def print_region_info(self):
print "REGION INFO"
print
print "For each feature set, the average sim score per region by cluster and the fixed weights"
print
for x, cluster in enumerate(self.clusters):
print "%d:\t%s\t%d\n" % (x, cluster.label, len(cluster.members))
for name in cluster.center.get_feature_set_names():
mats = map(lambda _doc: cluster.center.region_sim(_doc, name),
cluster.members)
avg_mat = utils.avg_mats(mats)
weight_mat = cluster.center.region_weights(name)
print name
utils.print_mat(utils.apply_mat(avg_mat, lambda x: "%.3f" % x))
print
utils.print_mat(
utils.apply_mat(weight_mat, lambda x: "%.3f" % x))
print
#list_of_sim_mats = map(lambda _doc: cluster.center.similarity_mats_by_name(_doc), cluster.members)
#list_of_weight_mats = cluster.center.similarity_weights_by_name(cluster.members[0])
#for name in cluster.center.similarity_function_names():
# mats = map(lambda x: x[name], list_of_sim_mats)
# avg_mat = utils.avg_mats(mats)
# weight_mat = list_of_weight_mats[name]
# print name
# utils.print_mat(utils.apply_mat(avg_mat, lambda x: "%.3f" % x))
# print
# utils.print_mat(utils.apply_mat(weight_mat, lambda x: "%.3f" % x))
# print
print
print
def main(args):
if(len(args) != 1):
print "Usage: mds.py C clustering.pkl"
print " C is the cluster in clustering.pkl to display"
sys.exit(0)
#C = int(args[1])
#path = args[2]
print "Loading"
#clustering = utils.load_obj(path)
#docs = clustering[C].members
docs = doc.get_docs_nested(driver.get_data_dir("small"))
print "Calculating Pairwise Similarities"
similarities = utils.pairwise(docs, lambda x,y: x.similarity(y))
#print "INITIAL SIMILARITIES:"
#utils.print_mat(similarities)
#similarities = [[0,93,82,133],[93,0,52,60],[82,52,0,111],[133,60,111,0]]
print "Starting MDS"
#pos = reduction(similarities)
pos = classicMDS(similarities)
print "MDS:"
utils.print_mat(pos)
def print_region_info(self): print "REGION INFO" print print "For each feature set, the average sim score per region by cluster and the fixed weights" print for x, cluster in enumerate(self.clusters): print "%d:\t%s\t%d\n" % (x, cluster.label, len(cluster.members)) for name in cluster.center.get_feature_set_names(): mats = map(lambda _doc: cluster.center.region_sim(_doc, name), cluster.members) avg_mat = utils.avg_mats(mats) weight_mat = cluster.center.region_weights(name) print name utils.print_mat(utils.apply_mat(avg_mat, lambda x: "%.3f" % x)) print utils.print_mat(utils.apply_mat(weight_mat, lambda x: "%.3f" % x)) print #list_of_sim_mats = map(lambda _doc: cluster.center.similarity_mats_by_name(_doc), cluster.members) #list_of_weight_mats = cluster.center.similarity_weights_by_name(cluster.members[0]) #for name in cluster.center.similarity_function_names(): # mats = map(lambda x: x[name], list_of_sim_mats) # avg_mat = utils.avg_mats(mats) # weight_mat = list_of_weight_mats[name] # print name # utils.print_mat(utils.apply_mat(avg_mat, lambda x: "%.3f" % x)) # print # utils.print_mat(utils.apply_mat(weight_mat, lambda x: "%.3f" % x)) # print print print
def check_init():
docs = doc.get_docs_nested(get_data_dir("test"))
random.shuffle(docs)
confirm = cluster.MaxCliqueInitCONFIRM(docs, 2, 10)
confirm._init_clusters()
print
print "Cluster Sim Mat"
sim_mat = confirm.get_cluster_sim_mat()
utils.print_mat(utils.apply_mat(sim_mat, lambda x: "%3.2f" % x))
