anemoi-utils 0.3.14__tar.gz → 0.3.15__tar.gz

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: anemoi-utils
-Version: 0.3.14
+Version: 0.3.15
 Summary: A package to hold various functions to support training of ML models on ECMWF data.
 Author-email: "European Centre for Medium-Range Weather Forecasts (ECMWF)" <software.support@ecmwf.int>
 License:                                  Apache License

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/src/anemoi/utils/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.3.14'
-__version_tuple__ = version_tuple = (0, 3, 14)
+__version__ = version = '0.3.15'
+__version_tuple__ = version_tuple = (0, 3, 15)

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/src/anemoi/utils/dates.py

@@ -15,17 +15,7 @@ import isodate
 from .hindcasts import HindcastDatesTimes
 
 
-def normalise_frequency(frequency):
-    if isinstance(frequency, int):
-        return frequency
-    assert isinstance(frequency, str), (type(frequency), frequency)
-
-    unit = frequency[-1].lower()
-    v = int(frequency[:-1])
-    return {"h": v, "d": v * 24}[unit]
-
-
-def no_time_zone(date):
+def _no_time_zone(date):
     """Remove time zone information from a date.
 
     Parameters
@@ -43,13 +33,15 @@ def no_time_zone(date):
 
 
 # this function is use in anemoi-datasets
-def as_datetime(date):
+def as_datetime(date, keep_time_zone=False):
     """Convert a date to a datetime object, removing any time zone information.
 
     Parameters
     ----------
     date : datetime.date or datetime.datetime or str
         The date to convert.
+    keep_time_zone : bool, optional
+        If True, the time zone information is kept, by default False.
 
     Returns
     -------
@@ -57,57 +49,98 @@ def as_datetime(date):
         The datetime object.
     """
 
+    tidy = _no_time_zone if not keep_time_zone else lambda x: x
+
     if isinstance(date, datetime.datetime):
-        return no_time_zone(date)
+        return tidy(date)
 
     if isinstance(date, datetime.date):
-        return no_time_zone(datetime.datetime(date.year, date.month, date.day))
+        return tidy(datetime.datetime(date.year, date.month, date.day))
 
     if isinstance(date, str):
-        return no_time_zone(datetime.datetime.fromisoformat(date))
+        return tidy(datetime.datetime.fromisoformat(date))
 
     raise ValueError(f"Invalid date type: {type(date)}")
 
 
-def _compress_dates(dates):
-    dates = sorted(dates)
-    if len(dates) < 3:
-        yield dates
-        return
+def frequency_to_timedelta(frequency):
+    """Convert a frequency to a timedelta object.
+
+    Parameters
+    ----------
+    frequency : int or str or datetime.timedelta
+        The frequency to convert. If an integer, it is assumed to be in hours. If a string, it can be in the format:
+
+        - "1h" for 1 hour
+        - "1d" for 1 day
+        - "1m" for 1 minute
+        - "1s" for 1 second
+        - "1:30" for 1 hour and 30 minutes
+        - "1:30:10" for 1 hour, 30 minutes and 10 seconds
+        - "PT10M" for 10 minutes (ISO8601)
 
-    prev = first = dates.pop(0)
-    curr = dates.pop(0)
-    delta = curr - prev
-    while curr - prev == delta:
-        prev = curr
-        if not dates:
-            break
-        curr = dates.pop(0)
+        If a timedelta object is provided, it is returned as is.
+
+    Returns
+    -------
+    datetime.timedelta
+        The timedelta object.
+
+    Raises
+    ------
+    ValueError
+        Exception raised if the frequency cannot be converted to a timedelta.
+    """
+
+    if isinstance(frequency, datetime.timedelta):
+        return frequency
+
+    if isinstance(frequency, int):
+        return datetime.timedelta(hours=frequency)
 
-    yield (first, prev, delta)
-    if dates:
-        yield from _compress_dates([curr] + dates)
+    assert isinstance(frequency, str), (type(frequency), frequency)
 
+    try:
+        return frequency_to_timedelta(int(frequency))
+    except ValueError:
+        pass
 
-def compress_dates(dates):
-    dates = [as_datetime(_) for _ in dates]
-    result = []
+    if re.match(r"^\d+[hdms]$", frequency, re.IGNORECASE):
+        unit = frequency[-1].lower()
+        v = int(frequency[:-1])
+        unit = {"h": "hours", "d": "days", "s": "seconds", "m": "minutes"}[unit]
+        return datetime.timedelta(**{unit: v})
 
