def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike (e.g. datetime64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
if not isinstance(data, Series):
raise TypeError("cannot convert an object of type {0} to a datetimelike index".format(type(data)))
index = data.index
if issubclass(data.dtype.type, np.datetime64):
return DatetimeProperties(DatetimeIndex(data, copy=copy), index)
else:
if com.is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy), index)
raise TypeError("cannot convert an object of type {0} to a datetimelike index".format(type(data)))
def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike
(e.g. datetime64[ns],timedelta64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
from pandas import Series
if not isinstance(data, Series):
raise TypeError("cannot convert an object of type {0} to a datetimelike index".format(type(data)))
index = data.index
if is_datetime64_dtype(data.dtype) or is_datetime64tz_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data, copy=copy, freq='infer'), index, name=data.name)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaProperties(TimedeltaIndex(data, copy=copy, freq='infer'), index, name=data.name)
else:
if is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy), index, name=data.name)
if is_datetime_arraylike(data):
return DatetimeProperties(DatetimeIndex(data, copy=copy, freq='infer'), index, name=data.name)
raise TypeError("cannot convert an object of type {0} to a datetimelike index".format(type(data)))
def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike (e.g. datetime64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
if not isinstance(data, Series):
raise TypeError(
"cannot convert an object of type {0} to a datetimelike index".
format(type(data)))
index = data.index
if issubclass(data.dtype.type, np.datetime64):
return DatetimeProperties(DatetimeIndex(data, copy=copy), index)
else:
if com.is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy), index)
raise TypeError(
"cannot convert an object of type {0} to a datetimelike index".format(
type(data)))
def maybe_to_datetimelike(data, copy=False):
"""
return a DelegatedClass of a Series that is datetimelike
(e.g. datetime64[ns],timedelta64[ns] dtype or a Series of Periods)
raise TypeError if this is not possible.
Parameters
----------
data : Series
copy : boolean, default False
copy the input data
Returns
-------
DelegatedClass
"""
from pandas import Series
if not isinstance(data, Series):
raise TypeError(
"cannot convert an object of type {0} to a datetimelike index".
format(type(data)))
index = data.index
if is_datetime64_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data, copy=copy, freq='infer'),
index,
name=data.name)
elif is_datetime64tz_dtype(data.dtype):
return DatetimeProperties(DatetimeIndex(data,
copy=copy,
freq='infer',
ambiguous='infer'),
index,
name=data.name)
elif is_timedelta64_dtype(data.dtype):
return TimedeltaProperties(TimedeltaIndex(data,
copy=copy,
freq='infer'),
index,
name=data.name)
else:
if is_period_arraylike(data):
return PeriodProperties(PeriodIndex(data, copy=copy),
index,
name=data.name)
if is_datetime_arraylike(data):
return DatetimeProperties(DatetimeIndex(data,
copy=copy,
freq='infer'),
index,
name=data.name)
raise TypeError(
"cannot convert an object of type {0} to a datetimelike index".format(
type(data)))
def _value_counts_arraylike(values, dropna=True):
is_datetimetz = com.is_datetimetz(values)
is_period = (isinstance(values, gt.ABCPeriodIndex) or
com.is_period_arraylike(values))
orig = values
from pandas.core.series import Series
values = Series(values).values
dtype = values.dtype
if com.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:
if isinstance(orig, gt.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 com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.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 = com.is_datetimetz(values)
is_period = (isinstance(values, gt.ABCPeriodIndex)
or com.is_period_arraylike(values))
orig = values
from pandas.core.series import Series
values = Series(values).values
dtype = values.dtype
if com.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:
if isinstance(orig, gt.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 com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.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 infer_freq(index, warn=True):
"""
Infer the most likely frequency given the input index. If the frequency is
uncertain, a warning will be printed.
