pthelma 1.0.0__cp310-cp310-win32.whl → 2.0.0__cp310-cp310-win32.whl

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):

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",

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)

haggregate/__init__.py

@@ -1,5 +1,2 @@
 from .haggregate import *  # NOQA
 from .regularize import *  # NOQA
-
-__author__ = """Antonis Christofides"""
-__email__ = "antonis@antonischristofides.com"

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 "

hspatial/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 +99,7 @@ class App:
                         0, iso8601.parse_date(datestring, default_timezone=timezone)
                     )
                 except iso8601.ParseError as e:
-                    raise iso8601.ParseError(
+                    raise click.ClickException(
                         str(e)
                         + " (file {}, {} lines from the end)".format(filename, i + 1)
                     )
@@ -146,7 +145,7 @@ class App:
         """
         Determine date_fmt based on time series time step.
         """
-        if self._time_step.endswith("min") or self._time_step.endswith("H"):
+        if self._time_step.endswith("min") or self._time_step.endswith("h"):
             return "%Y-%m-%d %H:%M%z"
         elif self._time_step.endswith("D"):
             return "%Y-%m-%d"
@@ -221,7 +220,6 @@ 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/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.0.0'
-__version_tuple__ = version_tuple = (1, 0, 0)
+__version__ = version = '2.0.0'
+__version_tuple__ = version_tuple = (2, 0, 0)

{pthelma-1.0.0.dist-info → pthelma-2.0.0.dist-info}/METADATA

@@ -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-2.0.0.dist-info/RECORD

@@ -0,0 +1,30 @@
+enhydris_api_client/__init__.py,sha256=TQQD2zgSAl-7eXOOHjgvHEqMW1D3GSmf9nI9cmR31c8,9592
+enhydris_cache/__init__.py,sha256=n3mAFeXUINSGpRkO-ZL1tkxyAuEabnMdlNPpmKur0AU,157
+enhydris_cache/cli.py,sha256=BEFBYdrfdJbEUyeY87BLWw7igKlfB2qzkpopPZrAIUQ,4743
+enhydris_cache/enhydris_cache.py,sha256=Mvpk2JxF6hSgk0qmGWEVFjIAoehFbdK41LyBJjAYhZc,2691
+evaporation/__init__.py,sha256=ekZNT_-GEt1lDmwbX_RIaOvHSRjX05iVWeupaxZV75Y,126
+evaporation/cli.py,sha256=06TIjd6Jr_p6YjM0bOGgKqSufj5exvHXElSEAvleaNA,28392
+evaporation/evaporation.py,sha256=87kNBAplijIEk_kzPWHBOYtWDWqNAK7_oZL_U2gaV9g,16702
+haggregate/__init__.py,sha256=KfFmAI6bvEsnaflhq9pK1nzOdoyySFiXnw9o1-Nmcus,70
+haggregate/cli.py,sha256=Ou2zQRnj9ZsNM6it7HFGLavrdGaExZDartlPGPuaNLc,3363
+haggregate/haggregate.py,sha256=nfOUW_M4q_qrS-rEQh7lJks9G9724xV6oX0ayF_Pmdw,5196
+haggregate/regularize.cp310-win32.pyd,sha256=toHZUXrk74qr-JXDtkimcT8WjSqHjnuPeC85rEne6_E,91136
+haggregate/regularize.pyx,sha256=aaxx-3wJtuo51G9n7GIzFb2qt6m7rXuoAES9zoI7Zcw,5800
+hspatial/__init__.py,sha256=dlTLFy7IqQwun4nz01qtYMQbU9kBmHEKoOXGIgCRf9c,123
+hspatial/cli.py,sha256=1iAY9-ATkO_xzlGCC_WSw42S9w2ca0uRLSxWG3WIat8,10638
+hspatial/hspatial.py,sha256=fv9xia23D9W5kXG00XlDrXYMF8KotUlIfL9ZjuGEyPg,16348
+hspatial/test.py,sha256=_YZzfgEtlCJmOGOdnxwpsPC48EBZ_QaKKBdyJRmg014,1050
+htimeseries/__init__.py,sha256=by-XbIt4Q-lHHKlHEcgXLi7AjEGNv0VGNmM0ZMl8L7M,75
+htimeseries/htimeseries.py,sha256=y8rIFabSCdBwmS3vWGEuyRMtQvIZy81jqg304-kIg3w,19771
+htimeseries/timezone_utils.py,sha256=jTWhKljHXQuD_drNgfI2ytD6atf6dwnsL4qCVK8wpgA,1282
+pthelma/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pthelma/_version.py,sha256=hje97DjNnjjzdk2AwQsDgJXvORhASGZ-8JywrlJVLIw,427
+rocc/__init__.py,sha256=KfFB3rfJXgYL4HnVa7MNYcotG3am-CajVvh65gm9v_s,281
+rocc/calculation.cp310-win32.pyd,sha256=MP6kMcCnkySzkOiLedLkvcPLmDwc9yRrbzjQGMxerbM,86528
+rocc/calculation.pyx,sha256=tWWSB1u2JTCnYv6mb_YwK97vPrL7JT_ymx_5TlmG_9Y,5938
+pthelma-2.0.0.dist-info/LICENSE.rst,sha256=v1ndaPoHsiO-q3mq-ibN0HooeO-LCZBvKPfwlJRIMWs,1379
+pthelma-2.0.0.dist-info/METADATA,sha256=QnFd03qXLTgir1qyXPxoob8pN0Uxp5Zu4U3hm6LyD_8,2018
+pthelma-2.0.0.dist-info/WHEEL,sha256=IJJUxdZyjrGcLR3XjvKOCbzRR0h6oB7KSRhSaDzEI7U,97
+pthelma-2.0.0.dist-info/entry_points.txt,sha256=Kh2gKKRhObmmOASJWIwX9dDEZQ5htc3ftBlqeoGer-s,155
+pthelma-2.0.0.dist-info/top_level.txt,sha256=kWL0AYuVd_5KzKWRBkAG576ag46gKbojnWdeH_c-bzo,92
+pthelma-2.0.0.dist-info/RECORD,,

