Climatic change in the last few decades has had a widespread impact on both natural and human systems, observable on all continents. Ecological and environmental models using climatic data often rely on gridded data, such as WorldClim.
WorldClim is a set of global climate layers (gridded climate data in GeoTiff format) that can be used for mapping and spatial modeling. WordlClim version 2 contains average monthly climatic gridded data for the period 1970-2000 with different spatial resolutions, from 30 seconds (~1 km2) to 10 minutes (~340 km2).
One of the key task of scientist is communicate your analysis and result to the different group of people. The typical data analysis workflow looks like this: you go out and collect data and you organize it in a file or spreadsheet or database. Then interact with R using scripts to run some analyses, perhaps saving some intermediate results along the way or maybe always working on the raw data.
In this post we will learn to work with date and time data in R. We will use the lubridate package developed by Garrett Grolemund and Hadley Wickham ~@lubridate. This package makes it easy to work with dates and time. Let’s us load the packages that we will use
require(lubridate) require(tidyverse) require(magrittr) require(oce) Data We will use the profiles data from Argo within the Indian Ocean. The data was downloaded from the Coriolis Global Data Assembly Center site (ftp://ftp.
One of the key task in data preparation is to organize thee dataset in a way that makes analysis and plottng easier. In practice, the data is often not stored like that and the data comes to us with repeated observations included on a single row. This is often done as a memory saving technique or because there is some structure in the data that makes the ‘wide’ format attractive.
Before a dataset can be analysed in R, its often manipulated or transformed in various ways. For years manipulating data in R required more programming than actually analyzing data. That has improved dramatically with the dplyr package. It provides programmers with an intuitive vocabulary for executing data management and analysis tasks. Hadley Wickham [-@dplyr], the original creator of the dplyr package, refers to it as a Grammar of Data Manipulation.