def display(self): ''' prints the cost_mat and the op_mat ''' print "Cost Matrix" utils.print_mat(self.cost_mat) print print "Operations Matrix" utils.print_mat(self.op_mat) print
def print_label_conf_mat(self):
print "LABEL CONFUSION MATRIX:"
print "\tRows are actual predictions. Columns are true labels"
mat = self.calc_conf_mat()
labels = sorted(mat.keys())
mat = utils.format_as_mat(mat)
utils.insert_indices(mat)
print "\tMat index\tLabel Name"
for x, label in enumerate(labels):
print "\t%d:\t%s" % (x, label)
print
utils.print_mat(mat)
print
print
def print_label_conf_mat(self): print "LABEL CONFUSION MATRIX:" print "\tRows are actual predictions. Columns are true labels" mat = self.calc_conf_mat() labels = sorted(mat.keys()) mat = utils.format_as_mat(mat) utils.insert_indices(mat) print "\tMat index\tLabel Name" for x,label in enumerate(labels): print "\t%d:\t%s" % (x, label) print utils.print_mat(mat) print print
def _init_clusters(self): super(MaxCliqueInitCONFIRM, self)._init_clusters() sub_docs = self.docs[:self.num_instances] sim_mat = utils.pairwise(sub_docs, lambda x, y: max(self.doc_similarity(x, y), self.doc_similarity(y, x))) print print "Doc Sim Mat" utils.print_mat(utils.apply_mat(sim_mat, lambda x: "%3.2f" % x)) idxs = utils.find_best_clique(sim_mat, self.num_clust) print print "Cluster Labels:" for idx in idxs: self._add_cluster(self.docs[idx], member=False) print idx, self.docs[idx].label
def print_label_cluster_mat(self):
print "LABEL-CLUSTER MATRIX:"
print "\tSeries of matricies. Labels are rows. Clusters are columns."
mat = self.label_cluster_mat
labels = sorted(mat.keys())
mat = utils.format_as_mat(mat)
clusters_per_mat = 20
mats = utils.split_mat(mat, clusters_per_mat) # 10 clusters per matrix
print "\tMat index\tLabel Name"
for x, label in enumerate(labels):
print "\t%d:\t%s" % (x, label)
print
for x, mat in enumerate(mats):
utils.insert_indices(mat, col_start=(clusters_per_mat * x))
utils.print_mat(mat)
print
print
def print_label_cluster_mat(self): print "LABEL-CLUSTER MATRIX:" print "\tSeries of matricies. Labels are rows. Clusters are columns." mat = self.label_cluster_mat labels = sorted(mat.keys()) mat = utils.format_as_mat(mat) clusters_per_mat = 20 mats = utils.split_mat(mat, clusters_per_mat) # 10 clusters per matrix print "\tMat index\tLabel Name" for x,label in enumerate(labels): print "\t%d:\t%s" % (x, label) print for x, mat in enumerate(mats): utils.insert_indices(mat, col_start=(clusters_per_mat * x)) utils.print_mat(mat) print print
def _init_clusters(self):
super(MaxCliqueInitCONFIRM, self)._init_clusters()
sub_docs = self.docs[:self.num_instances]
sim_mat = utils.pairwise(
sub_docs, lambda x, y: max(self.doc_similarity(x, y),
self.doc_similarity(y, x)))
print
print "Doc Sim Mat"
utils.print_mat(utils.apply_mat(sim_mat, lambda x: "%3.2f" % x))
idxs = utils.find_best_clique(sim_mat, self.num_clust)
print
print "Cluster Labels:"
for idx in idxs:
self._add_cluster(self.docs[idx], member=False)
print idx, self.docs[idx].label
