## 6 2014 Lienchiang County 2 21 6 0 0head(arrange(.data = dead,desc(pop)))## year county sex age cause pop num
## 1 2012 New Taipei City 2 7 1 184883 0
## 2 2012 New Taipei City 2 7 2 184883 1
## 3 2012 New Taipei City 2 7 3 184883 0
## 4 2012 New Taipei City 2 7 4 184883 0
## 5 2012 New Taipei City 2 7 5 184883 1
## 6 2012 New Taipei City 2 7 6 184883 1
7.2 對列篩選 filter
表示方式：filter(dataframe, 要進行篩選的列,….)
head(filter(.data =dead,year==2014 ))## year county sex age cause pop num
## 1 2014 Changhua County 1 1 1 28476 0
## 2 2014 Changhua County 1 1 2 28476 0
## 3 2014 Changhua County 1 1 3 28476 2
## 4 2014 Changhua County 1 1 4 28476 0
## 5 2014 Changhua County 1 1 5 28476 0
## 6 2014 Changhua County 1 1 6 28476 1
7.3 選取變數 select
表示方式：select(dataframe, 要選取的變數,….)
head(select(.data = dead,year,sex,age))## year sex age
## 1 2012 1 1
## 2 2012 1 1
## 3 2012 1 1
## 4 2012 1 1
## 5 2012 1 1
## 6 2012 1 1#用負號表示不要的變數
head(select(.data = dead,-year,-sex,-age))## county cause pop num
## 1 Changhua County 1 29188 0
## 2 Changhua County 2 29188 0
## 3 Changhua County 3 29188 0
## 4 Changhua County 4 29188 0
## 5 Changhua County 5 29188 0
## 6 Changhua County 6 29188 0
7.4 新增欄位 mutate
表示方式：mutate(dataframe, 想要新增的欄位,….)
head(mutate(.data = dead,rate=num/pop))## year county sex age cause pop num rate
## 1 2012 Changhua County 1 1 1 29188 0 0
## 2 2012 Changhua County 1 1 2 29188 0 0
## 3 2012 Changhua County 1 1 3 29188 0 0
## 4 2012 Changhua County 1 1 4 29188 0 0
## 5 2012 Changhua County 1 1 5 29188 0 0
## 6 2012 Changhua County 1 1 6 29188 0 0
7.5 樞紐分析 group_by + summarise
7.5.1 基本算子 %>%
%>% 會將算子左邊的物件 (object) 傳到右邊的函數 (function) 中第一個argument
輸入方式：ctrl+shift+M
dead %>% select(year,sex,age) %>% head()## year sex age
## 1 2012 1 1
## 2 2012 1 1
## 3 2012 1 1
## 4 2012 1 1
## 5 2012 1 1
## 6 2012 1 1
7.5.2 group_by + summarise
先利用group_by進行分組，再用summarise進行組內運算。
dead %>%
group_by(sex) %>%
summarise(sum=sum(as.numeric(pop)))## # A tibble: 2 x 2
## sex sum
## <int> <dbl>
## 1 1 9477926235
## 2 2 9520111980
也可以利用filter 和 %in% 一次篩選多個值。
dead %>%
filter(cause %in% c(1:10)) %>%
head()## year county sex age cause pop num
## 1 2012 Changhua County 1 1 1 29188 0
## 2 2012 Changhua County 1 1 2 29188 0
## 3 2012 Changhua County 1 1 3 29188 0
## 4 2012 Changhua County 1 1 4 29188 0
## 5 2012 Changhua County 1 1 5 29188 0
## 6 2012 Changhua County 1 1 6 29188 0
8. 資料視覺化 Data Visualization
為什麼我們需要將資料視覺化？
8.1 plot
可以快速但粗糙的瞭解資料的分布。
plot(x = c(1,3,5,3,6,2),y = c(7,4,6,3,9,5))
8.2 ggplot
library(ggplot2)
8.2.1 設計理念
(1)採用圖層系統
(2)用抽象的概念來控制圖形避免細節繁瑣
(3)圖形美觀
8.2.2 基本架構
(1)資料 (data) 和映射 (mapping)
(2)幾何對象 (geometric)
(3)座標尺度 (scale)
(4)統計轉換 (statistics)
(5)座標系統 (coordinante)
(6)圖層 (layer)
(7)刻面 (facet)
(8)主題 (theme)
8.2.3 注意事項
(1)使用 data.frame 儲存資料 (不可以丟 matrix 物件)
(2)使用 long format
8.2.4 開始繪圖
(1) summary
str(diamonds)## Classes 'tbl_df', 'tbl' and 'data.frame': 53940 obs. of 10 variables:
