Systems and methods for selecting variable transformations

1. A computer-implemented method of determining whether a set of data is to be graphically plotted in linear space or logarithmic space, the method comprising:

receiving, by a computer device, a set of data points to be plotted;

determining, by the compute device, whether the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points;

upon a determination that the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points:

classifying, by the computer device, the data points into a first plurality of bins;

computing, by the computer device, a first entropy of a frequency of the data points based on a percentage of the data points that fall into each of the first plurality of bins;

computing, by the computer device, a logarithmic transformation of each of the data points;

classifying, by the computer device, the logarithmic transformations of the data points into a second plurality of bins;

computing, by the computer device, a second entropy of a frequency of the logarithmic transformations of the data points based on a percentage of the logarithmic transformations that fall into each of the second plurality of bins;

comparing, by the computer device, the first entropy to the second entropy; and

causing to be graphically plotted, by the computer device, the data points in one of the following manners:

(a) plotting the data points in linear space upon a determination that the first entropy is greater than the second entropy; or

(b) plotting the data points in logarithmic space upon a determination that the first entropy is less than the second entropy, wherein both an x axis and a y axis are scaled linearly in the linear space, and wherein both the x axis and the y axis are scaled logarithmically in the logarithmic space,

wherein the computer device comprises a processor and a memory that stores instructions executed by the processor.

2. The method of claim 1 , wherein classifying logarithmic transformations of the data points includes binning the logarithmic transformations of the data points with a triangular kernel.

3. The method of claim 1 , further comprising graphically plotting the data points in linear space when there is less than 5 unique data points.

4. The method of claim 1 , further comprising graphically plotting the data points in linear space when a number of the data points that are non-positive is greater than a predetermined number.

5. The method of claim 1 , wherein classifying the data points includes binning the data points with a triangular kernel.

6. The method of claim 5 , wherein the first plurality of bins comprises ten bins and the second plurality of bins comprises ten bins.

7. The method of claim 5 , wherein the first entropy of the frequency of the data points is calculated based on the equation

H

⁡

(

x

)

=

-

∑

i

=

1

N

⁢

p

i

⁢

log

⁡

(

p

i

)

,

where H(x) is the first entropy, x represents the data points, p is the percentage points of data points that fall into the bins of the first plurality of bins, and N is the number of data points.

8. A system for determining whether a set of data is to be graphically plotted in linear space or logarithmic space, the system comprising:

a server having graphical plotting software, the graphical plotting software configured to:

receive a set of data points to be plotted;

determine whether the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points; and

upon a determination that the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points:

classify the data points into a first plurality of bins;

compute a first entropy of a frequency of the data points based on a percentage of the data points that fall into each of the first plurality of bins;

compute a logarithmic transformation of each of the data points;

classify the logarithmic transformations of the data points into a second plurality of bins;

compute a second entropy of a frequency of the logarithmic transformations of the data points based on a percentage of the logarithmic transformations that fall into each of the second plurality of bins;

compare the first entropy to the second entropy; and

determine whether the data points should be graphically plotted in linear space or logarithmic space based on the comparison of the first entropy to the second entropy by one of the following:

determining that the data points should be graphically plotted in linear space when the first entropy is greater than the second entropy, wherein both an x axis and a y axis are scaled linearly in the linear space; and

determining that the data points should be graphically plotted in logarithmic space when the first entropy is less than the second entropy, wherein both the x axis and the y axis are scaled logarithmically in the logarithmic space; and

at least one computer in communication with the server that displays a graphical plot of the data points in the space determined by the server.

9. The system of claim 8 , wherein the at least one computer is in communication with the server via a network.

10. The system of claim 9 , wherein the network is one of the Internet, a LAN, a WAN, and an intranet.

11. A non-transitory computer readable medium having stored thereon instructions which, when executed by a processor, cause the processor to:

receive a set of data points to be plotted;

determine whether the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points;

upon a determination that the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points

classify the data points into a first plurality of bins;

compute a first entropy of a frequency of the data points based on a percentage of the data points that fall into each of the first plurality of bins;

compute a logarithmic transformation of each of the data points;

classify the logarithmic transformations of the data points into a second plurality of bins;

compute a second entropy of a frequency of the logarithmic transformations of the data points based on a percentage of the logarithmic transformations that fall into each of the second plurality of bins;

compare the first entropy to the second entropy; and

determine whether the data points should be graphically plotted in linear space logarithmic space based on the comparison of the first entropy to the second entropy by one of the following:

determining that the data points should be plotted in linear space when the first entropy is greater than the second entropy, wherein both an x axis and a y axis are scaled linearly in the linear space; and

determining that the data points should be plotted in logarithmic space when the first entropy is less than the second entropy, wherein both the x axis and the y axis are scaled logarithmically in the logarithmic space.

12. An apparatus for determining whether a set of data is to be graphically plotted in linear space or logarithmic space, the apparatus comprising:

means for determining whether the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points;

means for classifying, upon a determination that the set of data points has a number of unique data points greater than or equal to a threshold number of unique data points, a plurality of data points into a first plurality of bins;

means for computing a first entropy of a frequency of the data points based on a percentage of the data points that fall into each of the first plurality of bins;

means for computing a logarithmic transformation of each of the data points;

means for classifying the logarithmic transformations of the data points into a second plurality of bins;

means for computing a second entropy of a frequency of logarithmic transformations of the data points based on a percentage of the logarithmic transformations that fall into each of the second plurality of bins;

means for comparing the first entropy to the second entropy; and

means for graphically plotting the data points in one of the following manners:

in linear space when the first entropy is greater than the second entropy; and

in logarithmic space when the first entropy is less than the second entropy,

wherein both an x axis and a y axis are scaled linearly in the linear space, and wherein both the x axis and the y axis are scaled logarithmically in the logarithmic space.

13. A computer-implemented method of determining whether a set of data is to be graphically plotted in linear space or logarithmic space, the method comprising:

receiving, by a computer device, a set of data points to be plotted;

determining, by the computer device, that the data points should be plotted in linear space when the number of data points in the set of data points that is unique is less than a threshold number;

when the number of data points in the set of data points that is unique is not less than the threshold number, determining, by the compute device, that the data points should be plotted in linear space when a percentage of the data points in the set of data points that is non-positive is less than a threshold percentage; and

when both (i) the number of data points in the set of data points that is unique is not less than the threshold number and (ii) the percentage of the data points in the set of data points that is non-positive is not less than the threshold percentage:

classifying, by the computer device, the data points into a first plurality of bins;

computing, by the computer device, a first entropy of a frequency of the data points based on a percentage of the data points that fall into each of the first plurality of bins;

computing, by the computer device, a logarithmic transformation of each of the data points;

classifying, by the computer device, the logarithmic transformations of the data points into a second plurality of bins;

computing, by the computer device, a second entropy of a frequency of the logarithmic transformations of the data points based on a percentage of the logarithmic transformations that fall into each of the second plurality of bins;

comparing, by the computer device, the first entropy to the second entropy; and

causing to be graphically plotted, by the computer device, the data points in one of the following manners:

in linear space when the first entropy is greater than the second entropy; and

in logarithmic space when the first entropy is less than the second entropy,

wherein both an x axis and a y axis are scaled linearly in the linear space, and wherein both the x axis and the y axis are scaled logarithmically in the logarithmic space; and

wherein the computer device comprises a processor and a memory that stores instructions executed by the processor.