pthelma 1.0.0__tar.gz → 2.0.0__tar.gz

{pthelma-1.0.0 → pthelma-2.0.0}/.github/workflows/build_wheels.yml

@@ -1,15 +1,10 @@
 name: Build wheels
 
 on:
-  push:
-    branches:
-      - master
-  pull_request:
-    branches:
-      - master
   release:
     types:
       - published
+  workflow_dispatch:
 
 jobs:
   build_wheels:

{pthelma-1.0.0 → pthelma-2.0.0}/.github/workflows/run-tests.yml

@@ -1,4 +1,4 @@
-name: Run tests
+name: Tests
 
 on:
   push:

{pthelma-1.0.0 → pthelma-2.0.0}/.gitignore

@@ -40,3 +40,4 @@ _version.py
 
 # cython
 src/haggregate/regularize.c
+src/rocc/calculation.c

{pthelma-1.0.0 → pthelma-2.0.0}/CHANGELOG.rst

@@ -2,6 +2,17 @@
 Changelog
 =========
 
+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)
+==================
+
+Added package rocc (equivalent to rocc 3.0).
+
 1.0.0 (2024-11-29)
 ==================
 

{pthelma-1.0.0/src/pthelma.egg-info → pthelma-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pthelma
-Version: 1.0.0
+Version: 2.0.0
 Summary: Utilities for hydrological and meteorological time series processing
 Author-email: Antonis Christofides <antonis@antonischristofides.com>
 Maintainer-email: Antonis Christofides <antonis@antonischristofides.com>
@@ -34,9 +34,9 @@ Requires-Dist: gdal<4,>=1.10; extra == "all"
 pthelma
 =======
 
-.. image:: https://github.com/openmeteo/pthelma/actions/workflows/run-tests-automatically.yml/badge.svg
+.. image:: https://github.com/openmeteo/pthelma/actions/workflows/run-tests.yml/badge.svg
     :alt: Build button
-    :target: https://github.com/openmeteo/pthelma/actions/workflows/run-tests-automatically.yml
+    :target: https://github.com/openmeteo/pthelma/actions/workflows/run-tests.yml
 
 .. image:: https://codecov.io/github/openmeteo/pthelma/coverage.svg?branch=master
     :alt: Coverage
@@ -45,10 +45,6 @@ pthelma
 .. image:: https://img.shields.io/pypi/v/pthelma.svg
         :target: https://pypi.python.org/pypi/pthelma
 
-.. image:: https://pyup.io/repos/github/openmeteo/pthelma/shield.svg
-         :target: https://pyup.io/repos/github/openmeteo/pthelma/
-         :alt: Updates
-
 A Python library with utilities for hydrological and meteorological time
 series processing.
 

{pthelma-1.0.0 → pthelma-2.0.0}/README.rst

@@ -1,9 +1,9 @@
 pthelma
 =======
 
-.. image:: https://github.com/openmeteo/pthelma/actions/workflows/run-tests-automatically.yml/badge.svg
+.. image:: https://github.com/openmeteo/pthelma/actions/workflows/run-tests.yml/badge.svg
     :alt: Build button
-    :target: https://github.com/openmeteo/pthelma/actions/workflows/run-tests-automatically.yml
+    :target: https://github.com/openmeteo/pthelma/actions/workflows/run-tests.yml
 
 .. image:: https://codecov.io/github/openmeteo/pthelma/coverage.svg?branch=master
     :alt: Coverage
@@ -12,10 +12,6 @@ pthelma
 .. image:: https://img.shields.io/pypi/v/pthelma.svg
         :target: https://pypi.python.org/pypi/pthelma
 
-.. image:: https://pyup.io/repos/github/openmeteo/pthelma/shield.svg
-         :target: https://pyup.io/repos/github/openmeteo/pthelma/
-         :alt: Updates
-
 A Python library with utilities for hydrological and meteorological time
 series processing.
 

