def reduce_data():
flucs = []
data = collect_data()
for element in data:
flucs.append(element.fluc.flatten())
flucs = np.vstack(flucs)
p = Pca(flucs, energy_treshold=0.5)
#save compressed vector
for element in data:
if True:#not os.path.isfile(element.path+"fluc_comp_1.npy"):
fluc_comp = p.project_data(element.fluc.flatten()[:,np.newaxis])
np.save(os.path.join(element.path,"fluc_comp_"+element.name), fluc_comp)
"""reduced = p.project_data(flucs.transpose())
np.save("reduced_data",reduced)"""
np.save("/home/kayibal/sc-recom/code/data_aq/pca/energies",p.en)
np.save("/home/kayibal/sc-recom/code/data_aq/pca/mean",p.mean)
np.save("/home/kayibal/sc-recom/code/data_aq/pca/pcs",p.pcs)
def reduce_data():
flucs = []
data = collect_data()
for element in data:
flucs.append(element.fluc.flatten())
flucs = np.vstack(flucs)
p = Pca(flucs, energy_treshold=0.5)
#save compressed vector
for element in data:
if True: #not os.path.isfile(element.path+"fluc_comp_1.npy"):
fluc_comp = p.project_data(element.fluc.flatten()[:, np.newaxis])
np.save(os.path.join(element.path, "fluc_comp_" + element.name),
fluc_comp)
"""reduced = p.project_data(flucs.transpose())
np.save("reduced_data",reduced)"""
np.save("/home/kayibal/sc-recom/code/data_aq/pca/energies", p.en)
np.save("/home/kayibal/sc-recom/code/data_aq/pca/mean", p.mean)
np.save("/home/kayibal/sc-recom/code/data_aq/pca/pcs", p.pcs)
def read_file():
iris = load_iris()
return iris.data, iris.target
batch_size = 2
num_epochs = 1000
number_final_att = 13
if __name__ == '__main__':
############################################## 2d
inputs, labels = data.open_data('wine.arff', 3)
inputs = np.array(inputs)
labels = np.array(labels)
pca = Pca()
data = preprocessing.scale(inputs)
pcaAdapt = PcaAdapt(13)
pcaAdapt.train(data)
result = np.matrix.transpose(pcaAdapt.pca_result(data)).reshape(
len(data), number_final_att)
mlp = MLP(3)
points = result
inputs = points
mlp.create_network(inputs.shape[1:], 0.001)
mlp.train(inputs, labels, num_epochs, batch_size)
'''
def pca_async_processing(database_url_input, label_name, pca_filename):
pca_generator = Pca(database_url_input)
pca_generator.create_image(label_name, pca_filename)
def read_file():
iris = load_iris()
return iris.data, iris.target
colors = {0: 'ro',
1: 'bo',
2: 'go'}
if __name__ == '__main__':
############################################## 2d
data, target = read_file()
data = preprocessing.scale(data)
pca = Pca()
cov = pca.cov_matrix(data[:, 0], data[:, 1], data[:, 2], data[:, 3])
values, vectors = pca.eigen_values_vectors(cov)
values, vectors = pca.sort_eigen(values, vectors)
vectors = pca.eigen_strip_vectors(values, vectors, 0.90)
print(vectors)
values = values[:len(vectors[0])]
result = np.matrix.transpose(pca.pca_result(data,
vectors)).reshape(len(data), len(data[0])-2)
result[:, 1] = -result[:, 1]
points = result
count = 0
mlp = MLP(3)
# loading data
inputs, labels = data.open_data('wine.arff', 3)
inputs = np.array(inputs)
labels = np.array(labels)
# # without pca
batch_size = 2
# print(inputs[0])
# leng = [len(inp) for inp in inputs]
# print(max(leng), min(leng))
# print(inputs.shape[1:])
# mlp.create_network(inputs.shape[1:], 0.001)
# mlp.train(inputs, labels, num_epochs, batch_size)
# with pca
pca = Pca()
data = preprocessing.scale(inputs)
cov = np.cov(data, rowvar=False)
values, vectors = pca.eigen_values_vectors(cov)
values, vectors = pca.sort_eigen(values, vectors)
vectors = pca.eigen_strip_vectors(values, vectors, 0.98)
print(vectors.shape)
values = values[:len(vectors[0])]
result = np.matrix.transpose(pca.pca_result(data, vectors)).reshape(
len(data), 8)
print(result.shape)
points = result
# kmeans.distribute()
# error = kmeans.check()
# print('separated sets normalize')
# print("error is %f%%" % (error*100))
#
# print('none separated sets')
# points = Points()
# points.init(file_name="sets_connected.xls", start_row=0, dim=5)
# kmeans = Kmeans(points=points.points, centroid_num=5)
# kmeans.distribute()
# error = kmeans.check()
# print('none separated sets')
# print("error is %f%%" % (error*100))
#
# print('none separated sets normalize')
# points = Points()
# points.init(file_name="sets_connected_norma.xls", start_row=0, dim=5)
# kmeans = Kmeans(points=points.points, centroid_num=5)
# kmeans.distribute()
# error = kmeans.check()
# print('none separated sets normalize')
# print("error is %f%%" % (error*100))
points = Points()
points.init(file_name="iris.xls", start_row=0, end_row=2, dim=4)
prc = Pca(points=points.points)
prc.distribute()
error = prc.check()
print("error is %f%%" % (error*100))
def compress(self, compression):
# compress using PCA
k = int(self.data.shape[1] * compression)
pca = Pca(self.data)
compressed_vectors = [pca.project(vector, k) for vector in self.data]
return CompressionInfo(compressed_vectors, pca, self.data.shape)
def compress(self, compression):
# compress using PCA
k = int(self.data.shape[1]*compression)
pca = Pca(self.data)
compressed_vectors = [pca.project(vector, k) for vector in self.data]
return CompressionInfo(compressed_vectors, pca, self.data.shape)