{pthelma-1.0.0.dist-info → pthelma-2.0.0.dist-info}/top_level.txt

@@ -5,3 +5,4 @@ haggregate
 hspatial
 htimeseries
 pthelma
+rocc

rocc/__init__.py

@@ -0,0 +1,9 @@
+from collections import namedtuple
+
+from .calculation import Rocc
+
+Threshold = namedtuple("Threshold", ["delta_t", "allowed_diff"])
+
+
+def rocc(*, timeseries, thresholds, symmetric=False, flag="TEMPORAL"):
+    return Rocc(timeseries, thresholds, symmetric, flag).execute()

rocc/calculation.pyx

@@ -0,0 +1,182 @@
+# cython: language_level=3
+import datetime as dt
+
+cimport numpy as np
+from cpython cimport array
+
+import numpy as np
+import pandas as pd
+
+
+class Rocc:
+    def __init__(self, timeseries, thresholds, symmetric, flag):
+        self.htimeseries = timeseries
+        self.thresholds = thresholds
+        self.symmetric = symmetric
+        self.flag = flag or ""
+
+    def execute(self):
+        self._transform_thresholds()
+        self._transform_to_plain_numpy()
+        failures = self._do_actual_job()
+        self._transform_to_pandas()
+        return failures
+
+    def _transform_thresholds(self):
+        threshold_deltas = array.array("l")
+        threshold_allowed_diffs = array.array("d")
+
+        for threshold in self.thresholds:
+            delta_t = int(self._get_delta_t_transformed(threshold.delta_t))
+            threshold_deltas.append(delta_t)
+            threshold_allowed_diffs.append(threshold.allowed_diff)
+        self.threshold_deltas = threshold_deltas
+        self.threshold_allowed_diffs = threshold_allowed_diffs
+
+    def _get_delta_t_transformed(self, delta_t):
+        if not delta_t[0].isdigit():
+            delta_t = "1" + delta_t
+        return pd.Timedelta(delta_t).to_timedelta64()
+
+    def _transform_to_plain_numpy(self):
+        flag_lengths = self.htimeseries.data["flags"].str.len()
+        max_flag_length = 0 if flag_lengths.empty else max(flag_lengths)
+        flags_dtype = "U" + str(max_flag_length + 1 + len(self.flag))
+        self.ts_index = self.htimeseries.data.index.values.astype(long)
+        self.ts_values = self.htimeseries.data["value"].values
+        self.ts_flags = self.htimeseries.data["flags"].values.astype(flags_dtype)
+        try:
+            utc_offset = self.htimeseries.data.index.tz.utcoffset(dt.datetime.now())
+        except AttributeError:
+            utc_offset = dt.timedelta(0)
+        self.ts_utc_offset_minutes = int(utc_offset.total_seconds() / 60)
+
+    def _do_actual_job(self):
+        return _perform_rocc(
+            self.ts_index,
+            self.ts_values,
+            self.ts_flags,
+            self.ts_utc_offset_minutes,
+            list(self.thresholds),
+            self.threshold_deltas,
+            self.threshold_allowed_diffs,
+            self.symmetric,
+            self.flag,
+        )
+
+    def _transform_to_pandas(self):
+        self.htimeseries.data = pd.DataFrame(
+            index=self.htimeseries.data.index,
+            columns=["value", "flags"],
+            data=np.vstack((self.ts_values, self.ts_flags)).transpose(),
+        )
+        self.htimeseries.data["value"] = self.htimeseries.data["value"].astype(np.float64)
+
+
