def test_value_counts_bins(self):
s = [1, 2, 3, 4]
result = algos.value_counts(s, bins=1)
self.assertEqual(result.tolist(), [4])
self.assertEqual(result.index[0], 0.997)
result = algos.value_counts(s, bins=2, sort=False)
self.assertEqual(result.tolist(), [2, 2])
self.assertEqual(result.index[0], 0.997)
self.assertEqual(result.index[1], 2.5)
def test_value_counts(self):
from pandas.tools.tile import cut
arr = np.random.randn(4)
factor = cut(arr, 4)
tm.assert_isinstance(factor, Categorical)
result = algos.value_counts(factor)
expected = algos.value_counts(np.asarray(factor))
tm.assert_series_equal(result, expected)
def test_value_counts_dtypes(self):
result = algos.value_counts([1, 1.])
self.assertEqual(len(result), 1)
result = algos.value_counts([1, 1.], bins=1)
self.assertEqual(len(result), 1)
result = algos.value_counts(Series([1, 1., '1'])) # object
self.assertEqual(len(result), 2)
self.assertRaises(TypeError, lambda s: algos.value_counts(s, bins=1), ['1', 1])
def test_value_counts_nat(self):
td = Series([np.timedelta64(10000), pd.NaT], dtype='timedelta64[ns]')
dt = pd.to_datetime(['NaT', '2014-01-01'])
for s in [td, dt]:
vc = algos.value_counts(s)
vc_with_na = algos.value_counts(s, dropna=False)
self.assertEqual(len(vc), 1)
self.assertEqual(len(vc_with_na), 2)
exp_dt = pd.Series({pd.Timestamp('2014-01-01 00:00:00'): 1})
tm.assert_series_equal(algos.value_counts(dt), exp_dt)
def value_counts(self, normalize=False, sort=True, ascending=False,
bins=None, dropna=True):
"""
Returns object containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
"""
from pandas.core.algorithms import value_counts
result = value_counts(self, sort=sort, ascending=ascending,
normalize=normalize, bins=bins, dropna=dropna)
return result
def value_counts(self, dropna=False):
from pandas import Series, PeriodIndex
if dropna:
values = self[~self.isna()]._data
else:
values = self._data
cls = type(self)
result = algos.value_counts(values, sort=False)
index = PeriodIndex(cls(result.index, freq=self.freq),
name=result.index.name)
return Series(result.values, index=index, name=result.name)
def test_value_counts(self):
np.random.seed(1234)
from pandas.tools.tile import cut
arr = np.random.randn(4)
factor = cut(arr, 4)
tm.assertIsInstance(factor, Categorical)
result = algos.value_counts(factor)
cats = ['(-1.194, -0.535]', '(-0.535, 0.121]', '(0.121, 0.777]',
'(0.777, 1.433]']
expected_index = CategoricalIndex(cats, cats, ordered=True)
expected = Series([1, 1, 1, 1], index=expected_index)
tm.assert_series_equal(result.sort_index(), expected.sort_index())
def value_counts(self, normalize=False, sort=True, ascending=False, bins=None, dropna=True):
"""
Returns object containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
"""
from pandas.core.algorithms import value_counts
from pandas.tseries.api import DatetimeIndex, PeriodIndex
from pandas import Index
result = value_counts(self, sort=sort, ascending=ascending, normalize=normalize, bins=bins, dropna=dropna)
if isinstance(self, PeriodIndex):
# preserve freq
result.index = self._simple_new(result.index.values, freq=self.freq)
elif isinstance(self, DatetimeIndex):
result.index = self._simple_new(result.index.values, tz=getattr(self, "tz", None))
if isinstance(self, Index):
return result
else:
return self._constructor(result)
def value_counts(self, dropna=True):
"""
Returns a Series containing counts of each interval.
Parameters
----------
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
See Also
--------
Series.value_counts
"""
# TODO: implement this is a non-naive way!
from pandas.core.algorithms import value_counts
return value_counts(np.asarray(self), dropna=dropna)
def value_counts(self, dropna=True):
"""
Returns a Series containing counts of each interval.
