def max(self):
"""
Return the maximum value of the Index.
Returns
-------
scalar
Maximum value.
See Also
--------
Index.min : Return the minimum value in an Index.
Series.max : Return the maximum value in a Series.
DataFrame.max : Return the maximum values in a DataFrame.
Examples
--------
>>> idx = pd.Index([3, 2, 1])
>>> idx.max()
3
>>> idx = pd.Index(['c', 'b', 'a'])
>>> idx.max()
'c'
For a MultiIndex, the maximum is determined lexicographically.
>>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)])
>>> idx.max()
('b', 2)
"""
return nanops.nanmax(self.values)
def max(self):
"""
Return the maximum value of the Index.
Returns
-------
scalar
Maximum value.
See Also
--------
Index.min : Return the minimum value in an Index.
Series.max : Return the maximum value in a Series.
DataFrame.max : Return the maximum values in a DataFrame.
Examples
--------
>>> idx = pd.Index([3, 2, 1])
>>> idx.max()
3
>>> idx = pd.Index(['c', 'b', 'a'])
>>> idx.max()
'c'
For a MultiIndex, the maximum is determined lexicographically.
>>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)])
>>> idx.max()
('b', 2)
"""
return nanops.nanmax(self.values)
def max(self, *, axis=None, skipna: bool = True, **kwargs) -> Scalar:
nv.validate_max((), kwargs)
result = nanops.nanmax(values=self._ndarray,
axis=axis,
mask=self.isna(),
skipna=skipna)
return self._wrap_reduction_result(axis, result)
def max(self, axis=None, skipna: bool = True, *args, **kwargs):
"""
Return the maximum value of the Index.
Parameters
----------
axis : int, optional
For compatibility with NumPy. Only 0 or None are allowed.
skipna : bool, default True
Exclude NA/null values when showing the result.
*args, **kwargs
Additional arguments and keywords for compatibility with NumPy.
Returns
-------
scalar
Maximum value.
See Also
--------
Index.min : Return the minimum value in an Index.
Series.max : Return the maximum value in a Series.
DataFrame.max : Return the maximum values in a DataFrame.
Examples
--------
>>> idx = pd.Index([3, 2, 1])
>>> idx.max()
3
>>> idx = pd.Index(['c', 'b', 'a'])
>>> idx.max()
'c'
For a MultiIndex, the maximum is determined lexicographically.
>>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)])
>>> idx.max()
('b', 2)
"""
nv.validate_minmax_axis(axis)
nv.validate_max(args, kwargs)
return nanops.nanmax(self._values, skipna=skipna)
def max(self, axis=None, skipna=True, *args, **kwargs):
"""
Return the maximum value of the Index.
Parameters
----------
axis : int, optional
For compatibility with NumPy. Only 0 or None are allowed.
skipna : bool, default True
Returns
-------
scalar
Maximum value.
See Also
--------
Index.min : Return the minimum value in an Index.
Series.max : Return the maximum value in a Series.
DataFrame.max : Return the maximum values in a DataFrame.
Examples
--------
>>> idx = pd.Index([3, 2, 1])
>>> idx.max()
3
>>> idx = pd.Index(['c', 'b', 'a'])
>>> idx.max()
'c'
For a MultiIndex, the maximum is determined lexicographically.
>>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)])
>>> idx.max()
('b', 2)
"""
nv.validate_minmax_axis(axis)
nv.validate_max(args, kwargs)
return nanops.nanmax(self._values, skipna=skipna)
def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
include_lowest=False):
"""
Return indices of half-open bins to which each value of `x` belongs.
Parameters
----------
x : array-like
Input array to be binned. It has to be 1-dimensional.
bins : int or sequence of scalars
If `bins` is an int, it defines the number of equal-width bins in the
range of `x`. However, in this case, the range of `x` is extended
by .1% on each side to include the min or max values of `x`. If
`bins` is a sequence it defines the bin edges allowing for
non-uniform bin width. No extension of the range of `x` is done in
this case.
right : bool, optional
Indicates whether the bins include the rightmost edge or not. If
right == True (the default), then the bins [1,2,3,4] indicate
(1,2], (2,3], (3,4].
labels : array or boolean, default None
Labels to use for bin edges, or False to return integer bin labels
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
Returns
-------
out : Categorical or array of integers if labels is False
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
The `cut` function can be useful for going from a continuous variable to
a categorical variable. For example, `cut` could convert ages to groups
of age ranges.
