pandas (git://github.com/pydata/pandas.git) /pandas/tseries/resample.py
(//srv.carbonads.net/ads/click/x/GTND42QLCKAD42QNCWB4YKQMCV7I52QWCWYILZ3JCW7DC2JMCKADV27KC6BI6K7YC6B segment=placement:searchcodecom;&encredirect=https%3A%2F%2Fslack.com%2Flp%3Fcvosrc%3Ddisplay.carbon.green%20d
All the tools your team needs in one place. Slack: Where work happens. (//srv.carbonads.net/ads/click/x/GTND42QLCKAD42QNCWB4YKQMCV7I52QWCWYILZ3JCW7DC2JMCKADV27KC6BI6K7YC6B segment=placement:searchcodecom;&encredirect=https%3A%2F%2Fslack.com%2Flp%3Fcvosrc%3Ddisplay.carbon.green%20d ads via Carbon (http://carbonads.net/? utm_source=searchcodecom&utm_medium=ad_via_link&utm_campaign=in_unit&utm_term=carbon)
Language
Python
MD5 Hash
e2ef86f1423dc11e662e1513904a4005
Repository
git://github.com/pydata/pandas.git
Show 5 matches
Lines
View Raw File (/codesearch/raw/14704200)
View File Tree
from datetime import timedelta import numpy as np 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
from pandas.core.groupby import BinGrouper, Grouper from pandas.tseries.frequencies import to_offset, is_subperiod, is_superperiod from pandas.tseries.index import DatetimeIndex, date_range from pandas.tseries.offsets import DateOffset, Tick, _delta_to_nanoseconds from pandas.tseries.period import PeriodIndex, period_range import pandas.tseries.tools as tools import pandas.core.common as com import pandas.compat as compat from pandas.lib import Timestamp import pandas.lib as lib import pandas.tslib as tslib
_DEFAULT_METHOD = 'mean'
class TimeGrouper(Grouper): """ Custom groupby class for time-interval grouping Parameters --------- freq : pandas date offset or offset alias for identifying bin edges closed : closed end of interval; left or right label : interval boundary to use for labeling; left or right nperiods : optional, integer convention : {'start', 'end', 'e', 's'} If axis is PeriodIndex Notes ---- Use begin, end, nperiods to generate intervals that cannot be derived directly from the associated object """ def __init__(self, freq='Min', closed=None, label=None, how='mean', nperiods=None, axis=0, fill_method=None, limit=None, loffset=None, kind=None, convention=None, base=0, **kwargs): freq = to_offset(freq) end_types = set(['M', 'A', 'Q', 'BM', 'BA', 'BQ', 'W']) rule = freq.rule_code if (rule in end_types or ('-' in rule and rule[:rule.find('-')] in end_types)): if closed is None: closed = 'right' if label is None: label = 'right' else: if closed is None: closed = 'left' if label is None: label = 'left' self.closed = closed self.label = label self.nperiods = nperiods self.kind = kind self.convention = convention or 'E' self.convention = self.convention.lower() self.loffset = loffset self.how = how self.fill_method = fill_method self.limit = limit self.base = base # always sort time groupers kwargs['sort'] = True super(TimeGrouper, self).__init__(freq=freq, axis=axis, **kwargs) def resample(self, obj): self._set_grouper(obj, sort=True) ax = self.grouper if isinstance(ax, DatetimeIndex): rs = self._resample_timestamps() elif isinstance(ax, PeriodIndex): offset = to_offset(self.freq) if offset.n > 1: if self.kind == 'period': # pragma: no cover print('Warning: multiple of frequency -> timestamps') # Cannot have multiple of periods, convert to timestamp self.kind = 'timestamp' if self.kind is None or self.kind == 'period': rs = self._resample_periods() else: obj = self.obj.to_timestamp(how=self.convention) self._set_grouper(obj) rs = self._resample_timestamps() elif len(ax) == 0: return self.obj else: # pragma: no cover raise TypeError('Only valid with DatetimeIndex or PeriodIndex') rs_axis = rs._get_axis(self.axis) rs_axis.name = ax.name return rs def _get_grouper(self, obj): self._set_grouper(obj) return self._get_binner_for_resample() def _get_binner_for_resample(self): # create the BinGrouper # assume that self.set_grouper(obj) has already been called ax = self.ax if self.kind is None or self.kind == 'timestamp': self.binner, bins, binlabels = self._get_time_bins(ax) else: self.binner, bins, binlabels = self._get_time_period_bins(ax) self.grouper = BinGrouper(bins, binlabels) return self.binner, self.grouper, self.obj def _get_binner_for_grouping(self, obj): # return an ordering of the transformed group labels, # suitable for multi-grouping, e.g the labels for # the resampled intervals ax = self._set_grouper(obj) self._get_binner_for_resample() # create the grouper binner = self.binner l = [] for key, group in self.grouper.get_iterator(ax): l.extend([key]*len(group)) grouper = binner.