def print_cluster_sim_mat(self): print "CLUSTER SIM MATRICES:" centers = map(lambda cluster: cluster.center, self.clusters) feature_set_names = self.docs[0].get_feature_set_names() for name in feature_set_names: print print "Similarity Type: %s" % name mat = utils.pairwise(centers, lambda doc1, doc2: doc1.global_sim(doc2, name)) mat = utils.apply_mat(mat, lambda x: "%3.2f" % x) utils.insert_indices(mat) utils.print_mat(mat) print print "Similarity Type: Cluster sim by CONFIRM" sub_mat = utils.pairwise(self.clusters, lambda c1, c2: self.confirm.cluster_similarity(c1, c2)) sub_mat = utils.apply_mat(sub_mat, lambda x: "%3.2f" % x) utils.insert_indices(sub_mat) utils.print_mat(sub_mat) print print
def cmp_test():
doc1 = doc.get_doc(single_dir, single_file)
doc2 = doc.get_doc(second_dir, second_file)
doc1._load_check()
doc2._load_check()
doc1.display()
doc2.display()
global_region_sims = doc1.global_region_sim(doc2)
global_region_weights = doc1.global_region_weights()
global_sims = doc1.global_sim(doc2)
region_sims = doc1.region_sim(doc2)
region_weights1 = doc1.region_weights()
region_weights2 = doc2.region_weights()
for x, name in enumerate(doc1.feature_set_names):
print
print name
print "Global Sim:", global_sims[x]
print "Region Sims:"
print
utils.print_mat(utils.apply_mat(region_sims[x], lambda x: "%.3f" % x))
print
print "Region Weights doc1:"
print
utils.print_mat(utils.apply_mat(region_weights1[x], lambda x: "%.3f" % x))
print
print "Region Weights doc2:"
print
utils.print_mat(utils.apply_mat(region_weights2[x], lambda x: "%.3f" % x))
print
print "Match Vec"
print
match_vec = doc1.match_vector(doc2)
for x in xrange(len(match_vec) / 10):
print match_vec[10 * x: 10 * (x + 1)]
print
print "Sim Vector:"
print " ".join(map(lambda x: "%.2f" % x, global_region_sims))
print "Sim Weights:"
print " ".join(map(lambda x: "%.2f" % x, global_region_weights))
#doc1.draw().save("output/doc1.png")
#doc2.draw().save("output/doc2.png")
#doc1.push_away(doc2)
#doc1.draw().save("output/doc1_pushed.png")
#doc2.draw().save("output/doc2_pushed.png")
#doc1.push_away(doc2)
doc1.aggregate(doc2)
doc1.display()
def print_cluster_sim_mat(self):
print "CLUSTER SIM MATRICES:"
centers = map(lambda cluster: cluster.center, self.clusters)
feature_set_names = self.docs[0].get_feature_set_names()
for name in feature_set_names:
print
print "Similarity Type: %s" % name
mat = utils.pairwise(
centers, lambda doc1, doc2: doc1.global_sim(doc2, name))
mat = utils.apply_mat(mat, lambda x: "%3.2f" % x)
utils.insert_indices(mat)
utils.print_mat(mat)
print
print "Similarity Type: Cluster sim by CONFIRM"
sub_mat = utils.pairwise(
self.clusters,
lambda c1, c2: self.confirm.cluster_similarity(c1, c2))
sub_mat = utils.apply_mat(sub_mat, lambda x: "%3.2f" % x)
utils.insert_indices(sub_mat)
utils.print_mat(sub_mat)
print
print
break
x = R[idx:, idx]
if np.linalg.norm(x) == 0.:
continue
e = np.zeros_like(x)
e[0] = np.linalg.norm(x)
u = x - e
v = u / np.linalg.norm(u)
Q_cnt = np.identity(m)
Q_cnt[idx:, idx:] -= 2.0 * np.outer(v, v) #
R = np.dot(Q_cnt, R) #R=P1P2..PnA
Q = np.dot(Q_cnt, Q) #Q=P1P2P3...Pn
return np.round(Q.T, 3), np.round(R, 3) #保留三位
# return Q.T,R
if __name__ == "__main__":
path = r'data.txt'
matrix = load_mat(path, "HR")
if matrix.size == 0:
print("input Error!")
sys.exit()
Q, R = Householder_Reduction(matrix)
m, _ = Q.shape
m, n = R.shape
print(np.round(np.dot(Q, R), 2))
print("Q=")
print_mat(Q, m, m)
print("R=")
print_mat(R, m, n)
def main(args):
path = args.files
matrix = load_mat(path, args.mode)
if matrix.size == 0:
print("input Matrix Error!")
