pthelma 1.1.0__tar.gz → 2.1.0__tar.gz

{pthelma-1.1.0 → pthelma-2.1.0}/.github/workflows/run-tests.yml

@@ -37,6 +37,7 @@ jobs:
 
     - name: Install Dependencies
       run: |
+        sudo apt-get update
         sudo apt-get install -y gdal-bin libgdal-dev postgresql-14-postgis-3
         source ~/.venv/bin/activate
         # numpy<2 is needed for gdal to contain support for gdal array

{pthelma-1.1.0 → pthelma-2.1.0}/CHANGELOG.rst

@@ -2,6 +2,20 @@
 Changelog
 =========
 
+
+2.1.0 (2025-01-10)
+==================
+
+* haggregate: The ``missing_flag`` parameter to ``aggregate()`` can now
+  include the substring "{}", which will be replaced with the number of
+  missing values.
+
+2.0.0 (2024-12-04)
+==================
+
+We now use "h" instead of "H", and generally we use modern pandas time
+step ("frequency") designations.
+
 1.1.0 (2024-12-01)
 ==================
 

{pthelma-1.1.0/src/pthelma.egg-info → pthelma-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: pthelma
-Version: 1.1.0
+Version: 2.1.0
 Summary: Utilities for hydrological and meteorological time series processing
 Author-email: Antonis Christofides <antonis@antonischristofides.com>
 Maintainer-email: Antonis Christofides <antonis@antonischristofides.com>

{pthelma-1.1.0 → pthelma-2.1.0}/docs/evaporation/api.rst

@@ -44,7 +44,7 @@ evaporation API
    (negative for west or south). Only *latitude* needs to be specified
    for calculating daily evaporation.
 
-   *time_step* is a string: "D" for daily, "H" for hourly.
+   *time_step* is a string: "D" for daily, "h" for hourly.
 
    In order to estimate the outgoing radiation, the ratio of incoming
    solar radiation to clear sky solar radiation is used as a

{pthelma-1.1.0 → pthelma-2.1.0}/docs/haggregate/api.rst

@@ -34,7 +34,14 @@ haggregate API
    than *min_count* source records corresponding, the resulting
    destination record is null; otherwise, the destination record is
    derived even though some records are missing.  In that case, the flag
-   specified by *missing_flag* is raised in the destination record.
+   specified by *missing_flag* is raised in the destination record. If
+   missing flag contains the string ``{}``, it is replaced with the
+   number of missing records. The recommended setting for *missing_flag*
+   is ``MISSING{}``, which, for example, will result in ``MISSING3``
+   when three records are missing. The default for *missing_flag* is
+   ``MISS`` for backwards compatibility (it was ``MISS`` for some years,
+   however this was undocumented), but this is deprecated; use
+   ``MISSING{}``.
 
    If an error occurs, such as *ts* not having a strictly regular step,
    :exc:`AggregateError` (or a subclass) is raised.

{pthelma-1.1.0 → pthelma-2.1.0}/docs/haggregate/usage.rst

@@ -53,9 +53,9 @@ explanatory comments that follow it:
     loglevel = INFO
     logfile = /var/log/haggregate/haggregate.log
     base_dir = /var/cache/timeseries/
-    target_step = 1H
+    target_step = 1h
     min_count = 2
-    missing_flag = DATEINSERT
+    missing_flag = MISSING{}
 
     [temperature]
     source_file = temperature-10min.hts
@@ -69,7 +69,7 @@ explanatory comments that follow it:
 
 With the above configuration file, ``haggregate`` will log information
 in the file specified by ``logfile``. It will aggregate the
-specified time series into hourly (``1H``). The filenames specified with
+specified time series into hourly (``1h``). The filenames specified with
 :option:`source_file` and :option:`target_file` are relative to
 ``base_dir``. For the temperature, source records will be
 averaged, whereas for rainfall they will be summed.
@@ -108,8 +108,8 @@ General parameters
 .. option:: target_step
 
    A string specifying the target time step, as a pandas "frequency".
-   Examples of steps are "1D" for day, "1H" for hour, "1T" or "1min" for
-   minute. You can also use larger multipliers, like "30T" for 30 minutes.
+   Examples of steps are "1D" for day, "1h" for hour, "1min" for
+   minute. You can also use larger multipliers, like "30min" for 30 minutes.
    The program hasn't been tested for monthly or larger time steps.
 
 .. option:: target_timestamp_offset
@@ -133,7 +133,8 @@ General parameters
    to a destination record, the resulting destination record is null;
    otherwise, the destination record is derived even though some records
    are missing. In that case, the flag specified by
-   :option:`missing_flag` is raised in the destination record.
+   :option:`missing_flag` is raised in the destination record. See
+   :meth:`~haggregate.aggregate` for details on :option:`missing_flag`.
 
 Time series sections
 --------------------

{pthelma-1.1.0 → pthelma-2.1.0}/docs/htimeseries.rst

@@ -250,8 +250,8 @@ The parameters available are:
 
 **Time_step**
     In version 5, a pandas "frequency" string such as ``10min`` (10
-    minutes), ``H`` (hour), or ``2M`` (two months). If missing or empty,
-    the time series is without time step.
+    minutes), ``1h`` (one hour), or ``2M`` (two months). If missing or
+    empty, the time series is without time step.
 
     Up to version 4, a comma-separated pair of integers; the number of
     minutes and months in the time step (one of the two must be zero).

