Module 11: Data Manipulation III
Becca Whitaker
2025-06-07
library(data.table)## Warning: package 'data.table' was built under R version 4.4.3library(ggplot2)
temp <- fread("./data/Temperature.csv")#Extract all winter data
temp[Season=="winter"]## Sample Date DateNr dDay1 dDay2 dDay3 Station Area
## <char> <int> <char> <int> <int> <int> <char> <char>
## 1: DANT.19900110 19900110 10/1/90 7 9 9 DANT WZ
## 2: DANT.19900206 19900206 6/2/90 34 36 36 DANT WZ
## 3: DANT.19901212 19901212 12/12/90 343 345 345 DANT WZ
## 4: DANT.19910116 19910116 1/16/1991 378 380 15 DANT WZ
## 5: DANT.19910226 19910226 2/26/1991 419 421 56 DANT WZ
## ---
## 1702: ZUID.20040216 20040216 2/16/2004 5157 5159 46 ZUID WZ
## 1703: ZUID.20041208 20041208 8/12/04 5453 5455 342 ZUID WZ
## 1704: ZUID.20050119 20050119 1/19/2005 5495 5497 18 ZUID WZ
## 1705: ZUID.20050218 20050218 2/18/2005 5525 5527 48 ZUID WZ
## 1706: ZUID.20051212 20051212 12/12/05 5822 5824 345 ZUID WZ
## 31UE_ED50 31UN_ED50 Year Month Season Salinity Temperature CHLFa
## <num> <num> <int> <int> <char> <num> <num> <num>
## 1: 681379.6 5920571 1990 1 winter 29.19 4.00 1.30
## 2: 681379.6 5920571 1990 2 winter 27.37 6.00 NA
## 3: 681379.6 5920571 1990 12 winter 31.50 4.20 60.50
## 4: 681379.6 5920571 1991 1 winter 20.83 -0.30 2.30
## 5: 681379.6 5920571 1991 2 winter 28.06 3.90 3.52
## ---
## 1702: 733386.3 5928197 2004 2 winter 24.70 4.40 NA
## 1703: 733386.3 5928197 2004 12 winter 28.67 4.72 1.52
## 1704: 733386.3 5928197 2005 1 winter 28.39 3.57 4.12
## 1705: 733386.3 5928197 2005 2 winter 29.31 1.31 6.56
## 1706: 733386.3 5928197 2005 12 winter 29.08 5.13 2.38#Extract all winter observations for zone NC
temp[Season=="winter" & Area=="NC"]## Sample Date DateNr dDay1 dDay2 dDay3 Station Area
## <char> <int> <char> <int> <int> <int> <char> <char>
## 1: T100.19900103 19900103 3/1/90 0 2 2 T100 NC
## 2: T100.19900205 19900205 5/2/90 33 35 35 T100 NC
## 3: T100.19901218 19901218 12/18/1990 349 351 351 T100 NC
## 4: T100.19910116 19910116 1/16/1991 378 380 15 T100 NC
## 5: T100.19910205 19910205 5/2/91 398 400 35 T100 NC
## ---
## 177: T235.20040209 20040209 9/2/04 5150 5152 39 T235 NC
## 178: T235.20041214 20041214 12/14/2004 5459 5461 348 T235 NC
## 179: T235.20050126 20050126 1/26/2005 5502 5504 25 T235 NC
## 180: T235.20050214 20050214 2/14/2005 5521 5523 44 T235 NC
## 181: T235.20051220 20051220 12/20/2005 5830 5832 353 T235 NC
## 31UE_ED50 31UN_ED50 Year Month Season Salinity Temperature CHLFa
## <num> <num> <int> <int> <char> <num> <num> <num>
## 1: 587650.2 6001110 1990 1 winter 34.82 8.50 0.30
## 2: 587650.2 6001110 1990 2 winter NA NA NA
## 3: 587650.2 6001110 1990 12 winter 34.80 9.20 0.40
## 4: 587650.2 6001110 1991 1 winter 34.86 6.10 0.68
## 5: 587650.2 6001110 1991 2 winter 34.53 5.20 0.34
## ---
## 177: 510032.3 6114101 2004 2 winter NA NA NA
## 178: 510032.3 6114101 2004 12 winter 34.96 8.47 0.62
## 179: 510032.3 6114101 2005 1 winter 35.09 6.44 0.62
## 180: 510032.3 6114101 2005 2 winter NA NA NA
## 181: 510032.3 6114101 2005 12 winter 33.87 8.19 1.12#Select only the columns Area, Season and Temperature
temp[,c("Area", "Season", "Temperature")]## Area Season Temperature
