Hw exercise3
tjlee
2020-09-19
#本提亦可使用reshape2 # input data
dta <- read.csv("D:/sheu/nlsy86wide.csv")1 inspect data structure
str(dta)## 'data.frame': 166 obs. of 23 variables:
## $ id : int 23901 25601 37401 40201 63501 70301 72001 76101 76801 77001 ...
## $ sex : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 2 2 1 2 ...
## $ race : Factor w/ 2 levels "Majority","Minority": 1 1 1 1 1 1 1 1 1 1 ...
## $ grade86 : int 0 0 0 0 1 0 0 0 0 0 ...
## $ grade88 : int 2 1 2 1 3 2 1 3 2 2 ...
## $ grade90 : int 3 3 5 2 4 3 3 4 5 4 ...
## $ grade92 : int 5 6 6 5 6 5 5 6 6 5 ...
## $ age86year : int 6 6 6 5 7 5 6 7 6 6 ...
## $ age88year : int 8 8 8 8 9 8 8 9 9 8 ...
## $ age90year : int 10 10 10 9 11 10 10 11 11 10 ...
## $ age92year : int 12 12 12 12 13 12 12 13 13 12 ...
## $ age86month: int 67 66 67 60 78 62 66 79 76 67 ...
## $ age88month: int 96 95 95 91 108 93 94 109 104 94 ...
## $ age90month: int 119 119 122 112 132 117 118 131 128 117 ...
## $ age92month: int 142 143 144 139 155 139 140 154 151 139 ...
## $ math86 : num 14.29 20.24 17.86 7.14 29.76 ...
## $ math88 : num 15.5 36.9 22.6 21.4 50 ...
## $ math90 : num 38.1 52.4 53.6 53.6 47.6 ...
## $ math92 : num 41.7 58.3 58.3 51.2 71.4 ...
## $ read86 : num 19.05 21.43 21.43 7.14 30.95 ...
## $ read88 : num 29.8 32.1 45.2 21.4 50 ...
## $ read90 : num 28.6 45.2 69 50 63.1 ...
## $ read92 : num 45.2 57.1 78.6 59.5 82.1 ...2 examine first 6 lines
head(dta)## id sex race grade86 grade88 grade90 grade92 age86year age88year
## 1 23901 Female Majority 0 2 3 5 6 8
## 2 25601 Female Majority 0 1 3 6 6 8
## 3 37401 Female Majority 0 2 5 6 6 8
## 4 40201 Male Majority 0 1 2 5 5 8
## 5 63501 Male Majority 1 3 4 6 7 9
## 6 70301 Male Majority 0 2 3 5 5 8
## age90year age92year age86month age88month age90month age92month math86
## 1 10 12 67 96 119 142 14.285714
## 2 10 12 66 95 119 143 20.238095
## 3 10 12 67 95 122 144 17.857143
## 4 9 12 60 91 112 139 7.142857
## 5 11 13 78 108 132 155 29.761905
## 6 10 12 62 93 117 139 14.285714
## math88 math90 math92 read86 read88 read90 read92
## 1 15.47619 38.09524 41.66667 19.047619 29.76190 28.57143 45.23810
## 2 36.90476 52.38095 58.33333 21.428571 32.14286 45.23810 57.14286
## 3 22.61905 53.57143 58.33333 21.428571 45.23810 69.04762 78.57143
## 4 21.42857 53.57143 51.19048 7.142857 21.42857 50.00000 59.52381
## 5 50.00000 47.61905 71.42857 30.952381 50.00000 63.09524 82.14286
## 6 36.90476 55.95238 63.09524 17.857143 46.42857 64.28571 96.42857library(tidyverse)## -- Attaching packages ------------------------------------------ tidyverse 1.3.0 --## √ ggplot2 3.3.0 √ purrr 0.3.3
## √ tibble 2.1.3 √ dplyr 0.8.5
## √ tidyr 1.0.2 √ stringr 1.4.0
## √ readr 1.3.1 √ forcats 0.5.0## -- Conflicts --------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(tidyr)
library(dplyr)3 wide to long
###本人嘗試許多種方法，無論gather或reshape，但每當gather一次id就會增4倍，因此本人選擇用select再把他bind起來
## id sex race grade86 grade88 grade90 grade92
## 1 23901 Female Majority 0 2 3 5
## 2 25601 Female Majority 0 1 3 6
## 3 37401 Female Majority 0 2 5 6
## 4 40201 Male Majority 0 1 2 5
## 5 63501 Male Majority 1 3 4 6
## 6 70301 Male Majority 0 2 3 5## id sex race t_grade grade
## 659 1055401 Male Minority grade92 6
## 660 1187601 Male Majority grade92 6
## 661 1214801 Male Minority grade92 6
## 662 1218801 Female Minority grade92 6
## 663 1222801 Female Minority grade92 5
## 664 1224101 Male Minority grade92 6## age86year age88year age90year age92year
## 1 6 8 10 12
## 2 6 8 10 12
## 3 6 8 10 12
## 4 5 8 9 12
## 5 7 9 11 13
## 6 5 8 10 12## t_year year
## 659 age92year 13
## 660 age92year 12
## 661 age92year 12
## 662 age92year 12
## 663 age92year 11
## 664 age92year 12## id sex race t_grade grade t_year year t_mon month
## 659 1055401 Male Minority grade92 6 age92year 13 age92month 152
## 660 1187601 Male Majority grade92 6 age92year 12 age92month 147
## 661 1214801 Male Minority grade92 6 age92year 12 age92month 147
## 662 1218801 Female Minority grade92 6 age92year 12 age92month 145
## 663 1222801 Female Minority grade92 5 age92year 11 age92month 136
## 664 1224101 Male Minority grade92 6 age92year 12 age92month 149
## t_math math t_read read
## 659 math92 65.47619 read92 53.57143
## 660 math92 66.66667 read92 91.66667
## 661 math92 67.85714 read92 78.57143
## 662 math92 70.23810 read92 64.28571
## 663 math92 71.42857 read92 72.61905
## 664 math92 54.76190 read92 52.380954 plot
ggplot(data=longdta, aes(x=month, y=read, group=id)) +
geom_point(size=rel(.5)) +
stat_smooth(method ="lm", formula=y ~ x, se=F) +
facet_grid(race ~ sex) +
labs(x="Month", y="Reading score") +
theme_bw()
###