Any NA values will be NA in the result. Out of bounds values will be NA in
the resulting Categorical object
Examples
--------
>>> cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
(array([(0.191, 3.367], (0.191, 3.367], (0.191, 3.367], (3.367, 6.533],
(6.533, 9.7], (0.191, 3.367]], dtype=object),
array([ 0.1905 , 3.36666667, 6.53333333, 9.7 ]))
>>> cut(np.ones(5), 4, labels=False)
array([2, 2, 2, 2, 2])
"""
#NOTE: this binning code is changed a bit from histogram for var(x) == 0
if not np.iterable(bins):
if np.isscalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
# handle empty arrays. Can't determine range, so use 0-1.
rng = (0, 1)
else:
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if mn == mx: # adjust end points before binning
mn -= .001 * mn
mx += .001 * mx
bins = np.linspace(mn, mx, bins+1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins+1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
else:
bins = np.asarray(bins)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
return _bins_to_cuts(x, bins, right=right, labels=labels,
retbins=retbins, precision=precision,
include_lowest=include_lowest)
def cut(
x,
bins,
right: bool = True,
labels=None,
retbins: bool = False,
precision: int = 3,
include_lowest: bool = False,
duplicates: str = "raise",
):
"""
Bin values into discrete intervals.
Use `cut` when you need to segment and sort data values into bins. This
function is also useful for going from a continuous variable to a
categorical variable. For example, `cut` could convert ages to groups of
age ranges. Supports binning into an equal number of bins, or a
pre-specified array of bins.
Parameters
----------
x : array-like
The input array to be binned. Must be 1-dimensional.
bins : int, sequence of scalars, or IntervalIndex
The criteria to bin by.
* int : Defines the number of equal-width bins in the range of `x`. The
range of `x` is extended by .1% on each side to include the minimum
and maximum values of `x`.
* sequence of scalars : Defines the bin edges allowing for non-uniform
width. No extension of the range of `x` is done.
* IntervalIndex : Defines the exact bins to be used. Note that
IntervalIndex for `bins` must be non-overlapping.
right : bool, default True
Indicates whether `bins` includes the rightmost edge or not. If
``right == True`` (the default), then the `bins` ``[1, 2, 3, 4]``
indicate (1,2], (2,3], (3,4]. This argument is ignored when
`bins` is an IntervalIndex.
labels : array or False, default None
Specifies the labels for the returned bins. Must be the same length as
the resulting bins. If False, returns only integer indicators of the
bins. This affects the type of the output container (see below).
This argument is ignored when `bins` is an IntervalIndex. If True,
raises an error.
retbins : bool, default False
Whether to return the bins or not. Useful when bins is provided
as a scalar.
precision : int, default 3
The precision at which to store and display the bins labels.
include_lowest : bool, default False
Whether the first interval should be left-inclusive or not.
duplicates : {default 'raise', 'drop'}, optional
If bin edges are not unique, raise ValueError or drop non-uniques.
.. versionadded:: 0.23.0
Returns
-------
out : Categorical, Series, or ndarray
An array-like object representing the respective bin for each value
of `x`. The type depends on the value of `labels`.
* True (default) : returns a Series for Series `x` or a
Categorical for all other inputs. The values stored within
are Interval dtype.
* sequence of scalars : returns a Series for Series `x` or a
Categorical for all other inputs. The values stored within
are whatever the type in the sequence is.
* False : returns an ndarray of integers.
bins : numpy.ndarray or IntervalIndex.
The computed or specified bins. Only returned when `retbins=True`.
For scalar or sequence `bins`, this is an ndarray with the computed
bins. If set `duplicates=drop`, `bins` will drop non-unique bin. For
an IntervalIndex `bins`, this is equal to `bins`.
