def extract_compareClustering(clusterClass):
# Get data, n_bands=4
norm_img_path = "C:\\Users\\DELL\\Projects\\MLS_cluster\\image-v2-timeseries\\newest"
img = "4Band_Subtracted_20040514_20050427"
dataset = oi.open_tiff(norm_img_path, img)
H = dataset[1]
W = dataset[2]
n_bands = dataset[3]
org_data = art.tif2vec(dataset[0]) #NOTE: this step is really important
select_path = "C:\\Users\\DELL\\Projects\\MLS_cluster\\image-v2-timeseries\\EXTRACT"
select_img = "SOMOCLU_20_20_HDBSCAN_cl_2_2004_2005_min_cluster_size_4_alg_best_"
simg = oi.open_tiff(select_path, select_img)
select = simg[0] #(2720000)
changePos = DataProcess.selectArea(select, n_bands, -1, isStack=True)
ns_changePos = DataProcess.selectArea(select, n_bands, -1, isStack=False)
ns_nonChangePos = DataProcess.selectArea(select, n_bands, 0, isStack=False)
X_train = org_data[changePos].reshape(-1, n_bands)
result = np.zeros_like(select.reshape(-1, 1))
for cls_name, cls_class in clusterClass.items():
print("running", cls_name, "...")
t0 = time.clock()
cls_class.fit(X_train)
usingTime = time.clock() - t0
# combine the result
result[ns_changePos] = cls_class.labels_
result[ns_nonChangePos] = np.max(cls_class.labels_) + 1
evaluation = silhouette_score(X=org_data,
labels=result,
metric='euclidean',
sample_size=10000)
save_path = "C:\\Users\\DELL\\Projects\\MLS_cluster\\image-v2-timeseries\\sklearn_clustering\\compare"
DataProcess.visualize_class(
result.reshape(H, W),
save_path + '\\' + cls_name + "_change_area_class")
# save using time
print("save the information to txt file...")
with open(
save_path + '/' +
"Outlier Detection Algorithms Running Time.txt", 'a') as f:
f.write("detetion algorithm: " + cls_name + "\nsilhouette_score:" +
str(evaluation) + "\ndetection using time: " +
str(usingTime))
f.write("\n----------------------------------------------\n")
def runClusteringBased(img_path,img_name,data_path,data_name,outlier_save_path,\
clusteringPara,outlierPara,o_filter="highRank"):
#clusteringPara[0] is the name, the rest are parameters
#TODO:change score and filter para
org_data = DataProcess.csv_to_array(data_path, data_name)
AlgorithmName = clusteringPara[0]
print("running " + AlgorithmName + " for clustering...")
t0 = time.time()
if AlgorithmName == "kMeans":
d_label = cl.kMeans.getCluster(org_data, *(clusteringPara[1]))
elif AlgorithmName == "Affinity":
d_label = cl.Affinity.getCluster(org_data, *(clusteringPara[1]))
elif AlgorithmName == "MeanShift":
d_label = cl.MeanShift.getCluster(org_data, *(clusteringPara[1]))
elif AlgorithmName == "Spectral":
d_label = cl.Spectral.getCluster(org_data, *(clusteringPara[1]))
elif AlgorithmName == "Agglomerative":
d_label = cl.Agglomerative.getCluster(org_data, *(clusteringPara[1]))
AlgorithmName = AlgorithmName + '_' + clusteringPara[1][6]
elif AlgorithmName == "DBSCAN":
d_label = cl.DBSCAN.getCluster(org_data, *(clusteringPara[1]))
elif AlgorithmName == "BIRCH":
d_label = cl.BIRCH.getCluster(org_data, *(clusteringPara[1]))
else:
print("algorithm name ilegal")
exit()
AlgorithmName += '_'
#save the cluster information
saveclass_extend_name = '_' + AlgorithmName + "cluster_label"
DataProcess.int_to_csv(outlier_save_path, img_name, d_label,
saveclass_extend_name)
DataProcess.visualize_class(img_path, img_name, outlier_save_path,
img_name + saveclass_extend_name)
t1 = time.time()
print("running " + outlierPara[0] +
" for calculating the outlier scores...")
if outlierPara[0] == "LDCOF":
d_score = cb.calLDCOF.findLDCOF(org_data, d_label, outlierPara[1],
outlierPara[2], outlierPara[3])
if o_filter == "highRank":
outlier_label = sc2r.highRank.getOutliers(d_score, 98)
#save the label information for further usage
savelabel_extend_name = '_' + AlgorithmName + "outlier_label"
DataProcess.int_to_csv(outlier_save_path, img_name, outlier_label,
savelabel_extend_name)
GeoProcess.getSHP(
img_path, img_name, outlier_save_path, AlgorithmName,
outlier_label) #FIXME: the .tif file could not be specified the path
# DataProcess.visualize_class(img_path,img_name,outlier_save_path,img_name+savelabel_extend_name)
#calculate the Silhouette Coefficient as a reference of the performance of the outcome
#NOTE:due to the limited memory, I adjust the sample_size to 10000,which may cause the score less reliable
print("calculating Silhouette Coefficients...")
clusteringScore = cl.Silhouette.getSilhouette(org_data,
d_label,
sample_size=10000)
usingTime = t1 - t0
print("save the information to txt file...")
with open(data_path + '/' + "runningstatus.txt", 'a') as f:
f.write("clustering algorithm: " + AlgorithmName +
"\nsilhouette coefficient: " + str(clusteringScore) +
"\nclstering using time: " + str(usingTime))
f.write("\n----------------------------------------------\n")
org_data = None
return clusteringScore, usingTime