def _isfinite(values):
if is_datetime_or_timedelta_dtype(values):
return isnull(values)
if (is_complex_dtype(values) or is_float_dtype(values) or
is_integer_dtype(values) or is_bool_dtype(values)):
return ~np.isfinite(values)
return ~np.isfinite(values.astype('float64'))
def _isfinite(values):
if is_datetime_or_timedelta_dtype(values):
return isnull(values)
if (is_complex_dtype(values) or is_float_dtype(values)
or is_integer_dtype(values) or is_bool_dtype(values)):
return ~np.isfinite(values)
return ~np.isfinite(values.astype('float64'))
def _value_counts_arraylike(values, dropna=True):
is_datetimetz_type = is_datetimetz(values)
is_period = (isinstance(values, ABCPeriodIndex) or
is_period_arraylike(values))
orig = values
from pandas.core.series import Series
values = Series(values).values
dtype = values.dtype
if is_datetime_or_timedelta_dtype(dtype) or is_period:
from pandas.tseries.index import DatetimeIndex
from pandas.tseries.period import PeriodIndex
if is_period:
values = PeriodIndex(values)
freq = values.freq
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
# dtype handling
if is_datetimetz_type:
if isinstance(orig, ABCDatetimeIndex):
tz = orig.tz
else:
tz = orig.dt.tz
keys = DatetimeIndex._simple_new(keys, tz=tz)
if is_period:
keys = PeriodIndex._simple_new(keys, freq=freq)
elif is_integer_dtype(dtype):
values = _ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif is_float_dtype(dtype):
values = _ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = _ensure_object(values)
mask = isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna and mask.any():
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
return keys, counts
def _value_counts_arraylike(values, dropna=True):
is_datetimetz_type = is_datetimetz(values)
is_period = (isinstance(values, ABCPeriodIndex)
or is_period_arraylike(values))
orig = values
from pandas.core.series import Series
values = Series(values).values
dtype = values.dtype
if is_datetime_or_timedelta_dtype(dtype) or is_period:
from pandas.tseries.index import DatetimeIndex
from pandas.tseries.period import PeriodIndex
if is_period:
values = PeriodIndex(values)
freq = values.freq
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values, dropna)
if dropna:
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
# dtype handling
if is_datetimetz_type:
if isinstance(orig, ABCDatetimeIndex):
tz = orig.tz
else:
tz = orig.dt.tz
keys = DatetimeIndex._simple_new(keys, tz=tz)
if is_period:
keys = PeriodIndex._simple_new(keys, freq=freq)
elif is_integer_dtype(dtype):
values = _ensure_int64(values)
keys, counts = htable.value_count_int64(values, dropna)
elif is_float_dtype(dtype):
values = _ensure_float64(values)
keys, counts = htable.value_count_float64(values, dropna)
else:
values = _ensure_object(values)
mask = isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna and mask.any():
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
return keys, counts
def _bn_ok_dtype(dt, name):
# Bottleneck chokes on datetime64
if (not is_object_dtype(dt) and not is_datetime_or_timedelta_dtype(dt)):
# bottleneck does not properly upcast during the sum
# so can overflow
if name == 'nansum':
if dt.itemsize < 8:
return False
return True
return False
def _bn_ok_dtype(dt, name):
# Bottleneck chokes on datetime64
if (not is_object_dtype(dt) and not is_datetime_or_timedelta_dtype(dt)):
# bottleneck does not properly upcast during the sum
# so can overflow
if name == 'nansum':
if dt.itemsize < 8:
return False
return True
return False
def _get_prev_label(label):
dtype = getattr(label, 'dtype', type(label))
if isinstance(label, (Timestamp, Timedelta)):
dtype = 'datetime64'
if is_datetime_or_timedelta_dtype(dtype):
return label - np.timedelta64(1, 'ns')
elif is_integer_dtype(dtype):
return label - 1
elif is_float_dtype(dtype):
return np.nextafter(label, -np.infty)
else:
raise TypeError('cannot determine next label for type %r' %
type(label))
def duplicated(values, keep='first'):
"""
Return boolean ndarray denoting duplicate values
.. versionadded:: 0.19.0
Parameters
----------
keep : {'first', 'last', False}, default 'first'
- ``first`` : Mark duplicates as ``True`` except for the first
occurrence.
