p54 example
kevin = c(85,73)
marry = c(72,64)
jerry = c(59,66)
mat = matrix(c(kevin, marry, jerry), nrow=3, byrow= TRUE)
colnames(mat) = c('first', 'second')
rownames(mat) = c('kevin', 'marry', 'jerry')
final = mat %*% c(0.4,0.6)
final
## [,1]
## kevin 77.8
## marry 67.2
## jerry 63.2
cbind(mat,final)
## first second
## kevin 85 73 77.8
## marry 72 64 67.2
## jerry 59 66 63.2
mat2 = cbind(mat,final)
mat2
## first second
## kevin 85 73 77.8
## marry 72 64 67.2
## jerry 59 66 63.2
colnames(mat2)[ncol(mat2)] = 'final'
mat2
## first second final
## kevin 85 73 77.8
## marry 72 64 67.2
## jerry 59 66 63.2
Dataframe
name <- c("Joe", "Bob", "Vicky")
age <- c(28, 26, 34)
gender <- c("Male","Male","Female")
df <- data.frame(name, age, gender)
class(df)
## [1] "data.frame"
str(df)
## 'data.frame': 3 obs. of 3 variables:
## $ name : Factor w/ 3 levels "Bob","Joe","Vicky": 2 1 3
## $ age : num 28 26 34
## $ gender: Factor w/ 2 levels "Female","Male": 2 2 1
summary(df)
## name age gender
## Bob :1 Min. :26.00 Female:1
## Joe :1 1st Qu.:27.00 Male :2
## Vicky:1 Median :28.00
## Mean :29.33
## 3rd Qu.:31.00
## Max. :34.00
data(iris)
head(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
tail(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica
tail(iris, 10)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 141 6.7 3.1 5.6 2.4 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica
str(iris)
## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
#取前三列資料
iris[1:3,]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
#取前三列第一行的資料
iris[1:3,1]
## [1] 5.1 4.9 4.7
#取前三列Sepal.Length欄位的資料
iris[1:3,"Sepal.Length"]
## [1] 5.1 4.9 4.7
head(iris[,1:2])
## Sepal.Length Sepal.Width
## 1 5.1 3.5
## 2 4.9 3.0
## 3 4.7 3.2
## 4 4.6 3.1
## 5 5.0 3.6
## 6 5.4 3.9
iris$"Sepal.Length"[1:3]
## [1] 5.1 4.9 4.7
#取前五筆包含length 及 width 的資料
Five.Sepal.iris = iris[1:5, c("Sepal.Length","Sepal.Width")]
#可以用條件做篩選
setosa.data = iris[iris$Species=="setosa",1:5]
str(setosa.data)
## 'data.frame': 50 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
#使用which 做資料篩選
which(iris$Species=="setosa")
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
## [47] 47 48 49 50
#用order做資料排序
iris[order(iris$Sepal.Length, decreasing = TRUE),]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 132 7.9 3.8 6.4 2.0 virginica
