def handleCluster(self, event=None):
'''Creates ClusterDialog object.'''
print('handleCluster')
self.ClusterWindow = ClusterDialog(self.root, self.dataObj)
if self.ClusterWindow.headers == None:
tkMessageBox.showerror('No File Opened!', 'Please open a file first')
return
if self.ClusterWindow.result == None:
return
self.ClusterObjects = []
A = self.dataObj.columns_data(self.ClusterWindow.result[0])
A = A.astype(float)
m = np.mean(A, axis=0)
D = A - m
U, S, V = np.linalg.svd(D, full_matrices=False)
projectedData = (V * D.T).T
means, codebook, self.errors = analysis.kmeans(self.dataObj, self.ClusterWindow.result[0], self.ClusterWindow.result[1])
c_object = ClusterData(projectedData, self.ClusterWindow.result[0], self.ClusterWindow.result[1], codebook, means, self.errors)
self.ClusterObjects.append(c_object)
codebook = codebook.T.tolist()[0]
self.dataObj.addColumn(codebook, 'cluster', 'numeric')
if self.ClusterWindow.result[1] == None:
name = 'Cluster' + str(self.ClusterNum)
self.ClusterNum += 1
else:
name = self.ClusterWindow.result[1]
self.ClusterBoxA.insert(tk.END, name)
def handleClustering(self, event=None):
if self.data == None:
print "Choose input file"
return
# Create selection dialog box
dialog = clusterDialog(self.root, self.data.get_headers(),
"Select columns for clustering analysis")
# Terminate if cancelled
if len(dialog.cols) == 0:
return
elif len(dialog.cols) == 1:
print "Select at least 2 columns for clustering analysis"
return
try:
n = int(dialog.num.get())
except ValueError:
print "Please enter an integer for the number of clusters"
return
if n == 0:
print "Please enter a positive integer for the number of clusters"
return
self.means, ids, self.errors = analysis.kmeans(self.data,
dialog.cols, n, dialog.metric)
self.clusterData = data.ClusterData(self.data.get_headers(),
self.data.get_data(self.data.get_headers()))
self.clusterData.add_column(str(n)+"clusterIds", ids)
print "Press 'Show clusters' and select the clusterIds column to view clustering"
def build(self, A, categories, K=None, kmeans2=False):
'''Builds the classifier give the data points in A and the categories'''
# figure out how many categories there are and get the mapping (np.unique)
unique, mapping = np.unique(np.array(categories.T),
return_inverse=True)
self.num_classes = len(unique)
self.num_features = A.shape[1]
self.class_labels = unique
for i in range(self.num_classes):
if K is None:
# append to exemplars a matrix with all of the rows of A where the category/mapping is i
self.exemplars.append(A[(mapping == i), :])
else:
if kmeans2:
codebook = an.kmeans2(A[(mapping == i), :],
self.KNN_headers,
K,
whiten=False)[0]
else:
codebook = an.kmeans(A[(mapping == i), :],
self.KNN_headers,
K,
whiten=False)[0]
self.exemplars.append(codebook)
return
def cluster(self, event = None):
if self.data == None:
tkMessageBox.showwarning("Instructions", "You must read in a file first")
return
headers = self.data.get_headers()
output = ClusterSelect(self.root, headers)
if output.okField == False:
self.label['text'] = "Data selection cancelled"
return
if output.result == False:
return
print output.result
codes = analysis.kmeans(self.data, output.result[0], output.result[1], whiten=True, categories = '')[1]
newCol = ["Categories", "numeric"]
codes = codes.T.tolist()[0]
for code in codes:
newCol.append(code)
self.data.addData(newCol)
newHeaders =output.result[0]
newHeaders.append("Categories")
print "Cheking if checked"
print output.result[1]
d = self.handlePlotData(newHeaders, output.result[2], codes)
# removes the added Categories column once finished
self.data.removeLast()
def handleClustering(self,event=None): self.cbox = ClusterDialogBox(self.root,self.data.get_headers()) self.numclusters=int(self.cbox.clusterNum) self.smoothclrscheme=self.cbox.getContinuousColorScheme() if len(self.cbox.datacols)!=0 and self.numclusters>0: headers=[] for head in self.cbox.datacols: headers.append(head) self.codebook, self.codes, self.errors = an.kmeans(self.data,headers,self.numclusters) self.clusterList.append([self.codebook, self.codes, self.errors,headers]) if self.cbox.getName() == None: name = "Cluster #" + str(self.num_cluster) self.num_cluster += 1 else: name = self.cbox.getName() self.clusterWindow.insert(tk.END, name) print name if self.cbox.headers == None: print "Select a file" self.handleOpen() if self.cbox.getDatacols() == None: return