- ``last`` : Mark duplicates as ``True`` except for the last
occurrence.
- False : Mark all duplicates as ``True``.
Returns
-------
duplicated : ndarray
"""
dtype = values.dtype
# no need to revert to original type
if is_datetime_or_timedelta_dtype(dtype) or is_datetimetz(dtype):
if isinstance(values, (ABCSeries, ABCIndex)):
values = values.values.view(np.int64)
else:
values = values.view(np.int64)
elif is_period_arraylike(values):
from pandas.tseries.period import PeriodIndex
values = PeriodIndex(values).asi8
elif is_categorical_dtype(dtype):
values = values.values.codes
elif isinstance(values, (ABCSeries, ABCIndex)):
values = values.values
if is_integer_dtype(dtype):
values = _ensure_int64(values)
duplicated = htable.duplicated_int64(values, keep=keep)
elif is_float_dtype(dtype):
values = _ensure_float64(values)
duplicated = htable.duplicated_float64(values, keep=keep)
else:
values = _ensure_object(values)
duplicated = htable.duplicated_object(values, keep=keep)
return duplicated
def duplicated(values, keep='first'):
"""
Return boolean ndarray denoting duplicate values
.. versionadded:: 0.19.0
Parameters
----------
keep : {'first', 'last', False}, default 'first'
- ``first`` : Mark duplicates as ``True`` except for the first
occurrence.
- ``last`` : Mark duplicates as ``True`` except for the last
occurrence.
- False : Mark all duplicates as ``True``.
Returns
-------
duplicated : ndarray
"""
dtype = values.dtype
# no need to revert to original type
if is_datetime_or_timedelta_dtype(dtype) or is_datetimetz(dtype):
if isinstance(values, (ABCSeries, ABCIndex)):
values = values.values.view(np.int64)
else:
values = values.view(np.int64)
elif is_period_arraylike(values):
from pandas.tseries.period import PeriodIndex
values = PeriodIndex(values).asi8
elif is_categorical_dtype(dtype):
values = values.values.codes
elif isinstance(values, (ABCSeries, ABCIndex)):
values = values.values
if is_integer_dtype(dtype):
values = _ensure_int64(values)
duplicated = htable.duplicated_int64(values, keep=keep)
elif is_float_dtype(dtype):
values = _ensure_float64(values)
duplicated = htable.duplicated_float64(values, keep=keep)
else:
values = _ensure_object(values)
duplicated = htable.duplicated_object(values, keep=keep)
return duplicated
def to_numeric(arg, errors='raise', downcast=None):
"""
Convert argument to a numeric type.
Parameters
----------
arg : list, tuple, 1-d array, or Series
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaN
- If 'ignore', then invalid parsing will return the input
downcast : {'integer', 'signed', 'unsigned', 'float'} , default None
If not None, and if the data has been successfully cast to a
numerical dtype (or if the data was numeric to begin with),
downcast that resulting data to the smallest numerical dtype
possible according to the following rules:
- 'integer' or 'signed': smallest signed int dtype (min.: np.int8)
- 'unsigned': smallest unsigned int dtype (min.: np.uint8)
- 'float': smallest float dtype (min.: np.float32)
As this behaviour is separate from the core conversion to
numeric values, any errors raised during the downcasting
will be surfaced regardless of the value of the 'errors' input.
In addition, downcasting will only occur if the size
of the resulting data's dtype is strictly larger than
the dtype it is to be cast to, so if none of the dtypes
checked satisfy that specification, no downcasting will be
performed on the data.