## 118 7.7 3.8 6.7 2.2 virginica
## 119 7.7 2.6 6.9 2.3 virginica
## 123 7.7 2.8 6.7 2.0 virginica
## 136 7.7 3.0 6.1 2.3 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 131 7.4 2.8 6.1 1.9 virginica
## 108 7.3 2.9 6.3 1.8 virginica
## 110 7.2 3.6 6.1 2.5 virginica
## 126 7.2 3.2 6.0 1.8 virginica
## 130 7.2 3.0 5.8 1.6 virginica
## 103 7.1 3.0 5.9 2.1 virginica
## 51 7.0 3.2 4.7 1.4 versicolor
## 53 6.9 3.1 4.9 1.5 versicolor
## 121 6.9 3.2 5.7 2.3 virginica
## 140 6.9 3.1 5.4 2.1 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 77 6.8 2.8 4.8 1.4 versicolor
## 113 6.8 3.0 5.5 2.1 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 66 6.7 3.1 4.4 1.4 versicolor
## 78 6.7 3.0 5.0 1.7 versicolor
## 87 6.7 3.1 4.7 1.5 versicolor
## 109 6.7 2.5 5.8 1.8 virginica
## 125 6.7 3.3 5.7 2.1 virginica
## 141 6.7 3.1 5.6 2.4 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 59 6.6 2.9 4.6 1.3 versicolor
## 76 6.6 3.0 4.4 1.4 versicolor
## 55 6.5 2.8 4.6 1.5 versicolor
## 105 6.5 3.0 5.8 2.2 virginica
## 111 6.5 3.2 5.1 2.0 virginica
## 117 6.5 3.0 5.5 1.8 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 52 6.4 3.2 4.5 1.5 versicolor
## 75 6.4 2.9 4.3 1.3 versicolor
## 112 6.4 2.7 5.3 1.9 virginica
## 116 6.4 3.2 5.3 2.3 virginica
## 129 6.4 2.8 5.6 2.1 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 138 6.4 3.1 5.5 1.8 virginica
## 57 6.3 3.3 4.7 1.6 versicolor
## 73 6.3 2.5 4.9 1.5 versicolor
## 88 6.3 2.3 4.4 1.3 versicolor
## 101 6.3 3.3 6.0 2.5 virginica
## 104 6.3 2.9 5.6 1.8 virginica
## 124 6.3 2.7 4.9 1.8 virginica
## 134 6.3 2.8 5.1 1.5 virginica
## 137 6.3 3.4 5.6 2.4 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 69 6.2 2.2 4.5 1.5 versicolor
## 98 6.2 2.9 4.3 1.3 versicolor
## 127 6.2 2.8 4.8 1.8 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 64 6.1 2.9 4.7 1.4 versicolor
## 72 6.1 2.8 4.0 1.3 versicolor
## 74 6.1 2.8 4.7 1.2 versicolor
## 92 6.1 3.0 4.6 1.4 versicolor
## 128 6.1 3.0 4.9 1.8 virginica
## 135 6.1 2.6 5.6 1.4 virginica
## 63 6.0 2.2 4.0 1.0 versicolor
## 79 6.0 2.9 4.5 1.5 versicolor
## 84 6.0 2.7 5.1 1.6 versicolor
## 86 6.0 3.4 4.5 1.6 versicolor
## 120 6.0 2.2 5.0 1.5 virginica
## 139 6.0 3.0 4.8 1.8 virginica
## 62 5.9 3.0 4.2 1.5 versicolor
## 71 5.9 3.2 4.8 1.8 versicolor
## 150 5.9 3.0 5.1 1.8 virginica
## 15 5.8 4.0 1.2 0.2 setosa
## 68 5.8 2.7 4.1 1.0 versicolor
## 83 5.8 2.7 3.9 1.2 versicolor
## 93 5.8 2.6 4.0 1.2 versicolor
## 102 5.8 2.7 5.1 1.9 virginica
## 115 5.8 2.8 5.1 2.4 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 16 5.7 4.4 1.5 0.4 setosa
## 19 5.7 3.8 1.7 0.3 setosa
## 56 5.7 2.8 4.5 1.3 versicolor
## 80 5.7 2.6 3.5 1.0 versicolor
## 96 5.7 3.0 4.2 1.2 versicolor
## 97 5.7 2.9 4.2 1.3 versicolor
## 100 5.7 2.8 4.1 1.3 versicolor
## 114 5.7 2.5 5.0 2.0 virginica
## 65 5.6 2.9 3.6 1.3 versicolor
## 67 5.6 3.0 4.5 1.5 versicolor
## 70 5.6 2.5 3.9 1.1 versicolor
## 89 5.6 3.0 4.1 1.3 versicolor
## 95 5.6 2.7 4.2 1.3 versicolor
