-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathNote10_AboutData_H24071126葉嘉浤.Rmd
151 lines (144 loc) · 4.34 KB
/
Note10_AboutData_H24071126葉嘉浤.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
---
title: "Note_AboutData_H24071126葉嘉浤"
author: "H24071126葉嘉浤"
date: "2020/5/5"
output: html_document
---
# 1.移除NA值
## 當資料有NA值
1.is.na(X)：用於向量
2.complete.cases(X)：用於向量、矩陣或資料框
3.na.omit(X)
```{r}
#Ex
airquality[1:8,]
dim(airquality)
no.na <- complete.cases(airquality)
head(airquality[no.na,])
#檢驗刪除NA值後，資料的dimension
data.no.na.1 <- airquality[no.na,]
dim(data.no.na.1)
#用na.omit忽略NA值後，看資料的dimension
data.no.na.2 <- na.omit(airquality)
dim(data.no.na.2)
```
# 2.數據處理
## 用 cbind和rbind合併資料
## 用 cat 分類資料或賦予資料標籤
```{r}
#將資料中的變數"wind"分組
grouped1 <- cut(airquality[,3], 5)
head(grouped1)
#將分組後的數值增加標籤
grouped2 <- cut(airquality[,3], 5,
labels = c("G1", "G2", "G3", "G4", "G5"))
head(grouped2)
#計算每組的數量
airquality$group <- grouped2
table(grouped2)
#用group排序資料
order.data.1 <- airquality[order(airquality$group),]
head(order.data.1)
order.data.2 <- airquality[order(airquality$group,
airquality$Temp), ]
head(order.data.2)
```
# 3.package：reshape2
```{r}
#install.packages("reshape2")
game <- c("G1", "G2", "G3", "G4", "G5")
site <- c("M", "O", "L", "O", "L")
Lin <- c(15, 6, 26, 22, 18)
Jordan <- c(18, 32, 21, 25, 12)
Peter <- c(10, 6, 22, 9, 12)
ballgames <- data.frame(game, site, Lin, Jordan, Peter)
ballgames
#用melt(data, id.vars)重塑資料的形狀、大小
#保留game、site，其他column轉為variable、value兩個column
#variable為原本沒保留的column名稱，value為對應值
library(reshape2)
after.reshape <- melt(ballgames, id.vars = c("game", "site"))
after.reshape
#用dcast呈現特定的格式
#dcast(dataset,label~variable,value)
#game、site當標籤、variable為變數、sum為對應的值
name <- c("Lin","Jordan","Peter")
after.reshape1 <- dcast(after.reshape,game + site ~ variable,sum)
after.reshape1
#variable當標籤、game為變數、sum為對應的值
after.reshape2 <- dcast(after.reshape, variable ~ game, sum)
after.reshape2
#variable當標籤、site為變數、mean為對應的值
after.reshape3 <- dcast(after.reshape, variable ~ site, mean)
after.reshape3
#variable、site當標籤、game為變數、sum為對應的值
after.reshape4 <- dcast(after.reshape, variable + site ~ game, sum)
after.reshape4
#name的欄位出現NA值(因name的長度只有3，但game的長度有9)
after.reshape4[1:3,1] <- c("Jordan")
after.reshape4[4:6,1] <- c("Lin")
after.reshape4[7:9,1] <- c("Peter")
after.reshape4
```
```{r}
#用merge合併資料
Lin.game <- ballgames[ballgames[,"Lin"] > 20,
c("game", "site", "Lin")]
Jordan.game <- ballgames[ballgames[,"Jordan"] > 20,
c("game", "site", "Jordan")]
Lin.game;Jordan.game
#合併兩筆資料(交集)
JL.game <- merge(Lin.game, Jordan.game)
JL.game
#合併兩筆資料(聯集)
merge(Lin.game, Jordan.game, all = TRUE)
#用特定的資料集合併資料
merge(Lin.game, Jordan.game, all.x = TRUE)
merge(Lin.game, Jordan.game, all.y = TRUE)
```
# 4.迴歸
## 呈現兩個變數的關係
## 在資料分析前，需用變數關係圖，確認變數的關係
```{r}
pairs(airquality[,c(1,3,4)])
data1 <- airquality[1:120, ]
data2 <- airquality[121:153, ]
#lm(formula, data)：線性模型
#formula：y ~ x1 + x2 (with intercept)
#formula：y ~ x1 + x2 - 1(no intercept)
lm1 <- lm(Ozone ~ Temp, data = data1)
lm2 <- lm(Ozone ~ Temp - 1, data = data1)
summary(lm1)
summary(lm2)
#用適合的模型做預測
y.predict <- predict(lm1, data2)
y.predict
#測試模型的表現
plot(airquality[, 4], airquality[, 1], pch = 19)
abline(lm1)
points(airquality[121:153, 4], y.predict, col = 2, pch = 19)
#模型做預測的表現
plot(airquality[121:153, 1], y.predict, pch = 19)
abline(0, 1)
```
# 5.package：dplyr
```{r}
# install.packages("dplyr")
library(dplyr)
y <- sample(1:100, 10)
mean(y)
#%>%表示使用某個function
y %>% mean()
min(y)
y %>% min()
sample(1:100, 5) %>% mean()
sample(1:100, 10) %>% min()
nba_stars <- c("Stephen Curry", "LeBron James")
names <- strsplit(nba_stars, split = " ")
toupper(names[[1]][2])
nba_stars %>%
strsplit(, split = " ") %>%
`[[` (1) %>%
`[` (2) %>%
toupper()
```