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
if passed a Series will use the values of the series (NOT THE INDEX)
warn : boolean, default True
Returns
-------
freq : string or None
None if no discernible frequency
TypeError if the index is not datetime-like
ValueError if there are less than three values.
"""
import pandas as pd
if isinstance(index, com.ABCSeries):
values = index._values
if not (com.is_datetime64_dtype(values)
or com.is_timedelta64_dtype(values) or values.dtype == object):
raise TypeError(
"cannot infer freq from a non-convertible dtype on a Series of {0}"
.format(index.dtype))
index = values
if com.is_period_arraylike(index):
raise TypeError("PeriodIndex given. Check the `freq` attribute "
"instead of using infer_freq.")
elif isinstance(index, pd.TimedeltaIndex):
inferer = _TimedeltaFrequencyInferer(index, warn=warn)
return inferer.get_freq()
if isinstance(index, pd.Index) and not isinstance(index, pd.DatetimeIndex):
if isinstance(index, (pd.Int64Index, pd.Float64Index)):
raise TypeError(
"cannot infer freq from a non-convertible index type {0}".
format(type(index)))
index = index.values
if not isinstance(index, pd.DatetimeIndex):
try:
index = pd.DatetimeIndex(index)
except AmbiguousTimeError:
index = pd.DatetimeIndex(index.asi8)
inferer = _FrequencyInferer(index, warn=warn)
return inferer.get_freq()
def infer_freq(index, warn=True):
"""
Infer the most likely frequency given the input index. If the frequency is
uncertain, a warning will be printed.
Parameters
----------
index : DatetimeIndex or TimedeltaIndex
if passed a Series will use the values of the series (NOT THE INDEX)
warn : boolean, default True
Returns
-------
freq : string or None
None if no discernible frequency
TypeError if the index is not datetime-like
ValueError if there are less than three values.
"""
import pandas as pd
if isinstance(index, com.ABCSeries):
values = index._values
if not (com.is_datetime64_dtype(values) or
com.is_timedelta64_dtype(values) or
values.dtype == object):
raise TypeError("cannot infer freq from a non-convertible "
"dtype on a Series of {0}".format(index.dtype))
index = values
if com.is_period_arraylike(index):
raise TypeError("PeriodIndex given. Check the `freq` attribute "
"instead of using infer_freq.")
elif isinstance(index, pd.TimedeltaIndex):
inferer = _TimedeltaFrequencyInferer(index, warn=warn)
return inferer.get_freq()
if isinstance(index, pd.Index) and not isinstance(index, pd.DatetimeIndex):
if isinstance(index, (pd.Int64Index, pd.Float64Index)):
raise TypeError("cannot infer freq from a non-convertible index "
"type {0}".format(type(index)))
index = index.values
if not isinstance(index, pd.DatetimeIndex):
try:
index = pd.DatetimeIndex(index)
except AmbiguousTimeError:
index = pd.DatetimeIndex(index.asi8)
inferer = _FrequencyInferer(index, warn=warn)
return inferer.get_freq()
def convert(values, units, axis):
if not hasattr(axis, "freq"):
raise TypeError("Axis must have `freq` set to convert to Periods")
valid_types = (compat.string_types, datetime, Period, pydt.date, pydt.time)
if isinstance(values, valid_types) or com.is_integer(values) or com.is_float(values):
return get_datevalue(values, axis.freq)
if isinstance(values, PeriodIndex):
return values.asfreq(axis.freq).values
if isinstance(values, Index):
return values.map(lambda x: get_datevalue(x, axis.freq))
if com.is_period_arraylike(values):
return PeriodIndex(values, freq=axis.freq).values
if isinstance(values, (list, tuple, np.ndarray, Index)):
return [get_datevalue(x, axis.freq) for x in values]
return values
def convert(values, units, axis):
if not hasattr(axis, 'freq'):
raise TypeError('Axis must have `freq` set to convert to Periods')
valid_types = (compat.string_types, datetime, Period, pydt.date, pydt.time)
if (isinstance(values, valid_types) or com.is_integer(values) or
com.is_float(values)):
return get_datevalue(values, axis.freq)
if isinstance(values, PeriodIndex):
return values.asfreq(axis.freq).values
if isinstance(values, Index):
return values.map(lambda x: get_datevalue(x, axis.freq))
if com.is_period_arraylike(values):
return PeriodIndex(values, freq=axis.freq).values
if isinstance(values, (list, tuple, np.ndarray, Index)):