## <char> <char> <num>
## 1: WZ winter 4.00
## 2: WZ winter 6.00
## 3: WZ spring 7.30
## 4: WZ spring 8.20
## 5: WZ spring 17.40
## ---
## 8524: WZ autumn 15.47
## 8525: WZ autumn 13.45
## 8526: WZ autumn 12.09
## 8527: WZ autumn 9.03
## 8528: WZ winter 5.13#Select only the columns Area and Temperature but only for winter observations
temp[Season=="winter", c("Area", "Temperature")]## Area Temperature
## <char> <num>
## 1: WZ 4.00
## 2: WZ 6.00
## 3: WZ 4.20
## 4: WZ -0.30
## 5: WZ 3.90
## ---
## 1702: WZ 4.40
## 1703: WZ 4.72
## 1704: WZ 3.57
## 1705: WZ 1.31
## 1706: WZ 5.13#Find the total number of observations in winter
temp[Season=="winter", (.N)]## [1] 1706#Calculate the mean temperature and mean salinity in winter (Note that there are missing values so will have to use na.rm = TRUE)
temp[Season=="winter", lapply(.SD, mean, na.rm=TRUE), .SDcols = c("Temperature", "Salinity")]## Temperature Salinity
## <num> <num>
## 1: 5.57162 29.15756#Find the number of observations per station in winter
temp[Season=="winter", (.N), by = Station]## Station V1
## <char> <int>
## 1: DANT 50
## 2: DREI 52
## 3: G6 101
## 4: GROO 50
## 5: HAMM 55
## 6: HANS 56
## 7: HUIB 50
## 8: LODS 54
## 9: MARS 49
## 10: N02 115
## 11: N10 131
## 12: N20 50
## 13: N70 50
## 14: R03 32
## 15: SOEL 50
## 16: T004 97
## 17: T010 45
## 18: T100 45
## 19: T135 46
## 20: T175 45
## 21: T235 45
## 22: VLIS 84
## 23: W02 99
## 24: W20 47
## 25: W70 47
## 26: WISS 55
## 27: ZIJP 54
## 28: ZUID 52
## Station V1#Find the number of observations per station per season
temp[ , .(.N), by = c("Station", "Season")]## Station Season N
## <char> <char> <int>
## 1: DANT winter 50
## 2: DANT spring 89
## 3: DANT summer 89
## 4: DANT autumn 72
## 5: DREI winter 52
## ---
## 114: ZIJP autumn 61
## 115: ZUID winter 52
## 116: ZUID spring 89
## 117: ZUID summer 89
## 118: ZUID autumn 73#Estimate average temperatures by month
temp[, lapply(.SD, mean, na.rm=TRUE), by = Month, .SDcols = "Temperature"]## Month Temperature
## <int> <num>
## 1: 1 5.174210
## 2: 2 4.737400
## 3: 3 6.125961
## 4: 4 8.702035
## 5: 5 12.293479
## 6: 6 15.659933
## 7: 7 18.077343
## 8: 8 19.388355
## 9: 9 16.995974
## 10: 10 13.619670
## 11: 11 9.848891
## 12: 12 6.746339#Estimate average temperatures by month by area
temp[, lapply(.SD, mean, na.rm=TRUE), by = c("Month", "Area"), .SDcols = "Temperature"]## Month Area Temperature
## <int> <char> <num>
## 1: 1 WZ 3.377826
## 2: 2 WZ 3.925800
## 3: 3 WZ 5.818481
## 4: 4 WZ 9.270805
## 5: 5 WZ 13.398191
## ---
## 116: 1 NC 6.789808
## 117: 2 NC 5.682581
## 118: 3 NC 5.837500
## 119: 11 NC 10.978269
## 120: 12 NC 8.716957#Plot the output of the previous question using ggplot2 using the geom_line() geometry
ans<- temp[, lapply(.SD, mean, na.rm=TRUE), by = c("Month", "Area"), .SDcols = "Temperature"]
ggplot(ans, aes(x=Month, y=Temperature, colour = Area)) + geom_line()