fixe for new data_freq formatting (ME and MS) and hack for allowing y…

…early data when asking for data aggr.

lilio/utils.py

@@ -116,6 +116,11 @@ def infer_input_data_freq(
         if data_freq is None:  # Manually infer the frequency
             data_freq = (data.time.values[1:] - data.time.values[:-1]).min()
 
+    # anoying switch from "2M" to "2ME" format in pandas > 2.2.
+    # We will need to adapt to this in the future.
+    if len(data_freq) in [3, 4] and data_freq[1:] in ["ME", "MS"]:
+        data_freq = data_freq.replace(data_freq[1:], "M")
+
     if isinstance(data_freq, str):
         data_freq.replace("-", "")  # Get the absolute frequency
 
@@ -170,8 +175,9 @@ def check_input_frequency(
     data_freq = infer_input_data_freq(data)
     calendar_freq = get_smallest_calendar_freq(calendar)
 
-    # if "label" in data.coords:
-    #     return
+    if data_freq == pd.Timedelta("365.25d") and calendar_freq == pd.Timedelta("1d"):
+        # Allow yearly (one-datapoint-per-year) data to be resampled to daily data.
+        return None
 
     if calendar_freq < data_freq:
         raise ValueError(

tests/test_resample.py

@@ -280,6 +280,27 @@ def test_resample_with_year_freq(
         resampled = resample(cal, series)
         assert all(np.equal(test_data, resampled.data.values)), "Data not equal."
 
+    def test_resample_with_one_datapoint_per_year(
+        self,
+    ):
+        """Testing resampling when you have only 1 datapoint per year."""
+        years = list(range(2019, 2022))
+        time_index = pd.to_datetime([f"{year}-02-01" for year in years])
+        test_data = np.random.random(len(time_index))
+        initseries = pd.Series(test_data, index=time_index, name="data1")
+        # The calendar will skip the last timestep because of how pd.intervals are
+        # defined (with left and right bounds). This is not a problem for resampling,
+        # but it is a problem for the user to be aware of.
+        series = initseries._append(
+            pd.Series([np.nan], index=[pd.to_datetime("2022-02-01")])
+        )
+        cal = Calendar(anchor="02-01")
+        cal.add_intervals("target", length="1d")
+        cal.map_to_data(series)
+        cal.get_intervals()
+        resampled = resample(cal, series)
+        assert all(np.equal(test_data, resampled.data.values)), "Data not equal."
+
 
 TOO_LOW_FREQ_ERR = r".*lower time resolution than the calendar.*"
 TOO_LOW_FREQ_WARN = r".*input data frequency is very close to the Calendar's freq.*"