def prepare(mode, inp, out):
""" Transform the given dataset file """
if mode == 'help':
# log("Cognito CLI", color="blue", figlet=True)
click.echo(custom_fig.renderText('cognito'))
if mode == 'ml':
df = Table(inp)
response, encoder = df.generate()
click.echo(save_to(out, response, encoder))
if mode == 'report':
df = Table(inp)
table = PrettyTable([
'Features', 'Feature Type', 'Outliers', '% of outliers', 'Missing',
'%of missing'
])
for col in df.columns():
table.add_row([col, '', '', '', '', ''])
click.echo(table)
class Report:
def __init__(self, filename):
self.data = Table(filename)
def generate(self):
columns = self.data.columns()
table = PrettyTable(columns)
print(table)
def prepare(mode, inp, out):
""" Transform the given dataset file """
if mode == 'help':
# log("Cognito CLI", color="blue", figlet=True)
click.echo(custom_fig.renderText('cognito'))
if mode == 'prepare':
df = Table(inp)
response, encoder = df.generate()
click.echo(save_to(out, response, encoder))
if mode == 'autoML':
df = Table(inp)
click.echo(df.total_columns())
if mode == 'report':
df = Table(inp)
table = PrettyTable([
'Features', 'Feature Type', 'Outliers', '% of outliers', 'Missing',
'%of missing'
])
for col in df.columns():
table.add_row([col, '', '', '', '', ''])
click.echo(table)
if mode == 'decode':
with trange(11) as t:
for i in t:
t.set_description('C(x) decoding %i' % i)
sleep(0.1)
click.echo('Completed decoding')
click.echo(get_all_files())
def test_table_columns_two():
data = Table(os.path.join(os.path.dirname(__file__), 'data',
'student.csv'))
assert data.columns().tolist() == ['sex', 'age', 'Mjob', 'G1']
def test_table_columns_one():
data = Table(os.path.join(os.path.dirname(__file__), 'data', 'cereal.csv'))
assert data.columns().tolist() == [
'name', 'mfr', 'sodium', 'type', 'calories', 'sugars'
]
def test_load_table():
table = Table(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
print(table.columns())
def test_columns_three():
data = Table(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
assert data.columns() == [
'Location', 'population', 'nonwhite', 'density', 'crime'
]
