# Load the package
library(data.table)
Attaching package: 'data.table'The following object is masked from 'package:base':
%notin%library(ggplot2)Module11_Exercise: Data Manipulation
Setup
1. Read in the Data Using Fread
temp <- fread("./data/Temperature.csv")
temp 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[Season == "winter"]3. Extract All Winter Observations for Zone NC
winter_nc <- temp[Season == "winter" & Area == "NC"]4. Select Only the Columns Area, Season and Temperature
cols_select1 <- temp[, .(Area, Season, Temperature)]5. Select Only Area and Temperature but Only for Winter Observations
winter_cols <- temp[Season == "winter", .(Area, Temperature)]6. Find Total Number of Observations in Winter
winter_count <- temp[Season == "winter", .N]
winter_count[1] 17067. Calculate Mean Temperature and Mean Salinity in Winter (Note that there are missing values so will have to use na.rm = TRUE)
winter_means <- temp[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 Number of Observations Per Station in Winter
station_winter_count <- temp[Season == "winter", .N, by = Station]9. Find Number of Observations Per Station Per Season
station_season_count <- temp[, .N, by = .(Station, Season)]10. Estimate Average Temperatures by Month
month_avg <- temp[, .(mean_temp = mean(Temperature, na.rm = TRUE)), by = Month]
month_avg 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
month_area_avg <- temp[,
.(mean_temp = mean(Temperature, na.rm = TRUE)),
keyby = .(Month, Area)]12. Plot Output of Previous Question
ggplot(month_area_avg, aes(x = Month, y = mean_temp, col = Area)) +
geom_line() +
labs(title = "Average Temperature by Month and Area",
x = "Month",
y = "Mean Temperature") +
theme_minimal()