Change all freqs for newest syntax possible - fix were appropriate

docs/notebooks/example.ipynb

@@ -238,7 +238,7 @@
     "Almost all `xclim` indicators convert daily data to lower time frequencies, such as seasonal or annual values. This is done using `xarray.DataArray.resample` method. Resampling creates a grouped object over which you apply a reduction operation (e.g. mean, min, max). The list of available frequency is given in the link below, but the most often used are:\n",
     "\n",
     "- `YS`: annual starting in January\n",
-    "- `YS-JUL`: annual starting in July\n",
+    "- `AS-JUL`: annual starting in July\n",
     "- `MS`: monthly\n",
     "- `QS-DEC`: seasonal starting in December\n",
     "\n",

docs/notebooks/xclim_training/XCLIM_calculate_index-Exemple.ipynb

@@ -248,7 +248,7 @@
     "All `xclim` indicators convert daily data to lower time frequencies, such as monthly or annual values. This is done using `xarray.DataArray.resample` method. Resampling creates a grouped object over which you apply a reduction operation (e.g. mean, min, max). The list of available frequency is given in the link below, but the most often used are: \n",
     "\n",
     "- YS: annual starting in January\n",
-    "- YS-JUL: annual starting in July\n",
+    "- AS-JUL: annual starting in July\n",
     "- MS: monthly\n",
     "- QS-DEC: seasonal starting in December\n",
     "- 7D: 7 day (weekly)\n",

pyproject.toml

@@ -44,8 +44,8 @@ dependencies = [
   "lmoments3>=1.0.5",
   "numba",
   "numpy>=1.16",
-  "pandas>=0.23,<2.0; python_version == '3.8'",
-  "pandas>=0.23; python_version >= '3.9'",
+  "pandas>=1.0,<2.0; python_version == '3.8'",
+  "pandas>=1.0; python_version >= '3.9'",
   "pint>=0.10",
   "pyyaml",
   "scikit-learn>=0.21.3",

tests/test_atmos.py

@@ -272,7 +272,7 @@ def test_wind_power_potential_from_3h_series():
     from xclim.testing.helpers import test_timeseries
 
     w = test_timeseries(
-        np.ones(96) * 15, variable="sfcWind", start="7/1/2000", units="m s-1", freq="3H"
+        np.ones(96) * 15, variable="sfcWind", start="7/1/2000", units="m s-1", freq="3h"
     )
     out = atmos.wind_power_potential(wind_speed=w)
 

tests/test_calendar.py

@@ -57,7 +57,7 @@ def da(index):
     )
 
 
-@pytest.mark.parametrize("freq", ["6480H", "302431T", "23144781S"])
+@pytest.mark.parametrize("freq", ["6480h", "302431min", "23144781s"])
 def test_time_bnds(freq, datetime_index, cftime_index):
     da_datetime = da(datetime_index).resample(time=freq)
     da_cftime = da(cftime_index).resample(time=freq)
@@ -146,7 +146,7 @@ def test_percentile_doy_invalid():
     tas = xr.DataArray(
         [0, 1],
         dims=("time",),
-        coords={"time": pd.date_range("2000-01-01", periods=2, freq="H")},
+        coords={"time": pd.date_range("2000-01-01", periods=2, freq="h")},
     )
     with pytest.raises(ValueError):
         percentile_doy(tas)
@@ -155,10 +155,10 @@ def test_percentile_doy_invalid():
 @pytest.mark.parametrize(
     "freqA,op,freqB,exp",
     [
-        ("D", ">", "H", True),
+        ("D", ">", "h", True),
         ("2YS", "<=", "QS-DEC", False),
         ("4W", "==", "3W", False),
-        ("24H", "==", "D", True),
+        ("24h", "==", "D", True),
     ],
 )
 def test_compare_offsets(freqA, op, freqB, exp):
@@ -275,8 +275,8 @@ def test_get_calendar_errors(obj):
         ("standard", "noleap", True, "D"),
         ("noleap", "default", True, "D"),
         ("noleap", "all_leap", False, "D"),
-        ("proleptic_gregorian", "noleap", False, "4H"),
-        ("default", "noleap", True, "4H"),
+        ("proleptic_gregorian", "noleap", False, "4h"),
+        ("default", "noleap", True, "4h"),
     ],
 )
 def test_convert_calendar(source, target, target_as_str, freq):
@@ -311,7 +311,7 @@ def test_convert_calendar(source, target, target_as_str, freq):
     [
         ("standard", "360_day", "D"),
         ("360_day", "default", "D"),
-        ("proleptic_gregorian", "360_day", "4H"),
+        ("proleptic_gregorian", "360_day", "4h"),
     ],
 )
 @pytest.mark.parametrize("align_on", ["date", "year"])
@@ -356,7 +356,7 @@ def test_convert_calendar_360_days_random():
         dims=("time",),
         coords={
             "time": date_range(
-                "2004-01-01", "2004-12-31T23:59:59", freq="12H", calendar="default"
+                "2004-01-01", "2004-12-31T23:59:59", freq="12h", calendar="default"
             )
         },
     )
@@ -365,7 +365,7 @@ def test_convert_calendar_360_days_random():
         dims=("time",),
         coords={
             "time": date_range(
-                "2004-01-01", "2004-12-30T23:59:59", freq="12H", calendar="360_day"
+                "2004-01-01", "2004-12-30T23:59:59", freq="12h", calendar="360_day"
             )
         },
     )
@@ -394,7 +394,7 @@ def test_convert_calendar_360_days_random():
     "source,target,freq",
     [
         ("standard", "noleap", "D"),
-        ("noleap", "default", "4H"),
+        ("noleap", "default", "4h"),
         ("noleap", "all_leap", "M"),
         ("360_day", "noleap", "D"),
         ("noleap", "360_day", "D"),
@@ -415,7 +415,7 @@ def test_convert_calendar_missing(source, target, freq):
         np.linspace(0, 1, src.size), dims=("time",), coords={"time": src}
     )
     out = convert_calendar(da_src, target, missing=np.nan, align_on="date")
-    assert xr.infer_freq(out.time) == freq
+    assert fix_freq(xr.infer_freq(out.time), warn=False) == freq
     if source == "360_day":
         assert out.time[-1].dt.day == 31
 
