feature 1490 Python Embedding for Point Observations

.github/jobs/docker_setup.sh

@@ -33,18 +33,25 @@ export DOCKERFILE_PATH=${GITHUB_WORKSPACE}/scripts/docker/Dockerfile
 
 MET_TAG=`${GITHUB_WORKSPACE}/scripts/docker/hooks/get_met_version`
 
+MET_DOCKER_REPO=met-dev
+if [ "${MET_TAG}" != "develop" ]; then
+    MET_DOCKER_REPO=met
+fi
+
 # if MET_FORCE_TAG variable is set and not empty, use that version instead
 if [ ! -z "$MET_FORCE_TAG" ]; then
     MET_TAG=$MET_FORCE_TAG
 fi
 
+echo Using MET_DOCKER_REPO=$MET_DOCKER_REPO
 echo Using MET_TAG=$MET_TAG
 echo Setting DOCKER_BUILDKIT=1
 export DOCKER_BUILDKIT=1
 
 time_command docker build --pull --cache-from ${DOCKERHUB_TAG} \
 -t ${DOCKERHUB_TAG} \
 --build-arg OBTAIN_SOURCE_CODE=copy \
+--build-arg MET_DOCKER_REPO=$MET_DOCKER_REPO \
 --build-arg MET_TAG=$MET_TAG \
 -f ${DOCKERFILE_PATH} ${GITHUB_WORKSPACE}
 

.github/parm/use_case_groups.json

@@ -14,6 +14,11 @@
     "index_list": "59",
     "run": false
   },
+  {
+    "category": "met_tool_wrapper",
+    "index_list": "60",
+    "run": true
+  },
   {
     "category": "air_quality_and_comp",
     "index_list": "0",