{pthelma-1.1.0 → pthelma-2.1.0}/docs/rocc.rst

@@ -18,7 +18,7 @@ rocc - Rate-of-change check for time series
          thresholds=(
             Threshold("10min", 10),
             Threshold("20min", 15),
-            Threshold("H", 40),
+            Threshold("h", 40),
          ),
          symmetric=True,
          flag="MYFLAG",

{pthelma-1.1.0 → pthelma-2.1.0}/src/enhydris_cache/cli.py

@@ -2,7 +2,6 @@ import configparser
 import datetime as dt
 import logging
 import os
-import sys
 import traceback
 
 import click
@@ -81,7 +80,6 @@ class AppConfig:
         try:
             self._parse_config()
         except (OSError, configparser.Error) as e:
-            sys.stderr.write(str(e))
             raise click.ClickException(str(e))
 
     def _parse_config(self):

{pthelma-1.1.0 → pthelma-2.1.0}/src/evaporation/cli.py

@@ -2,7 +2,6 @@ import configparser
 import datetime as dt
 import logging
 import os
-import sys
 import traceback
 from glob import glob
 from io import StringIO
@@ -100,7 +99,6 @@ class AppConfig:
         try:
             self._parse_config()
         except (OSError, configparser.Error) as e:
-            sys.stderr.write(str(e))
             raise click.ClickException(str(e))
 
     def _parse_config(self):
@@ -155,10 +153,10 @@ class AppConfig:
         self.time_step = s
 
     def _check_time_step(self, s):
-        if s not in ("D", "H"):
+        if s not in ("D", "h"):
             raise WrongValueError(
                 '"{}" is not an appropriate time step; in this version of '
-                "vaporize, the step must be either D or H.".format(s)
+                "vaporize, the step must be either D or h.".format(s)
             )
 
     def _parse_unit_converters(self):
@@ -412,11 +410,11 @@ class ProcessAtPoint:
         self.pet.unit = "mm"
         self.pet.timezone = self.timezone
         self.pet.variable = "Potential Evapotranspiration"
-        self.pet.precision = 2 if self.config.time_step == "H" else 1
+        self.pet.precision = 2 if self.config.time_step == "h" else 1
         self.pet.location = self.location
 
     def _determine_variables_to_use_in_calculation(self):
-        if self.config.time_step == "H":
+        if self.config.time_step == "h":
             vars = ["temperature", "humidity", "wind_speed", "solar_radiation"]
             if "pressure" in self.input_timeseries:
                 vars.append("pressure")
@@ -571,7 +569,7 @@ class ProcessSpatial:
             self._read_input_geofile(var, timestamp)
 
     def _get_variables(self):
-        if self.config.time_step == "H":
+        if self.config.time_step == "h":
             return {
                 "temperature",
                 "humidity",

{pthelma-1.1.0 → pthelma-2.1.0}/src/evaporation/evaporation.py

@@ -45,7 +45,7 @@ class PenmanMonteith(object):
         self.unit_converters = unit_converters
 
     def calculate(self, **kwargs):
-        if self.time_step == "H":
+        if self.time_step == "h":
             return self.calculate_hourly(**kwargs)
         elif self.time_step == "D":
             return self.calculate_daily(**kwargs)

{pthelma-1.1.0 → pthelma-2.1.0}/src/haggregate/haggregate.py

@@ -75,8 +75,8 @@ class Aggregation:
     def get_result_flags(self):
         max_count = int(pd.Timedelta(self.result.time_step) / self.source.freq)
         values_count = self.resampler.count()
-        self.result.data["flags"] = (values_count < max_count).apply(
-            lambda x: self.missing_flag if x else ""
+        self.result.data["flags"] = (max_count - values_count).apply(
+            lambda x: self.missing_flag.format(x) if x else ""
         )
 
 
@@ -106,7 +106,7 @@ class SourceTimeseries(HTimeseries):
                 )
         except ValueError:
             raise CannotInferFrequency()
-        first_timestamp = (current_range[0] - pd.Timedelta("1S")).floor(target_step)
+        first_timestamp = (current_range[0] - pd.Timedelta("1s")).floor(target_step)
         end_timestamp = current_range[-1].ceil(target_step)
         new_range = pd.date_range(first_timestamp, end_timestamp, freq=self.freq)
         self.data = self.data.reindex(new_range)
@@ -116,8 +116,8 @@ class AggregatedTimeseries(HTimeseries):
     def set_metadata(self, source_timeseries):
         for attr in attrs:
             setattr(self, attr, getattr(source_timeseries, attr, None))
-        if self.time_step not in ("1H", "1D"):
-            raise AggregateError("The target step can currently only be 1H or 1D")
+        if self.time_step not in ("1h", "1D"):
+            raise AggregateError("The target step can currently only be 1h or 1D")
         if hasattr(source_timeseries, "title"):
             self.title = "Aggregated " + source_timeseries.title
         if hasattr(source_timeseries, "comment"):
@@ -140,7 +140,7 @@ class AggregatedTimeseries(HTimeseries):
 
 
 def _get_offset_in_minutes(timestamp_offset):
-    m = re.match(r"(-?)(\d*)(T|min)$", timestamp_offset)
+    m = re.match(r"(-?)(\d*)min$", timestamp_offset)
     if not m:
         raise AggregateError(
             "The target timestamp offset can currently only be a number of minutes "