Module 7 Assignment

Part 1

• First we will read in the data.

Temp <- read.csv("Temperature.csv")
ls(Temp)

##  [1] "Area"        "CHLFa"       "Date"        "DateNr"      "dDay1"      
##  [6] "dDay2"       "dDay3"       "Month"       "Salinity"    "Sample"     
## [11] "Season"      "Station"     "Temperature" "X31UE_ED50"  "X31UN_ED50" 
## [16] "Year"

library(ggplot2)
library(reshape2)

-Next we will utilize ggplot() to produce a histogram of salinity values

qplot(Salinity, data = Temp, geom = 'histogram', binwidth = 0.25)

## Warning: Removed 798 rows containing non-finite values (stat_bin).

-Then we will create a histogram of salinity values for each, and then each month of the study.

tempplot = ggplot(Temp, aes(x = Salinity))
tempplot + geom_histogram(binwidth = 1)

## Warning: Removed 798 rows containing non-finite values (stat_bin).

tempplot + geom_histogram(aes(fill = Year), position = "identity")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 798 rows containing non-finite values (stat_bin).

tempplot + geom_histogram(fill = 'darkorange', binwidth = 1) + 
  facet_wrap(Temp$Year)

## Warning: Removed 798 rows containing non-finite values (stat_bin).

tempplot + geom_histogram(fill = 'olivedrab', binwidth = 1) +
  facet_wrap(Temp$Month)

## Warning: Removed 798 rows containing non-finite values (stat_bin).

As you can see by the two graphs, I was able to utilize the face_wrap() feature to create different graphs for each of the months and years. - Next we created a boxplot based on the temperature values of each station.

tempbox = ggplot(Temp, aes(x = Temperature, y = Station))
tempbox + geom_boxplot()

## Warning: Removed 927 rows containing non-finite values (stat_boxplot).

ggsave("temp_vs_station_.png", tempbox)

## Saving 7 x 5 in image

-Finally as a bonus we attempted to reorganize the boxplot from low to high median temperatures.

tempbox + geom_boxplot(aes(x = reorder(Station, Temperature, median)))

- Dont really know if I did this right. Looks like a man-made horror far beyond my comprehension.

Part 2

• For this part we will be making some time series plots of temperature and salinity. In order to do so we decided to create a variable that represents cintinuous time from the start of observations. We created a decimal date variable to coding:

Temp$decdate <- Temp$Year + Temp$dDay3 / 365

• Now that we have this variable we will make a scatterplot of temperature and salinity over time with:

timeplot = ggplot(Temp, aes(x = Salinity, y = Temperature))
timeplot + geom_point()

## Warning: Removed 963 rows containing missing values (geom_point).

timeplot = ggplot(Temp, aes(x = Salinity, y = Temperature, color = decdate))
timeplot + geom_point() + scale_x_log10()

## Warning: Removed 963 rows containing missing values (geom_point).

timeplot + geom_point() + geom_smooth(method = 'lm')

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 963 rows containing non-finite values (stat_smooth).

## Warning: Removed 963 rows containing missing values (geom_point).

- Now utilizing the facet_wraap() command, we made a scatterplot of salinity grouped into different ‘Areas’:

scatsal = ggplot(Temp, aes(x = Salinity, y = Temperature))
scatsal + geom_point()

## Warning: Removed 963 rows containing missing values (geom_point).

scatsal + geom_point(color = 'lightblue', fill = 'white') + facet_wrap(~Area)

## Warning: Removed 963 rows containing missing values (geom_point).

- Finally we created a lineplot of salinity for each station grouped by area.

scatsal = ggplot(Temp, aes(x = Salinity, y = Station))
scatsal + geom_line() + scale_x_log10()

## Warning: Removed 798 row(s) containing missing values (geom_path).

scatsal + geom_line(color = 'olivedrab', fill = 'white') + facet_wrap(~Area)

## Warning: Ignoring unknown parameters: fill

## Warning: Removed 798 row(s) containing missing values (geom_path).