Correlation Analysis

Newdata <- read.csv(file = "D:/Jeremiah/Grouped_data.csv")
#print(Newdata)
  
# print number of columns
print (ncol(Newdata)) 

## [1] 9

# print number of rows
print(nrow(Newdata))  

## [1] 120148

# select numeric variables 
df <- dplyr::select_if(Newdata, is.numeric)
head(df,6)

##   precip_month_avg elevation_m_0buff temperature_month_avg_0km Count.of.Species
## 1          1.09252          1038.542                  34.73000                4
## 2          1.09252          1038.542                  36.88000                4
## 3          1.09252          1038.542                  32.47500                4
## 4          1.09252          1038.542                  42.71667                4
## 5          1.09252          1038.542                  38.91000                4
## 6          1.09252          1038.542                  30.67000                4

# calulate the correlations
r <- cor(df, use="complete.obs")
round(r,2)

##                           precip_month_avg elevation_m_0buff
## precip_month_avg                      1.00              0.16
## elevation_m_0buff                     0.16              1.00
## temperature_month_avg_0km            -0.22             -0.58
## Count.of.Species                     -0.08             -0.09
##                           temperature_month_avg_0km Count.of.Species
## precip_month_avg                              -0.22            -0.08
## elevation_m_0buff                             -0.58            -0.09
## temperature_month_avg_0km                      1.00             0.09
## Count.of.Species                               0.09             1.00

library(ggplot2)
library(ggcorrplot)
ggcorrplot(r)

ggcorrplot(r, 
           hc.order = TRUE, 
           type = "lower",
           lab = TRUE)