def build(self, A, categories, K=None):
'''Builds the classifier give the data points in A and the categories'''
# figure out how many categories there are and get the mapping (np.unique)
# print(A.get_data())
self.numCategories = len(categories)
self.numFeatures = A.get_data().shape[1]
self.unique, self.mapping, self.counts = np.unique(np.array(
categories.T),
return_inverse=True,
return_counts=True)
self.numClasses = self.unique.size
self.ogLabels = self.unique
self.exemplars = [
A.get_data()[(self.mapping == i), :]
for i in range(self.numClasses)
]
if K != None:
temp = []
for e in self.exemplars:
codebook, codes, error, quality = an.kmeans(None,
headers=None,
whiten=False,
K=K,
A=e)
temp.append(codebook)
self.exemplars = temp
return
def build(self, A, categories, K=None):
'''Builds the classifier give the data points in A and the categories'''
# figure out how many categories there are and get the mapping (np.unique)
# for each category i, build the set of exemplars
# if K is None
# append to exemplars a matrix with all of the rows of A where the category/mapping is i
# else
# run K-means on the rows of A where the category/mapping is i
# append the codebook to the exemplars
# store any other necessary information: # of classes, # of features, original labels
unique, mapping = np.unique(np.array(categories.T),
return_inverse=True)
self.num_class = len(unique)
self.num_feature = A.shape[1]
self.class_labels = unique
for i in range(self.num_class):
if K is None:
self.exemplar.append(A[(mapping == i), :])
else:
codebook, codes, errors = an.kmeans(A[(mapping == i), :],
self.headers,
K,
whiten=False)
self.exemplar.append(codebook)
return
def main():
d = data.Data("datasets/clusterdata.csv")
codebook, codes, errors = an.kmeans(d, d.getHeaderNum(), 2)
print "\nCodebook\n"
print codebook
print "\nCodes\n"
print codes
def handleCluster(self):
d = ClusterDialog(self.root, self.data.get_headers())
if d.result != None and int(d.clusters) > 0:
headers = []
for index in d.result:
headers.append(self.data.get_headers()[index])
codebook, codes, errors = analysis.kmeans(self.data, headers, int(d.clusters))
self.clusterCount += 1
self.data.addColumn("Clusters %d" % (self.clusterCount,), codes)
self.headers = self.data.get_headers()
def handleCluster(self):
d = clusterDialog(self.root, self.data.getHeaders())
if d.result != None and int(d.clusters) > 0:
print d.result
headers = []
for index in d.result:
headers.append(self.data.headersNumeric[index])
codebook, codes, errors = analysis.kmeans(self.data, headers, int(d.clusters))
print codes
self.clusterCount += 1
print self.clusterCount
self.data.addColumn("Clusters %d" % (self.clusterCount,), codes)
self.buildOptions()
def cluster(self):
if self.data is None:
print 'you have no data'
return
variables = Dialogs.ClusterDialog(self.root, self.data.get_headers())
if variables.result == []:
print 'you didn\'t pick anything'
return
self.clusternumber+=1
#print variables.numclusters
#self.uniqueColors = variables.distColors
#print self.uniqueColors
codebook, codes, errors = analysis.kmeans(self.data, variables.result, variables.numclusters)
#I add the col to the data so I can cluster the data itself to the PCA, rather than the transformed data
self.data.add_column('clustering%d'%(self.clusternumber),'numeric', codes)
def clusterPCA(self):
if self.PCAanalysis != [] and self.PCAListbox.curselection() != ():
self.PCA = self.PCAanalysis[self.PCAListbox.curselection()[0]]
if self.PCA is None:
print 'you have no data'
return
variables = Dialogs.ClusterDialog(self.root, self.PCA.get_headers())
if variables.result == []:
print 'you didn\'t pick anything'
return
self.clusternumber+=1
#print variables.numclusters
#self.uniqueColors = variables.distColors
#print self.uniqueColors
codebook, codes, errors = analysis.kmeans(self.PCA, variables.result, variables.numclusters)
self.PCA.add_column('clustering%d'%(self.clusternumber),'numeric', codes)
def main(argv):
if len(argv) < 2:
print( 'Usage: python %s <all numeric CSV file>' % (argv[0]))
exit(-1)
try:
d = data.Data( argv[1] )
except:
print( 'Unable to open %s' % (argv[1]))
