def update(request):
df_label = pd.read_csv(
os.path.join(settings.BASE_DIR, 'data/outcome_labels.csv'))
print("df_label", '\n', df_label)
df_data = pd.read_csv(
os.path.join(settings.BASE_DIR, 'data/features_rep.csv'))
#print("df_data", df_data)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
#rowIDLIst2 = pd.concat([df_label.id1,df_label.id2],axis = 1).unique().tolist()
print("rowIDLIst", '\n', rowIDLIst)
#print("rowIDLIst2",'\n', rowIDLIst2)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
print("lbl", lbl)
print("lbl[0]", lbl[0])
print("lbl[1]", lbl[1])
print("lbl[2]", lbl[2])
print("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),
"rowIDLIst.index(lbl[1])", rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print("cmatrix", '\n', cmatrix)
trainedData = []
for rid in rowIDLIst:
row = df_data.iloc[[rid]]
trainedData.append(row)
print("trainedData1", '\n', trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print("trainedData2" "\n", trainedData)
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_data)
al_selection = request.session['clustering']
num_clustering = request.session['num_cluster']
clusteringAndTSNE(newData, al_selection, num_clustering)
# context is a dict of html code, containing three types of features representation
content = {'Title': "Step 7: Clustering Visualization", "listId": "li7"}
return render(request, 'clustering/stp7-clu-visualisation.html', content)
def update():
df_label = pd.read_csv('data/outcome_labels.csv')
print "df_label", '\n', df_label
df_data = pd.read_csv('data/features_rep.csv')
#df_data = pd.read_csv('data/alvin_rep.csv')
print "df_data", '\n', df_data
#print("df_data", df_data)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
#rowIDLIst2 = pd.concat([df_label.id1,df_label.id2],axis = 1)
print "rowIDLIst", '\n', rowIDLIst
#print("rowIDLIst2",'\n', rowIDLIst2)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
#print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
#print ("lbl",lbl)
#print ("lbl[0]",lbl[0])
#print ("lbl[1]",lbl[1])
#print ("lbl[2]",lbl[2])
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print "cmatrixShape", '\n', cmatrix.shape
trainedData = []
for rid in rowIDLIst:
row = df_data.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "trainedData","\n", trainedData
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
#print "trainedData2", "\n", trainedData
print "trainedData.shape", '\n', trainedData.shape
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_data)
clusteringAndTSNE(newData)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
np.random.seed(1234)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
np.random.seed(1234)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
# Note: this is a flaky test, which fails for certain seeds.
# TODO: un-flake it!
np.random.seed(5555)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def test_iris(self):
num_constraints = 1500
n = self.iris_points.shape[0]
# Note: this is a flaky test, which fails for certain seeds.
# TODO: un-flake it!
np.random.seed(5555)
W = SDML.prepare_constraints(self.iris_labels, n, num_constraints)
# Test sparse graph inputs.
for graph in ((W, scipy.sparse.csr_matrix(W))):
sdml = SDML().fit(self.iris_points, graph)
csep = class_separation(sdml.transform(), self.iris_labels)
self.assertLess(csep, 0.25)
def metricLearning(data):
df_label = pd.read_csv('../TestAndLearn/data/outcome_labels.csv')
#print("df_label", '\n', df_label)
#get unique row ids
rowIDLIst = pd.concat([df_label.id1, df_label.id2],
axis=0).unique().tolist()
print("rowIDLIst", '\n', rowIDLIst)
#connectivity graph
cmatrix = np.zeros([len(rowIDLIst), len(rowIDLIst)])
#print("as_Matrix", '\n', df_label.as_matrix)
for lbl in df_label.as_matrix():
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print("cmatrix.shape", '\n', cmatrix.shape)
trainedData = []
for rid in rowIDLIst:
row = data.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "LentrainedData","\n", len(trainedData)
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print("trainedData.shape", "\n", trainedData.shape)
#print "trainedData2", "\n", trainedData
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(data)
return newData
#print ("lbl[0]",lbl[0])
#print ("lbl[1]",lbl[1])
#print ("lbl[2]",lbl[2])
#print ("rowIDLIst.index(lbl[0])", rowIDLIst.index(lbl[0]),"rowIDLIst.index(lbl[1])",rowIDLIst.index(lbl[1]))
cmatrix[rowIDLIst.index(lbl[0])][rowIDLIst.index(lbl[1])] = int(lbl[2])
cmatrix[rowIDLIst.index(lbl[1])][rowIDLIst.index(lbl[0])] = int(lbl[2])
print "cmatrix.shape", '\n', cmatrix.shape
trainedData = []
for rid in rowIDLIst:
row = df_reperent.iloc[[rid]]
#print "row","\n",row
#print "rowType","\n",type(row)
trainedData.append(row)
#print "LentrainedData","\n", len(trainedData)
#print "typetrainedData1", '\n', len(trainedData)
trainedData = pd.concat(trainedData, axis=0).as_matrix()
print "trainedData.shape", "\n", trainedData.shape
#print "trainedData2", "\n", trainedData
metric = SDML().fit(trainedData, cmatrix)
newData = metric.transform(df_reperent)
print type(newData)
print newData.shape