__class__(l,freq=binner.freq,name=binner.name) # since we may have had to sort # may need to reorder groups here if self.indexer is not None: indexer = self.indexer.argsort(kind='quicksort') grouper = grouper.take(indexer) return grouper def _get_time_bins(self, ax): if not isinstance(ax, DatetimeIndex): raise TypeError('axis must be a DatetimeIndex, but got ' 'an instance of %r' % type(ax).__name__) if len(ax) == 0: binner = labels = DatetimeIndex(data=[], freq=self.freq, name=ax.name) return binner, [], labels first, last = ax.min(), ax.max() first, last = _get_range_edges(first, last, self.freq, closed=self.closed, base=self.base) tz = ax.tz binner = labels = DatetimeIndex(freq=self.freq, start=first.replace(tzinfo=None), end=last.replace(tzinfo=None), tz=tz, name=ax.name) # a little hack trimmed = False if (len(binner) > 2 and binner[-2] == last and self.closed == 'right'): binner = binner[:-1] trimmed = True ax_values = ax.asi8 binner, bin_edges = self._adjust_bin_edges(binner, ax_values) # general version, knowing nothing about relative frequencies bins = lib.generate_bins_dt64(ax_values, bin_edges, self.closed, hasnans=ax.hasnans) if self.closed == 'right': labels = binner if self.label == 'right': labels = labels[1:] elif not trimmed: labels = labels[:-1] else: if self.label == 'right': labels = labels[1:] elif not trimmed: labels = labels[:-1] if ax.hasnans: binner = binner.insert(0, tslib.NaT) labels = labels.insert(0, tslib.NaT) # if we end up with more labels than bins # adjust the labels # GH4076 if len(bins) < len(labels): labels = labels[:len(bins)] return binner, bins, labels def _adjust_bin_edges(self, binner, ax_values): # Some hacks for > daily data, see #1471, #1458, #1483 bin_edges = binner.asi8 if self.freq != 'D' and is_superperiod(self.freq, 'D'): day_nanos = _delta_to_nanoseconds(timedelta(1)) if self.closed == 'right': bin_edges = bin_edges + day_nanos - 1 # intraday values on last day if bin_edges[-2] > ax_values.max(): bin_edges = bin_edges[:-1] binner = binner[:-1] return binner, bin_edges def _get_time_period_bins(self, ax): if not isinstance(ax, DatetimeIndex): raise TypeError('axis must be a DatetimeIndex, but got ' 'an instance of %r' % type(ax).__name__) if not len(ax): binner = labels = PeriodIndex(data=[], freq=self.freq, name=ax.name) return binner, [], labels labels = binner = PeriodIndex(start=ax[0], end=ax[-1], freq=self.freq, name=ax.name) end_stamps = (labels + 1).asfreq(self.freq, 's').to_timestamp() if ax.tzinfo: end_stamps = end_stamps.tz_localize(ax.tzinfo) bins = ax.searchsorted(end_stamps, side='left') return binner, bins, labels @property def _agg_method(self): return self.how if self.how else _DEFAULT_METHOD def _resample_timestamps(self): # assumes set_grouper(obj) already called axlabels = self.ax self._get_binner_for_resample() grouper = self.grouper binner = self.binner obj = self.obj # Determine if we're downsampling if axlabels.freq is not None or axlabels.inferred_freq is not None: if len(grouper.binlabels) < len(axlabels) or self.how is not None: # downsample grouped = obj.groupby(grouper, axis=self.axis) result = grouped.aggregate(self._agg_method) # GH2073 if self.fill_method is not None: result = result.fillna(method=self.fill_method, limit=self.limit) else: # upsampling shortcut if self.axis: raise AssertionError('axis must be 0') if self.closed == 'right': res_index = binner[1:] else: res_index = binner[:-1] # if we have the same frequency as our axis, then we are equal sampling # even if how is None if self.fill_method is None and self.limit is None and to_offset( axlabels.inferred_freq) == self.freq: result = obj.copy() result.index = res_index else: result = obj.reindex(res_index, method=self.fill_method, limit=self.limit) else: # Irregular data, have to use groupby grouped = obj.groupby(grouper, axis=self.axis) result = grouped.aggregate(self._agg_method) if self.fill_method is not None: result = result.fillna(method=self.fill_method, limit=self.limit) loffset = self.loffset if isinstance(loffset, compat.string_types): loffset = to_offset(self.loffset) if isinstance(loffset, (DateOffset, timedelta)): if (isinstance(result.index, DatetimeIndex) and len(result.index) > 0): result.index = result.index + loffset return result def _resample_periods(self): # assumes set_grouper(obj) already called axlabels = self.ax obj = self.obj if len(axlabels) == 0: new_index = PeriodIndex(data=[], freq=self.freq) return obj.reindex(new_index) else: start = axlabels[0].asfreq(self.freq, how=self.convention) end = axlabels[-1].asfreq(self.freq, how='end') new_index = period_range(start, end, freq=self.freq) # Start vs. end of period memb = axlabels.asfreq(self.freq, how=self.convention) if is_subperiod(axlabels.freq, self.freq) or self.how is not None: # Downsampling rng = np.arange(memb.values[0], memb.values[-1] + 1) bins = memb.searchsorted(rng, side='right') grouper = BinGrouper(bins, new_index) grouped = obj.groupby(grouper, axis=self.axis) return grouped.aggregate(self._agg_method) elif is_superperiod(axlabels.freq, self.freq): # Get the fill indexer indexer = memb.get_indexer(new_index, method=self.fill_method, limit=self.limit) return _take_new_index(obj, indexer, new_index, axis=self.axis) else: raise ValueError('Frequency %s cannot be resampled to %s' % (axlabels.freq, self.freq))
def _take_new_index(obj, indexer, new_index, axis=0): from pandas.core.api import Series, DataFrame if isinstance(obj, Series): new_values = com.take_1d(obj.values, indexer) return Series(new_values, index=new_index, name=obj.name) elif isinstance(obj, DataFrame): if axis == 1: raise NotImplementedError return DataFrame(obj._data.reindex_indexer( new_axis=new_index, indexer=indexer, axis=1)) else: raise NotImplementedError
def _get_range_edges(first, last, offset, closed='left', base=0): if isinstance(offset, compat.string_types): offset = to_offset(offset) if isinstance(offset, Tick): day_nanos = _delta_to_nanoseconds(timedelta(1)) # #1165 if (day_nanos % offset.nanos) == 0: return _adjust_dates_anchored(first, last, offset, closed=closed, base=base) if not isinstance(offset, Tick): # and first.time() != last.time(): # hack! first = tools.normalize_date(first) last = tools.normalize_date(last) if closed == 'left': first = Timestamp(offset.rollback(first)) else: first = Timestamp(first - offset) last = Timestamp(last + offset) return first, last
def _adjust_dates_anchored(first, last, offset, closed='right', base=0): from pandas.tseries.tools import normalize_date start_day_nanos = Timestamp(normalize_date(first)).value last_day_nanos = Timestamp(normalize_date(last)).value base_nanos = (base % offset.n) * offset.nanos // offset.n start_day_nanos += base_nanos last_day_nanos += base_nanos foffset = (first.value - start_day_nanos) % offset.nanos loffset = (last.value - last_day_nanos) % offset.nanos if closed == 'right': if foffset > 0: # roll back fresult = first.value - foffset else: fresult = first.value - offset.nanos if loffset > 0: # roll forward lresult = last.value + (offset.nanos - loffset) else: # already the end of the road lresult = last.value else: # closed == 'left' if foffset > 0: fresult = first.value - foffset else: # start of the road fresult = first.value if loffset > 0: # roll forward lresult = last.value + (offset.nanos - loffset) else: lresult = last.value + offset.nanos return (Timestamp(fresult, tz=first.tz), Timestamp(lresult, tz=last.tz))
def asfreq(obj, freq, method=None, how=None, normalize=False): """ Utility frequency conversion method for Series/DataFrame """ if isinstance(obj.index, PeriodIndex): if method is not None: raise NotImplementedError if how is None: how = 'E' new_index = obj.index.asfreq(freq, how=how) new_obj = obj.copy() new_obj.index = new_index return new_obj else: if len(obj.index) == 0: return obj.copy() dti = date_range(obj.index[0], obj.index[-1], freq=freq) rs = obj.reindex(dti, method=method) if normalize: rs.index = rs.index.normalize() return rs
About (/about/) Developers (/api/)
449
Updates (http://www.boyter.org/category/searchcode/) SPDX Search (/spdx/) searchcode server (https://searchcodeserver.com/) Subscribe to the searchcode newsletter Your email...
Subscribe
searchcode is proudly Made in Sydney | © searchcode 2016