exit(-1)
codebook, codes, errors = an.kmeans( d, d.get_headers(), 2 )
print( "\nCodebook\n")
print( codebook)
print( "\nCodes\n")
print( codes)
def main(argv):
if len(argv) < 2:
print('Usage: python %s <all numeric CSV file>' % (argv[0]))
exit(-1)
try:
d = data.Data( argv[1] )
except:
print('Unable to open %s' % (argv[1]))
exit(-1)
codebook, codes, errors = an.kmeans( d, d.get_headers(), 2 )
print("\nCodebook\n")
print(codebook)
print("\nCodes\n")
print(codes)
def main(argv):
# if len(argv) < 2:
# print 'Usage: python %s <all numeric CSV file>' % (argv[0])
# exit(-1)
#
# try:
# d = data.Data( argv[1] )
# except:
# print 'Unable to open %s' % (argv[1])
# exit(-1)
d = data.Data("clusterdata.csv")
codebook, codes, errors = an.kmeans(d, d.get_headers(), 2)
print "\nCodebook\n"
print codebook
print "\nCodes\n"
print codes
def handleKMeans(self):
#this line cannot go after the dialogs are created because if the user
#types something into the dialogs, it will deselect the columns
self.headers = self.cols.curselection()
nd = NameDialog(self.root)
name = nd.get_name()
kd = KDialog(self.root)
self.k = kd.get_k()
for i in range(len(self.headers)):
if self.headers[i] == 'None':
del self.headers[i]
print("headers to cluster:", self.headers)
codebook, codes, errors, quality = analysis.kmeans(self.data, self.headers, self.k, whiten=False, manhattan=self.manhattan)
print("MDL:",quality)
self.kmeans.append([codebook, codes, errors, quality])
if name == "Default":
self.PCAlistbox.insert(tk.END, "K-Means" + str(self.PCAlistbox.size()))
else:
self.PCAlistbox.insert(tk.END, name)
def main(argv): # if len(argv) < 2: # print 'Usage: python %s <all numeric CSV file>' % (argv[0]) # exit(-1) # # try: # d = data.Data( argv[1] ) # except: # print 'Unable to open %s' % (argv[1]) # exit(-1) d = data.Data( "clusterdata.csv" ) codebook, codes, errors = an.kmeans( d, d.get_headers(), 2 ) print "\nCodebook\n" print codebook print "\nCodes\n" print codes
def build(self, A, categories, K=None):
'''Builds the classifier give the data points in A and the categories'''
# figure out how many categories there are and get the mapping (np.unique)
unique, mapping = np.unique(np.array(categories.T),
return_inverse=True)
self.num_classes = len(unique)
self.NumFeature = A.shape[1]
self.class_labels = unique
for i in range(self.num_classes):
if K is None:
self.exemplars.append(A[(mapping == i), :])
else:
codebook, codes, errors = an.kmeans(A[(mapping == i), :],
self.headers,
K,
whiten=False)
'''extension2, using other method to get exemplars'''
self.exemplars.append(codebook)
def main(argv):
if len(argv) < 3:
print 'usage: python %s <Train CSV file> <Train categories CSV file>' % (argv[0])
exit(-1)
# read the features and categories data sets
print 'Reading %s and %s' % (argv[1], argv[2])
try:
d = data.Data(argv[1])
except:
print 'Unable to open %s' % (argv[1])
exit(-1)
try:
catdata = data.Data(argv[2])
except:
print 'Unable to open %s' % (argv[2])
exit(-1)
# execute PCA analysis
print 'Executing PCA'
pcadata = an.pca( d, d.get_headers(), False )
print 'Evaluating eigenvalues'
# identify how many dimensions it takes to represent 90% of the variation
evals = pcadata.get_eigenvalues()
#print "type:",type(evals)
evals=np.asmatrix(evals)
#print "type2:",type(evals)
#print "shape: ",evals.shape
esum = np.sum(evals)
cum = evals[0,0]
cumper = cum / esum
i = 1
while cumper < 0.999:
cum += evals[0,i]
cumper = cum/esum
i += 1
print 'Dimensions to reach 99.9% of variation:', i
cheaders = pcadata.get_headers()[:i]
# cluster the data
K = 6
# Use the average of each category as the initial means
truecats = catdata.get_data(catdata.get_headers()[0:1])
#tmpcats = truecats - 1
tmpcats = truecats # Don't adjust if we're using corrected labels
print 'Clustering to %d clusters' % (K)
codebook, codes, errors = an.kmeans(pcadata, cheaders, K, categories = tmpcats)
# build a confusion matrix
confmtx = [[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0]]
for i in range(codes.shape[0]):
#confmtx[codes[i,0]][int(truecats[i,0])-1] += 1
confmtx[codes[i,0]][int(truecats[i,0])] += 1 # don't adjust
print "\nConfusion Matrix:\n"
print 'Actual-> Walking Walk-up Walk-dwn Sitting Standing Laying'
for i in range(len(confmtx)):