## 122 5.6 2.8 4.9 2.0 virginica
## 34 5.5 4.2 1.4 0.2 setosa
## 37 5.5 3.5 1.3 0.2 setosa
## 54 5.5 2.3 4.0 1.3 versicolor
## 81 5.5 2.4 3.8 1.1 versicolor
## 82 5.5 2.4 3.7 1.0 versicolor
## 90 5.5 2.5 4.0 1.3 versicolor
## 91 5.5 2.6 4.4 1.2 versicolor
## 6 5.4 3.9 1.7 0.4 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 17 5.4 3.9 1.3 0.4 setosa
## 21 5.4 3.4 1.7 0.2 setosa
## 32 5.4 3.4 1.5 0.4 setosa
## 85 5.4 3.0 4.5 1.5 versicolor
## 49 5.3 3.7 1.5 0.2 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 29 5.2 3.4 1.4 0.2 setosa
## 33 5.2 4.1 1.5 0.1 setosa
## 60 5.2 2.7 3.9 1.4 versicolor
## 1 5.1 3.5 1.4 0.2 setosa
## 18 5.1 3.5 1.4 0.3 setosa
## 20 5.1 3.8 1.5 0.3 setosa
## 22 5.1 3.7 1.5 0.4 setosa
## 24 5.1 3.3 1.7 0.5 setosa
## 40 5.1 3.4 1.5 0.2 setosa
## 45 5.1 3.8 1.9 0.4 setosa
## 47 5.1 3.8 1.6 0.2 setosa
## 99 5.1 2.5 3.0 1.1 versicolor
## 5 5.0 3.6 1.4 0.2 setosa
## 8 5.0 3.4 1.5 0.2 setosa
## 26 5.0 3.0 1.6 0.2 setosa
## 27 5.0 3.4 1.6 0.4 setosa
## 36 5.0 3.2 1.2 0.2 setosa
## 41 5.0 3.5 1.3 0.3 setosa
## 44 5.0 3.5 1.6 0.6 setosa
## 50 5.0 3.3 1.4 0.2 setosa
## 61 5.0 2.0 3.5 1.0 versicolor
## 94 5.0 2.3 3.3 1.0 versicolor
## 2 4.9 3.0 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 58 4.9 2.4 3.3 1.0 versicolor
## 107 4.9 2.5 4.5 1.7 virginica
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 48 4.6 3.2 1.4 0.2 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 14 4.3 3.0 1.1 0.1 setosa
sort(iris$Sepal.Length, decreasing = TRUE)
## [1] 7.9 7.7 7.7 7.7 7.7 7.6 7.4 7.3 7.2 7.2 7.2 7.1 7.0 6.9 6.9 6.9 6.9
## [18] 6.8 6.8 6.8 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.7 6.6 6.6 6.5 6.5 6.5 6.5
## [35] 6.5 6.4 6.4 6.4 6.4 6.4 6.4 6.4 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3 6.3
## [52] 6.2 6.2 6.2 6.2 6.1 6.1 6.1 6.1 6.1 6.1 6.0 6.0 6.0 6.0 6.0 6.0 5.9
## [69] 5.9 5.9 5.8 5.8 5.8 5.8 5.8 5.8 5.8 5.7 5.7 5.7 5.7 5.7 5.7 5.7 5.7
## [86] 5.6 5.6 5.6 5.6 5.6 5.6 5.5 5.5 5.5 5.5 5.5 5.5 5.5 5.4 5.4 5.4 5.4
## [103] 5.4 5.4 5.3 5.2 5.2 5.2 5.2 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.1 5.0
## [120] 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 4.9 4.9 4.9 4.9 4.9 4.9 4.8 4.8
## [137] 4.8 4.8 4.8 4.7 4.7 4.6 4.6 4.6 4.6 4.5 4.4 4.4 4.4 4.3
File read and write
# getwd()
setwd('~/lecture/riii')
# setwd("__your_working_directory_path__")
tw2330 = read.csv("data/2330.csv", header=TRUE)
#tw2330 = read.csv('https://github.com/YuHsuanLin/riii/raw/master/data/2330.csv')
test.data = read.table("data/match.txt" ,header = FALSE, sep="|")
p70
setwd('~/lecture/riii')
tw2330 = read.csv("./data/2330.csv", header=TRUE)
str(tw2330)
