def test_scalar(self): N = 30 rng = date_range('1/1/1990', periods=N, freq='53s') ts = Series(np.arange(N), index=rng) ts[5:10] = np.NaN ts[15:20] = np.NaN val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) self.assertEqual(val1, ts[4]) self.assertEqual(val2, ts[14]) # accepts strings val1 = ts.asof(str(ts.index[7])) self.assertEqual(val1, ts[4]) # in there result = ts.asof(ts.index[3]) self.assertEqual(result, ts[3]) # no as of value d = ts.index[0] - offsets.BDay() self.assertTrue(np.isnan(ts.asof(d)))
def test_scalar(self): N = 30 rng = date_range('1/1/1990', periods=N, freq='53s') ts = Series(np.arange(N), index=rng) ts[5:10] = np.NaN ts[15:20] = np.NaN val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) assert val1 == ts[4] assert val2 == ts[14] # accepts strings val1 = ts.asof(str(ts.index[7])) assert val1 == ts[4] # in there result = ts.asof(ts.index[3]) assert result == ts[3] # no as of value d = ts.index[0] - offsets.BDay() assert np.isnan(ts.asof(d))
def test_basic(self): # array or list or dates N = 50 rng = date_range('1/1/1990', periods=N, freq='53s') ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range('1/1/1990', periods=N * 3, freq='25s') result = ts.asof(dates) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] mask = (result.index >= lb) & (result.index < ub) rs = result[mask] self.assertTrue((rs == ts[lb]).all()) val = result[result.index[result.index >= ub][0]] self.assertEqual(ts[ub], val)
def test_basic(self): # array or list or dates N = 50 rng = date_range("1/1/1990", periods=N, freq="53s") ts = Series(np.random.randn(N), index=rng) ts.iloc[15:30] = np.nan dates = date_range("1/1/1990", periods=N * 3, freq="25s") result = ts.asof(dates) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] mask = (result.index >= lb) & (result.index < ub) rs = result[mask] assert (rs == ts[lb]).all() val = result[result.index[result.index >= ub][0]] assert ts[ub] == val
def test_scalar(self): N = 30 rng = date_range("1/1/1990", periods=N, freq="53s") ts = Series(np.arange(N), index=rng) ts.iloc[5:10] = np.NaN ts.iloc[15:20] = np.NaN val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) assert val1 == ts[4] assert val2 == ts[14] # accepts strings val1 = ts.asof(str(ts.index[7])) assert val1 == ts[4] # in there result = ts.asof(ts.index[3]) assert result == ts[3] # no as of value d = ts.index[0] - offsets.BDay() assert np.isnan(ts.asof(d))
def test_basic(self): # array or list or dates N = 50 rng = date_range('1/1/1990', periods=N, freq='53s') ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range('1/1/1990', periods=N * 3, freq='25s') result = ts.asof(dates) assert notnull(result).all() lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) assert notnull(result).all() lb = ts.index[14] ub = ts.index[30] mask = (result.index >= lb) & (result.index < ub) rs = result[mask] assert (rs == ts[lb]).all() val = result[result.index[result.index >= ub][0]] assert ts[ub] == val
def test_asof_more(self): from pandas import date_range s = Series([nan, nan, 1, 2, nan, nan, 3, 4, 5], index=date_range('1/1/2000', periods=9)) dates = s.index[[4, 5, 6, 2, 1]] result = s.asof(dates) expected = Series([2, 2, 3, 1, np.nan], index=dates) assert_series_equal(result, expected) s = Series([1.5, 2.5, 1, 2, nan, nan, 3, 4, 5], index=date_range('1/1/2000', periods=9)) result = s.asof(s.index[0]) self.assertEqual(result, s[0])
