Skip to content

REF: use _get_string_slice in PeriodIndex.get_value #31058

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.

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

Merged
merged 6 commits into from
Jan 20, 2020
Merged
Changes from all commits
Commits
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
85 changes: 29 additions & 56 deletions pandas/core/indexes/period.py
Original file line number Diff line number Diff line change
Expand Up @@ -483,25 +483,20 @@ def get_value(self, series, key):
return series.iat[key]

if isinstance(key, str):
try:
loc = self._get_string_slice(key)
return series[loc]
except (TypeError, ValueError):
pass

asdt, reso = parse_time_string(key, self.freq)
grp = resolution.Resolution.get_freq_group(reso)
freqn = resolution.get_freq_group(self.freq)

vals = self._ndarray_values

# if our data is higher resolution than requested key, slice
if grp < freqn:
iv = Period(asdt, freq=(grp, 1))
ord1 = iv.asfreq(self.freq, how="S").ordinal
ord2 = iv.asfreq(self.freq, how="E").ordinal
# _get_string_slice will handle cases where grp < freqn
assert grp >= freqn

if ord2 < vals[0] or ord1 > vals[-1]:
raise KeyError(key)

pos = np.searchsorted(self._ndarray_values, [ord1, ord2])
key = slice(pos[0], pos[1] + 1)
return series[key]
elif grp == freqn:
if grp == freqn:
key = Period(asdt, freq=self.freq)
loc = self.get_loc(key)
return series.iloc[loc]
Expand Down Expand Up @@ -643,61 +638,39 @@ def _maybe_cast_slice_bound(self, label, side, kind):

return label

def _parsed_string_to_bounds(self, reso, parsed):
if reso == "year":
t1 = Period(year=parsed.year, freq="A")
elif reso == "month":
t1 = Period(year=parsed.year, month=parsed.month, freq="M")
elif reso == "quarter":
q = (parsed.month - 1) // 3 + 1
t1 = Period(year=parsed.year, quarter=q, freq="Q-DEC")
elif reso == "day":
t1 = Period(year=parsed.year, month=parsed.month, day=parsed.day, freq="D")
elif reso == "hour":
t1 = Period(
year=parsed.year,
month=parsed.month,
day=parsed.day,
hour=parsed.hour,
freq="H",
)
elif reso == "minute":
t1 = Period(
year=parsed.year,
month=parsed.month,
day=parsed.day,
hour=parsed.hour,
minute=parsed.minute,
freq="T",
)
elif reso == "second":
t1 = Period(
year=parsed.year,
month=parsed.month,
day=parsed.day,
hour=parsed.hour,
minute=parsed.minute,
second=parsed.second,
freq="S",
)
else:
def _parsed_string_to_bounds(self, reso: str, parsed: datetime):
if reso not in ["year", "month", "quarter", "day", "hour", "minute", "second"]:
raise KeyError(reso)
return (t1.asfreq(self.freq, how="start"), t1.asfreq(self.freq, how="end"))

grp = resolution.Resolution.get_freq_group(reso)
iv = Period(parsed, freq=(grp, 1))
return (iv.asfreq(self.freq, how="start"), iv.asfreq(self.freq, how="end"))

def _get_string_slice(self, key: str, use_lhs: bool = True, use_rhs: bool = True):
# TODO: Check for non-True use_lhs/use_rhs
raw = key
if not self.is_monotonic:
raise ValueError("Partial indexing only valid for ordered time series")

parsed, reso = parse_time_string(key, self.freq)
grp = resolution.Resolution.get_freq_group(reso)
freqn = resolution.get_freq_group(self.freq)
if reso in ["day", "hour", "minute", "second"] and not grp < freqn:
raise KeyError(key)
Copy link
Member Author

Choose a reason for hiding this comment

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

@jreback i think you wrote most of this, do you remember what the reso checks here are for?

Copy link
Contributor

Choose a reason for hiding this comment

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

nope


if not grp < freqn:
# TODO: we used to also check for
# reso in ["day", "hour", "minute", "second"]
# why is that check not needed?
raise TypeError(key)

t1, t2 = self._parsed_string_to_bounds(reso, parsed)
if len(self):
if t2 < self.min() or t1 > self.max():
raise KeyError(raw)

# Use asi8 searchsorted to avoid overhead of re-validating inputs
return slice(
self.searchsorted(t1, side="left"), self.searchsorted(t2, side="right")
self.asi8.searchsorted(t1.ordinal, side="left"),
self.asi8.searchsorted(t2.ordinal, side="right"),
)

def _convert_tolerance(self, tolerance, target):
Expand Down