-    for n in _compress_dates(dates):
-        if isinstance(n, list):
-            result.extend([str(_) for _ in n])
-        else:
-            result.append(" ".join([str(n[0]), "to", str(n[1]), "by", str(n[2])]))
+    m = frequency.split(":")
+    if len(m) == 2:
+        return datetime.timedelta(hours=int(m[0]), minutes=int(m[1]))
 
-    return result
+    if len(m) == 3:
+        return datetime.timedelta(hours=int(m[0]), minutes=int(m[1]), seconds=int(m[2]))
 
+    # ISO8601
+    try:
+        return isodate.parse_duration(frequency)
+    except isodate.isoerror.ISO8601Error:
+        pass
 
-def print_dates(dates):
-    print(compress_dates(dates))
+    raise ValueError(f"Cannot convert frequency {frequency} to timedelta")
 
 
 def frequency_to_string(frequency):
-    # TODO: use iso8601
+    """Convert a frequency (i.e. a datetime.timedelta) to a string.
+
+    Parameters
+    ----------
+    frequency : datetime.timedelta
+        The frequency to convert.
+
+    Returns
+    -------
+    str
+        A string representation of the frequency.
+    """
+
     frequency = frequency_to_timedelta(frequency)
 
     total_seconds = frequency.total_seconds()
@@ -141,48 +174,23 @@ def frequency_to_string(frequency):
     return str(frequency)
 
 
-def frequency_to_timedelta(frequency):
-    # TODO: use iso8601 or check pytimeparse
-
-    if isinstance(frequency, datetime.timedelta):
-        return frequency
+def frequency_to_seconds(frequency):
+    """Convert a frequency to seconds.
 
-    if isinstance(frequency, int):
-        return datetime.timedelta(hours=frequency)
-
-    assert isinstance(frequency, str), (type(frequency), frequency)
-
-    try:
-        return frequency_to_timedelta(int(frequency))
-    except ValueError:
-        pass
-
-    if re.match(r"^\d+[hdms]$", frequency, re.IGNORECASE):
-        unit = frequency[-1].lower()
-        v = int(frequency[:-1])
-        unit = {"h": "hours", "d": "days", "s": "seconds", "m": "minutes"}[unit]
-        return datetime.timedelta(**{unit: v})
-
-    m = frequency.split(":")
-    if len(m) == 2:
-        return datetime.timedelta(hours=int(m[0]), minutes=int(m[1]))
-
-    if len(m) == 3:
-        return datetime.timedelta(hours=int(m[0]), minutes=int(m[1]), seconds=int(m[2]))
-
-    # ISO8601
-    try:
-        return isodate.parse_duration(frequency)
-    except isodate.isoerror.ISO8601Error:
-        pass
-
-    raise ValueError(f"Cannot convert frequency {frequency} to timedelta")
+    Parameters
+    ----------
+    frequency : _type_
+        _description_
 
+    Returns
+    -------
+    int
+        Number of seconds.
+    """
 
-def normalize_date(x):
-    if isinstance(x, str):
-        return no_time_zone(datetime.datetime.fromisoformat(x))
-    return x
+    result = frequency_to_timedelta(frequency).total_seconds()
+    assert int(result) == result, result
+    return int(result)
 
 
 DOW = {
@@ -261,7 +269,7 @@ class DateTimes:
         """
         self.start = as_datetime(start)
         self.end = as_datetime(end)
-        self.increment = datetime.timedelta(hours=increment)
+        self.increment = frequency_to_timedelta(increment)
         self.day_of_month = _make_day(day_of_month)
         self.day_of_week = _make_week(day_of_week)
         self.calendar_months = _make_months(calendar_months)
@@ -392,8 +400,7 @@ def datetimes_factory(*args, **kwargs):
 
         kwargs = kwargs.copy()
         if "frequency" in kwargs:
-            freq = kwargs.pop("frequency")
-            kwargs["increment"] = normalise_frequency(freq)
+            kwargs["increment"] = kwargs.pop("frequency")
         return DateTimes(**kwargs)
 
     if not any((isinstance(x, dict) or isinstance(x, list)) for x in args):

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/src/anemoi/utils/humanize.py

@@ -15,6 +15,8 @@ import re
 import warnings
 from collections import defaultdict
 