def test_periodindex(self): from pandas import ( PeriodIndex, period_range, ) # array or list or dates N = 50 rng = period_range("1/1/1990", periods=N, freq="H") ts = Series(np.random.randn(N), index=rng) ts.iloc[15:30] = np.nan dates = date_range("1/1/1990", periods=N * 3, freq="37min") result = ts.asof(dates) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] pix = PeriodIndex(result.index.values, freq="H") mask = (pix >= lb) & (pix < ub) rs = result[mask] assert (rs == ts[lb]).all() ts.iloc[5:10] = np.nan ts.iloc[15:20] = np.nan val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) assert val1 == ts[4] assert val2 == ts[14] # accepts strings val1 = ts.asof(str(ts.index[7])) assert val1 == ts[4] # in there assert ts.asof(ts.index[3]) == ts[3] # no as of value d = ts.index[0].to_timestamp() - offsets.BDay() assert isna(ts.asof(d)) # Mismatched freq msg = "Input has different freq" with pytest.raises(IncompatibleFrequency, match=msg): ts.asof(rng.asfreq("D"))
def test_errors(self): s = Series([1, 2, 3], index=[Timestamp('20130101'), Timestamp('20130103'), Timestamp('20130102')]) # non-monotonic assert not s.index.is_monotonic with pytest.raises(ValueError): s.asof(s.index[0]) # subset with Series N = 10 rng = date_range('1/1/1990', periods=N, freq='53s') s = Series(np.random.randn(N), index=rng) with pytest.raises(ValueError): s.asof(s.index[0], subset='foo')
def test_errors(self): s = Series( [1, 2, 3], index=[Timestamp("20130101"), Timestamp("20130103"), Timestamp("20130102")], ) # non-monotonic assert not s.index.is_monotonic with pytest.raises(ValueError, match="requires a sorted index"): s.asof(s.index[0]) # subset with Series N = 10 rng = date_range("1/1/1990", periods=N, freq="53s") s = Series(np.random.randn(N), index=rng) with pytest.raises(ValueError, match="not valid for Series"): s.asof(s.index[0], subset="foo")
def test_asof(self): # array or list or dates N = 50 rng = date_range('1/1/1990', periods=N, freq='53s') ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range('1/1/1990', periods=N * 3, freq='25s') result = ts.asof(dates) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] mask = (result.index >= lb) & (result.index < ub) rs = result[mask] self.assertTrue((rs == ts[lb]).all()) val = result[result.index[result.index >= ub][0]] self.assertEqual(ts[ub], val) self.ts[5:10] = np.NaN self.ts[15:20] = np.NaN val1 = self.ts.asof(self.ts.index[7]) val2 = self.ts.asof(self.ts.index[19]) self.assertEqual(val1, self.ts[4]) self.assertEqual(val2, self.ts[14]) # accepts strings val1 = self.ts.asof(str(self.ts.index[7])) self.assertEqual(val1, self.ts[4]) # in there self.assertEqual(self.ts.asof(self.ts.index[3]), self.ts[3]) # no as of value d = self.ts.index[0] - datetools.bday self.assertTrue(np.isnan(self.ts.asof(d)))
def test_asof_preserves_bool_dtype(self): # GH#16063 was casting bools to floats dti = date_range("2017-01-01", freq="MS", periods=4) ser = Series([True, False, True], index=dti[:-1]) ts = dti[-1] res = ser.asof([ts]) expected = Series([True], index=[ts]) tm.assert_series_equal(res, expected)
def test_asof_nanosecond_index_access(self): ts = Timestamp("20130101").value dti = DatetimeIndex([ts + 50 + i for i in range(100)]) ser = Series(np.random.randn(100), index=dti) first_value = ser.asof(ser.index[0]) # this used to not work bc parsing was done by dateutil that didn't # handle nanoseconds assert first_value == ser["2013-01-01 00:00:00.000000050+0000"] expected_ts = np.datetime64("2013-01-01 00:00:00.000000050", "ns") assert first_value == ser[Timestamp(expected_ts)]