@@ -624,7 +624,7 @@ def test_doy_to_days_since():
     [
         ("4AS-JUL", 4, "A", True, "JUL"),
         ("M", 1, "M", False, None),
-        ("YS", 1, "A", True, "JAN"),
+        ("YS", 1, "Y", True, "JAN"),
         ("3A", 3, "A", False, "DEC"),
         ("D", 1, "D", True, None),
         ("3W", 21, "D", True, None),
@@ -710,11 +710,14 @@ def test_convert_doy():
     "freq,exp,to,warn",
     [
         ("Y", "YE-DEC", "new", "end-anchored"),
-        ("YS", "YS-JAN", "new", "Pandas changed"),
+        ("AS", "YS-JAN", "new", "Pandas changed"),
         ("T", "min", "new", "T should now be written min"),
         ("56S", "56s", "new", "S should now be written s"),
         ("MS", "MS", "new", None),
-        ("AS-MAR", "YS-MAR", "old", None),
+        ("Y", "A-DEC", "inter", None),
+        ("AS", "AS-JAN", "inter", None),
+        ("T", "min", "inter", "T should now be written min"),
+        ("AS-MAR", "AS-MAR", "old", None),
         ("min", "T", "old", None),
         ("4Q-DEC", "4Q-DEC", "old", None),
     ],

tests/test_checks.py

@@ -149,25 +149,25 @@ def test_check_hourly(self, date_range, random):
         }
 
         n = 100
-        time = date_range("2000-01-01", freq="H", periods=n)
+        time = date_range("2000-01-01", freq="h", periods=n)
         da = xr.DataArray(random.random(n), [("time", time)], attrs=tas_attrs)
-        datachecks.check_freq(da, "H")
+        datachecks.check_freq(da, "h")
 
-        time = date_range("2000-01-01", freq="3H", periods=n)
+        time = date_range("2000-01-01", freq="3h", periods=n)
         da = xr.DataArray(random.random(n), [("time", time)], attrs=tas_attrs)
         with pytest.raises(ValidationError):
-            datachecks.check_freq(da, "H")
+            datachecks.check_freq(da, "h")
 
         with pytest.raises(ValidationError):
-            datachecks.check_freq(da, ["H", "D"])
+            datachecks.check_freq(da, ["h", "D"])
 
-        datachecks.check_freq(da, "H", strict=False)
-        datachecks.check_freq(da, ["H", "D"], strict=False)
-        datachecks.check_freq(da, "3H")
-        datachecks.check_freq(da, ["H", "3H"])
+        datachecks.check_freq(da, "h", strict=False)
+        datachecks.check_freq(da, ["h", "D"], strict=False)
+        datachecks.check_freq(da, "3h")
+        datachecks.check_freq(da, ["h", "3h"])
 
         with pytest.raises(ValidationError, match="Unable to infer the frequency of"):
-            datachecks.check_freq(da.where(da.time.dt.dayofyear != 5, drop=True), "3H")
+            datachecks.check_freq(da.where(da.time.dt.dayofyear != 5, drop=True), "3h")
 
     def test_common_time(self, tas_series, date_range, random):
         tas_attrs = {
@@ -176,7 +176,7 @@ def test_common_time(self, tas_series, date_range, random):
         }
 
         n = 100
-        time = date_range("2000-01-01", freq="H", periods=n)
+        time = date_range("2000-01-01", freq="h", periods=n)
         da = xr.DataArray(random.random(n), [("time", time)], attrs=tas_attrs)
 
