# Load the package
library(data.table)
Attaching package: 'data.table'The following object is masked from 'package:base':
%notin%library(ggplot2)exercise11
0. Setting
1. Read in the data using fread
temp_data <- fread("./data/Temperature.csv")
temp_data 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.19900308 19900308 8/3/90 64 66 66 DANT WZ
4: DANT.19900404 19900404 4/4/90 91 93 93 DANT WZ
5: DANT.19900509 19900509 9/5/90 126 128 128 DANT WZ
---
8524: ZUID.20050926 20050926 9/26/2005 5745 5747 268 ZUID WZ
8525: ZUID.20051012 20051012 12/10/05 5761 5763 284 ZUID WZ
8526: ZUID.20051027 20051027 10/27/2005 5776 5778 299 ZUID WZ
8527: ZUID.20051110 20051110 10/11/05 5790 5792 313 ZUID WZ
8528: 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 3 spring 24.99 7.30 21.10
4: 681379.6 5920571 1990 4 spring 28.79 8.20 25.00
5: 681379.6 5920571 1990 5 spring 33.28 17.40 10.20
---
8524: 733386.3 5928197 2005 9 autumn 30.91 15.47 11.40
8525: 733386.3 5928197 2005 10 autumn 31.18 13.45 8.30
8526: 733386.3 5928197 2005 10 autumn 28.67 12.09 4.56
8527: 733386.3 5928197 2005 11 autumn 29.53 9.03 4.94
8528: 733386.3 5928197 2005 12 winter 29.08 5.13 2.382. Extract all winter observations
winter_obs <- temp_data[Season == "winter"]
head(winter_obs) Sample Date DateNr dDay1 dDay2 dDay3 Station Area 31UE_ED50
<char> <int> <char> <int> <int> <int> <char> <char> <num>
1: DANT.19900110 19900110 10/1/90 7 9 9 DANT WZ 681379.6
2: DANT.19900206 19900206 6/2/90 34 36 36 DANT WZ 681379.6
3: DANT.19901212 19901212 12/12/90 343 345 345 DANT WZ 681379.6
4: DANT.19910116 19910116 1/16/1991 378 380 15 DANT WZ 681379.6
5: DANT.19910226 19910226 2/26/1991 419 421 56 DANT WZ 681379.6
6: DANT.19911219 19911219 12/19/1991 715 717 352 DANT WZ 681379.6
31UN_ED50 Year Month Season Salinity Temperature CHLFa
<num> <int> <int> <char> <num> <num> <num>
1: 5920571 1990 1 winter 29.19 4.0 1.30
2: 5920571 1990 2 winter 27.37 6.0 NA
3: 5920571 1990 12 winter 31.50 4.2 60.50
4: 5920571 1991 1 winter 20.83 -0.3 2.30
5: 5920571 1991 2 winter 28.06 3.9 3.52
6: 5920571 1991 12 winter 25.31 3.9 3.503. Extract all winter observations for zone NC
winter_nc <- temp_data[Season == "winter" & Area == "NC"]
head(winter_nc) Sample Date DateNr dDay1 dDay2 dDay3 Station Area 31UE_ED50
<char> <int> <char> <int> <int> <int> <char> <char> <num>
1: T100.19900103 19900103 3/1/90 0 2 2 T100 NC 587650.2
2: T100.19900205 19900205 5/2/90 33 35 35 T100 NC 587650.2
3: T100.19901218 19901218 12/18/1990 349 351 351 T100 NC 587650.2
4: T100.19910116 19910116 1/16/1991 378 380 15 T100 NC 587650.2
5: T100.19910205 19910205 5/2/91 398 400 35 T100 NC 587650.2
6: T100.19911211 19911211 11/12/91 707 709 344 T100 NC 587650.2
31UN_ED50 Year Month Season Salinity Temperature CHLFa
<num> <int> <int> <char> <num> <num> <num>
1: 6001110 1990 1 winter 34.82 8.5 0.30
2: 6001110 1990 2 winter NA NA NA
3: 6001110 1990 12 winter 34.80 9.2 0.40
4: 6001110 1991 1 winter 34.86 6.1 0.68
5: 6001110 1991 2 winter 34.53 5.2 0.34
6: 6001110 1991 12 winter 34.79 9.7 0.444. Select only the columns Area, Season and Temperature
cols_select1 <- temp_data[, .(Area, Season, Temperature)]
head(cols_select1) Area Season Temperature
<char> <char> <num>
1: WZ winter 4.0
2: WZ winter 6.0
3: WZ spring 7.3
4: WZ spring 8.2
5: WZ spring 17.4
6: WZ summer 18.15. Select only the columns Area and Temperature but only for winter observations
winter_cols <- temp_data[Season == "winter", .(Area, Temperature)]
head(winter_cols) Area Temperature
<char> <num>
1: WZ 4.0
2: WZ 6.0
3: WZ 4.2
4: WZ -0.3
5: WZ 3.9
6: WZ 3.96. Find the total number of observations in winter
winter_count <- temp_data[Season == "winter", .N]
winter_count[1] 17067. Calculate the mean temperature and mean salinity in winter (Note that there are missing values so will have to use na.rm = TRUE)
winter_means <- temp_data[Season == "winter",
.(mean_temp = mean(Temperature, na.rm = TRUE),
mean_sal = mean(Salinity, na.rm = TRUE))]
winter_means mean_temp mean_sal
<num> <num>
1: 5.57162 29.157568. Find the number of observations per station in winter
station_winter_count <- temp_data[Season == "winter", .N, by = Station]
head(station_winter_count) Station N
<char> <int>
1: DANT 50
2: DREI 52
3: G6 101
4: GROO 50
5: HAMM 55
6: HANS 569. Find the number of observations per station per season
station_season_count <- temp_data[, .N, by = .(Station, Season)]
head(station_season_count) 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
6: DREI spring 9210. Estimate average temperatures by month
avg_temp_month <- temp_data[, .(mean_temp = mean(Temperature, na.rm = TRUE)), by = Month]
avg_temp_month 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 6.74633911. Estimate average temperatures by month by area
avg_temp_month_area <- temp_data[,
.(mean_temp = mean(Temperature, na.rm = TRUE)),
keyby = .(Month, Area)]
head(avg_temp_month_area)Key: <Month, Area>
Month Area mean_temp
<int> <char> <num>
1: 1 ED 3.086333
2: 1 GM 4.308750
3: 1 KZ 5.296222
4: 1 NC 6.789808
5: 1 NZ 8.122000
6: 1 OS 4.86802812. Plot the output of the previous question using ggplot2 using the geom_line() geometry
ggplot(avg_temp_month_area, aes(x = Month, y = mean_temp, col = Area)) +
geom_line() +
labs(title = "Average Temperature by Month and Area",
x = "Month",
y = "Mean Temperature")