Skip to content

Fix performance issues when creating multiple instances of Period (#12903, #11831) #12909

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 6 commits into from
Closed

Fix performance issues when creating multiple instances of Period (#12903, #11831) #12909

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
fec1b51
Fix performance issues when creating multiple instances of Period (#1…
rs2 Apr 16, 2016
5b3e291
Moved constants to frequencies.py
rs2 Apr 19, 2016
8f254e3
Added a whatsnew entry + ensured constants are imported correctly by …
rs2 Apr 20, 2016
8bcfd57
Reworded whatsnew
rs2 Apr 20, 2016
1c5a2ab
Added asv benchmark for Period, PeriodIndex
rs2 Apr 20, 2016
0d9712d
Make RESO constants global in period.pyx and reduce the number of loo…
rs2 Apr 20, 2016
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
31 changes: 7 additions & 24 deletions pandas/src/period.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,13 @@ from tslib cimport (
_nat_scalar_rules,
)

from pandas.tseries.frequencies import _period_alias_dict
from pandas.tseries.frequencies import _get_freq_str
from pandas.tseries.frequencies import to_offset
from pandas.tseries.frequencies import get_freq_code as _gfc
from pandas.tseries import frequencies
from pandas.tseries.constants import US_RESO, MS_RESO, S_RESO, T_RESO, H_RESO, D_RESO

Copy link
Contributor

Choose a reason for hiding this comment

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

what you need to do is at the top here type and import all of the freqs that you need e.g

cdef int D_RESO = frequencies.D_RESO
...

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Will do in a moment.

from sys import version_info

cdef bint PY2 = version_info[0] == 2
Expand Down Expand Up @@ -476,12 +483,6 @@ cpdef resolution(ndarray[int64_t] stamps, tz=None):
reso = curr_reso
return reso

US_RESO = 0
MS_RESO = 1
S_RESO = 2
T_RESO = 3
H_RESO = 4
D_RESO = 5

cdef inline int _reso_stamp(pandas_datetimestruct *dts):
if dts.us != 0:
Expand Down Expand Up @@ -662,16 +663,12 @@ cdef class Period(object):
def _maybe_convert_freq(cls, object freq):

if isinstance(freq, compat.string_types):
from pandas.tseries.frequencies import _period_alias_dict
freq = freq.upper()
freq = _period_alias_dict.get(freq, freq)
elif isinstance(freq, (int, tuple)):
from pandas.tseries.frequencies import get_freq_code as _gfc
from pandas.tseries.frequencies import _get_freq_str
code, stride = _gfc(freq)
freq = _get_freq_str(code, stride)

from pandas.tseries.frequencies import to_offset
freq = to_offset(freq)

if freq.n <= 0:
Expand All @@ -691,9 +688,6 @@ cdef class Period(object):
def __init__(self, value=None, freq=None, ordinal=None,
year=None, month=1, quarter=None, day=1,
hour=0, minute=0, second=0):
from pandas.tseries import frequencies
from pandas.tseries.frequencies import get_freq_code as _gfc

# freq points to a tuple (base, mult); base is one of the defined
# periods such as A, Q, etc. Every five minutes would be, e.g.,
# ('T', 5) but may be passed in as a string like '5T'
Expand Down Expand Up @@ -771,7 +765,6 @@ cdef class Period(object):

def __richcmp__(self, other, op):
if isinstance(other, Period):
from pandas.tseries.frequencies import get_freq_code as _gfc
if other.freq != self.freq:
msg = _DIFFERENT_FREQ.format(self.freqstr, other.freqstr)
raise IncompatibleFrequency(msg)
Expand All @@ -790,7 +783,6 @@ cdef class Period(object):
return hash((self.ordinal, self.freq))