+# IMPORTANT: There's some plain Python in the Cython below. Specifically, there are some
+# Python lists and some places with undeclared variables. These are only used when a
+# failure is found. Given that failures should be very few, this should not affect the
+# overall speed. But I'm not really a Cython expert and I don't know exactly how it
+# works.
+
+
+def _perform_rocc(
+    np.ndarray ts_index,
+    np.ndarray ts_values,
+    np.ndarray ts_flags,
+    int ts_utc_offset_minutes,
+    list thresholds,
+    array.array threshold_deltas,
+    array.array threshold_allowed_diffs,
+    int symmetric,
+    str flag,
+):
+    cdef int i, record_fails_check
+    cdef list failures = []
+
+    for i in range(ts_index.size):
+        record_fails_check = _record_fails_check(
+            i,
+            ts_index,
+            ts_values,
+            ts_utc_offset_minutes,
+            thresholds,
+            threshold_deltas,
+            threshold_allowed_diffs,
+            symmetric,
+            failures,
+        )
+        if record_fails_check and flag:
+            _add_flag(i, ts_flags, flag)
+    return failures
+
+
+def _add_flag(int i, np.ndarray ts_flags, str flag):
+    if ts_flags[i]:
+        ts_flags[i] = ts_flags[i] + " "
+    ts_flags[i] = ts_flags[i] + flag
+
+
+def _record_fails_check(
+    int record_index,
+    np.ndarray ts_index,
+    np.ndarray ts_values,
+    int ts_utc_offset_minutes,
+    list thresholds,
+    array.array threshold_deltas,
+    array.array threshold_allowed_diffs,
+    int symmetric,
+    list failures,
+):
+    cdef int ti
+    cdef double diff
+
+    for ti in range(len(threshold_deltas)):
+        diff = _record_fails_threshold(
+            record_index,
+            threshold_deltas[ti],
+            threshold_allowed_diffs[ti],
+            ts_index,
+            ts_values,
+            symmetric,
+        )
+        if diff:
+            timestamp = ts_index[record_index].item()
+            datestr = str(
+                np.datetime64(timestamp, "ns") + np.timedelta64(ts_utc_offset_minutes, "m")
+            )[:16]
+            diffsign = '+' if diff > 0 else ''
+            thresholdsign = '-' if diff < 0 else ''
+            cmpsign = '>' if diff > 0 else '<'
+            failures.append(
+                f"{datestr}  {diffsign}{diff} in {thresholds[ti].delta_t} "
+                f"({cmpsign} {thresholdsign}{threshold_allowed_diffs[ti]})"
+            )
+            return True
+    return False
+
+
+def _record_fails_threshold(
+    int record_index,
+    long threshold_delta,
+    double threshold_allowed_diff,
+    np.ndarray ts_index,
+    np.ndarray ts_values,
+    int symmetric,
+):
+    cdef double current_value = ts_values[record_index]
+    cdef long current_timestamp = ts_index[record_index]
+    cdef int i, fails
+    cdef double diff;
+
+    for i in range(record_index - 1, -1, -1):
+        if current_timestamp - ts_index[i] > threshold_delta:
+            return False
+        diff = current_value - ts_values[i];
+        fails = (
+            diff > threshold_allowed_diff
+            or (symmetric and diff < -threshold_allowed_diff)
+        )
+        if fails:
+            return diff
+    return False