See Also
--------
qcut : Discretize variable into equal-sized buckets based on rank
or based on sample quantiles.
Categorical : Array type for storing data that come from a
fixed set of values.
Series : One-dimensional array with axis labels (including time series).
IntervalIndex : Immutable Index implementing an ordered, sliceable set.
Notes
-----
Any NA values will be NA in the result. Out of bounds values will be NA in
the resulting Series or Categorical object.
Examples
--------
Discretize into three equal-sized bins.
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]), 3)
... # doctest: +ELLIPSIS
[(0.994, 3.0], (5.0, 7.0], (3.0, 5.0], (3.0, 5.0], (5.0, 7.0], ...
Categories (3, interval[float64]): [(0.994, 3.0] < (3.0, 5.0] ...
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]), 3, retbins=True)
... # doctest: +ELLIPSIS
([(0.994, 3.0], (5.0, 7.0], (3.0, 5.0], (3.0, 5.0], (5.0, 7.0], ...
Categories (3, interval[float64]): [(0.994, 3.0] < (3.0, 5.0] ...
array([0.994, 3. , 5. , 7. ]))
Discovers the same bins, but assign them specific labels. Notice that
the returned Categorical's categories are `labels` and is ordered.
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]),
... 3, labels=["bad", "medium", "good"])
[bad, good, medium, medium, good, bad]
Categories (3, object): [bad < medium < good]
``labels=False`` implies you just want the bins back.
>>> pd.cut([0, 1, 1, 2], bins=4, labels=False)
array([0, 1, 1, 3])
Passing a Series as an input returns a Series with categorical dtype:
>>> s = pd.Series(np.array([2, 4, 6, 8, 10]),
... index=['a', 'b', 'c', 'd', 'e'])
>>> pd.cut(s, 3)
... # doctest: +ELLIPSIS
a (1.992, 4.667]
b (1.992, 4.667]
c (4.667, 7.333]
d (7.333, 10.0]
e (7.333, 10.0]
dtype: category
Categories (3, interval[float64]): [(1.992, 4.667] < (4.667, ...
Passing a Series as an input returns a Series with mapping value.
It is used to map numerically to intervals based on bins.
>>> s = pd.Series(np.array([2, 4, 6, 8, 10]),
... index=['a', 'b', 'c', 'd', 'e'])
>>> pd.cut(s, [0, 2, 4, 6, 8, 10], labels=False, retbins=True, right=False)
... # doctest: +ELLIPSIS
(a 0.0
b 1.0
c 2.0
d 3.0
e 4.0
dtype: float64, array([0, 2, 4, 6, 8]))
Use `drop` optional when bins is not unique
>>> pd.cut(s, [0, 2, 4, 6, 10, 10], labels=False, retbins=True,
... right=False, duplicates='drop')
... # doctest: +ELLIPSIS
(a 0.0
b 1.0
c 2.0
d 3.0
e 3.0
dtype: float64, array([0, 2, 4, 6, 8]))
Passing an IntervalIndex for `bins` results in those categories exactly.
Notice that values not covered by the IntervalIndex are set to NaN. 0
is to the left of the first bin (which is closed on the right), and 1.5
falls between two bins.
>>> bins = pd.IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)])
>>> pd.cut([0, 0.5, 1.5, 2.5, 4.5], bins)
[NaN, (0, 1], NaN, (2, 3], (4, 5]]
Categories (3, interval[int64]): [(0, 1] < (2, 3] < (4, 5]]
"""
# NOTE: this binning code is changed a bit from histogram for var(x) == 0
# for handling the cut for datetime and timedelta objects
original = x
x = _preprocess_for_cut(x)
x, dtype = _coerce_to_type(x)
if not np.iterable(bins):
if is_scalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
raise ValueError("Cannot cut empty array")
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if np.isinf(mn) or np.isinf(mx):
# GH 24314
raise ValueError(
"cannot specify integer `bins` when input data contains infinity"
)
elif mn == mx: # adjust end points before binning
mn -= 0.001 * abs(mn) if mn != 0 else 0.001
mx += 0.001 * abs(mx) if mx != 0 else 0.001
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
elif isinstance(bins, IntervalIndex):
if bins.is_overlapping:
raise ValueError("Overlapping IntervalIndex is not accepted.")
