def split_by_rows(parameters):
"""
Split a dataset into n datasets of m rows.
:param parameters: The parameters of the function (dataset name, size of the split dataset for the rows).
"""
workspace = al.Workspace()
name_data = parameters['Dataset']
dataset = workspace.get_dataset(name_data)
if parameters['split']:
div = int(parameters['split'])
else:
print('How many rows will each dataset have?')
query = al.query_input()
while not al.isnumber(query):
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one:')
query = al.query_input()
div = int(query)
it = 0
names = []
while it < dataset.index.size:
div_dataset = dataset.iloc[it:it + div]
num = workspace.get_counter('split')
name = name_data + 'r' + str(num)
names.append(name)
workspace.save_dataset(name, div_dataset)
it = it + div
print('The splits of ' + name_data + ' are saved as: ' + str(names)[1:-1])
def rand_param(parameters):
"""
Obtains the parameters for the random dataset generator.
:param parameters: The parameters for the creation (number of rows, numbers of columns,...).
:return: A tuple of the parameters.
"""
num_rows, num_col, values = 0, 0, []
if parameters["columns"]:
num_col = int(parameters["columns"])
else:
print('How many columns?')
al.voice('How many columns?')
query = al.query_input()
while not query.isnumeric():
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
num_col = int(query)
if parameters["rows"]:
num_rows = int(parameters["rows"])
else:
print('How many rows?')
al.voice('How many rows?')
query = al.query_input()
while not query.isnumeric():
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
num_rows = int(query)
if parameters["values"]:
values = parameters["values"]
else:
print('What is the minimum value?')
al.voice('What is the minimum value?')
query = al.query_input()
while not al.isnumber(query):
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one:')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
values.append(float(query))
print('And the maximum?')
al.voice('And the maximum?')
query = al.query_input()
while not al.isnumber(query):
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one:')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
values.append(float(query))
return num_rows, num_col, values
def get_subdataset_rows(parameters):
"""
Obtains a subset of the dataset by its rows.
:param parameters: The parameter of the function(dataset name,...).
"""
workspace = al.Workspace()
data_name = parameters['Dataset']
dataset = workspace.get_dataset(data_name)
if parameters["from"]:
index_a = int(parameters["from"])
else:
print('From what row number?')
al.voice('From what row number?')
query = al.query_input()
while not al.isnumber(query):
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one:')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
index_a = int(query)
if parameters["to"]:
index_b = int(parameters['to'])
else:
print('To what row number?')
al.voice('To what row number?')
query = al.query_input()
while not al.isnumber(query):
print(
'Incorrect input.\nIt is not a number.\nPlease introduce one:')
al.voice(
'Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
index_b = int(query)
if index_b < index_a:
print(
'This operation cannot be done.\nThe starting row number is greater than the last row number.'
)
raise Exception()
dataset = dataset.iloc[index_a:index_b]
num = workspace.get_counter('sub')
name = 'subrow' + str(num) + data_name
workspace.save_dataset(name, dataset)
txt = 'The sub-dataset by the rows is saved as ' + name
print(txt)
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 get_int_number(parameters):
"""
Obtains or asks for a integer number.
:param parameters: the parameters of the function(number,...).
:return: An integer number.
"""
if parameters["number"]:
num_points = int(parameters["number"])
else:
print('How many point do you want to reduce it?')
al.voice('How many point do you want to reduce it?')
query = al.query_input()
while not query.isnumeric():
print('Incorrect input.\nIt is not a number.\nPlease introduce one.')
al.voice('Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
num_points = int(query)
return num_points
def get_epsilon(parameters):
"""
Obtains or asks for the epsilon.
:param parameters: the parameters of the function(number,...).
:return: The epsilon value.
"""
# Although we are asking for the epsilon, the value it is saved in the key number
if parameters["number"]:
num_points = parameters["number"]
else:
print('What is the value of epsilon?')
al.voice('What is the value of epsilon?')
query = al.query_input()
while not query.isnumeric():
print('Incorrect input.\nIt is not a number.\nPlease introduce one.')
al.voice('Incorrect input.\nIt is not a number.\nPlease introduce one.')
query = al.query_input()
num_points = float(query)
return num_points
def ask_for_dataset_extension(files):
"""
Ask for the dataset extension file.
:param files: All files with the same name.
:return: The extension file.
"""
print('What is the file extension (txt, csv)?')
print('All the files that has been found with the same name: ' +
str(files))
return al.query_input()
def change_name(parameters):
"""
Change the name of an existing dataset.
:param parameters: The parameter of the function (dataset name,...).
"""
workspace = al.Workspace()
or_name = parameters['Dataset']
into_name = parameters['NameInto']
if not into_name:
print('Into what name do you want to change ' + or_name + '?')
into_name = al.query_input()
while into_name in workspace.get_all_dataset():
print('There is already a dataset with the name ' + into_name +
'.\nPlease write another name.')
into_name = al.query_input()
data = workspace.get_value(or_name)
workspace.remove_dataset(or_name)
workspace.save_dataset(into_name, data)
print('The dataset named ' + or_name + ' has been updated into ' +
into_name)
def ask_for_dataset_path():
"""
Ask for the dataset path.
:return: The path introduced.
"""
print('Where is it located?')
print('Current path is ' + os.getcwd())
query = al.query_input()
if query == 'here':
path = os.getcwd()
else:
path = query
return path
