def generateInitialDistanceMatrix(cls, test=False):
''' Generate the initial nxn distance matrix by computing Distance between each DNA sequence '''
# For Testing Purpose
if test == True:
cls.simMatrix = np.array(
[[0, 9, 3, 6, 11], [9, 0, 7, 5, 10], [3, 7, 0, 9, 2],
[6, 5, 9, 0, 8], [11, 10, 2, 8, 0]],
dtype=float)
# Actual Dataset Implementation
else:
pickleFilePath = Path('data/simMat_3.pkl')
if pickleFilePath.exists():
# Load Pickle File storing the simMatrix
with open(pickleFilePath, 'rb') as file:
cls.simMatrix = pickle.load(file)
else:
# Compute Distance among DNA Sequence
cls.simMatrix = np.ones((cls.ClusterCount, cls.ClusterCount))
for cID in range(cls.ClusterCount):
clusterA = cls.getClusterById(cID)
for _cID in range(cID, cls.ClusterCount):
clusterB = cls.getClusterById(_cID)
seq1 = clusterA.sequences[0]
seq2 = clusterB.sequences[0]
similarity_1 = computeDistance(seq1, seq2)
cls.simMatrix[cID, _cID] = similarity_1
cls.simMatrix[_cID, cID] = similarity_1
# print("similarity between {} and {} = {}\r".format(cID, _cID, similarity_1), end='', flush=True)
sys.stdout.flush()
# print('')
# Save The Pickle File
with open(pickleFilePath, 'wb') as file:
pickle.dump(cls.simMatrix, file)
def genSimilarityMatrix(data):
indexes = list(data.keys())[:]
pickleFilePath = Path('data/simMatrix_K_Mediods.pkl')
if pickleFilePath.exists():
# Load Pickle File storing the simMatrix
with open(pickleFilePath, 'rb') as file:
simMatrix = pickle.load(file)
return simMatrix, indexes
ClusterCount = len(indexes)
simMatrix = np.ones((ClusterCount, ClusterCount))
for cID in range(ClusterCount):
strA = data[indexes[cID]]
for _cID in range(cID, ClusterCount):
strB = data[indexes[_cID]]
similarity_1 = computeDistance(strA, strB)
simMatrix[cID, _cID] = similarity_1
simMatrix[_cID, cID] = similarity_1
#print("similarity between {} and {} = {}\r".format(cID, _cID, similarity_1), end='', flush=True)
#sys.stdout.flush()
#print('')
print(simMatrix)
with open(pickleFilePath, 'wb') as file:
pickle.dump(simMatrix, file)
return simMatrix, indexes