library(data.table)Warning: package 'data.table' was built under R version 4.4.3temp <- fread("../data/temperature.csv")Module11_Gordon
Module 11
- Read in the data using
fread()
- Extract all winter observations
wint <- temp[Season == "winter"]
wint 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
wint_nc <- temp[Season == "winter" & Area == "NC"]
wint_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,SeasonandTemperature
AST <- temp[, .(Area, Season, Temperature)]
AST 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
AreaandTemperaturebut only for winter observations
AT_wint <- temp[Season == "winter", .(Area, Temperature)]
AT_wint 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
wint_count <- temp[Season == "winter", .N]
wint_count[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)
wint_means <- temp[Season == "winter",
lapply(.SD, mean, na.rm = TRUE),
.SDcols = c("Temperature", "Salinity")]
wint_means Temperature Salinity
<num> <num>
1: 5.57162 29.15756- Find the number of observations per station in winter
wint_station_counts <- temp[Season == "winter", .N, by = Station]
wint_station_counts Station N
<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 N- Find the number of observations per station per season
station_season_counts <- temp[, .N, by = .(Station, Season)]
station_season_counts 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
monthly_avg_temp <- temp[, .(mean_temp = mean(Temperature, na.rm = TRUE)), by = Month]
monthly_avg_temp Month mean_temp
<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
monthly_area_avg_temp <- temp[, .(mean_temp = mean(Temperature, na.rm = TRUE)), by = .(Month, Area)]
monthly_area_avg_temp Month Area mean_temp
<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
library(ggplot2)Warning: package 'ggplot2' was built under R version 4.4.3ggplot(monthly_area_avg_temp, aes(x = Month, y = mean_temp, color = Area)) +
geom_line()