{pthelma-1.0.0 → pthelma-2.0.0}/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-1.0.0 → pthelma-2.0.0}/docs/haggregate/usage.rst

@@ -53,7 +53,7 @@ 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
 
@@ -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

{pthelma-1.0.0 → pthelma-2.0.0}/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-1.0.0 → pthelma-2.0.0}/docs/index.rst

@@ -29,6 +29,7 @@ pthelma - Utilities for hydrological and meteorological time series processing
 
    haggregate/usage
    haggregate/api
+   rocc
 
 
 .. toctree::

pthelma-2.0.0/docs/rocc.rst

@@ -0,0 +1,77 @@
+===========================================
+rocc - Rate-of-change check for time series
+===========================================
+
+.. class:: Threshold
+
+   A named tuple whose items are :attr:`delta_t` (a pandas interval
+   specification) and :attr:`allowed_diff` (a floating point number).
+
+.. function:: rocc.rocc(ahtimeseries, thresholds, symmetric=False, flag="TEMPORAL")
+
+   Example ::
+
+      from rocc import Threshold, rocc
+
+      result = rocc(
+         timeseries=a_htimeseries_object,
+         thresholds=(
+            Threshold("10min", 10),
+            Threshold("20min", 15),
+            Threshold("h", 40),
+         ),
+         symmetric=True,
+         flag="MYFLAG",
+      )
+
+   ``timeseries`` is a :class:`HTimeseries` object.  ``thresholds`` is
+   a list of :class:`Threshold` objects.
+
+   The function checks whether there exist intervals during which the
+   value of the time series changes by more than the specified
+   threshold. The offending records are flagged with the specified
+   ``flag``.
+
+   It returns a list of strings describing where the thresholds have been
+   exceeded.
+
+   If ``flag`` is ``None`` or the empty string, then the offending records
+   are not flagged, and the only result is the returned value.
+
+   Here is an example time series::
+
+      2020-10-06 14:30    24.0
+      2020-10-06 14:40    25.0  
+      2020-10-06 14:50    36.0 *
+      2020-10-06 15:01    51.0
+      2020-10-06 15:21    55.0  
+      2020-10-06 15:31    65.0  
+      2020-10-06 15:41    75.0 *
+      2020-10-06 15:51    70.0
+
+   After running ``rocc()`` with the ``thresholds`` specified in the
+   example above, the records marked with a star will be flagged. The
+   record ``14:50`` will be flagged because in the preceding 10-minute
+   interval the value increases by 11, which is more than 10. The record
+   ``15:41`` will be flagged because in the preceding 20-minute interval
+   the value increases by 20, which is more than 15. The record ``15:01``
+   will be unflagged; although there's a large difference since ``14:40``,
+   this is 21 minutes, not 20, so the 20-minute threshold of 15 does not
+   apply; likewise, there's a difference of 15 from ``14:50``, which does
+   not exceed the 20-minute threshold of 15, and while it does exceed the
+   10-minute threshold of 10, it's 11 minutes, not 10. There's also not any
+   difference larger than 40 within an hour anywhere.
+
+   The return value in this example will be a list of two strings::
+
+      "2020-10-06T14:50  +11.0 in 10min (> 10.0)"
+      "2020-10-06T15:41  +20.0 in 20min (> 15.0)"
+
+   The return value should only be used for consumption by humans; it is
+   subject to change.
+
+   If ``symmetric`` is ``True``, it is the absolute value of the change
+   that matters, not its direction. In this case, ``allowed_diff`` must be
+   positive. If ``symmetric`` is ``False`` (the default), only rates larger
+   than positive ``allow_diff`` or rates smaller than negative
+   ``allow_diff`` are flagged.

{pthelma-1.0.0 → pthelma-2.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [build-system]
 # numpy<2 is not just a dependency, it's a build dependency, because it's
-# needed to build regularize.pyx (and the _gdal_array thing, which gdal won't
+# needed to build some .pyx files (and the _gdal_array thing, which gdal won't
 # build if numpy is not available at build time). It's at "<2" because of gdal;
 # pthelma can also use ">=2".
 requires = ["setuptools>=61.0", "setuptools-scm>=7.1", "cython", "numpy<2"]

pthelma-2.0.0/setup.py

@@ -0,0 +1,20 @@
+import numpy
+from Cython.Build import cythonize
+from setuptools import Extension, setup
+
+setup(
+    ext_modules=cythonize(
+        [
+            Extension(
+                "haggregate.regularize",
+                sources=["src/haggregate/regularize.pyx"],
+                include_dirs=[numpy.get_include()],
+            ),
+            Extension(
+                "rocc.calculation",
+                sources=["src/rocc/calculation.pyx"],
+                include_dirs=[numpy.get_include()],
+            ),
+        ]
+    ),
+)

{pthelma-1.0.0 → pthelma-2.0.0}/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-1.0.0 → pthelma-2.0.0}/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-1.0.0 → pthelma-2.0.0}/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-2.0.0/src/haggregate/__init__.py

@@ -0,0 +1,2 @@
+from .haggregate import *  # NOQA
+from .regularize import *  # NOQA

{pthelma-1.0.0 → pthelma-2.0.0}/src/haggregate/haggregate.py

@@ -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 "