pthelma-1.0.0.dist-info/RECORD

@@ -1,27 +0,0 @@
-enhydris_api_client/__init__.py,sha256=TQQD2zgSAl-7eXOOHjgvHEqMW1D3GSmf9nI9cmR31c8,9592
-enhydris_cache/__init__.py,sha256=n3mAFeXUINSGpRkO-ZL1tkxyAuEabnMdlNPpmKur0AU,157
-enhydris_cache/cli.py,sha256=aqlcp0zXVNSmMAVfjVz_2ri6V7pHiSRPthO4y1LCdf4,4793
-enhydris_cache/enhydris_cache.py,sha256=Mvpk2JxF6hSgk0qmGWEVFjIAoehFbdK41LyBJjAYhZc,2691
-evaporation/__init__.py,sha256=ekZNT_-GEt1lDmwbX_RIaOvHSRjX05iVWeupaxZV75Y,126
-evaporation/cli.py,sha256=4HdusE0Trt81HsNlClvlrAu-493GtGa6bn_KuV4opzs,28442
-evaporation/evaporation.py,sha256=twTkFsuI5QRcof1XbnOG5vhnEMgrA2zXYHxYleKV5-k,16702
-haggregate/__init__.py,sha256=rqRWh8aJ44DEnAnxfwOWfqFKMZGkvewH81SH5RcSGGM,160
-haggregate/cli.py,sha256=Ou2zQRnj9ZsNM6it7HFGLavrdGaExZDartlPGPuaNLc,3363
-haggregate/haggregate.py,sha256=pXzT2z_LshxFD9USiV1je-swAj8n-iY7fetxVO8XJ-A,5200
-haggregate/regularize.cp310-win32.pyd,sha256=KmtJqW086sQcmRL7cdR14mN1-2HfN3ypevli28heH4U,91136
-haggregate/regularize.pyx,sha256=aaxx-3wJtuo51G9n7GIzFb2qt6m7rXuoAES9zoI7Zcw,5800
-hspatial/__init__.py,sha256=dlTLFy7IqQwun4nz01qtYMQbU9kBmHEKoOXGIgCRf9c,123
-hspatial/cli.py,sha256=alkp-IxwMBErwL2sjZmSLWeRG3DXr0c4A4GV0O0Fk0o,10686
-hspatial/hspatial.py,sha256=fv9xia23D9W5kXG00XlDrXYMF8KotUlIfL9ZjuGEyPg,16348
-hspatial/test.py,sha256=_YZzfgEtlCJmOGOdnxwpsPC48EBZ_QaKKBdyJRmg014,1050
-htimeseries/__init__.py,sha256=by-XbIt4Q-lHHKlHEcgXLi7AjEGNv0VGNmM0ZMl8L7M,75
-htimeseries/htimeseries.py,sha256=y8rIFabSCdBwmS3vWGEuyRMtQvIZy81jqg304-kIg3w,19771
-htimeseries/timezone_utils.py,sha256=jTWhKljHXQuD_drNgfI2ytD6atf6dwnsL4qCVK8wpgA,1282
-pthelma/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pthelma/_version.py,sha256=dJiaCltLFgci5aFfMnwDnv8BAhveHDCtWSHatUxAG1Q,427
-pthelma-1.0.0.dist-info/LICENSE.rst,sha256=v1ndaPoHsiO-q3mq-ibN0HooeO-LCZBvKPfwlJRIMWs,1379
-pthelma-1.0.0.dist-info/METADATA,sha256=gBNt0yEQnHNL-PA_mwPtpStaW7yHwk677_IJVF4fGdQ,2209
-pthelma-1.0.0.dist-info/WHEEL,sha256=IJJUxdZyjrGcLR3XjvKOCbzRR0h6oB7KSRhSaDzEI7U,97
-pthelma-1.0.0.dist-info/entry_points.txt,sha256=Kh2gKKRhObmmOASJWIwX9dDEZQ5htc3ftBlqeoGer-s,155
-pthelma-1.0.0.dist-info/top_level.txt,sha256=tmHh9NPLZEWJBUT19b-ZqJmAOG6QAfyM_Z3d-B7XS7w,87
-pthelma-1.0.0.dist-info/RECORD,,