Parameters
----------
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
See Also
--------
Series.value_counts
"""
# TODO: implement this is a non-naive way!
from pandas.core.algorithms import value_counts
return value_counts(np.asarray(self), dropna=dropna)
def value_counts(self, normalize=False, sort=True, ascending=False,
bins=None, dropna=True):
"""
Returns object containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
"""
from pandas.core.algorithms import value_counts
from pandas.tseries.api import DatetimeIndex, PeriodIndex
result = value_counts(self, sort=sort, ascending=ascending,
normalize=normalize, bins=bins, dropna=dropna)
if isinstance(self, PeriodIndex):
# preserve freq
result.index = self._simple_new(result.index.values,
freq=self.freq)
elif isinstance(self, DatetimeIndex):
result.index = self._simple_new(result.index.values,
tz=getattr(self, 'tz', None))
return result
def value_counts(self,
normalize=False,
sort=True,
ascending=False,
bins=None,
dropna=True):
"""
Returns object containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
"""
from pandas.core.algorithms import value_counts
return value_counts(self.values,
sort=sort,
ascending=ascending,
normalize=normalize,
bins=bins,
dropna=dropna)
def value_counts(self,
normalize=False,
sort=True,
ascending=False,
bins=None,
dropna=True):
"""
Return a Series containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by frequencies.
ascending : boolean, default False
Sort in ascending order.
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for ``pd.cut``, only works with numeric data.
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
Series
See Also
--------
Series.count: Number of non-NA elements in a Series.
DataFrame.count: Number of non-NA elements in a DataFrame.
Examples
--------
>>> index = pd.Index([3, 1, 2, 3, 4, np.nan])
>>> index.value_counts()
3.0 2
4.0 1
2.0 1
1.0 1
dtype: int64
With `normalize` set to `True`, returns the relative frequency by
dividing all values by the sum of values.
>>> s = pd.Series([3, 1, 2, 3, 4, np.nan])
>>> s.value_counts(normalize=True)
3.0 0.4
4.0 0.2
2.0 0.2
1.0 0.2
dtype: float64
**bins**
Bins can be useful for going from a continuous variable to a
categorical variable; instead of counting unique
apparitions of values, divide the index in the specified
number of half-open bins.
>>> s.value_counts(bins=3)
(2.0, 3.0] 2
(0.996, 2.0] 2
(3.0, 4.0] 1
dtype: int64
**dropna**
With `dropna` set to `False` we can also see NaN index values.
>>> s.value_counts(dropna=False)
3.0 2
NaN 1
4.0 1
2.0 1
1.0 1
dtype: int64
"""
from pandas.core.algorithms import value_counts
result = value_counts(self,
sort=sort,
ascending=ascending,
normalize=normalize,
bins=bins,
dropna=dropna)
return result
def value_counts(self, dropna: bool = True):
from pandas.core.algorithms import value_counts
return value_counts(self.to_numpy(), dropna=dropna)
def value_counts(self, normalize=False, sort=True, ascending=False,
bins=None, dropna=True):
"""
Return a Series containing counts of unique values.
The resulting object will be in descending order so that the
first element is the most frequently-occurring element.
Excludes NA values by default.
Parameters
----------
normalize : boolean, default False
If True then the object returned will contain the relative
frequencies of the unique values.
sort : boolean, default True
Sort by values.
ascending : boolean, default False
Sort in ascending order.
bins : integer, optional
Rather than count values, group them into half-open bins,
a convenience for ``pd.cut``, only works with numeric data.
dropna : boolean, default True
Don't include counts of NaN.
Returns
-------
counts : Series
See Also
--------
Series.count: number of non-NA elements in a Series
DataFrame.count: number of non-NA elements in a DataFrame
Examples
--------
>>> index = pd.Index([3, 1, 2, 3, 4, np.nan])
>>> index.value_counts()
3.0 2
4.0 1
2.0 1
1.0 1
dtype: int64
With `normalize` set to `True`, returns the relative frequency by
dividing all values by the sum of values.
>>> s = pd.Series([3, 1, 2, 3, 4, np.nan])
>>> s.value_counts(normalize=True)
3.0 0.4
4.0 0.2
2.0 0.2
1.0 0.2
dtype: float64
**bins**
Bins can be useful for going from a continuous variable to a
categorical variable; instead of counting unique
apparitions of values, divide the index in the specified
number of half-open bins.
>>> s.value_counts(bins=3)
(2.0, 3.0] 2
(0.996, 2.0] 2
(3.0, 4.0] 1
dtype: int64
**dropna**
With `dropna` set to `False` we can also see NaN index values.
>>> s.value_counts(dropna=False)
3.0 2
NaN 1
4.0 1
2.0 1
1.0 1
dtype: int64
"""
from pandas.core.algorithms import value_counts
result = value_counts(self, sort=sort, ascending=ascending,
normalize=normalize, bins=bins, dropna=dropna)
return result