## 'data.frame': 1801 obs. of 6 variables:
## $ Date : Factor w/ 1801 levels "2011-01-03","2011-01-04",..: 1801 1800 1799 1798 1797 1796 1795 1794 1793 1792 ...
## $ Open : num 224 225 225 226 225 ...
## $ High : num 228 226 226 226 228 ...
## $ Low : num 222 221 221 224 225 ...
## $ Close : num 227 224 222 225 227 ...
## $ Volume: int 6448117 7619247 10731921 10535437 9272078 16080436 29507056 7758149 10130508 10232257 ...
tw2330$Date = as.Date(tw2330$Date)
tw2330_2017 = tw2330[(tw2330$Date >= '2017-01-01' & tw2330$Date < '2018-01-01'),]
max(tw2330_2017$Close)
## [1] 244
ordered_stock = tw2330_2017[order(tw2330_2017$Close, decreasing = T),]
List
item= list(thing='hat',size=8.25)
item$thing
## [1] "hat"
item$size
## [1] 8.25
flower= list(title="iris dataset", data= iris)
class(flower)
## [1] "list"
class(flower$data)
## [1] "data.frame"
flower$data[1,"Sepal.Width"]
## [1] 3.5
li = list(c(1,2,3,4),c(5,6,7,8))
li[[1]]
## [1] 1 2 3 4
two dataframes join
#merge進行資料合併
df1 = data.frame(CustomerId = c(1:6), Product = c(rep("Toaster", 3), rep("Radio", 3)))
df2 = data.frame(CustomerId = c(2, 4, 6), State = c(rep("Alabama", 2), rep("Ohio", 1)))
#Inner join:
merge(x = df1, y= df2, by="CustomerId")
## CustomerId Product State
## 1 2 Toaster Alabama
## 2 4 Radio Alabama
## 3 6 Radio Ohio
#Outer join:
merge(x = df1, y = df2, by = "CustomerId", all = TRUE)
## CustomerId Product State
## 1 1 Toaster <NA>
## 2 2 Toaster Alabama
## 3 3 Toaster <NA>
## 4 4 Radio Alabama
## 5 5 Radio <NA>
## 6 6 Radio Ohio
#Left outer:
merge(x = df1, y = df2, by = "CustomerId", all.x = TRUE)
## CustomerId Product State
## 1 1 Toaster <NA>
## 2 2 Toaster Alabama
## 3 3 Toaster <NA>
## 4 4 Radio Alabama
## 5 5 Radio <NA>
## 6 6 Radio Ohio
#Right outer:
merge(x = df1, y = df2, by = "CustomerId", all.y = TRUE)
## CustomerId Product State
## 1 2 Toaster Alabama
## 2 4 Radio Alabama
## 3 6 Radio Ohio
#Cross join:
merge(x = df1, y = df2, by = NULL)
## CustomerId.x Product CustomerId.y State
## 1 1 Toaster 2 Alabama
## 2 2 Toaster 2 Alabama
## 3 3 Toaster 2 Alabama
## 4 4 Radio 2 Alabama
## 5 5 Radio 2 Alabama
## 6 6 Radio 2 Alabama
## 7 1 Toaster 4 Alabama
## 8 2 Toaster 4 Alabama
## 9 3 Toaster 4 Alabama
## 10 4 Radio 4 Alabama
## 11 5 Radio 4 Alabama
## 12 6 Radio 4 Alabama
## 13 1 Toaster 6 Ohio
## 14 2 Toaster 6 Ohio
## 15 3 Toaster 6 Ohio
## 16 4 Radio 6 Ohio
## 17 5 Radio 6 Ohio
## 18 6 Radio 6 Ohio
readr package
#install.packages("tidyverse")
#install.packages("readr")
library('tidyverse')
## ─ Attaching packages ─────────────────── tidyverse 1.2.1 ─
## ✔ ggplot2 3.1.0 ✔ purrr 0.2.5
## ✔ tibble 2.1.1 ✔ dplyr 0.8.0.1
## ✔ tidyr 0.8.1 ✔ stringr 1.3.1
## ✔ readr 1.3.1 ✔ forcats 0.3.0
## Warning: package 'tibble' was built under R version 3.5.2
## Warning: package 'dplyr' was built under R version 3.5.2
## ─ Conflicts ──────────────────── tidyverse_conflicts() ─
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
setwd('~/lecture/riii')
stock = read_csv('data/2330.csv',col_names=T)
## Parsed with column specification:
## cols(
## Date = col_date(format = ""),
## Open = col_double(),
## High = col_double(),
## Low = col_double(),
## Close = col_double(),
## Volume = col_double()
## )
read_csv('data/2330.csv',col_names=T,col_types = cols(
Date = col_date(format = ""),
Open = col_double(),
High = col_double(),
Low = col_double(),
Close = col_double(),
Volume = col_double()
))