.. versionadded:: 0.19.0
Returns
-------
ret : numeric if parsing succeeded.
Return type depends on input. Series if Series, otherwise ndarray
Examples
--------
Take separate series and convert to numeric, coercing when told to
>>> import pandas as pd
>>> s = pd.Series(['1.0', '2', -3])
>>> pd.to_numeric(s)
0 1.0
1 2.0
2 -3.0
dtype: float64
>>> pd.to_numeric(s, downcast='float')
0 1.0
1 2.0
2 -3.0
dtype: float32
>>> pd.to_numeric(s, downcast='signed')
0 1
1 2
2 -3
dtype: int8
>>> s = pd.Series(['apple', '1.0', '2', -3])
>>> pd.to_numeric(s, errors='ignore')
0 apple
1 1.0
2 2
3 -3
dtype: object
>>> pd.to_numeric(s, errors='coerce')
0 NaN
1 1.0
2 2.0
3 -3.0
dtype: float64
"""
if downcast not in (None, 'integer', 'signed', 'unsigned', 'float'):
raise ValueError('invalid downcasting method provided')
is_series = False
is_index = False
is_scalar = False
if isinstance(arg, pd.Series):
is_series = True
values = arg.values
elif isinstance(arg, pd.Index):
is_index = True
values = arg.asi8
if values is None:
values = arg.values
elif isinstance(arg, (list, tuple)):
values = np.array(arg, dtype='O')
elif np.isscalar(arg):
if is_number(arg):
return arg
is_scalar = True
values = np.array([arg], dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a list, tuple, 1-d array, or Series')
else:
values = arg
try:
if is_numeric_dtype(values):
pass
elif is_datetime_or_timedelta_dtype(values):
values = values.astype(np.int64)
else:
values = _ensure_object(values)
coerce_numeric = False if errors in ('ignore', 'raise') else True
values = lib.maybe_convert_numeric(values,
set(),
coerce_numeric=coerce_numeric)
except Exception:
if errors == 'raise':
raise
# attempt downcast only if the data has been successfully converted
# to a numerical dtype and if a downcast method has been specified
if downcast is not None and is_numeric_dtype(values):
typecodes = None
if downcast in ('integer', 'signed'):
typecodes = np.typecodes['Integer']
elif downcast == 'unsigned' and np.min(values) > 0:
typecodes = np.typecodes['UnsignedInteger']
elif downcast == 'float':
typecodes = np.typecodes['Float']
# pandas support goes only to np.float32,
# as float dtypes smaller than that are
# extremely rare and not well supported
float_32_char = np.dtype(np.float32).char
float_32_ind = typecodes.index(float_32_char)
typecodes = typecodes[float_32_ind:]
if typecodes is not None:
# from smallest to largest
for dtype in typecodes:
if np.dtype(dtype).itemsize < values.dtype.itemsize:
values = _possibly_downcast_to_dtype(values, dtype)
# successful conversion
if values.dtype == dtype:
break
if is_series:
return pd.Series(values, index=arg.index, name=arg.name)
elif is_index:
# because we want to coerce to numeric if possible,
# do not use _shallow_copy_with_infer
return Index(values, name=arg.name)
elif is_scalar:
return values[0]
else:
return values
def _view_if_needed(values):
if is_datetime_or_timedelta_dtype(values):
return values.view(np.int64)
return values
def _view_if_needed(values):
if is_datetime_or_timedelta_dtype(values):
return values.view(np.int64)
return values
def to_numeric(arg, errors='raise', downcast=None):
"""
Convert argument to a numeric type.