         # No freq
@@ -187,7 +187,7 @@ def test_common_time(self, tas_series, date_range, random):
             datachecks.check_common_time([db, da])
 
         # Not same freq
-        time = date_range("2000-01-01", freq="6H", periods=n)
+        time = date_range("2000-01-01", freq="6h", periods=n)
         db = xr.DataArray(random.random(n), [("time", time)], attrs=tas_attrs)
         with pytest.raises(ValidationError, match="Inputs have different frequencies"):
             datachecks.check_common_time([db, da])
@@ -197,6 +197,6 @@ def test_common_time(self, tas_series, date_range, random):
         db["time"] = db.time + pd.Timedelta(30, "min")
         with pytest.raises(
             ValidationError,
-            match=r"All inputs have the same frequency \(H\), but they are not anchored on the same minutes",
+            match=r"All inputs have the same frequency \(h\), but they are not anchored on the same minutes",
         ):
             datachecks.check_common_time([db, da])

tests/test_generic_indicators.py

@@ -104,7 +104,7 @@ def test_missing(self, ndq_series):
         np.testing.assert_array_equal(out.sel(time="1902").isnull(), True)
 
     def test_3hourly(self, pr_hr_series, random):
-        pr = pr_hr_series(random.random(366 * 24)).resample(time="3H").mean()
+        pr = pr_hr_series(random.random(366 * 24)).resample(time="3h").mean()
         out = generic.stats(pr, freq="MS", op="var")
         assert out.units == "kg^2 m-4 s-2"
         assert out.long_name == "Variance of variable"

tests/test_helpers.py

@@ -88,7 +88,7 @@ def test_day_lengths(method):
 
 
 def test_cosine_of_solar_zenith_angle():
-    time = xr.date_range("1900-01-01T00:30", "1900-01-03", freq="H")
+    time = xr.date_range("1900-01-01T00:30", "1900-01-03", freq="h")
     time = xr.DataArray(time, dims=("time",), coords={"time": time}, name="time")
     lat = xr.DataArray(
         [0, 45, 70], dims=("site",), name="lat", attrs={"units": "degree_north"}

tests/test_indices.py

@@ -974,7 +974,7 @@ def test_southhemisphere(self, tas_series):
         tas = tas_series(np.zeros(2 * 365), start="2000/1/1")
         warm_period = tas.sel(time=slice("2000-11-01", "2001-03-01"))
         tas = tas.where(~tas.time.isin(warm_period.time), 280)
-        gsl = xci.growing_season_length(tas, mid_date="01-01", freq="AS-Jul")
+        gsl = xci.growing_season_length(tas, mid_date="01-01", freq="AS-JUL")
         np.testing.assert_array_equal(gsl.sel(time="2000-07-01"), 121)
 
 

tests/test_missing.py

@@ -17,9 +17,9 @@ class TestMissingBase:
     def test_3hourly_input(self, random):
         """Creating array with 21 days of 3h"""
         n = 21 * 8
-        time = xr.cftime_range(start="2002-01-01", periods=n, freq="3H")
+        time = xr.cftime_range(start="2002-01-01", periods=n, freq="3h")
         ts = xr.DataArray(random.random(n), dims="time", coords={"time": time})
-        mb = missing.MissingBase(ts, freq="MS", src_timestep="3H")
+        mb = missing.MissingBase(ts, freq="MS", src_timestep="3h")
         # Make sure count is 31  * 8, because we're requesting a MS freq.
         assert mb.count == 31 * 8
 
@@ -35,7 +35,7 @@ def test_monthly_input(self, random):
         n = 5
         time = xr.cftime_range(start="2002-06-01", periods=n, freq="MS")
         ts = xr.DataArray(random.random(n), dims="time", coords={"time": time})
-        mb = missing.MissingBase(ts, freq="AS", src_timestep="M", season="JJA")
+        mb = missing.MissingBase(ts, freq="YS", src_timestep="M", season="JJA")
         assert mb.count == 3
 
     def test_seasonal_input(self, random):
@@ -139,14 +139,14 @@ def test_no_freq(self, tasmin_series):
         t = list(range(31))
         t.pop(5)
         ts2 = ts.isel(time=t)
-        miss = missing.missing_any(ts2, freq=None, src_timestep="H")
+        miss = missing.missing_any(ts2, freq=None, src_timestep="h")
         np.testing.assert_array_equal(miss, True)
 