else:
if is_datetime64tz_dtype(bins):
bins = np.asarray(bins, dtype=_NS_DTYPE)
else:
bins = np.asarray(bins)
bins = _convert_bin_to_numeric_type(bins, dtype)
# GH 26045: cast to float64 to avoid an overflow
if (np.diff(bins.astype("float64")) < 0).any():
raise ValueError("bins must increase monotonically.")
fac, bins = _bins_to_cuts(
x,
bins,
right=right,
labels=labels,
precision=precision,
include_lowest=include_lowest,
dtype=dtype,
duplicates=duplicates,
)
return _postprocess_for_cut(fac, bins, retbins, dtype, original)
def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
include_lowest=False):
"""
Return indices of half-open bins to which each value of `x` belongs.
Parameters
----------
x : array-like
Input array to be binned. It has to be 1-dimensional.
bins : int, sequence of scalars, or IntervalIndex
If `bins` is an int, it defines the number of equal-width bins in the
range of `x`. However, in this case, the range of `x` is extended
by .1% on each side to include the min or max values of `x`. If
`bins` is a sequence it defines the bin edges allowing for
non-uniform bin width. No extension of the range of `x` is done in
this case.
right : bool, optional
Indicates whether the bins include the rightmost edge or not. If
right == True (the default), then the bins [1,2,3,4] indicate
(1,2], (2,3], (3,4].
labels : array or boolean, default None
Used as labels for the resulting bins. Must be of the same length as
the resulting bins. If False, return only integer indicators of the
bins.
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
precision : int, optional
The precision at which to store and display the bins labels
include_lowest : bool, optional
Whether the first interval should be left-inclusive or not.
Returns
-------
out : Categorical or Series or array of integers if labels is False
The return type (Categorical or Series) depends on the input: a Series
of type category if input is a Series else Categorical. Bins are
represented as categories when categorical data is returned.
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
The `cut` function can be useful for going from a continuous variable to
a categorical variable. For example, `cut` could convert ages to groups
of age ranges.
Any NA values will be NA in the result. Out of bounds values will be NA in
the resulting Categorical object
Examples
--------
>>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
... # doctest: +ELLIPSIS
([(0.19, 3.367], (0.19, 3.367], (0.19, 3.367], (3.367, 6.533], ...
Categories (3, interval[float64]): [(0.19, 3.367] < (3.367, 6.533] ...
>>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]),
... 3, labels=["good", "medium", "bad"])
... # doctest: +SKIP
[good, good, good, medium, bad, good]
Categories (3, object): [good < medium < bad]
>>> pd.cut(np.ones(5), 4, labels=False)
array([1, 1, 1, 1, 1])
"""
# NOTE: this binning code is changed a bit from histogram for var(x) == 0
# for handling the cut for datetime and timedelta objects
x_is_series, series_index, name, x = _preprocess_for_cut(x)
x, dtype = _coerce_to_type(x)
if not np.iterable(bins):
if is_scalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
raise ValueError('Cannot cut empty array')
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if mn == mx: # adjust end points before binning
mn -= .001 * abs(mn) if mn != 0 else .001
mx += .001 * abs(mx) if mx != 0 else .001
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
elif isinstance(bins, IntervalIndex):
pass
else:
bins = np.asarray(bins)
bins = _convert_bin_to_numeric_type(bins, dtype)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
fac, bins = _bins_to_cuts(x, bins, right=right, labels=labels,
precision=precision,
include_lowest=include_lowest,
dtype=dtype)
return _postprocess_for_cut(fac, bins, retbins, x_is_series,
series_index, name)
def cut(x, bins, right=True, labels=None, retbins=False, precision=3):
"""
Return indices of half-open bins to which each value of `x` belongs.