docs/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.py

@@ -0,0 +1,135 @@
+"""
+PointStat: Using Python Embedding for Point Observations
+========================================================
+
+met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf
+
+"""
+##############################################################################
+# Scientific Objective
+# --------------------
+#
+# Compare hourly forecasts for temperature, u-, and v-wind components to observations
+# in a 3-hour observation window. Generate statistics of the results.
+# Calls a Python Embedding script to read point observations.
+
+##############################################################################
+# Datasets
+# --------
+#
+# | **Forecast:** NAM temperature, u-wind component, and v-wind component
+# | **Observation:** prepBUFR data that has been converted to NetCDF format via PB2NC
+#
+# | **Location:** All of the input data required for this use case can be found in the met_test sample data tarball. Click here to the METplus releases page and download sample data for the appropriate release: https://github.com/dtcenter/METplus/releases
+# | This tarball should be unpacked into the directory that you will set the value of INPUT_BASE. See `Running METplus`_ section for more information.
+#
+# | **Data Source:** Unknown
+# |
+
+##############################################################################
+# METplus Components
+# ------------------
+#
+# This use case utilizes the METplus PointStat wrapper to search for
+# files that are valid at a given run time and generate a command to run
+# the MET tool point_stat if all required files are found.
+# This example demonstrates how to configure a use case to call a Python
+# Embedding script to read in point observations into point_stat.
+
+##############################################################################
+# METplus Workflow
+# ----------------
+#
+# PointStat is the only tool called in this example. It processes the following
+# run times:
+#
+# | **Valid:** 2007-03-30_0Z
+# |
+
+##############################################################################
+# METplus Configuration
+# ---------------------
+#
+# METplus first loads all of the configuration files found in parm/metplus_config,
+# then it loads any configuration files passed to METplus via the command line
+# with the -c option, i.e. -c parm/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf
+#
+# .. highlight:: bash
+# .. literalinclude:: ../../../../parm/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf
+
+##############################################################################
+# MET Configuration
+# ---------------------
+#
+# METplus sets environment variables based on user settings in the METplus configuration file. 
+# See :ref:`How METplus controls MET config file settings<metplus-control-met>` for more details. 
+#
+# **YOU SHOULD NOT SET ANY OF THESE ENVIRONMENT VARIABLES YOURSELF! THEY WILL BE OVERWRITTEN BY METPLUS WHEN IT CALLS THE MET TOOLS!**
+#
+# If there is a setting in the MET configuration file that is currently not supported by METplus you'd like to control, please refer to:
+# :ref:`Overriding Unsupported MET config file settings<met-config-overrides>`
+#
+# .. note:: See the :ref:`PointStat MET Configuration<point-stat-met-conf>` section of the User's Guide for more information on the environment variables used in the file below:
+#
+# .. highlight:: bash
+# .. literalinclude:: ../../../../parm/met_config/PointStatConfig_wrapped
+
+##############################################################################
+# Running METplus
+# ---------------
+#
+# This use case can be run two ways:
+#
+# 1) Passing in PointStat_python_embedding_obs.conf then a user-specific system configuration file::
+#
+#        run_metplus.py -c /path/to/METplus/parm/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf -c /path/to/user_system.conf
+#
+# 2) Modifying the configurations in parm/metplus_config, then passing in PointStat_python_embedding_obs.conf::
+#
+#        run_metplus.py -c /path/to/METplus/parm/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf
+#
+# The former method is recommended. Whether you add them to a user-specific configuration file or modify the metplus_config files, the following variables must be set correctly:
+#
+# * **INPUT_BASE** - Path to directory where sample data tarballs are unpacked (See Datasets section to obtain tarballs). This is not required to run METplus, but it is required to run the examples in parm/use_cases
+# * **OUTPUT_BASE** - Path where METplus output will be written. This must be in a location where you have write permissions
+# * **MET_INSTALL_DIR** - Path to location where MET is installed locally
+#
+# Example User Configuration File::
+#
+#   [dir]
+#   INPUT_BASE = /path/to/sample/input/data
+#   OUTPUT_BASE = /path/to/output/dir
+#   MET_INSTALL_DIR = /path/to/met-X.Y 
+#
+# **NOTE:** All of these items must be found under the [dir] section.
+#
+
+##############################################################################
+# Expected Output
+# ---------------
+#
+# A successful run will output the following both to the screen and to the logfile::
+#
+#   INFO: METplus has successfully finished running.
+#
+# Refer to the value set for **OUTPUT_BASE** to find where the output data was generated.
+# Output for this use case will be found in point_stat_py_embed_obs
+# (relative to **OUTPUT_BASE**) and will contain the following files:
+#
+# * point_stat_360000L_20070331_120000V.stat
+
+##############################################################################
+# Keywords
+# --------
+#
+# .. note::
+#
+#   * PointStatToolUseCase
+#   * PythonEmbeddingFileUseCase
+#
+#   Navigate to the :ref:`quick-search` page to discover other similar use cases.
+#
+#
+#
+# sphinx_gallery_thumbnail_path = '_static/met_tool_wrapper-PointStat.png'
+#

internal_tests/use_cases/all_use_cases.txt

@@ -59,6 +59,7 @@ Category: met_tool_wrapper
 57::GFDLTracker_Genesis::met_tool_wrapper/GFDLTracker/GFDLTracker_Genesis.conf::gfdl-tracker_env
 58::GenEnsProd::met_tool_wrapper/GenEnsProd/GenEnsProd.conf
 59::IODA2NC::met_tool_wrapper/IODA2NC/IODA2NC.conf
+60::PointStat_python_embedding_obs:: met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf
 
 Category: air_quality_and_comp
 0::EnsembleStat_fcstICAP_obsMODIS_aod::model_applications/air_quality_and_comp/EnsembleStat_fcstICAP_obsMODIS_aod.conf

metplus/util/met_util.py

@@ -1188,6 +1188,12 @@ def preprocess_file(filename, data_type, config, allow_dir=False):
     if os.path.basename(filename) in PYTHON_EMBEDDING_TYPES:
         return os.path.basename(filename)
 
+    # if filename starts with a python embedding type, return the full value
+    for py_embed_type in PYTHON_EMBEDDING_TYPES:
+        if filename.startswith(py_embed_type):
+            return filename
+
+    # if _INPUT_DATATYPE value contains PYTHON, return the full value
     if data_type is not None and 'PYTHON' in data_type:
         return filename
 

metplus/wrappers/compare_gridded_wrapper.py

@@ -379,10 +379,16 @@ def get_command(self):
             return None
 
         # add forecast file
-        cmd += self.infiles[0] + ' '
+        fcst_file = self.infiles[0]
+        if fcst_file.startswith('PYTHON'):
+            fcst_file = f"'{fcst_file}'"
+        cmd += f'{fcst_file} '
 