return [get_datevalue(x, axis.freq) for x in values]
return values
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas import Index, PeriodIndex, DatetimeIndex
name = getattr(values, 'name', None)
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
if com.is_categorical_dtype(values.dtype):
result = values.value_counts(dropna)
else:
dtype = values.dtype
is_period = com.is_period_arraylike(values)
is_datetimetz = com.is_datetimetz(values)
if com.is_datetime_or_timedelta_dtype(
dtype) or is_period or is_datetimetz:
if is_period:
values = PeriodIndex(values)
elif is_datetimetz:
tz = getattr(values, 'tz', None)
values = DatetimeIndex(values).tz_localize(None)
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# localize to the original tz if necessary
if is_datetimetz:
keys = DatetimeIndex(keys).tz_localize(tz)
# convert the keys back to the dtype we came in
else:
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.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())
if not isinstance(keys, Index):
keys = Index(keys)
result = Series(counts, index=keys, name=name)
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)),
fill_value=0)
result.index = bins[:-1]
if sort:
result = result.sort_values(ascending=ascending)
if normalize:
result = result / float(values.size)
return result
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas.tseries.period import PeriodIndex
is_period = com.is_period_arraylike(values)
values = Series(values).values
is_category = com.is_categorical_dtype(values.dtype)
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
elif is_category:
bins = values.categories
cat = values
values = cat.codes
dtype = values.dtype
if issubclass(values.dtype.type,
(np.datetime64, np.timedelta64)) or is_period:
if is_period:
values = PeriodIndex(values)
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna:
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)), fill_value=0)
if not is_category:
result.index = bins[:-1]
else:
result.index = cat.categories
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result
def value_counts(values, sort=True, ascending=False, normalize=False,
bins=None, dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas import Index, PeriodIndex, DatetimeIndex
name = getattr(values, 'name', None)
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
if com.is_categorical_dtype(values.dtype):
result = values.value_counts(dropna)
else:
dtype = values.dtype
is_period = com.is_period_arraylike(values)
is_datetimetz = com.is_datetimetz(values)
if com.is_datetime_or_timedelta_dtype(dtype) or is_period or \
is_datetimetz:
if is_period:
values = PeriodIndex(values)
elif is_datetimetz:
tz = getattr(values, 'tz', None)
values = DatetimeIndex(values).tz_localize(None)
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# localize to the original tz if necessary
if is_datetimetz:
keys = DatetimeIndex(keys).tz_localize(tz)
# convert the keys back to the dtype we came in
else:
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.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())
if not isinstance(keys, Index):
keys = Index(keys)
result = Series(counts, index=keys, name=name)
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)),
fill_value=0)
result.index = bins[:-1]
if sort:
result = result.sort_values(ascending=ascending)
if normalize:
result = result / float(values.size)
return result
def value_counts(values, sort=True, ascending=False, normalize=False,
bins=None, dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas.tseries.period import PeriodIndex
is_period = com.is_period_arraylike(values)
values = Series(values).values
is_category = com.is_categorical_dtype(values.dtype)
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
elif is_category:
bins = values.categories
cat = values
values = cat.codes
dtype = values.dtype
if issubclass(values.dtype.type, (np.datetime64, np.timedelta64)) or is_period:
if is_period:
values = PeriodIndex(values)
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna:
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)), fill_value=0)
if not is_category:
result.index = bins[:-1]
else:
result.index = cat.categories
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result