Parameters
----------
x : array-like
Input array to be binned. It has to be 1-dimensional.
bins : int or sequence of scalars
If `bins` is an int, it defines the number of equal-width bins in the
range of `x`. However, in this case, the range of `x` is extended
by .1% on each side to include the min or max values of `x`. If
`bins` is a sequence it defines the bin edges allowing for
non-uniform bin width. No extension of the range of `x` is done in
this case.
right : bool, optional
Indicates whether the bins include the rightmost edge or not. If
right == True (the default), then the bins [1,2,3,4] indicate
(1,2], (2,3], (3,4].
labels : array or boolean, default None
Labels to use for bin edges, or False to return integer bin labels
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
Returns
-------
out : ndarray of labels
Same shape as `x`. Array of strings by default, integers if
labels=False
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
The `cut` function can be useful for going from a continuous variable to
a categorical variable. For example, `cut` could convert ages to groups
of age ranges.
Any NA values will be NA in the result
Examples
--------
>>> cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
(array([(0.191, 3.367], (0.191, 3.367], (0.191, 3.367], (3.367, 6.533],
(6.533, 9.7], (0.191, 3.367]], dtype=object),
array([ 0.1905 , 3.36666667, 6.53333333, 9.7 ]))
>>> cut(np.ones(5), 4, labels=False)
array([2, 2, 2, 2, 2])
"""
#NOTE: this binning code is changed a bit from histogram for var(x) == 0
if not np.iterable(bins):
if np.isscalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
# handle empty arrays. Can't determine range, so use 0-1.
rng = (0, 1)
else:
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if mn == mx: # adjust end points before binning
mn -= .001 * mn
mx += .001 * mx
bins = np.linspace(mn, mx, bins+1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins+1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
else:
bins = np.asarray(bins)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
side = 'left' if right else 'right'
ids = bins.searchsorted(x, side=side)
mask = com.isnull(x)
has_nas = mask.any()
if labels is not False:
if labels is None:
labels = bins
else:
if len(labels) != len(bins):
raise ValueError('labels must be same length as bins')
fmt = lambda v: _format_label(v, precision=precision)
if right:
strings = ['(%s, %s]' % (fmt(x), fmt(y))
for x, y in zip(labels, labels[1:])]
else:
strings = ['[%s, %s)' % (fmt(x), fmt(y))
for x, y in zip(labels, labels[1:])]
strings = np.asarray(strings, dtype=object)
if has_nas:
np.putmask(ids, mask, 0)
labels = com.take_1d(strings, ids - 1)
else:
labels = ids
if has_nas:
labels = labels.astype(np.float64)
np.putmask(labels, mask, np.nan)
if not retbins:
return labels
return labels, bins
def max(self, axis=None, out=None, keepdims=False, skipna=True):
nv.validate_max((), dict(out=out, keepdims=keepdims))
return nanops.nanmax(self._ndarray, axis=axis, skipna=skipna)
def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
include_lowest=False, duplicates='raise'):
"""
Bin values into discrete intervals.
Use `cut` when you need to segment and sort data values into bins. This
function is also useful for going from a continuous variable to a
categorical variable. For example, `cut` could convert ages to groups of
age ranges. Supports binning into an equal number of bins, or a
pre-specified array of bins.
Parameters
----------
x : array-like
The input array to be binned. Must be 1-dimensional.
bins : int, sequence of scalars, or IntervalIndex
The criteria to bin by.
* int : Defines the number of equal-width bins in the range of `x`. The
range of `x` is extended by .1% on each side to include the minimum
and maximum values of `x`.
* sequence of scalars : Defines the bin edges allowing for non-uniform
width. No extension of the range of `x` is done.
* IntervalIndex : Defines the exact bins to be used. Note that
IntervalIndex for `bins` must be non-overlapping.
right : bool, default True
Indicates whether `bins` includes the rightmost edge or not. If
``right == True`` (the default), then the `bins` ``[1, 2, 3, 4]``
indicate (1,2], (2,3], (3,4]. This argument is ignored when
`bins` is an IntervalIndex.
labels : array or bool, optional
Specifies the labels for the returned bins. Must be the same length as
the resulting bins. If False, returns only integer indicators of the
bins. This affects the type of the output container (see below).