sys.exit()
m, n = matrix.shape
if args.mode == "LU":
print("LU Factorization, the input should be a square matrix.\n")
elif args.mode == "QR":
r = np.linalg.matrix_rank(matrix)
if r < n:
print(
"Error!\n QR Factorization, The matrix has linearly dependent columns can not be uniquely factored as A=QR!\n"
)
print("=" * 50, "\norigin matrix type: {m} * {n}".format(m=m, n=n),
"\nOrigin Matrix A = ")
print_mat(matrix, m, n)
print("\nThe factorization is processing!\n ")
if args.mode == "LU":
P, L, U = LU_factorization(matrix)
m, n = P.shape
print("L=")
print_mat(L, m, m)
print("U=")
print_mat(U, m, m)
print("P=")
print_mat(P, m, m)
elif args.mode == "QR":
Q, R = QR(matrix)
m, n = Q.shape
m1, n1 = R.shape
print("Q=")
print_mat(Q, m, n)
print("R=")
print_mat(R, m1, n1)
elif args.mode == "Householder":
Q, R = Householder_Reduction(matrix)
m, n = Q.shape
m1, n1 = R.shape
print("Q=")
print_mat(Q, m, n)
print("R=")
print_mat(R, m1, n1)
elif args.mode == "Givens":
Q, R = Givens_Reduction(matrix)
m, n = Q.shape
m1, n1 = R.shape
print("Q=")
print_mat(Q, m, n)
print("R=")
print_mat(R, m1, n1)
elif args.mode == "URV":
U, R, V = URV(matrix)
m, n = U.shape
m1, n1 = R.shape
m2, n2 = V.shape
print("U=")
print_mat(U, m, n)
print("R=")
print_mat(R, m1, n1)
print("V=")
print_mat(V, m2, n2)
def show_pixel(mat):
replace = lambda x:'M' if x != 0 else ' '
print_mat(mat,replace=replace)
mat[i, row] = factor
plus = -1 * factor * mat[row, row + 1:-1]
mat[i, row + 1:-1] += plus
temp = mat.copy()
# print_mat(mat,m,n)
U = np.triu(mat[:, :-1], 0)
for i in range(m):
temp[i, i] = 1
L = np.tril(temp[:, :-1], 0)
P = np.zeros(shape=(m, n - 1))
for j in range(m):
row_idx = int(mat[j, -1])
P[j, row_idx - 1] = 1
return P, L, U
if __name__ == "__main__":
path = r"data.txt"
matrix = load_mat(path, "LU")
if matrix.size == 0:
print("input Error!")
sys.exit()
P, L, U = LU_factorization(matrix)
m, n = P.shape
print("L=")
print_mat(L, m, m)
print("U=")
print_mat(U, m, m)
print("P=")
print_mat(P, m, m)
输出U为mxm正交矩阵，R为nxn正交矩阵，R为分块矩阵mxn
"""
Q, R = Givens_Reduction(mat)
# print(R)
r = np.linalg.matrix_rank(mat)
mat1 = R[0:r, :]
Q1, R1 = Givens_Reduction(mat1.T)
# Q1, R1 = Givens_Reduction(R.T)
U = Q
V = Q1
R1 = np.dot(np.dot(U.T, mat), V)
return U, R1, V
if __name__ == "__main__":
path = r'data.txt'
matrix = load_mat(path, "HR")
if matrix.size == 0:
print("input Error!")
sys.exit()
U, R, V = URV(matrix)
m, n = U.shape
m1, n1 = R.shape
m2, n2 = V.shape
print("U=")
print_mat(U, m, n)
print("R=")
print_mat(R, m1, n1)
print("V=")
print_mat(V, m2, n2)
print(np.dot(np.dot(U, R), V.T))
norm = math.sqrt(R[i, i] ** 2 + cur_col[j] ** 2)
P_cnt = np.identity(m)
P_cnt[i, i] = R[i, i] / norm #计算旋转矩阵P_cnt
P_cnt[i, i + j + 1] = cur_col[j] / norm
P_cnt[i + j + 1, i] = -cur_col[j] / norm
P_cnt[i + j + 1, i + j + 1] = R[i, i] / norm
Q = np.dot(P_cnt, Q) #Q=P1P2P3...Pn
R = np.dot(P_cnt, R) #R=P1P2..PnA
# Q = np.round(np.dot(P_cnt, Q), 4)
# R = np.round(np.dot(P_cnt, R), 4)
return np.round(Q.T, 3), np.round(R, 3) #保留三位
# return Q.T,R
if __name__ == "__main__":
path = r'data.txt'
matrix = load_mat(path, "HR")
if matrix.size == 0:
print("input Error!")
sys.exit()
Q, R = Givens_Reduction(matrix)
a = np.round(np.dot(Q, R), 2)
print(a)
m1, _ = Q.shape
m, n = R.shape
print("Q=")
print_mat(Q, m1, m1)
print("R=")
print_mat(R, m, n)
def show_pixel(mat):
replace = lambda x: 'M' if x == 255 else ' '
print_mat(mat, replace=replace)