Parameters
----------
arg : list, tuple, 1-d array, or Series
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaN
- If 'ignore', then invalid parsing will return the input
downcast : {'integer', 'signed', 'unsigned', 'float'} , default None
If not None, and if the data has been successfully cast to a
numerical dtype (or if the data was numeric to begin with),
downcast that resulting data to the smallest numerical dtype
possible according to the following rules:
- 'integer' or 'signed': smallest signed int dtype (min.: np.int8)
- 'unsigned': smallest unsigned int dtype (min.: np.uint8)
- 'float': smallest float dtype (min.: np.float32)
As this behaviour is separate from the core conversion to
numeric values, any errors raised during the downcasting
will be surfaced regardless of the value of the 'errors' input.
In addition, downcasting will only occur if the size
of the resulting data's dtype is strictly larger than
the dtype it is to be cast to, so if none of the dtypes
checked satisfy that specification, no downcasting will be
performed on the data.
.. versionadded:: 0.19.0
Returns
-------
ret : numeric if parsing succeeded.
Return type depends on input. Series if Series, otherwise ndarray
Examples
--------
Take separate series and convert to numeric, coercing when told to
>>> import pandas as pd
>>> s = pd.Series(['1.0', '2', -3])
>>> pd.to_numeric(s)
0 1.0
1 2.0
2 -3.0
dtype: float64
>>> pd.to_numeric(s, downcast='float')
0 1.0
1 2.0
2 -3.0
dtype: float32
>>> pd.to_numeric(s, downcast='signed')
0 1
1 2
2 -3
dtype: int8
>>> s = pd.Series(['apple', '1.0', '2', -3])
>>> pd.to_numeric(s, errors='ignore')
0 apple
1 1.0
2 2
3 -3
dtype: object
>>> pd.to_numeric(s, errors='coerce')
0 NaN
1 1.0
2 2.0
3 -3.0
dtype: float64
"""
if downcast not in (None, 'integer', 'signed', 'unsigned', 'float'):
raise ValueError('invalid downcasting method provided')
is_series = False
is_index = False
is_scalar = False
if isinstance(arg, pd.Series):
is_series = True
values = arg.values
elif isinstance(arg, pd.Index):
is_index = True
values = arg.asi8
if values is None:
values = arg.values
elif isinstance(arg, (list, tuple)):
values = np.array(arg, dtype='O')
elif np.isscalar(arg):
if is_number(arg):
return arg
is_scalar = True
values = np.array([arg], dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a list, tuple, 1-d array, or Series')
else:
values = arg
try:
if is_numeric_dtype(values):
pass
elif is_datetime_or_timedelta_dtype(values):
values = values.astype(np.int64)
else:
values = _ensure_object(values)
coerce_numeric = False if errors in ('ignore', 'raise') else True
values = lib.maybe_convert_numeric(values, set(),
coerce_numeric=coerce_numeric)
except Exception:
if errors == 'raise':
raise
# attempt downcast only if the data has been successfully converted
# to a numerical dtype and if a downcast method has been specified
if downcast is not None and is_numeric_dtype(values):
typecodes = None
if downcast in ('integer', 'signed'):
typecodes = np.typecodes['Integer']
elif downcast == 'unsigned' and np.min(values) > 0:
typecodes = np.typecodes['UnsignedInteger']
elif downcast == 'float':
typecodes = np.typecodes['Float']
# pandas support goes only to np.float32,
# as float dtypes smaller than that are
# extremely rare and not well supported
float_32_char = np.dtype(np.float32).char
float_32_ind = typecodes.index(float_32_char)
typecodes = typecodes[float_32_ind:]
if typecodes is not None:
# from smallest to largest
for dtype in typecodes:
if np.dtype(dtype).itemsize < values.dtype.itemsize:
values = _possibly_downcast_to_dtype(
values, dtype)
# successful conversion
if values.dtype == dtype:
break
if is_series:
return pd.Series(values, index=arg.index, name=arg.name)
elif is_index:
# because we want to coerce to numeric if possible,
# do not use _shallow_copy_with_infer
return Index(values, name=arg.name)
elif is_scalar:
return values[0]
else:
return values