## # A tibble: 1,801 x 6
## Date Open High Low Close Volume
## <date> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2018-04-30 224. 228 222. 227 6448117
## 2 2018-04-27 225 226. 221 224. 7619247
## 3 2018-04-26 225 226. 221 222 10731921
## 4 2018-04-25 226. 226 224 225 10535437
## 5 2018-04-24 225 228. 225 227 9272078
## 6 2018-04-23 226. 228. 225 226. 16080436
## 7 2018-04-20 228 232. 228 229 29507056
## 8 2018-04-19 242 244. 241 244. 7758149
## 9 2018-04-18 240. 242. 236. 238 10130508
## 10 2018-04-17 243 244. 238. 238 10232257
## # … with 1,791 more rows
read excel file
#install.packages("readxl")
library(readxl)
setwd('~/lecture/riii/')
FinancialReport <- read_excel("./data/FinancialReport.xlsx")
#View(FinancialReport)
summary(FinancialReport)
## 年度 股本 財報評分 收盤
## Min. :1999 Min. : 767 Min. :59.00 Min. : 42.60
## 1st Qu.:2003 1st Qu.:2027 1st Qu.:89.00 1st Qu.: 62.50
## Median :2007 Median :2583 Median :92.00 Median : 71.00
## Mean :2007 Mean :2249 Mean :88.24 Mean : 83.75
## 3rd Qu.:2011 3rd Qu.:2592 3rd Qu.:94.00 3rd Qu.: 97.00
## Max. :2015 Max. :2643 Max. :96.00 Max. :167.00
## 平均 漲跌 漲跌__1 營業收入
## Min. : 52.40 Min. :-88.500 Min. :-53.00 Min. : 731
## 1st Qu.: 56.40 1st Qu.: -5.500 1st Qu.: -8.10 1st Qu.:2030
## Median : 67.40 Median : 6.500 Median : 8.80 Median :3174
## Mean : 82.29 Mean : 4.235 Mean : 11.77 Mean :3576
## 3rd Qu.:104.00 3rd Qu.: 20.100 3rd Qu.: 28.00 3rd Qu.:4271
## Max. :147.00 Max. : 96.000 Max. :135.00 Max. :8435
## 營業毛利 營業利益 業外損益 稅後淨利
## Min. : 315 Min. : 128 Min. :-43.70 Min. : 145
## 1st Qu.: 765 1st Qu.: 613 1st Qu.: 4.97 1st Qu.: 651
## Median :1417 Median :1044 Median : 35.00 Median : 999
## Mean :1639 Mean :1238 Mean : 50.67 Mean :1179
## 3rd Qu.:2071 3rd Qu.:1592 3rd Qu.: 62.10 3rd Qu.:1616
## Max. :4104 Max. :3200 Max. :304.00 Max. :3066
## ROA EPS
## Min. : 3.93 Min. : 0.830
## 1st Qu.:15.50 1st Qu.: 3.450
## Median :18.40 Median : 4.140
## Mean :17.15 Mean : 4.969
## 3rd Qu.:19.40 3rd Qu.: 6.240
## Max. :24.70 Max. :11.820
read json
setwd('~/lecture/riii/')
library(jsonlite)
##
## Attaching package: 'jsonlite'
## The following object is masked from 'package:purrr':
##
## flatten
json_data<- fromJSON('./data/rent.json')
## Warning: JSON string contains (illegal) UTF8 byte-order-mark!
json_data <- as_tibble(json_data)
head(json_data)
## # A tibble: 6 x 11
## 縣市 經管單位 用途限制 實際用途 每月租金 租期屆滿 建物面積 構造
## <chr> <chr> <chr> <chr> <dbl> <chr> <chr> <chr>
## 1 臺北市… 台北所 辦公或住宅或法… 商店 22900 105.12.… 190 木石磚造…
## 2 臺北市… 台北所 辦公或住宅或法… 辦公室 187000 107.6.7… 252 磚造
## 3 臺北市… 台北所 辦公或住宅或法… 商店 56899 105.2.3… 132 加強磚造…
## 4 臺北市… 台北所 住宅或法律許可… 商店 31850 107.7.2… 72 加強磚造…
## 5 臺北市… 臺北所 辦公或住宅或法… 商業 31860 105.12.… 171 磚造
## 6 臺北市… 臺北所 辦公或住宅或法… 商業 34000 106.2.2… 145.1 RC加強…
## # … with 3 more variables: 總樓層數 <chr>, 建物現況 <chr>, 房屋座落 <chr>
read xml
#install.packages("XML")
library(XML)
#url <- 'http://opendata.epa.gov.tw/ws/Data/ATM00698/?$format=xml'
#weather <- xmlToDataFrame(url)
#View(weather)
#str(weather)
#weather[ weather$SiteName == '臺北', c('DataCreationDate','Temperature') ]
Flow Control
x=5;
if(x>3){
print("x > 3")
}else{
print("x <= 3")
}
## [1] "x > 3"
if(x>3) print("x > 3") else print("x <= 3")
## [1] "x > 3"
test = ifelse(x>3,"x > 3","x <= 3")
test
## [1] "x > 3"
data(iris)
iris$new_species = factor(ifelse(iris$Species == "setosa","IsSetosa","NotSetosa"))
str(iris)
## 'data.frame': 150 obs. of 6 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ new_species : Factor w/ 2 levels "IsSetosa","NotSetosa": 1 1 1 1 1 1 1 1 1 1 ...