def test_periodindex(self): from pandas import period_range, PeriodIndex # array or list or dates N = 50 rng = period_range("1/1/1990", periods=N, freq="H") ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range("1/1/1990", periods=N * 3, freq="37min") result = ts.asof(dates) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) assert notna(result).all() lb = ts.index[14] ub = ts.index[30] pix = PeriodIndex(result.index.values, freq="H") mask = (pix >= lb) & (pix < ub) rs = result[mask] assert (rs == ts[lb]).all() ts[5:10] = np.nan ts[15:20] = np.nan val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) assert val1 == ts[4] assert val2 == ts[14] # accepts strings val1 = ts.asof(str(ts.index[7])) assert val1 == ts[4] # in there assert ts.asof(ts.index[3]) == ts[3] # no as of value d = ts.index[0].to_timestamp() - offsets.BDay() assert isna(ts.asof(d))
def test_asof_periodindex(self): from pandas import period_range, PeriodIndex # array or list or dates N = 50 rng = period_range('1/1/1990', periods=N, freq='H') ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range('1/1/1990', periods=N * 3, freq='37min') result = ts.asof(dates) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) self.assertTrue(notnull(result).all()) lb = ts.index[14] ub = ts.index[30] pix = PeriodIndex(result.index.values, freq='H') mask = (pix >= lb) & (pix < ub) rs = result[mask] self.assertTrue((rs == ts[lb]).all()) ts[5:10] = np.NaN ts[15:20] = np.NaN val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) self.assertEqual(val1, ts[4]) self.assertEqual(val2, ts[14]) # accepts strings val1 = ts.asof(str(ts.index[7])) self.assertEqual(val1, ts[4]) # in there self.assertEqual(ts.asof(ts.index[3]), ts[3]) # no as of value d = ts.index[0].to_timestamp() - datetools.bday self.assertTrue(np.isnan(ts.asof(d)))
def test_periodindex(self): from pandas import period_range, PeriodIndex # array or list or dates N = 50 rng = period_range('1/1/1990', periods=N, freq='H') ts = Series(np.random.randn(N), index=rng) ts[15:30] = np.nan dates = date_range('1/1/1990', periods=N * 3, freq='37min') result = ts.asof(dates) assert notnull(result).all() lb = ts.index[14] ub = ts.index[30] result = ts.asof(list(dates)) assert notnull(result).all() lb = ts.index[14] ub = ts.index[30] pix = PeriodIndex(result.index.values, freq='H') mask = (pix >= lb) & (pix < ub) rs = result[mask] assert (rs == ts[lb]).all() ts[5:10] = np.nan ts[15:20] = np.nan val1 = ts.asof(ts.index[7]) val2 = ts.asof(ts.index[19]) assert val1 == ts[4] assert val2 == ts[14] # accepts strings val1 = ts.asof(str(ts.index[7])) assert val1 == ts[4] # in there assert ts.asof(ts.index[3]) == ts[3] # no as of value d = ts.index[0].to_timestamp() - offsets.BDay() assert isnull(ts.asof(d))
class AsOf(object): goal_time = 0.2 def setup(self): self.N = 10000 self.rng = date_range(start='1/1/1990', periods=self.N, freq='53s') self.ts = Series(np.random.randn(self.N), index=self.rng) self.dates = date_range(start='1/1/1990', periods=(self.N * 10), freq='5s') self.ts2 = self.ts.copy() self.ts2[250:5000] = np.nan self.ts3 = self.ts.copy() self.ts3[-5000:] = np.nan # test speed of pre-computing NAs. def time_asof(self): self.ts.asof(self.dates) # should be roughly the same as above. def time_asof_nan(self): self.ts2.asof(self.dates) # test speed of the code path for a scalar index # without *while* loop def time_asof_single(self): self.ts.asof(self.dates[0]) # test speed of the code path for a scalar index # before the start. should be the same as above. def time_asof_single_early(self): self.ts.asof(self.dates[0] - dt.timedelta(10)) # test the speed of the code path for a scalar index # with a long *while* loop. should still be much # faster than pre-computing all the NAs. def time_asof_nan_single(self): self.ts3.asof(self.dates[-1])