         # With indexer
         miss = missing.missing_any(ts, freq=None, month=[7])
         np.testing.assert_array_equal(miss, False)
 
-        miss = missing.missing_any(ts2, freq=None, month=[7], src_timestep="H")
+        miss = missing.missing_any(ts2, freq=None, month=[7], src_timestep="h")
         np.testing.assert_array_equal(miss, True)
 
     def test_hydro(self, open_dataset):
@@ -264,23 +264,23 @@ def pr(self, pr_hr_series):
 
     def test_any(self, pr_hr_series):
         pr = self.pr(pr_hr_series)
-        out = missing.missing_any(pr, "D", src_timestep="H")
+        out = missing.missing_any(pr, "D", src_timestep="h")
         np.testing.assert_array_equal(
             out,
             [True] + 8 * [False] + [True],
         )
 
     def test_pct(self, pr_hr_series):
         pr = self.pr(pr_hr_series)
-        out = missing.missing_pct(pr, "D", src_timestep="H", tolerance=0.1)
+        out = missing.missing_pct(pr, "D", src_timestep="h", tolerance=0.1)
         np.testing.assert_array_equal(
             out,
             9 * [False] + [True],
         )
 
     def test_at_least_n_valid(self, pr_hr_series):
         pr = self.pr(pr_hr_series)
-        out = missing.at_least_n_valid(pr, "D", src_timestep="H", n=20)
+        out = missing.at_least_n_valid(pr, "D", src_timestep="h", n=20)
         np.testing.assert_array_equal(
             out,
             9 * [False] + [True],

tests/test_precip.py

@@ -575,7 +575,7 @@ def test_days_over_precip_thresh__seasonal_indexer(open_dataset):
     per = pr.quantile(0.8, "time", keep_attrs=True)
     # WHEN
     out = atmos.days_over_precip_thresh(
-        pr, per, freq="AS", date_bounds=("01-10", "12-31")
+        pr, per, freq="YS", date_bounds=("01-10", "12-31")
     )
     # THEN
     np.testing.assert_almost_equal(out[0], np.array([81.0, 66.0, 66.0, 75.0]))

tests/test_temperature.py

@@ -1144,7 +1144,7 @@ def test_tx90p__seasonal_indexer(self, tasmax_series):
         # create cold spell in june
         tas[175:180] = 1
         # WHEN
-        out = atmos.tx90p(tas, t90, freq="AS", season="JJA")
+        out = atmos.tx90p(tas, t90, freq="YS", season="JJA")
         # THEN
         assert out[0] == 87  # non regression test
 
@@ -1489,7 +1489,7 @@ def test_simple(self, tas_series):
 
         tg = tas_series(a + K2C, start="1/1/2000")
 
-        out = atmos.cold_spell_frequency(tg, freq="AS")
+        out = atmos.cold_spell_frequency(tg, freq="YS")
         np.testing.assert_array_equal(out, 1)
 
 
@@ -1500,7 +1500,7 @@ def test_simple(self, tas_series):
 
         tg = tas_series(a + K2C, start="1/1/2000")
 
-        out = atmos.cold_spell_max_length(tg, freq="AS")
+        out = atmos.cold_spell_max_length(tg, freq="YS")
         np.testing.assert_array_equal(out, 5)
 
 
@@ -1511,5 +1511,5 @@ def test_simple(self, tas_series):
 
         tg = tas_series(a + K2C, start="1/1/2000")
 
-        out = atmos.cold_spell_total_length(tg, freq="AS")
+        out = atmos.cold_spell_total_length(tg, freq="YS")
         np.testing.assert_array_equal(out, 8)

xclim/core/bootstrapping.py

@@ -13,7 +13,7 @@
 
 import xclim.core.utils
 
-from .calendar import convert_calendar, parse_offset, percentile_doy
+from .calendar import construct_offset, convert_calendar, parse_offset, percentile_doy
 
 BOOTSTRAP_DIM = "_bootstrap"
 
@@ -202,12 +202,7 @@ def bootstrap_func(compute_index_func: Callable, **kwargs) -> xarray.DataArray:
 
 def _get_bootstrap_freq(freq):
     _, base, start_anchor, anchor = parse_offset(freq)  # noqa
-    bfreq = "A"
-    if start_anchor:
-        bfreq += "S"
-    if base in ["A", "Q"] and anchor is not None:
-        bfreq = f"{bfreq}-{anchor}"
-    return bfreq
+    return construct_offset(1, "Y", start_anchor, anchor)
 
 
 def _get_year_label(year_dt) -> str: