cancor_eof: Performs CCA using Empirical Orthogonal Functions (EOFs) from...

In stxplore: Exploration of Spatio-Temporal Data

Performs CCA using Empirical Orthogonal Functions (EOFs) from a lagged dataset

Description

Performs Canonical Correlation Analysis (CCA) using Empirical Orthogonal Function analysis using in a dataframe or a stars object. The autoplot function can plot the outputs.

The variations are * 'cancor_eof.data.frame()' if the input is a dataframe * 'cancor_eof.stars()' if the input is a stars object * 'autoplot.cancoreof()' to plot the outputs.

Usage

cancor_eof(x, lag, n_eof, ...)

## S3 method for class 'data.frame'
cancor_eof(x, lag = 7, n_eof = 10, values_df, ...)

## S3 method for class 'stars'
cancor_eof(x, lag = 7, n_eof = 10, ...)

## S3 method for class 'cancoreof'
autoplot(
  object,
  line_plot = TRUE,
  space_plot = TRUE,
  palette = "Spectral",
  xlab = "Time",
  ...
)

Arguments

x	The dataframe or stars object. If it is a dataframe, then it should have the locations.
lag	Specifies the lag to be used.
n_eof	The number of EOFs to be used.
...	Other arguments currently ignored.
values_df	For dataframes: the dataframe of dimension length(times) x length(locations) containing the quantity of interest.
object	autoplot parameter: the output of the function ‘cancor_eof’.
line_plot	autoplot parameter: if set to TRUE, then the line plot is included.
space_plot	autoplot parameter: if set to TRUE, the space splot is included.
palette	autoplot parameter: the color palette to use for plotting.
xlab	autoplot parameter:: he label on the x-axis for the line plot.

Value

A cancoreof object with CCA output, EOF output, original data and cancor object from 'stats'.

Examples

# Dataframe example
data(SSTlonlatshort)
data(SSTdatashort)
cancor_df <- cancor_eof(x = SSTlonlatshort,
           lag = 7,
           n_eof = 8,
           values_df = SSTdatashort)
autoplot(cancor_df)

# Stars example
library(dplyr)
library(stars)
# Create a stars object from a data frame
precip_df <- NOAA_df_1990[NOAA_df_1990$proc == 'Precip', ] %>%
  filter(date >= "1992-02-01" & date <= "1992-02-28")
precip <- precip_df[ ,c('lat', 'lon', 'date', 'z')]
st_precip <- st_as_stars(precip, dims = c("lon", "lat", "date"))
cancor_st <- cancor_eof(st_precip)
autoplot(cancor_st, line_plot = TRUE, space_plot = FALSE)

stxplore documentation built on Feb. 16, 2023, 9:53 p.m.