s = 'Cluster %d' % (i)
for val in confmtx[i]:
s += "%10d" % (val)
print s
print
# Calculate alpha for each fracture population on every outcrop
data2 = calcAlpha(data2)
dataBeni = calcAlpha(dataBeni)
# Weighting the data by density. Approximate all outcrops as 10 m radius circular disks
data2 = weightByN(data2)
data2 = data2.sort_values('Id', ascending = True)
dataBeni = weightByN(dataBeni)
dataBeni = dataBeni.sort_values('Id', ascending = True)
# Calculate the centers of n clusters
strikes = data2['strike'].as_matrix()
dips = data2['dip'].as_matrix()
centers1 = analysis.kmeans(strikes, dips, num=5, bidirectional=True, measurement='poles', tolerance=1e-15)
cstrikes = np.zeros(1)
cdips = np.zeros(1)
counter = 0
for i in centers1:
cstrike, cdip = stereonet_math.geographic2pole(i[0],i[1])
cstrikes = np.append(cstrikes,cstrike)
cdips = np.append(cdips,cdip)
counter += 1
cstrikes = cstrikes[1:]
cdips = cdips[1:]
# Classify the data into populations by comparing the poles with a set of test poles
def main(argv):
if len(argv) < 3:
print 'usage: python %s <Train CSV file> <Train categories CSV file>' % (argv[0])
exit(-1)
# read the features and categories data sets
print 'Reading %s and %s' % (argv[1], argv[2])
try:
d = data.Data(argv[1])
except:
print 'Unable to open %s' % (argv[1])
exit(-1)
try:
catdata = data.Data(argv[2])
except:
print 'Unable to open %s' % (argv[2])
exit(-1)
# execute PCA analysis
print 'Executing PCA'
pcadata = an.pca( d.getHeaderRaw(), d )
print 'Evaluating eigenvalues'
# identify how many dimensions it takes to represent 90% of the variation
evals = pcadata.getEigenvalues()
esum = np.sum(evals)
cum = evals[0]
cumper = cum / esum
i = 1
while cumper < .999:
cum += evals[i]
cumper = cum/esum
i += 1
print 'Dimensions to reach 99.9% of variation:', i
cheaders = pcadata.getHeaderRaw()[:i]
# cluster the data
K = 6
# Use the average of each category as the initial means
truecats = catdata.getDataNum(catdata.getHeaderRaw()[0:1])
tmpcats = truecats - 1
print "categoroties:", #tmpcats.tolist()
print 'Clustering to %d clusters' % (K)
# print pcadata
# print cheaders
# print K
codebook, codes, errors = an.kmeans(pcadata, cheaders, K, categories = tmpcats)
print len(codes)
print codebook
# build a confusion matrix
confmtx = [[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0]]
codes = codes.astype(int)
truecats = truecats.astype(int)
print len(codes)
print len(truecats)
for i in range(codes.shape[0]):
confmtx[codes[i,0]][int(truecats[i,0])-1] += 1
print "\nConfusion Matrix:\n"
print 'Actual-> Walking Walk-up Walk-dwn Sitting Standing Laying'
for i in range(len(confmtx)):
s = 'Cluster %d' % (i)
for val in confmtx[i]:
s += "%10d" % (val)
print s
print
def main(argv):
if len(argv) < 3:
print('usage: python %s <Train CSV file> <Train categories CSV file>' % (argv[0]))
exit(-1)
# read the features and categories data sets
print('Reading %s and %s' % (argv[1], argv[2]))
try:
d = data.Data(argv[1])
except:
print('Unable to open %s' % (argv[1]))
exit(-1)
try:
catdata = data.Data(argv[2])
except:
print('Unable to open %s' % (argv[2]))
exit(-1)
# execute PCA analysis
print('Executing PCA')
pcadata = an.pca( d, d.get_headers() )
print('Evaluating eigenvalues')
# identify how many dimensions it takes to represent 90% of the variation
evals = pcadata.get_eigenvalues()
esum = np.sum(evals)
cum = evals[0,0]
cumper = cum / esum
i = 1
while cumper < 0.9:
cum += evals[0,i]
cumper = cum/esum
i += 1
print('Dimensions to reach 90% of variation:', i)
cheaders = pcadata.get_headers()[:i]
# cluster the data
K = 6
# Use the average of each category as the initial means
truecats = catdata.get_data(catdata.get_headers()[0:1])
tmpcats = truecats - 1
print('Clustering to %d clusters' % (K))
codebook, codes, errors = an.kmeans(pcadata, cheaders, K, categories=tmpcats)
# build a confusion matrix
confmtx = [[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0],[0,0,0,0,0,0]]
for i in range(codes.shape[0]):
confmtx[int(codes[i, 0])][int(truecats[i, 0])-1] += 1
print("\nConfusion Matrix:\n")
print('Actual-> Walking Walk-up Walk-dwn Sitting Standing Laying')
for i in range(len(confmtx)):
s = 'Cluster %d' % (i)
for val in confmtx[i]:
s += "%10d" % (val)
print(s)
print()
