def setUp(self):
self.data = {
'id': [chr(97 + c) for c in range(1, 10)],
'x': [50, 50, -10, 0, 0, 5, 15, -3, None],
'y': [
0.000001, 654.152, None, 15.984512, 3122, -3.1415926535, 111,
15.9, 13.5
],
'cat': [
'a', 'long text value', u'Élysée', '', None,
'some <b> B.s </div> </div> HTML stuff', 'c', 'c', 'c'
],
's1':
np.ones(9),
's2':
[u'some constant text $ % value {obj} ' for _ in range(1, 10)],
'somedate': [
datetime.date(2011, 7, 4),
datetime.datetime(2022, 1, 1, 13, 57),
datetime.datetime(1990, 12, 9), None,
datetime.datetime(1990, 12, 9),
datetime.datetime(1950, 12, 9),
datetime.datetime(1898, 1, 2),
datetime.datetime(1950, 12, 9),
datetime.datetime(1950, 12, 9)
]
}
self.df = pd.DataFrame(self.data)
self.df['somedate'] = pd.to_datetime(self.df['somedate'])
self.results = describe(self.df)
self.test_dir = tempfile.mkdtemp()
def test_recoding_reject(self):
self.data = {
'x': [
'chien', 'chien', 'chien', 'chien', 'chat', 'chat', 'chameaux',
'chameaux'
],
'y': ['dog', 'dog', 'dog', 'dog', 'cat', 'cat', 'camel', 'camel'],
}
self.df = pd.DataFrame(self.data)
self.results = describe(self.df)
self.assertEqual(self.results['variables'].loc['x']['type'], 'RECODED')
self.assertEqual(self.results['variables'].loc['x']['correlation_var'],
'y')
expected_results = {
'total_missing': 0.0,
'UNIQUE': 0,
'CONST': 0,
'nvar': 2,
'REJECTED': 1,
'n': 8,
'RECODED': 1,
'CORR': 0,
'DATE': 0,
'NUM': 0,
'CAT': 1,
'n_duplicates': 5
}
for key in expected_results:
self.assertEqual(self.results['table'][key], expected_results[key])
def setUp(self):
self.data = {'id': [chr(97+c) for c in range(1,10)],
'x': [50, 50, -10, 0, 0, 5, 15, -3, None],
'y': [0.000001, 654.152, None, 15.984512, 3122, -3.1415926535, 111, 15.9, 13.5],
'cat': ['a', 'long text value', u'Élysée', '', None, 'some <b> B.s </div> </div> HTML stuff', 'c',
'c',
'c'],
's1': np.ones(9),
's2': [u'some constant text $ % value {obj} ' for _ in range(1, 10)],
'somedate': [datetime.date(2011, 7, 4), datetime.datetime(2022, 1, 1, 13, 57),
datetime.datetime(1990, 12, 9), None,
datetime.datetime(1990, 12, 9), datetime.datetime(1950, 12, 9),
datetime.datetime(1898, 1, 2), datetime.datetime(1950, 12, 9)
, datetime.datetime(1950, 12, 9)]}
self.df = pd.DataFrame(self.data)
self.df['somedate'] = pd.to_datetime(self.df['somedate'])
self.results = describe(self.df)
self.test_dir = tempfile.mkdtemp()
def __init__(self, df):
description_set = describe(df)
self.html = to_html(df.head(),
description_set)
def test_bins(self):
self.results = describe(self.df, bins=100)
self.test_describe_df()
def test_bins(self):
self.results = describe(self.df, bins=100)
self.test_describe_df()