def _add_delta(self, other):
from pandas.tseries import frequencies
if isinstance(other, (timedelta, np.timedelta64, offsets.Tick, Timedelta)):
offset = frequencies.to_offset(self.freq.rule_code)
if isinstance(offset, offsets.Tick):
Expand Down Expand Up @@ -868,7 +860,6 @@ cdef class Period(object):
-------
resampled : Period
"""
from pandas.tseries.frequencies import get_freq_code as _gfc
how = _validate_end_alias(how)
base1, mult1 = _gfc(self.freq)
base2, mult2 = _gfc(freq)
Expand Down Expand Up @@ -918,8 +909,6 @@ cdef class Period(object):
-------
Timestamp
"""
from pandas.tseries import frequencies
from pandas.tseries.frequencies import get_freq_code as _gfc
how = _validate_end_alias(how)

if freq is None:
Expand All @@ -933,7 +922,6 @@ cdef class Period(object):
return Timestamp(dt64, tz=tz)

cdef _field(self, alias):
from pandas.tseries.frequencies import get_freq_code as _gfc
base, mult = _gfc(self.freq)
return get_period_field(alias, self.ordinal, base)

Expand Down Expand Up @@ -996,7 +984,6 @@ cdef class Period(object):
return self.freq.freqstr

def __repr__(self):
from pandas.tseries.frequencies import get_freq_code as _gfc
base, mult = _gfc(self.freq)
formatted = period_format(self.ordinal, base)
return "Period('%s', '%s')" % (formatted, self.freqstr)
Expand All @@ -1008,7 +995,6 @@ cdef class Period(object):
Invoked by unicode(df) in py2 only. Yields a Unicode String in both
py2/py3.
"""
from pandas.tseries.frequencies import get_freq_code as _gfc
base, mult = _gfc(self.freq)
formatted = period_format(self.ordinal, base)
value = ("%s" % formatted)
Expand Down Expand Up @@ -1159,14 +1145,12 @@ cdef class Period(object):
>>> a.strftime('%b. %d, %Y was a %A')
'Jan. 01, 2001 was a Monday'
"""
from pandas.tseries.frequencies import get_freq_code as _gfc
base, mult = _gfc(self.freq)
return period_format(self.ordinal, base, fmt)


def _ordinal_from_fields(year, month, quarter, day, hour, minute,
second, freq):
from pandas.tseries.frequencies import get_freq_code as _gfc
base, mult = _gfc(freq)
if quarter is not None:
year, month = _quarter_to_myear(year, quarter, freq)
Expand All @@ -1179,7 +1163,6 @@ def _quarter_to_myear(year, quarter, freq):
if quarter <= 0 or quarter > 4:
raise ValueError('Quarter must be 1 <= q <= 4')

from pandas.tseries import frequencies
mnum = frequencies._month_numbers[frequencies._get_rule_month(freq)] + 1
month = (mnum + (quarter - 1) * 3) % 12 + 1
if month > mnum:
Expand Down
7 changes: 7 additions & 0 deletions pandas/tseries/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
US_RESO = 0
MS_RESO = 1
Copy link
Contributor

Choose a reason for hiding this comment

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

don't add another module instead put these in frequencies

S_RESO = 2
T_RESO = 3
H_RESO = 4
D_RESO = 5

14 changes: 7 additions & 7 deletions pandas/tseries/frequencies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
import pandas.core.common as com
import pandas.lib as lib
import pandas.tslib as tslib
import pandas._period as period
from pandas.tseries import constants
from pandas.tslib import Timedelta
from pytz import AmbiguousTimeError

Expand All @@ -38,12 +38,12 @@ class Resolution(object):

# defined in period.pyx
# note that these are different from freq codes
RESO_US = period.US_RESO
RESO_MS = period.MS_RESO
RESO_SEC = period.S_RESO
RESO_MIN = period.T_RESO
RESO_HR = period.H_RESO
RESO_DAY = period.D_RESO
RESO_US = constants.US_RESO
RESO_MS = constants.MS_RESO
RESO_SEC = constants.S_RESO
RESO_MIN = constants.T_RESO
RESO_HR = constants.H_RESO
RESO_DAY = constants.D_RESO

_reso_str_map = {
RESO_US: 'microsecond',
Expand Down