def iteration(self,data_sets):
covs=[]
avgs=[]
new_data_sets=[[] for _ in range(len(data_sets))]
#get the expectation and covariance matrix
for data_set in data_sets:
cov=Multi_Dimension_Data_Statictis.get_covariance_matrix(data_set)
avg=Multi_Dimension_Data_Statictis.get_average(data_set)
covs.append(cov)
avgs.append(avg)
# assign data to cluster
for data in self.data:
max_p=0
max_p_index=0
for index in range(len(data_sets)):
gauss_value=Gaussian.gaussian([[_n] for _n in data], avgs[index], covs[index])
if gauss_value>max_p:
max_p=gauss_value
max_p_index=index
new_data_sets[max_p_index].append(data)
covs=[]
avgs=[]
#calculate the new expectation and covariance matrix
for data_set in data_sets:
cov=Multi_Dimension_Data_Statictis.get_covariance_matrix(data_set)
avg=Multi_Dimension_Data_Statictis.get_average(data_set)
covs.append(cov)
avgs.append(avg)
likehood=0
# calculate the likelihood
for index in range(len(data_sets)):
temp=0
for data in data_sets[index]:
gauss_value=Gaussian.gaussian([[_n] for _n in data], avgs[index], covs[index])
temp+=gauss_value
likehood+=log(temp)
return likehood,new_data_sets
def analysis(self,k):
# Calculate the empirical mean
means=Multi_Dimension_Data_Statictis.get_average(self.data)
# Calculate the deviations from the mean
deviations=Multi_Dimension_Data_Statictis.get_deviations(self.data) #unused
mean_subtracted_data=Matrix.minus(self.data, Matrix.multiply([[1] for _ in range(len(self.data))], Matrix.transpose(means)))
# Find the covariance matrix
covariance_matrix=Multi_Dimension_Data_Statictis.get_covariance_matrix(mean_subtracted_data)
# Find the eigenvectors and eigenvalues of the covariance matrix
x= np.mat(covariance_matrix)
eigenvalues,eigenvectors=np.linalg.eigh(x)
eigenvalues=eigenvalues.tolist()
eigenvectors=Matrix.transpose(eigenvectors.tolist())
# Rearrange the eigenvectors and eigenvalues
eigenvalue_and_eigenvector=[]
for i in range(len(eigenvalues)):
eigenvalue_and_eigenvector.append((eigenvalues[i],eigenvectors[i]))
eigenvalue_and_eigenvector=sorted(eigenvalue_and_eigenvector, reverse=True)
# Choosing k eigenvectors with the largest eigenvalues
transform_matrix=[]
for i in range(k):
transform_matrix.append(eigenvalue_and_eigenvector[i][1])
return Matrix.transpose(Matrix.multiply(transform_matrix,Matrix.transpose(self.data)))
def test_get_variance(self):
data=[[1,2,3],[4,5,6],[7,8,9]]
expected_result=[[6],[6],[6]]
actual_result=Multi_Dimension_Data_Statictis.get_variance(data)
self.assertEqual(expected_result, actual_result)