Merge PR #340 (Replace whitespace in Ref and Dev version labels)

This merge brings PR #340 (Replace whitespace in Ref and Dev version
labels in benchmarking code, by @yantosca) into the GCPy 1.6.0
development stream.

This PR makes sure that any spaces in the Ref and Dev version
labels are replaced with underscores.  This will prevent
file names from having spaces.

Signed-off-by: Bob Yantosca <[email protected]>

CHANGELOG.md

@@ -26,6 +26,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 - In environment files `read_the_docs_environment.yml` and `read_the_docs_requirements.txt`
   - Update `jinja` to 3.1.4 (fixes a security issue)
 - Update `gcpy/setup.py` with the new Python package version numbers
+- Updated code in `gcpy/benchmark/modules/` to replace whitespace in Ref and Dev labels with underscores
 
 ### Fixed
 - Fixed formatting error in `.github/workflows/stale.yml` that caused the Mark Stale Issues action not to run

gcpy/benchmark/modules/benchmark_drydep.py

@@ -1,14 +1,13 @@
 """
 Specific utilities for creating plots from GEOS-Chem benchmark simulations.
 """
-import os
 import gc
 import numpy as np
 from gcpy import util
 from gcpy.plot.compare_single_level import compare_single_level
 from gcpy.benchmark.modules.benchmark_utils import \
-    get_lumped_species_definitions, make_output_dir, \
-    pdf_filename, print_sigdiffs, read_ref_and_dev
+    get_common_varnames, make_output_dir, pdf_filename, \
+    print_sigdiffs, read_ref_and_dev
 
 # Suppress numpy divide by zero warnings to prevent output spam
 np.seterr(divide="ignore", invalid="ignore")
@@ -95,6 +94,10 @@ def make_benchmark_drydep_plots(
         msg = "The spcdb_dir argument has not been specified!"
         raise ValueError(msg)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = util.replace_whitespace(refstr)
+    devstr = util.replace_whitespace(devstr)
+
     # Create directory for plots (if it doesn't exist)
     dst = make_output_dir(
         dst,

gcpy/benchmark/modules/benchmark_funcs.py

@@ -16,6 +16,7 @@
 from gcpy import util
 from gcpy.regrid import create_regridders
 from gcpy.grid import get_troposphere_mask
+from gcpy.util import replace_whitespace
 from gcpy.units import convert_units
 from gcpy.constants import COL_WIDTH, MW_AIR_g, skip_these_vars, TABLE_WIDTH
 from gcpy.plot.compare_single_level import compare_single_level
@@ -155,6 +156,10 @@ def create_total_emissions_table(
         quiet=True
     )
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Get the list of emission variables for which we will print totals
     # ==================================================================
@@ -447,6 +452,10 @@ def create_global_mass_table(
         quiet=True
     )
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Open file for output
     # ==================================================================
@@ -692,6 +701,10 @@ def create_mass_accumulation_table(
         quiet=True
     )
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Open file for output
     # ==================================================================
@@ -1032,6 +1045,10 @@ def make_benchmark_conc_plots(
     else:
         extra_title_txt = None
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Pick the proper function to read the data
     reader = util.dataset_reader(time_mean, verbose=verbose)
 
@@ -1710,6 +1727,10 @@ def make_benchmark_emis_plots(
     else:
         extra_title_txt = None
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Get the function that will read the dataset
     reader = util.dataset_reader(time_mean, verbose=verbose)
 
@@ -2098,6 +2119,10 @@ def make_benchmark_emis_tables(
     if not os.path.isdir(emisdir):
         os.mkdir(emisdir)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Read data from netCDF into Dataset objects
     # ==================================================================
@@ -2343,6 +2368,10 @@ def make_benchmark_jvalue_plots(
     # Create the directory for output
     util.make_directory(dst, overwrite)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Get the function that will read file(s) into a Dataset
     reader = util.dataset_reader(time_mean, verbose=verbose)
 
@@ -2727,6 +2756,10 @@ def make_benchmark_aod_plots(
     else:
         extra_title_txt = None
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Get the function that will read file(s) into a dataset
     reader = util.dataset_reader(time_mean, verbose=verbose)
 
@@ -3009,11 +3042,19 @@ def make_benchmark_mass_tables(
             which do not contain the Area variable.
             Default value: ''
     """
+    # ==================================================================
+    # Initialization
+    # ==================================================================
+
     # Make sure the species database folder is passed
     if spcdb_dir is None:
         msg = "The 'spcdb_dir' argument has not been specified!"
         raise ValueError(msg)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Define destination directory
     # ==================================================================
@@ -3275,11 +3316,19 @@ def make_benchmark_mass_accumulation_tables(
             Directory of species_datbase.yml file
             Default value: None
     """
+    # ==================================================================
+    # Initialization
+    # ==================================================================
+
     # Make sure the species database folder is passed
     if spcdb_dir is None:
         msg = "The 'spcdb_dir' argument has not been specified!"
         raise ValueError(msg)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Define destination directory
     # ==================================================================
@@ -3543,10 +3592,16 @@ def make_benchmark_oh_metrics(
     """
 
     # ==================================================================
-    # Define destination directory
+    # Initialization
     # ==================================================================
+
+    # Define destination directory
     util.make_directory(dst, overwrite)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # ==================================================================
     # Read data from netCDF into Dataset objects
     # ==================================================================
@@ -3833,6 +3888,10 @@ def make_benchmark_wetdep_plots(
         if not os.path.isdir(targetdst):
             os.mkdir(targetdst)
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Get the function that will read file(s) into a dataset
     reader = util.dataset_reader(time_mean, verbose=verbose)
 