x=5;
if(x>3){
print ("x > 3");
} else if (x ==3){
print ("x == 3");
}else{
print("x <= 3");
}
## [1] "x > 3"
for(i in 1:10){
print(i)
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
sum=0
for(i in 1:100){
sum= sum+ i;
}
sum
## [1] 5050
sum(1:100)
## [1] 5050
mat = matrix(1:9, byrow=TRUE, nrow=3)
for(i in 1:nrow(mat)){
for(j in 1:ncol(mat)){
print(mat[i,j])
}
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
sum = 0;
cnt = 0;
while(cnt <= 100){
sum = sum + cnt;
cnt = cnt + 1;
}
sum
## [1] 5050
p86
mat = matrix(data=rep(1,9^2),nrow = 9)
mat = matrix(data=0,nrow=9,ncol=9)
for(i in 1:nrow(mat)){
for(j in 1:ncol(mat)){
#mat[i,j] = i * j;
#mat[i,j] = paste(i,"*",j,"= ",i*j)
mat[i,j] = sprintf("%s * %s = %s",i,j,i*j)
}
}
mat
## [,1] [,2] [,3] [,4] [,5]
## [1,] "1 * 1 = 1" "1 * 2 = 2" "1 * 3 = 3" "1 * 4 = 4" "1 * 5 = 5"
## [2,] "2 * 1 = 2" "2 * 2 = 4" "2 * 3 = 6" "2 * 4 = 8" "2 * 5 = 10"
## [3,] "3 * 1 = 3" "3 * 2 = 6" "3 * 3 = 9" "3 * 4 = 12" "3 * 5 = 15"
## [4,] "4 * 1 = 4" "4 * 2 = 8" "4 * 3 = 12" "4 * 4 = 16" "4 * 5 = 20"
## [5,] "5 * 1 = 5" "5 * 2 = 10" "5 * 3 = 15" "5 * 4 = 20" "5 * 5 = 25"
## [6,] "6 * 1 = 6" "6 * 2 = 12" "6 * 3 = 18" "6 * 4 = 24" "6 * 5 = 30"
## [7,] "7 * 1 = 7" "7 * 2 = 14" "7 * 3 = 21" "7 * 4 = 28" "7 * 5 = 35"
## [8,] "8 * 1 = 8" "8 * 2 = 16" "8 * 3 = 24" "8 * 4 = 32" "8 * 5 = 40"
## [9,] "9 * 1 = 9" "9 * 2 = 18" "9 * 3 = 27" "9 * 4 = 36" "9 * 5 = 45"
## [,6] [,7] [,8] [,9]
## [1,] "1 * 6 = 6" "1 * 7 = 7" "1 * 8 = 8" "1 * 9 = 9"
## [2,] "2 * 6 = 12" "2 * 7 = 14" "2 * 8 = 16" "2 * 9 = 18"
## [3,] "3 * 6 = 18" "3 * 7 = 21" "3 * 8 = 24" "3 * 9 = 27"
## [4,] "4 * 6 = 24" "4 * 7 = 28" "4 * 8 = 32" "4 * 9 = 36"
## [5,] "5 * 6 = 30" "5 * 7 = 35" "5 * 8 = 40" "5 * 9 = 45"
## [6,] "6 * 6 = 36" "6 * 7 = 42" "6 * 8 = 48" "6 * 9 = 54"
## [7,] "7 * 6 = 42" "7 * 7 = 49" "7 * 8 = 56" "7 * 9 = 63"
## [8,] "8 * 6 = 48" "8 * 7 = 56" "8 * 8 = 64" "8 * 9 = 72"
## [9,] "9 * 6 = 54" "9 * 7 = 63" "9 * 8 = 72" "9 * 9 = 81"
rep(1,9^2)
## [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## [36] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## [71] 1 1 1 1 1 1 1 1 1 1 1
mat1 = matrix(1:9, nrow = 9);
mat2 = matrix(1:9, nrow = 1);
mat = mat1 %*% mat2;
mat
## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