         # add observation file
-        cmd += self.infiles[1] + ' '
+        obs_file = self.infiles[1]
+        if obs_file.startswith('PYTHON'):
+            obs_file = f"'{obs_file}'"
+        cmd += f'{obs_file} '
 
         if self.param == '':
             self.log_error('Must specify config file to run MET tool')

metplus/wrappers/ensemble_stat_wrapper.py

@@ -616,6 +616,8 @@ def get_command(self):
             cmd += self.param + " "
 
         for obs_file in self.point_obs_files:
+            if obs_file.startswith('PYTHON'):
+                obs_file = f"'{obs_file}'"
             cmd += "-point_obs " + obs_file + " "
 
         for obs_file in self.grid_obs_files:

metplus/wrappers/point2grid_wrapper.py

@@ -126,6 +126,8 @@ def get_command(self):
 
         # add input files
         for infile in self.infiles:
+            if infile.startswith('PYTHON'):
+                infile = f"'{infile}'"
             cmd += ' ' + infile
 
         # add grid name

parm/use_cases/met_tool_wrapper/PointStat/PointStat_python_embedding_obs.conf

@@ -0,0 +1,145 @@
+[config]
+
+PROCESS_LIST = PointStat
+
+###
+# Time Info
+###
+
+LOOP_BY = INIT
+INIT_TIME_FMT = %Y%m%d
+INIT_BEG = 20070330
+INIT_END = 20070330
+INIT_INCREMENT = 1M
+
+LEAD_SEQ = 36
+
+###
+# File I/O
+###
+
+FCST_POINT_STAT_INPUT_DIR = {INPUT_BASE}/met_test/data/sample_fcst
+FCST_POINT_STAT_INPUT_TEMPLATE = {init?fmt=%Y%m%d%H}/nam.t00z.awip1236.tm00.{init?fmt=%Y%m%d}.grb
+
+OBS_POINT_STAT_INPUT_DIR =
+OBS_POINT_STAT_INPUT_TEMPLATE = PYTHON_NUMPY= {MET_INSTALL_DIR}/share/met/python/read_met_point_obs.py {INPUT_BASE}/met_test/out/pb2nc/sample_pb.nc
+
+POINT_STAT_OUTPUT_DIR = {OUTPUT_BASE}/point_stat_py_embed_obs
+
+POINT_STAT_CLIMO_MEAN_INPUT_DIR =
+POINT_STAT_CLIMO_MEAN_INPUT_TEMPLATE =
+
+POINT_STAT_CLIMO_STDEV_INPUT_DIR =
+POINT_STAT_CLIMO_STDEV_INPUT_TEMPLATE =
+
+###
+# Field Info
+###
+
+POINT_STAT_ONCE_PER_FIELD = False
+
+#POINT_STAT_FCST_FILE_TYPE =
+#POINT_STAT_OBS_FILE_TYPE =
+
+FCST_VAR1_NAME = TMP
+FCST_VAR1_LEVELS = P750-900
+FCST_VAR1_THRESH = <=273, >273
+OBS_VAR1_NAME = TMP
+OBS_VAR1_LEVELS = P750-900
+OBS_VAR1_THRESH = <=273, >273
+
+FCST_VAR2_NAME = UGRD
+FCST_VAR2_LEVELS = Z10
+FCST_VAR2_THRESH = >=5
+OBS_VAR2_NAME = UGRD
