8000 WIP: DatetimeArray+TimedeltaArray by jbrockmendel · Pull Request #23415 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

WIP: DatetimeArray+TimedeltaArray #23415

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 10 commits into from
Closed

WIP: DatetimeArray+TimedeltaArray #23415

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
e7ecbf8
Implement concat_same_type, take
jbrockmendel Oct 30, 2018
e309ab9
implement from_sequence, from_factorized, values_for_factore, copy
jbrockmendel Oct 31, 2018
423a357
rename DatetimeArrayMixin-->DatetimeArray
jbrockmendel Oct 31, 2018
47689be
implement unique
jbrockmendel Nov 2, 2018
dc4a264
commit prelim some I can rebase
jbrockmendel Nov 2, 2018
f92843b
Merge branch 'master' of https://github.com/pandas-dev/pandas into dl…
jbrockmendel Nov 2, 2018
92923b2
update name
jbrockmendel Nov 8, 2018
77e9a48
Merge branch 'master' of https://github.com/pandas-dev/pandas into dl…
jbrockmendel Nov 8, 2018
07d4d97
Merge branch 'master' of https://github.com/pandas-dev/pandas into dl…
jbrockmendel Nov 11, 2018
cd63892
update imports
jbrockmendel Nov 11, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
implement from_sequence, from_factorized, values_for_factore, copy
  • Loading branch information
@jbrockmendel
jbrockmendel committed Oct 31, 2018
commit e309ab94ef38c77136fef733613c600761899b99
56 changes: 56 additions & 0 deletions pandas/core/arrays/datetimelike.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,10 @@ def asi8(self):
# ------------------------------------------------------------------
# Array-like Methods

@property
def nbytes(self):
return self.asi8.nbytes

@property
def shape(self):
return (len(self),)
Expand Down Expand Up @@ -211,6 +215,31 @@ def astype(self, dtype, copy=True):

# ------------------------------------------------------------------
# ExtensionArray Interface
# isna
# __getitem__
# __len__
# nbytes
# take
# _concat_same_type
# copy
# _from_factorized
# factorize / _values_for_factorize
# _from_sequence
# unique
#
# dtype
#
# dropna
#
#* _formatting_values
#* fillna
#* argsort / _values_for_argsort
#* _reduce

def unique(self):
from pandas.core.algorithms import unique1d
result = unique1d(self.asi8)
return self._shallow_copy(result)

def _validate_fill_value(self, fill_value):
"""
Expand Down Expand Up @@ -254,9 +283,36 @@ def _concat_same_type(cls, to_concat):
values = np.concatenate([x._data for x in to_concat])
return cls._simple_new(values, freq=freq)

def copy(self, deep=False):
# TODO: should `deep` determine whether we copy self.asi8?
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes like

values = self.asi8
if deep:
    values = values.copy()
....

if is_datetime64tz_dtype(self):
return type(self)(self.asi8.copy(), tz=self.tz, freq=self.freq)
return type(self)(self.asi8.copy(), freq=self.freq)

def _values_for_factorize(self):
return self.asi8, iNaT

@classmethod
def _from_factorized(cls, values, original):
if is_datetime64tz_dtype(original):
return cls(values, tz=original.tz, freq=original.freq)
return cls(values, freq=original.freq)

@classmethod
def _from_sequence(cls, scalars, dtype=None, copy=False):
arr = np.asarray(scalars, dtype=object)
if copy:
arr = arr.copy()

# If necessary this will infer tz from dtype
return cls(arr, dtype=dtype)

# ------------------------------------------------------------------
# Null Handling

def isna(self):
return self._isnan

@property # NB: override with cache_readonly in immutable subclasses
def _isnan(self):
""" return if each value is nan"""
Expand Down
22 changes: 0 additions & 22 deletions pandas/core/arrays/period.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,14 +211,6 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
ordinals = libperiod.extract_ordinals(periods, freq)
return cls(ordinals, freq=freq)

def _values_for_factorize(self):
return self.asi8, iNaT

@classmethod
def _from_factorized(cls, values, original):
# type: (Sequence[Optional[Period]], PeriodArray) -> PeriodArray
return cls(values, freq=original.freq)

@classmethod
def _from_datetime64(cls, data, freq, tz=None):
"""Construct a PeriodArray from a datetime64 array
Expand Down Expand Up @@ -257,14 +249,6 @@ def _generate_range(cls, start, end, periods, freq, fields):

return subarr, freq

@classmethod
def _concat_same_type(cls, to_concat):
freq = {x.freq for x in to_concat}
assert len(freq) == 1
freq = list(freq)[0]
values = np.concatenate([x._data for x in to_concat])
return cls(values, freq=freq)

# --------------------------------------------------------------------
# Data / Attributes
@property
Expand Down Expand Up @@ -400,9 +384,6 @@ def take(self, indices, allow_fill=False, fill_value=None):

return type(self)(new_values, self.freq)

def isna(self):
return self._data == iNaT

def fillna(self, value=None, method=None, limit=None):
# TODO(#20300)
# To avoid converting to object, we re-implement here with the changes
Expand Down Expand Up @@ -438,9 +419,6 @@ def fillna(self, value=None, method=None, limit=None):
new_values = self.copy()
return new_values

def copy(self, deep=False):
return type(self)(self._data.copy(), freq=self.freq)

def value_counts(self, dropna=False):
from pandas import Series, PeriodIndex

Expand Down
0