This argument is ignored when `bins` is an IntervalIndex.
retbins : bool, default False
Whether to return the bins or not. Useful when bins is provided
as a scalar.
precision : int, default 3
The precision at which to store and display the bins labels.
include_lowest : bool, default False
Whether the first interval should be left-inclusive or not.
duplicates : {default 'raise', 'drop'}, optional
If bin edges are not unique, raise ValueError or drop non-uniques.
.. versionadded:: 0.23.0
Returns
-------
out : Categorical, Series, or ndarray
An array-like object representing the respective bin for each value
of `x`. The type depends on the value of `labels`.
* True (default) : returns a Series for Series `x` or a
Categorical for all other inputs. The values stored within
are Interval dtype.
* sequence of scalars : returns a Series for Series `x` or a
Categorical for all other inputs. The values stored within
are whatever the type in the sequence is.
* False : returns an ndarray of integers.
bins : numpy.ndarray or IntervalIndex.
The computed or specified bins. Only returned when `retbins=True`.
For scalar or sequence `bins`, this is an ndarray with the computed
bins. If set `duplicates=drop`, `bins` will drop non-unique bin. For
an IntervalIndex `bins`, this is equal to `bins`.
See Also
--------
qcut : Discretize variable into equal-sized buckets based on rank
or based on sample quantiles.
Categorical : Array type for storing data that come from a
fixed set of values.
Series : One-dimensional array with axis labels (including time series).
IntervalIndex : Immutable Index implementing an ordered, sliceable set.
Notes
-----
Any NA values will be NA in the result. Out of bounds values will be NA in
the resulting Series or Categorical object.
Examples
--------
Discretize into three equal-sized bins.
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]), 3)
... # doctest: +ELLIPSIS
[(0.994, 3.0], (5.0, 7.0], (3.0, 5.0], (3.0, 5.0], (5.0, 7.0], ...
Categories (3, interval[float64]): [(0.994, 3.0] < (3.0, 5.0] ...
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]), 3, retbins=True)
... # doctest: +ELLIPSIS
([(0.994, 3.0], (5.0, 7.0], (3.0, 5.0], (3.0, 5.0], (5.0, 7.0], ...
Categories (3, interval[float64]): [(0.994, 3.0] < (3.0, 5.0] ...
array([0.994, 3. , 5. , 7. ]))
Discovers the same bins, but assign them specific labels. Notice that
the returned Categorical's categories are `labels` and is ordered.
>>> pd.cut(np.array([1, 7, 5, 4, 6, 3]),
... 3, labels=["bad", "medium", "good"])
[bad, good, medium, medium, good, bad]
Categories (3, object): [bad < medium < good]
``labels=False`` implies you just want the bins back.
>>> pd.cut([0, 1, 1, 2], bins=4, labels=False)
array([0, 1, 1, 3])
Passing a Series as an input returns a Series with categorical dtype:
>>> s = pd.Series(np.array([2, 4, 6, 8, 10]),
... index=['a', 'b', 'c', 'd', 'e'])
>>> pd.cut(s, 3)
... # doctest: +ELLIPSIS
a (1.992, 4.667]
b (1.992, 4.667]
c (4.667, 7.333]
d (7.333, 10.0]
e (7.333, 10.0]
dtype: category
Categories (3, interval[float64]): [(1.992, 4.667] < (4.667, ...
Passing a Series as an input returns a Series with mapping value.
It is used to map numerically to intervals based on bins.
>>> s = pd.Series(np.array([2, 4, 6, 8, 10]),
... index=['a', 'b', 'c', 'd', 'e'])
>>> pd.cut(s, [0, 2, 4, 6, 8, 10], labels=False, retbins=True, right=False)
... # doctest: +ELLIPSIS
(a 0.0
b 1.0
c 2.0
d 3.0
e 4.0
dtype: float64, array([0, 2, 4, 6, 8]))
Use `drop` optional when bins is not unique
>>> pd.cut(s, [0, 2, 4, 6, 10, 10], labels=False, retbins=True,
... right=False, duplicates='drop')
... # doctest: +ELLIPSIS
(a 0.0
b 1.0
c 2.0
d 3.0
e 3.0
dtype: float64, array([0, 2, 4, 6, 8]))
Passing an IntervalIndex for `bins` results in those categories exactly.