+OBS_VAR2_LEVELS = Z10
+OBS_VAR2_THRESH = >=5
+
+FCST_VAR3_NAME = VGRD
+FCST_VAR3_LEVELS = Z10
+FCST_VAR3_THRESH = >=5
+OBS_VAR3_NAME = VGRD
+OBS_VAR3_LEVELS = Z10
+OBS_VAR3_THRESH = >=5
+
+###
+# PointStat
+###
+
+#LOG_POINT_STAT_VERBOSITY = 2
+
+POINT_STAT_CONFIG_FILE ={PARM_BASE}/met_config/PointStatConfig_wrapped
+
+#POINT_STAT_OBS_QUALITY_INC = 1, 2, 3
+#POINT_STAT_OBS_QUALITY_EXC =
+
+POINT_STAT_CLIMO_MEAN_TIME_INTERP_METHOD = NEAREST
+#POINT_STAT_CLIMO_STDEV_TIME_INTERP_METHOD =
+
+#POINT_STAT_INTERP_VLD_THRESH =
+#POINT_STAT_INTERP_SHAPE =
+POINT_STAT_INTERP_TYPE_METHOD = BILIN
+POINT_STAT_INTERP_TYPE_WIDTH = 2
+
+#POINT_STAT_OUTPUT_FLAG_FHO =
+#POINT_STAT_OUTPUT_FLAG_CTC =
+#POINT_STAT_OUTPUT_FLAG_CTS =
+#POINT_STAT_OUTPUT_FLAG_MCTC =
+#POINT_STAT_OUTPUT_FLAG_MCTS =
+#POINT_STAT_OUTPUT_FLAG_CNT =
+POINT_STAT_OUTPUT_FLAG_SL1L2 = STAT
+#POINT_STAT_OUTPUT_FLAG_SAL1L2 =
+POINT_STAT_OUTPUT_FLAG_VL1L2 = STAT
+#POINT_STAT_OUTPUT_FLAG_VAL1L2 =
+#POINT_STAT_OUTPUT_FLAG_VCNT =
+#POINT_STAT_OUTPUT_FLAG_PCT =
+#POINT_STAT_OUTPUT_FLAG_PSTD =
+#POINT_STAT_OUTPUT_FLAG_PJC =
+#POINT_STAT_OUTPUT_FLAG_PRC =
+#POINT_STAT_OUTPUT_FLAG_ECNT =
+#POINT_STAT_OUTPUT_FLAG_RPS =
+#POINT_STAT_OUTPUT_FLAG_ECLV =
+#POINT_STAT_OUTPUT_FLAG_MPR =
+#POINT_STAT_OUTPUT_FLAG_ORANK =
+
+#POINT_STAT_CLIMO_CDF_BINS = 1
+#POINT_STAT_CLIMO_CDF_CENTER_BINS = False
+#POINT_STAT_CLIMO_CDF_WRITE_BINS = True
+#POINT_STAT_CLIMO_CDF_DIRECT_PROB =
+
+#POINT_STAT_HSS_EC_VALUE =
+
+OBS_POINT_STAT_WINDOW_BEGIN = -5400
+OBS_POINT_STAT_WINDOW_END = 5400
+
+POINT_STAT_OFFSETS = 0
+
+MODEL = WRF
+
+POINT_STAT_DESC = NA
+OBTYPE =
+
+POINT_STAT_REGRID_TO_GRID = NONE
+POINT_STAT_REGRID_METHOD = BILIN
+POINT_STAT_REGRID_WIDTH = 2
+
+POINT_STAT_OUTPUT_PREFIX =
+
+#POINT_STAT_OBS_VALID_BEG = {valid?fmt=%Y%m%d_%H}
+#POINT_STAT_OBS_VALID_END = {valid?fmt=%Y%m%d_%H}
+
+POINT_STAT_MASK_GRID = DTC165, DTC166
+POINT_STAT_MASK_POLY = MET_BASE/poly/LMV.poly
+POINT_STAT_MASK_SID =
+#POINT_STAT_MASK_LLPNT =
+
+POINT_STAT_MESSAGE_TYPE = ADPUPA, ADPSFC
+
+#POINT_STAT_HIRA_FLAG =
+#POINT_STAT_HIRA_WIDTH =
+#POINT_STAT_HIRA_VLD_THRESH =
+#POINT_STAT_HIRA_COV_THRESH =
+#POINT_STAT_HIRA_SHAPE =
+#POINT_STAT_HIRA_PROB_CAT_THRESH =
+
+#POINT_STAT_MESSAGE_TYPE_GROUP_MAP =