EX1

# 讀取資料，進行轉置
dta <- read.csv("nlsy86long.csv" , header=T)
head(dta)
##     id    sex     race time grade year month      math      read
## 1 2390 Female Majority    1     0    6    67 14.285714 19.047619
## 2 2560 Female Majority    1     0    6    66 20.238095 21.428571
## 3 3740 Female Majority    1     0    6    67 17.857143 21.428571
## 4 4020   Male Majority    1     0    5    60  7.142857  7.142857
## 5 6350   Male Majority    1     1    7    78 29.761905 30.952381
## 6 7030   Male Majority    1     0    5    62 14.285714 17.857143
dtaNew <- dta %>% 
 gather(key = test_var, value = test_score, 8:9)
head(dtaNew)
##     id    sex     race time grade year month test_var test_score
## 1 2390 Female Majority    1     0    6    67     math  14.285714
## 2 2560 Female Majority    1     0    6    66     math  20.238095
## 3 3740 Female Majority    1     0    6    67     math  17.857143
## 4 4020   Male Majority    1     0    5    60     math   7.142857
## 5 6350   Male Majority    1     1    7    78     math  29.761905
## 6 7030   Male Majority    1     0    5    62     math  14.285714

EX2

# 確認Vocab檔案後進行製圖
head(Vocab)
##          year    sex education vocabulary
## 20040001 2004 Female         9          3
## 20040002 2004 Female        14          6
## 20040003 2004   Male        14          9
## 20040005 2004 Female        17          8
## 20040008 2004   Male        14          1
## 20040010 2004   Male        14          7
Vocab %>%
 rename(Gender = sex) %>%
 group_by(Gender, year) %>%
 summarize(edu_m = mean(education, na.rm = T),
           edu_se = sd(education, na.rm = T)/sqrt(n()),
           voc_m = mean(vocabulary, na.rm = T),
           voc_se = sd(vocabulary, na.rm = T)/sqrt(n())) %>%
 ggplot(data = ., aes(x = year, y = edu_m, color = Gender)) +
  geom_point(position = position_dodge(.5), size = rel(2))+
  geom_line(aes(group = Gender), position = position_dodge(.5)) +
  geom_errorbar(aes(ymin = edu_m - 2*edu_se, ymax = edu_m + 2*edu_se), width = .1, position = position_dodge(.5)) + 
  geom_point(aes(y = voc_m), position = position_dodge(.5), size = rel(2), pch = 1)+
  geom_line(aes(y = voc_m, group = Gender), position = position_dodge(.5), linetype = "dashed") +
  geom_errorbar(aes(ymin = voc_m - 2*voc_se, ymax = voc_m + 2*voc_se), width = .1, position = position_dodge(.5)) + 
  labs(x = "Year", y = "Average Education Year and Vocabulary") +
  theme_bw() 
## Warning: package 'bindrcpp' was built under R version 3.4.4

## EX3

# 讀取檔案
dta2 <- read.table("probeL.txt", header = T)
head(dta2)
##    ID Response_Time Position
## 1 S01            51        1
## 2 S01            36        2
## 3 S01            50        3
## 4 S01            35        4
## 5 S01            42        5
## 6 S02            27        1
# 轉為wide format
dta2 %>% 
  mutate(Position = paste("Pos", Position, sep = "_")) %>% 
  spread(Position, Response_Time)
##     ID Pos_1 Pos_2 Pos_3 Pos_4 Pos_5
## 1  S01    51    36    50    35    42
## 2  S02    27    20    26    17    27
## 3  S03    37    22    41    37    30
## 4  S04    42    36    32    34    27
## 5  S05    27    18    33    14    29
## 6  S06    43    32    43    35    40
## 7  S07    41    22    36    25    38
## 8  S08    38    21    31    20    16
## 9  S09    36    23    27    25    28
## 10 S10    26    31    31    32    36
## 11 S11    29    20    25    26    25

EX4

dta3.1 <- read.table("nobel_countries.txt", header = T)
dta3.2 <- read.table("nobel_winners.txt", header = T)
# 將兩個argument共通部分進行合併
inner_join(dta3.1, dta3.2)
## Joining, by = "Year"
##   Country Year              Name Gender
## 1  France 2014   Patrick Modiano   Male
## 2      UK 1950 Bertrand  Russell   Male
## 3      UK 2017    Kazuo Ishiguro   Male
## 4      US 2016        Bob  Dylan   Male
## 5  Canada 2013      Alice  Munro Female
## 6   China 2012            Mo Yan   Male
# 以第一個argument內的變項為基準，與第二個進行合併
left_join(dta3.1, dta3.2)
## Joining, by = "Year"
##   Country Year              Name Gender
## 1  France 2014   Patrick Modiano   Male
## 2      UK 1950 Bertrand  Russell   Male
## 3      UK 2017    Kazuo Ishiguro   Male
## 4      US 2016        Bob  Dylan   Male
## 5  Canada 2013      Alice  Munro Female
## 6   China 2012            Mo Yan   Male
## 7  Russia 2015              <NA>   <NA>
## 8  Sweden 2011              <NA>   <NA>
# 以兩者共通資料，並以第一個argument為基礎進行合併
semi_join(dta3.1, dta3.2)
## Joining, by = "Year"
##   Country Year
## 1  France 2014
## 2      UK 1950
## 3      UK 2017
## 4      US 2016
## 5  Canada 2013
## 6   China 2012
# 將無法順利合併的資料列出
anti_join(dta3.1, dta3.2)
## Joining, by = "Year"
##   Country Year
## 1  Russia 2015
## 2  Sweden 2011
# 將所有情況合併列出，無論適合與否
full_join(dta3.1, dta3.2)
## Joining, by = "Year"
##   Country Year              Name Gender
## 1  France 2014   Patrick Modiano   Male
## 2      UK 1950 Bertrand  Russell   Male
## 3      UK 2017    Kazuo Ishiguro   Male
## 4      US 2016        Bob  Dylan   Male
## 5  Canada 2013      Alice  Munro Female
## 6   China 2012            Mo Yan   Male
## 7  Russia 2015              <NA>   <NA>
## 8  Sweden 2011              <NA>   <NA>
## 9    <NA> 1938        Pearl Buck Female