# code from http://danieljlewis.org/files/2010/06/Jenks.pdf | |
# described at http://danieljlewis.org/2010/06/07/jenks-natural-breaks-algorithm-in-python/ | |
def getJenksBreaks( dataList, numClass ): | |
dataList.sort() | |
mat1 = [] | |
for i in range(0,len(dataList)+1): | |
temp = [] | |
for j in range(0,numClass+1): | |
temp.append(0) | |
mat1.append(temp) | |
mat2 = [] | |
for i in range(0,len(dataList)+1): | |
temp = [] | |
for j in range(0,numClass+1): | |
temp.append(0) | |
mat2.append(temp) | |
for i in range(1,numClass+1): | |
mat1[1][i] = 1 | |
mat2[1][i] = 0 | |
for j in range(2,len(dataList)+1): | |
mat2[j][i] = float('inf') | |
v = 0.0 | |
for l in range(2,len(dataList)+1): | |
s1 = 0.0 | |
s2 = 0.0 | |
w = 0.0 | |
for m in range(1,l+1): | |
i3 = l - m + 1 | |
val = float(dataList[i3-1]) | |
s2 += val * val | |
s1 += val | |
w += 1 | |
v = s2 - (s1 * s1) / w | |
i4 = i3 - 1 | |
if i4 != 0: | |
for j in range(2,numClass+1): | |
if mat2[l][j] >= (v + mat2[i4][j - 1]): | |
mat1[l][j] = i3 | |
mat2[l][j] = v + mat2[i4][j - 1] | |
mat1[l][1] = 1 | |
mat2[l][1] = v | |
k = len(dataList) | |
kclass = [] | |
for i in range(0,numClass+1): | |
kclass.append(0) | |
kclass[numClass] = float(dataList[len(dataList) - 1]) | |
countNum = numClass | |
while countNum >= 2:#print "rank = " + str(mat1[k][countNum]) | |
id = int((mat1[k][countNum]) - 2) | |
#print "val = " + str(dataList[id]) | |
kclass[countNum - 1] = dataList[id] | |
k = int((mat1[k][countNum] - 1)) | |
countNum -= 1 | |
return kclass | |
def getGVF( dataList, numClass ): | |
""" | |
The Goodness of Variance Fit (GVF) is found by taking the | |
difference between the squared deviations | |
from the array mean (SDAM) and the squared deviations from the | |
class means (SDCM), and dividing by the SDAM | |
""" | |
breaks = getJenksBreaks(dataList, numClass) | |
dataList.sort() | |
listMean = sum(dataList)/len(dataList) | |
print listMean | |
SDAM = 0.0 | |
for i in range(0,len(dataList)): | |
sqDev = (dataList[i] - listMean)**2 | |
SDAM += sqDev | |
SDCM = 0.0 | |
for i in range(0,numClass): | |
if breaks[i] == 0: | |
classStart = 0 | |
else: | |
classStart = dataList.index(breaks[i]) | |
classStart += 1 | |
classEnd = dataList.index(breaks[i+1]) | |
classList = dataList[classStart:classEnd+1] | |
classMean = sum(classList)/len(classList) | |
print classMean | |
preSDCM = 0.0 | |
for j in range(0,len(classList)): | |
sqDev2 = (classList[j] - classMean)**2 | |
preSDCM += sqDev2 | |
SDCM += preSDCM | |
return (SDAM - SDCM)/SDAM | |
# written by Drew | |
# used after running getJenksBreaks() | |
def classify(value, breaks): | |
for i in range(1, len(breaks)): | |
if value < breaks[i]: | |
return i | |
return len(breaks) - 1 |
This comment has been minimized.
This comment has been minimized.
The site (http://danieljlewis.org/2010/06/07/jenks-natural-breaks-algorithm-in-python/) seems to be down! Is there another description anywhere? |
This comment has been minimized.
This comment has been minimized.
The Jenks technique is discussed here. The blog post points to this repo for a JavaSript implementation. That repo removed their implementation of Jenks in favor of a Ckmeans. There is an R implementation of Ckmeans in the package Ckmeans.1d.dp. See this SO question for a discussion of porting that code to Python. |
This comment has been minimized.
This comment has been minimized.
Does anyone know the arguments and return values for these functions? I have the code running, but I'm not sure what the output means. For example if I run |
This comment has been minimized.
This comment has been minimized.
VeloSteve, this is great that you have the code running. I still have to learn Python to do these calculations, however, I did the example you cited in RealStatistics in Excel. The values 0, 1 and 5 that you got seems to be the lower value of the classes and 9 is the last upper value. Check the image below. Note that RealStatistics express the classes with the values existent in the table and that's why the values are not exactly the same as yours. Best regards! |
This comment has been minimized.
This comment has been minimized.
Hello everyone. I tested the code with some of my own cases and found some differences to the jenkspy library (used it previously but was looking for Jenks Breaks on pure python code recently). Shouldn't the last while loop of the "getJenksBreaks" function include a line to make the first element of kclass equal to the first element of dataLis? Something like:
I could be wrong but this corrected any divergences between the jenkspy library and this code. |
This comment has been minimized.
This comment has been minimized.
How do I use this on Google cloud |
This comment has been minimized.
Did you test this?