def test_uint64_overflow(self):
exp = Series([2**63], dtype=np.uint64)
s = Series([1, 2**63, 2**63], dtype=np.uint64)
tm.assert_series_equal(algos.mode(s), exp)
exp = Series([], dtype=np.uint64)
s = Series([1, 2**63], dtype=np.uint64)
tm.assert_series_equal(algos.mode(s), exp)
def test_no_mode(self):
exp = Series([], dtype=np.float64)
tm.assert_series_equal(algos.mode([]), exp)
exp = Series([], dtype=np.int)
tm.assert_series_equal(algos.mode([1]), exp)
exp = Series([], dtype=np.object)
tm.assert_series_equal(algos.mode(['a', 'b', 'c']), exp)
def test_timedelta_mode(self):
exp = Series([], dtype='timedelta64[ns]')
s = Series(['1 days', '-1 days', '0 days'],
dtype='timedelta64[ns]')
tm.assert_series_equal(algos.mode(s), exp)
exp = Series(['2 min', '1 day'], dtype='timedelta64[ns]')
s = Series(['1 day', '1 day', '-1 day', '-1 day 2 min',
'2 min', '2 min'], dtype='timedelta64[ns]')
tm.assert_series_equal(algos.mode(s), exp)
def test_datelike_mode(self):
exp = Series([], dtype="M8[ns]")
s = Series(['2011-01-03', '2013-01-02',
'1900-05-03'], dtype='M8[ns]')
tm.assert_series_equal(algos.mode(s), exp)
exp = Series(['2011-01-03', '2013-01-02'], dtype='M8[ns]')
s = Series(['2011-01-03', '2013-01-02', '1900-05-03',
'2011-01-03', '2013-01-02'], dtype='M8[ns]')
tm.assert_series_equal(algos.mode(s), exp)
def test_categorical(self):
c = Categorical([1, 2])
exp = Series([], dtype=np.int64)
tm.assert_series_equal(algos.mode(c), exp)
c = Categorical([1, 'a', 'a'])
exp = Series(['a'], dtype=object)
tm.assert_series_equal(algos.mode(c), exp)
c = Categorical([1, 1, 2, 3, 3])
exp = Series([1, 3], dtype=np.int64)
tm.assert_series_equal(algos.mode(c), exp)
def missing_values(self):
for attribute in self.meta_data:
if self.meta_data[attribute] == "NUMERIC":
self.train[attribute] = self.train.groupby("class").transform(
lambda x: x.fillna(x.mean()))
self.test[attribute] = self.test.groupby("class").transform(
lambda x: x.fillna(x.mean()))
else:
self.train[attribute].fillna(mode(self.train[attribute])[0],
inplace=True)
self.test[attribute].fillna(mode(self.test[attribute])[0],
inplace=True)
def test_strobj_mode(self):
exp = ['b']
data = ['a'] * 2 + ['b'] * 3
s = Series(data, dtype='c')
exp = Series(exp, dtype='c')
tm.assert_series_equal(algos.mode(s), exp)
exp = ['bar']
data = ['foo'] * 2 + ['bar'] * 3
for dt in [str, object]:
s = Series(data, dtype=dt)
exp = Series(exp, dtype=dt)
tm.assert_series_equal(algos.mode(s), exp)
def test_number_mode(self):
exp_single = [1]
data_single = [1] * 5 + [2] * 3
exp_multi = [1, 3]
data_multi = [1] * 5 + [2] * 3 + [3] * 5
for dt in np.typecodes['AllInteger'] + np.typecodes['Float']:
s = Series(data_single, dtype=dt)
exp = Series(exp_single, dtype=dt)
tm.assert_series_equal(algos.mode(s), exp)
s = Series(data_multi, dtype=dt)
exp = Series(exp_multi, dtype=dt)
tm.assert_series_equal(algos.mode(s), exp)
def detect_frequency(idx):
"""
Return the most plausible frequency of DatetimeIndex idx (even when gaps in it).
It calculates the delta between element of the index (idx[1:] - idx[:1]), gets the 'mode' of the delta (most frequent delta) and transforms it into a frequency ('H','15T',...)
A solution exists in pandas:
..ipython:
from pandas.tseries.frequencies import _TimedeltaFrequencyInferer
inferer = _TimedeltaFrequencyInferer(idx)
freq = inferer.get_freq()
But for intraday frequencies, if it is not regular (like for 'publication_date'
of forecast timeseries), then the inferer.get_freq() return None.
In those cases, we are going to return the smallest frequency possible.
:param idx: DatetimeIndex
:return: str
"""
if len(idx) < 2:
raise ValueError(
"Cannot detect frequency of index when index as less than two elements"
)
# calculates the delta
delta_idx = idx[1:] - idx[:-1]
delta_mode = mode(delta_idx)
if len(delta_mode) == 0:
# if no clear mode, take the smallest delta_idx
td = min(delta_idx)
else:
# infer frequency from most frequent timedelta
td = delta_mode[0]
return to_offset(td)
def test_index(self):
idx = Index([1, 2, 3])
exp = Series([], dtype=np.int64)
tm.assert_series_equal(algos.mode(idx), exp)
idx = Index([1, 'a', 'a'])
exp = Series(['a'], dtype=object)
tm.assert_series_equal(algos.mode(idx), exp)
idx = Index([1, 1, 2, 3, 3])
exp = Series([1, 3], dtype=np.int64)
tm.assert_series_equal(algos.mode(idx), exp)
exp = Series(['2 min', '1 day'], dtype='timedelta64[ns]')
idx = Index(['1 day', '1 day', '-1 day', '-1 day 2 min',
'2 min', '2 min'], dtype='timedelta64[ns]')
tm.assert_series_equal(algos.mode(idx), exp)
def test_mixed_dtype(self):
exp = Series(['foo'])
s = Series([1, 'foo', 'foo'])
tm.assert_series_equal(algos.mode(s), exp)