Notice that values not covered by the IntervalIndex are set to NaN. 0
is to the left of the first bin (which is closed on the right), and 1.5
falls between two bins.
>>> bins = pd.IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)])
>>> pd.cut([0, 0.5, 1.5, 2.5, 4.5], bins)
[NaN, (0, 1], NaN, (2, 3], (4, 5]]
Categories (3, interval[int64]): [(0, 1] < (2, 3] < (4, 5]]
"""
# NOTE: this binning code is changed a bit from histogram for var(x) == 0
# for handling the cut for datetime and timedelta objects
x_is_series, series_index, name, x = _preprocess_for_cut(x)
x, dtype = _coerce_to_type(x)
if not np.iterable(bins):
if is_scalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
raise ValueError('Cannot cut empty array')
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if np.isinf(mn) or np.isinf(mx):
# GH 24314
raise ValueError('cannot specify integer `bins` when input data '
'contains infinity')
elif mn == mx: # adjust end points before binning
mn -= .001 * abs(mn) if mn != 0 else .001
mx += .001 * abs(mx) if mx != 0 else .001
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
elif isinstance(bins, IntervalIndex):
if bins.is_overlapping:
raise ValueError('Overlapping IntervalIndex is not accepted.')
else:
if is_datetime64tz_dtype(bins):
bins = np.asarray(bins, dtype=_NS_DTYPE)
else:
bins = np.asarray(bins)
bins = _convert_bin_to_numeric_type(bins, dtype)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
fac, bins = _bins_to_cuts(x, bins, right=right, labels=labels,
precision=precision,
include_lowest=include_lowest,
dtype=dtype,
duplicates=duplicates)
return _postprocess_for_cut(fac, bins, retbins, x_is_series,
series_index, name, dtype)
def is_valid(self, data_row):
return nanmax(data_row) >= self._highest_pileup_threshold
def is_valid(self, data_row):
return nanmax(data_row) >= self._highest_pileup_threshold
def cut(x, bins, right=True, labels=None, retbins=False, precision=3):
"""
Return indices of half-open bins to which each value of `x` belongs.
Parameters
----------
x : array-like
Input array to be binned. It has to be 1-dimensional.
bins : int or sequence of scalars
If `bins` is an int, it defines the number of equal-width bins in the
range of `x`. However, in this case, the range of `x` is extended
by .1% on each side to include the min or max values of `x`. If
`bins` is a sequence it defines the bin edges allowing for
non-uniform bin width. No extension of the range of `x` is done in
this case.
right : bool, optional
Indicates whether the bins include the rightmost edge or not. If
right == True (the default), then the bins [1,2,3,4] indicate
(1,2], (2,3], (3,4].
labels : array or boolean, default None
Labels to use for bin edges, or False to return integer bin labels
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
Returns
-------
out : ndarray of labels
Same shape as `x`. Array of strings by default, integers if
labels=False
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
The `cut` function can be useful for going from a continuous variable to
a categorical variable. For example, `cut` could convert ages to groups
of age ranges.
Any NA values will be NA in the result
Examples
--------
>>> cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
(array([(0.191, 3.367], (0.191, 3.367], (0.191, 3.367], (3.367, 6.533],
(6.533, 9.7], (0.191, 3.367]], dtype=object),
array([ 0.1905 , 3.36666667, 6.53333333, 9.7 ]))
>>> cut(np.ones(5), 4, labels=False)
array([2, 2, 2, 2, 2])
"""
#NOTE: this binning code is changed a bit from histogram for var(x) == 0
if not np.iterable(bins):
