def get_subdataset_columns(parameters):
"""
Obtains a subset of the dataset by its columns.
:param parameters: The parameter of the function(dataset name,...).
"""
workspace = al.Workspace()
data_name = parameters['Dataset']
dataset = workspace.get_dataset(data_name)
cols = []
if parameters["cols"]:
cols = parameters['cols']
else:
stop = False
while not stop:
cols.append(al.obtain_column(dataset))
print('Do you want to continue? yes or no?')
response = al.query_input()
if response == 'no':
stop = True
dataset = dataset[cols]
num = workspace.get_counter('sub')
name = 'subcol' + str(num) + data_name
workspace.save_dataset(name, dataset)
txt = 'The sub-dataset by the rows is saved as ' + name
print(txt)
def paa(dataset, parameters):
"""
Executes the function paa of khiva.
:param dataset: The dataset which is computed.
:param parameters: The parameters of the function (number of points).
:return: The timeserie with the reduced points.
"""
num_points = al.get_int_number(parameters)
if dataset.columns.size > 1:
dataset = dataset[al.obtain_column(dataset)]
k_array = kv.Array(dataset)
result = kv.paa(k_array, num_points)
return result.to_pandas()
def ramer_douglas_peucker(dataset, parameters):
"""
Executes the function Ramer-Douglas-Peucker of khiva.
:param dataset: The dataset which is computed.
:param parameters: The parameters of the function (epsilon).
:return: The timeserie with the reduced points.
"""
epsilon = al.get_float_number(parameters)
if dataset.columns.size > 1:
dataset = dataset[al.obtain_column(dataset)]
k_array = kv.Array([range(dataset.size), dataset.to_numpy().flatten()])
result = kv.ramer_douglas_peucker(k_array, epsilon).transpose()
result = result.to_pandas()
result.set_index(0, inplace=True)
result.set_index(result.index.astype('int32'), inplace=True)
return result
def pip(dataset, parameters):
"""
Executes the function pip of khiva.
:param dataset: The dataset which is computed.
:param parameters: The parameters of the function (number of pip).
:return: The timeserie with the reduced points.
"""
num_pip = al.get_int_number(parameters)
if dataset.columns.size > 1:
dataset = dataset[al.obtain_column(dataset)]
k_array = kv.Array([range(dataset.size), dataset.to_numpy().flatten()])
result = kv.pip(k_array, num_pip).transpose()
result = result.to_pandas()
result.set_index(0, inplace=True)
result.set_index(result.index.astype('int32'), inplace=True)
return result
def plot_dataset(dataset, parameters):
"""
Plots graphically a column of the dataset.
:param dataset: The current dataset.
:param parameters: The parameter for the graphic.
"""
a = int(parameters['from'] if parameters['from'] else 0)
b = int(parameters['to'] if parameters['to'] else dataset.index.size)
if b < a:
print(
'This operation cannot be done.\nThe starting row number is greater than the last row number.'
)
raise Exception()
if b:
dataset = dataset.iloc[:b]
if a:
dataset = dataset.iloc[a:]
ncol = dataset.columns.size
if ncol > 1:
if not parameters["columns"]:
column_name = al.obtain_column(dataset)
plt.figure()
plt.plot(dataset[column_name])
plt.title(column_name)
plt.show(block=False)
else:
for column_name in parameters["columns"]:
plt.figure()
plt.plot(dataset[column_name])
plt.title(column_name)
plt.show(block=False)
else:
plt.figure()
plt.plot(dataset)
plt.title(parameters["Dataset"])
plt.show(block=False)
def do_matrix(parameters):
"""
Do a operation of matrix.
:param parameters: The parameters of the function (name of the operation, number of clusters, ...).
"""
op = parameters.pop("operation")
workspace = al.Workspace()
if op == "stomp" and not parameters.get('Dataset2'):
op = 'stomp_self_join'
if op == "stomp":
data_name = parameters["Dataset"]
data_name2 = parameters["Dataset2"]
dataset1 = workspace.get_dataset(data_name)
dataset2 = workspace.get_dataset(data_name2)
if dataset2 is None:
if not data_name2 == "":
print("The object " + data_name2 + " does not exist.")
al.voice("The object " + data_name2 + " does not exist.")
print("Please, provide the two datasets that should be stomped.")
al.voice("Please, provide the two datasets that should be stomped.")
return
col = ''
if dataset1.columns.size > 1:
col = al.obtain_column(dataset1)
dataset1 = dataset1[col]
if dataset2.columns.size > 1:
dataset2 = dataset2[al.obtain_column(dataset2)]
(stomp, m) = al.stomp(dataset1.values, dataset2.values, parameters)
number = workspace.get_counter('matrix_stomp')
workspace.save_dataset('stomp' + str(number), (stomp.to_json(), m, col, dataset1.to_json()))
print("The stomp is stored as stomp" + str(number))
elif op == "stomp_self_join":
data_name = parameters["Dataset"]
dataset1 = workspace.get_dataset(data_name)
col = ''
if dataset1.columns.size > 1:
col = al.obtain_column(dataset1)
dataset1 = dataset1[col]
(stomp, m) = al.stomp_self_join(dataset1.values, parameters)
number = workspace.get_counter('matrix_stomp')
workspace.save_dataset('stomp' + str(number), (stomp.to_json(), m, col, dataset1.to_json()))
print("The stomp is stored as stomp" + str(number))
elif op == "find_best_n_discords":
stomp_name = parameters['Dataset']
stomp = workspace.get_dataset(stomp_name)
m, col, dataset = workspace.get_value(stomp_name)[1:]
discords = al.find_best_n_discords(stomp, m, parameters, col, pd.read_json(dataset).sort_index())
number = workspace.get_counter('matrix_best_d')
workspace.save_dataset('discords' + str(number), discords)
print('The best ' + str(int(parameters['n'])) + ' discord segments are stored as discords' + str(number))
elif op == "find_best_n_motifs":
stomp_name = parameters['Dataset']
stomp = workspace.get_dataset(stomp_name)
m, col, dataset = workspace.get_value(stomp_name)[1:]
motifs = al.find_best_n_motifs(stomp, m, parameters, col, pd.read_json(dataset).sort_index())
number = workspace.get_counter('matrix_best_m')
workspace.save_dataset('motifs' + str(number), motifs)
print('The best ' + str(int(parameters['n'])) + ' motifs segments are stored as motifs' + str(number))