## $ carat : num 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
## $ cut : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
## $ color : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
## $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
## $ depth : num 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
## $ table : num 55 61 65 58 58 57 57 55 61 61 ...
## $ price : int 326 326 327 334 335 336 336 337 337 338 ...
## $ x : num 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
## $ y : num 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
## $ z : num 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...summary(diamonds)## carat cut color clarity
## Min. :0.2000 Fair : 1610 D: 6775 SI1 :13065
## 1st Qu.:0.4000 Good : 4906 E: 9797 VS2 :12258
## Median :0.7000 Very Good:12082 F: 9542 SI2 : 9194
## Mean :0.7979 Premium :13791 G:11292 VS1 : 8171
## 3rd Qu.:1.0400 Ideal :21551 H: 8304 VVS2 : 5066
## Max. :5.0100 I: 5422 VVS1 : 3655
## J: 2808 (Other): 2531
## depth table price x
## Min. :43.00 Min. :43.00 Min. : 326 Min. : 0.000
## 1st Qu.:61.00 1st Qu.:56.00 1st Qu.: 950 1st Qu.: 4.710
## Median :61.80 Median :57.00 Median : 2401 Median : 5.700
## Mean :61.75 Mean :57.46 Mean : 3933 Mean : 5.731
## 3rd Qu.:62.50 3rd Qu.:59.00 3rd Qu.: 5324 3rd Qu.: 6.540
## Max. :79.00 Max. :95.00 Max. :18823 Max. :10.740
##
## y z
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 4.720 1st Qu.: 2.910
## Median : 5.710 Median : 3.530
## Mean : 5.735 Mean : 3.539
## 3rd Qu.: 6.540 3rd Qu.: 4.040
## Max. :58.900 Max. :31.800
##
(2) 生成畫布
ggplot(data = diamonds,aes(x = carat,y = price))
(3) 基本圖形
Bar chart
diamonds<-diamonds
df1<-diamonds %>%
group_by(color) %>%
summarise(n=length(cut))
# Basic barplot
ggplot(data = df1,aes(x = color,y = n))+
geom_bar(stat="identity")
# Horizontal bar plot
ggplot(data = df1,aes(x = color,y = n))+
geom_bar(stat="identity")+
coord_flip()
# Change the width of bars, Change colors
ggplot(data = df1,aes(x = color,y = n))+
geom_bar(stat="identity",width=0.5,
color="blue",fill="white")
# Outside bars or nside bars
ggplot(data = df1,aes(x = color,y = n))+
geom_bar(stat="identity",color="blue",fill="white")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)
# Change barplot color(or fill) by groups
ggplot(data = df1,aes(x = color,y = n,
color=color,fill=color))+
geom_bar(stat="identity")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)
# Use custom color(or fill) palettes
#https://coolors.co/
#http://nipponcolors.com/
#http://colorbrewer2.org/#type=sequential&scheme=BuGn&n=3
ggplot(data = df1,aes(x = color,y = n,fill=color))+
geom_bar(stat="identity")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)+
scale_fill_manual(values=c("#999999","#E69F00",
"#56B4E9","#9E7A7A",
"#74673E","#2EA9DF",
"#707C74"))
# move legend (top bottom none)
ggplot(data = df1,aes(x = color,y = n,fill=color))+
geom_bar(stat="identity")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)+
scale_fill_manual(values=c("#999999","#E69F00",
"#56B4E9","#9E7A7A",
"#74673E","#2EA9DF",
"#707C74"))+
theme(legend.position="top")
# Change the order of items in the legend
ggplot(data = df1,aes(x = color,y = n,fill=color))+
geom_bar(stat="identity")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)+
scale_fill_manual(values=c("#999999","#E69F00",
"#56B4E9","#9E7A7A",
"#74673E","#2EA9DF",
"#707C74"))+
scale_x_discrete(limits=c("J","I","H","G","F","E","D"))
# title
ggplot(data = df1,aes(x = color,y = n,fill=color))+
geom_bar(stat="identity")+
geom_text(aes(label=n), vjust=-0.3, size=3.5)+
scale_fill_manual(values=c("#999999","#E69F00",
"#56B4E9","#9E7A7A",
"#74673E","#2EA9DF",
"#707C74"))+
labs(title="Bar chart",x="鑽石顏色",y="數量")+#加標題軸名
theme(plot.title=element_text(size = 30,hjust = 0.5),
axis.text.x=element_text(size = 15),
axis.text.y=element_text(size = 15),
axis.title.x=element_text(size = 25),
axis.title.y=element_text(size = 25))#修改字體
Scatter plot
ggplot(data=diamonds,aes(x=carat,y=price))+#生成畫布
geom_point(aes(color=cut))+#選擇類型
geom_smooth(color="#2ca25f")+#畫線
scale_color_manual(values =c("#7fc97f","#beaed4",
"#fdc086","#ffff99",
"#386cb0"),
guide=guide_legend(title = "Cut"))+#修改color和圖例
labs(title="散佈圖",x="鑽石重量",y="價格")+#加標題軸名
theme(plot.title=element_text(size = 30,hjust = 0.5),
axis.text.x=element_text(size = 15),
axis.text.y=element_text(size = 15),
axis.title.x=element_text(size = 25),
axis.title.y=element_text(size = 25))+#修改字體
coord_cartesian(xlim = c(0,3))+#x軸或y軸上下限
theme(legend.position = "top")#圖例位置## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'
Line chart
df2<-dead %>%
group_by(year) %>%
summarise(sum=sum(num))
ggplot(data = df2,aes(x = year,y = sum))+
geom_line()+
geom_point()+
labs(title="歷年死亡人口",x="年度",y="人數")