Pairs Plot Using R
This workflow uses a preprocessed portion of the well known "Airline" dataset to generate a pairs plot for meteorological variable using R scripting.
A "pairs" plot to shows relationships between combinations of variables in a data set. Here we filter the original data down to just five meteorological variables, aggregated daily:
PRCP_Orig: precipitation
SNWD_Orig: snow depth
SNOW_Orig: snowfall recieved
TMAX_Orig: maximum temperature
TMIN_Orig: minimum temperature
This produces a 5x5 grid. In the lower half of the grid we see scatter plots of variables plotted against one another, with a linear regression line overlaid in red to give an idea of a general trend. The upper half of the grid presents correlation values between the variables.
For example, we can see that there is not much relationship between snow depth and snowfall recieved, as the slope of the regression line is small, and the correlation is 0.02. Conversely, we can see that minimum and maximum temperature are closely related, with a large slope, and a high correlation (0.76).
This workflow uses a preprocessed portion of the well known "Airline" dataset to generate a pairs plot for meteorological variable using R scripting.
A "pairs" plot to shows relationships between combinations of variables in a data set. Here we filter the original data down to just five meteorological variables, aggregated daily:
PRCP_Orig: precipitation
SNWD_Orig: snow depth
SNOW_Orig: snowfall recieved
TMAX_Orig: maximum temperature
TMIN_Orig: minimum temperature
This produces a 5x5 grid. In the lower half of the grid we see scatter plots of variables plotted against one another, with a linear regression line overlaid in red to give an idea of a general trend. The upper half of the grid presents correlation values between the variables.
For example, we can see that there is not much relationship between snow depth and snowfall recieved, as the slope of the regression line is small, and the correlation is 0.02. Conversely, we can see that minimum and maximum temperature are closely related, with a large slope, and a high correlation (0.76).