if np.isscalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
# handle empty arrays. Can't determine range, so use 0-1.
rng = (0, 1)
else:
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if mn == mx: # adjust end points before binning
mn -= .001 * mn
mx += .001 * mx
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
else:
bins = np.asarray(bins)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
return _bins_to_cuts(x,
bins,
right=right,
labels=labels,
retbins=retbins,
precision=precision)
def max(self):
""" The maximum value of the object """
return nanops.nanmax(self.values)
def max(self, axis=None, out=None, keepdims=False, skipna=True):
nv.validate_max((), dict(out=out, keepdims=keepdims))
return nanops.nanmax(self._ndarray, axis=axis, skipna=skipna)
def cut(x,
bins,
right=True,
labels=None,
retbins=False,
precision=3,
include_lowest=False):
"""
Return indices of half-open bins to which each value of `x` belongs.
Parameters
----------
x : array-like
Input array to be binned. It has to be 1-dimensional.
bins : int or sequence of scalars
If `bins` is an int, it defines the number of equal-width bins in the
range of `x`. However, in this case, the range of `x` is extended
by .1% on each side to include the min or max values of `x`. If
`bins` is a sequence it defines the bin edges allowing for
non-uniform bin width. No extension of the range of `x` is done in
this case.
right : bool, optional
Indicates whether the bins include the rightmost edge or not. If
right == True (the default), then the bins [1,2,3,4] indicate
(1,2], (2,3], (3,4].
labels : array or boolean, default None
Used as labels for the resulting bins. Must be of the same length as
the resulting bins. If False, return only integer indicators of the
bins.
retbins : bool, optional
Whether to return the bins or not. Can be useful if bins is given
as a scalar.
precision : int
The precision at which to store and display the bins labels
include_lowest : bool
Whether the first interval should be left-inclusive or not.
Returns
-------
out : Categorical or Series or array of integers if labels is False
The return type (Categorical or Series) depends on the input: a Series
of type category if input is a Series else Categorical. Bins are
represented as categories when categorical data is returned.
bins : ndarray of floats
Returned only if `retbins` is True.
Notes
-----
The `cut` function can be useful for going from a continuous variable to
a categorical variable. For example, `cut` could convert ages to groups
of age ranges.
Any NA values will be NA in the result. Out of bounds values will be NA in
the resulting Categorical object
Examples
--------
>>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
([(0.191, 3.367], (0.191, 3.367], (0.191, 3.367], (3.367, 6.533],
(6.533, 9.7], (0.191, 3.367]]
Categories (3, object): [(0.191, 3.367] < (3.367, 6.533] < (6.533, 9.7]],
array([ 0.1905 , 3.36666667, 6.53333333, 9.7 ]))
>>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3,
labels=["good","medium","bad"])
[good, good, good, medium, bad, good]
Categories (3, object): [good < medium < bad]
>>> pd.cut(np.ones(5), 4, labels=False)
array([1, 1, 1, 1, 1], dtype=int64)
"""
# NOTE: this binning code is changed a bit from histogram for var(x) == 0
if not np.iterable(bins):
if is_scalar(bins) and bins < 1:
raise ValueError("`bins` should be a positive integer.")
try: # for array-like
sz = x.size
except AttributeError:
x = np.asarray(x)
sz = x.size
if sz == 0:
raise ValueError('Cannot cut empty array')
# handle empty arrays. Can't determine range, so use 0-1.
# rng = (0, 1)
else:
rng = (nanops.nanmin(x), nanops.nanmax(x))
mn, mx = [mi + 0.0 for mi in rng]
if mn == mx: # adjust end points before binning
mn -= .001 * abs(mn)
mx += .001 * abs(mx)
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
else: # adjust end points after binning
bins = np.linspace(mn, mx, bins + 1, endpoint=True)
adj = (mx - mn) * 0.001 # 0.1% of the range
if right:
bins[0] -= adj
else:
bins[-1] += adj
else:
bins = np.asarray(bins)
if (np.diff(bins) < 0).any():
raise ValueError('bins must increase monotonically.')
return _bins_to_cuts(x,
bins,
right=right,
labels=labels,
retbins=retbins,
precision=precision,
include_lowest=include_lowest)
def max(self):
# type: () -> Scalar
""" The maximum value of the object """
return nanops.nanmax(self.values)