+from anemoi.utils.dates import as_datetime
+
 
 def bytes_to_human(n: float) -> str:
     """Convert a number of bytes to a human readable string
@@ -625,3 +627,60 @@ def shorten_list(lst, max_length=5):
         if isinstance(lst, tuple):
             return tuple(result)
         return result
+
+
+def _compress_dates(dates):
+    dates = sorted(dates)
+    if len(dates) < 3:
+        yield dates
+        return
+
+    prev = first = dates.pop(0)
+    curr = dates.pop(0)
+    delta = curr - prev
+    while curr - prev == delta:
+        prev = curr
+        if not dates:
+            break
+        curr = dates.pop(0)
+
+    yield (first, prev, delta)
+    if dates:
+        yield from _compress_dates([curr] + dates)
+
+
+def compress_dates(dates):
+    """Compress a list of dates into a human-readable format.
+
+    Parameters
+    ----------
+    dates : list
+        A list of dates, as datetime objects or strings.
+
+    Returns
+    -------
+    str
+        A human-readable string representing the compressed dates.
+    """
+
+    dates = [as_datetime(_) for _ in dates]
+    result = []
+
+    for n in _compress_dates(dates):
+        if isinstance(n, list):
+            result.extend([str(_) for _ in n])
+        else:
+            result.append(" ".join([str(n[0]), "to", str(n[1]), "by", str(n[2])]))
+
+    return result
+
+
+def print_dates(dates):
+    """Print a list of dates in a human-readable format.
+
+    Parameters
+    ----------
+    dates : list
+        A list of dates, as datetime objects or strings.
+    """
+    print(compress_dates(dates))

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/src/anemoi_utils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: anemoi-utils
-Version: 0.3.14
+Version: 0.3.15
 Summary: A package to hold various functions to support training of ML models on ECMWF data.
 Author-email: "European Centre for Medium-Range Weather Forecasts (ECMWF)" <software.support@ecmwf.int>
 License:                                  Apache License

{anemoi_utils-0.3.14 → anemoi_utils-0.3.15}/src/anemoi_utils.egg-info/SOURCES.txt

@@ -51,4 +51,5 @@ src/anemoi_utils.egg-info/entry_points.txt
 src/anemoi_utils.egg-info/requires.txt
 src/anemoi_utils.egg-info/top_level.txt
 tests/test_dates.py
+tests/test_frequency.py
 tests/test_utils.py

anemoi_utils-0.3.15/tests/test_frequency.py

@@ -0,0 +1,37 @@
+# (C) Copyright 2023 European Centre for Medium-Range Weather Forecasts.
+# This software is licensed under the terms of the Apache Licence Version 2.0
+# which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
+# In applying this licence, ECMWF does not waive the privileges and immunities
+# granted to it by virtue of its status as an intergovernmental organisation
+# nor does it submit to any jurisdiction.
+
+import datetime
+
+from anemoi.utils.dates import frequency_to_string
+from anemoi.utils.dates import frequency_to_timedelta
+
+
+def test_frequency_to_string():
+    assert frequency_to_string(datetime.timedelta(hours=1)) == "1h"
+    assert frequency_to_string(datetime.timedelta(hours=1, minutes=30)) == "1:30:00"
+    assert frequency_to_string(datetime.timedelta(days=10)) == "10d"
+    assert frequency_to_string(datetime.timedelta(minutes=10)) == "10m"
+    assert frequency_to_string(datetime.timedelta(minutes=90)) == "1:30:00"
+
+
+def test_frequency_to_timedelta():
+    assert frequency_to_timedelta("1s") == datetime.timedelta(seconds=1)
+    assert frequency_to_timedelta("3m") == datetime.timedelta(minutes=3)
+    assert frequency_to_timedelta("1h") == datetime.timedelta(hours=1)
+    assert frequency_to_timedelta("3d") == datetime.timedelta(days=3)
+    assert frequency_to_timedelta("90m") == datetime.timedelta(hours=1, minutes=30)
+    assert frequency_to_timedelta("0:30") == datetime.timedelta(minutes=30)
+    assert frequency_to_timedelta("0:30:10") == datetime.timedelta(minutes=30, seconds=10)
+    assert frequency_to_timedelta("1:30:10") == datetime.timedelta(hours=1, minutes=30, seconds=10)
+
+    assert frequency_to_timedelta("PT10M") == datetime.timedelta(minutes=10)
+
+
+if __name__ == "__main__":
+    test_frequency_to_string()
+    test_frequency_to_timedelta()