## [1,] 1 2 3 4 5 6 7 8 9
## [2,] 2 4 6 8 10 12 14 16 18
## [3,] 3 6 9 12 15 18 21 24 27
## [4,] 4 8 12 16 20 24 28 32 36
## [5,] 5 10 15 20 25 30 35 40 45
## [6,] 6 12 18 24 30 36 42 48 54
## [7,] 7 14 21 28 35 42 49 56 63
## [8,] 8 16 24 32 40 48 56 64 72
## [9,] 9 18 27 36 45 54 63 72 81
Function
addThree = function(a){
return(a+3)
}
addThree(3)
## [1] 6
#with default arguments
addThree_2 = function(a = 3) {
return(a+3)
}
addThree_2()
## [1] 6
#每行程式結尾可加;可不加
addThree_3 = function(a = 3) {
a+3;
}
addThree_3()
## [1] 6
#lazy function
f2 = function(a, b = 2, c = NULL) {
return(b + 1)
}
f2()
## [1] 3
#local variable
b = 3
f3 = function() {
b = 2
return(b)
}
f3()
## [1] 2
lapply sapply
x = list(c(1,2,3,4), c(5,6,7,8))
## 回傳list的結果
lapply(x, sum)
## [[1]]
## [1] 10
##
## [[2]]
## [1] 26
class(lapply(x, sum))
## [1] "list"
## 回傳簡化的結果(vector,matrix)
sapply(x, sum)
## [1] 10 26
## sappply 等同 lapply unlist 後的結果
unlist(lapply(x, sum))
## [1] 10 26
class(sapply(x, sum))
## [1] "numeric"
lapply(x,addThree)
## [[1]]
## [1] 4 5 6 7
##
## [[2]]
## [1] 8 9 10 11
## 匿名函式
lapply(x,function(e){e+3})
## [[1]]
## [1] 4 5 6 7
##
## [[2]]
## [1] 8 9 10 11
m1 = matrix(1:4, byrow=TRUE, nrow=2)
m2 = matrix(5:8, byrow=TRUE, nrow=2)
li = list(m1, m2)
lapply(li, function(e){e[1,]})
## [[1]]
## [1] 1 2
##
## [[2]]
## [1] 5 6
lapply(li, mean)
## [[1]]
## [1] 2.5
##
## [[2]]
## [1] 6.5
apply tapply
m = matrix(1:4, byrow=TRUE, nrow=2)
apply(m, 1, sum) # rowsums
## [1] 3 7
apply(m, 2, sum) # colsums
## [1] 4 6
rowmeans = apply(m, 1, mean)
colmeans = apply(m, 2, mean)
x = c(80,70,59,88,72,57)
t = c(1,1,2,1,1,2)
tapply(x,t, mean)
## 1 2
## 77.5 58.0
data(iris)
tapply(iris$Sepal.Length, iris$Species, mean)
## setosa versicolor virginica
## 5.006 5.936 6.588
tapply(iris$Sepal.Length,iris$Species,function(e){list(avg=mean(e),md=median(e),s_d = sd(e))})
## $setosa
## $setosa$avg
## [1] 5.006
##
## $setosa$md
## [1] 5
##
## $setosa$s_d
## [1] 0.3524897
##
##
## $versicolor
## $versicolor$avg
## [1] 5.936
##
## $versicolor$md
## [1] 5.9
##
## $versicolor$s_d
## [1] 0.5161711
##
##
## $virginica
## $virginica$avg
## [1] 6.588
##
## $virginica$md
## [1] 6.5
##
## $virginica$s_d
## [1] 0.6358796
s = lapply(names(iris[1:4]),function(e){tapply(iris[,e],iris$Species,mean) })
names(s)
## NULL
names(s) = names(iris[1:4])
探索性資料分析
表格
#import data
#getwd()
setwd("~/lecture/riii")
load("./Statistics/cdc.Rdata")
getwd()
## [1] "/Users/YorkLin/lecture/riii"
str(cdc)
## 'data.frame': 20000 obs. of 9 variables:
## $ genhlth : Factor w/ 5 levels "excellent","very good",..: 3 3 3 3 2 2 2 2 3 3 ...
## $ exerany : num 0 0 1 1 0 1 1 0 0 1 ...
## $ hlthplan: num 1 1 1 1 1 1 1 1 1 1 ...
## $ smoke100: num 0 1 1 0 0 0 0 0 1 0 ...
## $ height : num 70 64 60 66 61 64 71 67 65 70 ...
## $ weight : int 175 125 105 132 150 114 194 170 150 180 ...
## $ wtdesire: int 175 115 105 124 130 114 185 160 130 170 ...
## $ age : int 77 33 49 42 55 55 31 45 27 44 ...
## $ gender : Factor w/ 2 levels "m","f": 1 2 2 2 2 2 1 1 2 1 ...
head(cdc)
## genhlth exerany hlthplan smoke100 height weight wtdesire age gender
## 1 good 0 1 0 70 175 175 77 m
## 2 good 0 1 1 64 125 115 33 f
## 3 good 1 1 1 60 105 105 49 f
## 4 good 1 1 0 66 132 124 42 f
## 5 very good 0 1 0 61 150 130 55 f
## 6 very good 1 1 0 64 114 114 55 f
names(cdc)
## [1] "genhlth" "exerany" "hlthplan" "smoke100" "height" "weight"
## [7] "wtdesire" "age" "gender"
#轉換資料類型
cdc$exerany = as.factor(cdc$exerany)
cdc$hlthplan = as.factor(cdc$hlthplan)
cdc$smoke100 = as.factor(cdc$smoke100)
str(cdc)
## 'data.frame': 20000 obs. of 9 variables:
## $ genhlth : Factor w/ 5 levels "excellent","very good",..: 3 3 3 3 2 2 2 2 3 3 ...
## $ exerany : Factor w/ 2 levels "0","1": 1 1 2 2 1 2 2 1 1 2 ...
## $ hlthplan: Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
## $ smoke100: Factor w/ 2 levels "0","1": 1 2 2 1 1 1 1 1 2 1 ...
## $ height : num 70 64 60 66 61 64 71 67 65 70 ...
## $ weight : int 175 125 105 132 150 114 194 170 150 180 ...
## $ wtdesire: int 175 115 105 124 130 114 185 160 130 170 ...
## $ age : int 77 33 49 42 55 55 31 45 27 44 ...
## $ gender : Factor w/ 2 levels "m","f": 1 2 2 2 2 2 1 1 2 1 ...
#一維次數分配表
table(cdc$exerany)
##
## 0 1
## 5086 14914
#相對比例
table(cdc$exerany) / length(cdc$exerany)
##
## 0 1
## 0.2543 0.7457
paste(table(cdc$exerany) / nrow(cdc) * 100, '%')
## [1] "25.43 %" "74.57 %"
#二維次數分配表
table(cdc$gender,cdc$exerany)
##
## 0 1
## m 2149 7420
## f 2937 7494
apply(table(cdc$gender,cdc$exerany),1,function(e){e/sum(e)})
##
## m f
## 0 0.2245794 0.2815646
## 1 0.7754206 0.7184354
表格(續)
#三維以上
table(cdc$gender,cdc$genhlth,cdc$exerany)
## , , = 0
##
##
## excellent very good good fair poor
## m 335 606 723 340 145
## f 427 746 1008 517 239
##
## , , = 1
##
##
## excellent very good good fair poor
## m 1963 2776 1999 544 138
## f 1932 2844 1945 618 155
#連續型資料作表
table(cdc$height)
##
## 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
## 2 1 1 2 2 7 3 4 17 20 51 170 613 594 1272
## 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
## 1368 1662 1568 1843 1671 1505 1380 1500 1296 1393 784 605 321 189 80
## 78 79 80 81 82 83 84 93
## 43 15 10 3 2 1 1 1
summary(cdc$height)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 48.00 64.00 67.00 67.18 70.00 93.00
head(cut(cdc$height,seq(45,95,by=5)))
## [1] (65,70] (60,65] (55,60] (65,70] (60,65] (60,65]
## 10 Levels: (45,50] (50,55] (55,60] (60,65] (65,70] (70,75] ... (90,95]
#包含上界不包含下界
table(cut(cdc$height,seq(45,95,by=5),right=T))
##
## (45,50] (50,55] (55,60] (60,65] (65,70] (70,75] (75,80] (80,85] (85,90]
## 4 18 871 6464 7899 4399 337 7 0
## (90,95]
## 1
#包含下界不包含上界
table(cut(cdc$height,seq(45,95,by=5),right=F))
##
## [45,50) [50,55) [55,60) [60,65) [65,70) [70,75) [75,80) [80,85) [85,90)
## 3 15 262 5509 7967 5578 648 17 0
## [90,95)
## 1