@@ -4388,6 +4447,9 @@ def make_benchmark_operations_budget(
             Directory containing the species_database.yml file.
             Default value: None
     """
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
 
     # ------------------------------------------
     # Column sections
@@ -5083,6 +5145,10 @@ def create_benchmark_summary_table(
     # Open file for output
     # ==================================================================
 
+    # Replace whitespace in the ref and dev labels
+    refstr = replace_whitespace(refstr)
+    devstr = replace_whitespace(devstr)
+
     # Create the directory for output
     util.make_directory(dst, overwrite)
 

gcpy/benchmark/modules/benchmark_gcclassic_stats.py

@@ -9,7 +9,7 @@
 """
 import sys
 import requests
-from gcpy.util import verify_variable_type
+from gcpy.util import replace_whitespace, verify_variable_type
 
 # ----------------------------------------------------------------------
 # Global variables
@@ -113,7 +113,7 @@ def scrape_stats(text):
             stats["CH3CCl3"] = line.split(":")[1].strip()
         if line_count == 18 and "Dev" in line:
             stats["Mean OH"] = line.split(":")[1].strip()
-            
+
         # Skip commands
         if "++ sed" in line:
             line_count += 1
@@ -168,6 +168,10 @@ def main(ref_label, dev_label):
     verify_variable_type(ref_label, str)
     verify_variable_type(dev_label, str)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Scrape the log file text into a variable
     bmk_id = f"gcc-4x5-1Mon-{dev_label}"
     text = get_text_from_web(LOG_TEMPLATE.replace("ID", bmk_id))

gcpy/benchmark/modules/benchmark_mass_cons_table.py

@@ -9,8 +9,8 @@
 from gcpy.constants import skip_these_vars
 from gcpy.units import convert_units
 from gcpy.util import \
-    replace_whitespace, dataset_reader, get_area_from_dataset, \
-    make_directory, read_config_file, verify_variable_type
+    dataset_reader, get_area_from_dataset, make_directory, \
+    read_config_file, replace_whitespace, verify_variable_type
 from gcpy.benchmark.modules.benchmark_utils import \
     get_datetimes_from_filenames
 
@@ -317,6 +317,10 @@ def make_benchmark_mass_conservation_table(
     # Create the destination folder
     make_directory(dst, overwrite)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Get a list of properties for the given species
     metadata = get_passive_tracer_metadata(spcdb_dir)
 

gcpy/benchmark/modules/benchmark_models_vs_obs.py

@@ -21,7 +21,8 @@
 import numpy as np
 import xarray as xr
 from gcpy.constants import skip_these_vars
-from gcpy.util import verify_variable_type, dataset_reader, make_directory
+from gcpy.util import \
+    dataset_reader, make_directory, replace_whitespace, verify_variable_type
 from gcpy.cstools import extract_grid
 from gcpy.grid import get_nearest_model_data
 from gcpy.benchmark.modules.benchmark_utils import \
@@ -51,6 +52,11 @@ def read_nas(
     if verbose:
         print(f"read_nas: Reading {input_file}")
 
+    # Initialize
+    lon = 0.0
+    lat = 0.0
+    alt = 0.0
+
     with open(input_file, encoding='UTF-8') as the_file:
         header = np.array(
             [next(the_file) for x in range(155) ]
@@ -113,11 +119,11 @@ def read_nas(
         index=obs_dataframe.index
     )
     obs_site_coords = { site:
-          {
-              'lon': lon,
-              'lat': lat,
-              'alt': alt
-          }
+        {
+            'lon': lon,
+            'lat': lat,
+            'alt': alt
+        }
     }
 
     return obs_dataframe, obs_site_coords
@@ -194,13 +200,12 @@ def read_model_data(
     Returns
     dataarray : xr.DataArray : GEOS-Chem data read from disk
     """
-
     # Read the Ref and Dev model data
     reader = dataset_reader(
         multi_files=True,
         verbose=verbose,
     )
-    
+
     # Read data and rename SpeciesConc_ to SpeciesConcVV_, if necessary
     # (needed for backwards compatibility with older versions.)
     dataset = reader(filepaths,drop_variables=skip_these_vars).load()
@@ -755,6 +760,10 @@ def make_benchmark_models_vs_obs_plots(
     verify_variable_type(dev_filepaths, (str, list))
     verify_variable_type(dev_label, str)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Create the destination folder
     make_directory(
         dst,

gcpy/benchmark/modules/benchmark_models_vs_sondes.py

@@ -11,7 +11,7 @@
 import matplotlib.pyplot as plt
 from gcpy.cstools import extract_grid
 from gcpy.grid import get_nearest_model_data, get_vert_grid
-from gcpy.util import make_directory, verify_variable_type
+from gcpy.util import make_directory, replace_whitespace, verify_variable_type
 from gcpy.benchmark.modules.benchmark_utils import \
     read_ref_and_dev, rename_speciesconc_to_speciesconcvv
 
@@ -522,6 +522,10 @@ def make_benchmark_models_vs_sondes_plots(
     verify_variable_type(dev_filepaths, (str, list))
     verify_variable_type(dev_label, str)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Create the destination folder
     make_directory(
         dst,

gcpy/benchmark/modules/benchmark_scrape_gcclassic_timers.py

@@ -261,6 +261,10 @@ def make_benchmark_gcclassic_timing_table(
     # Create the destination folder
     make_directory(dst, overwrite)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Strip timing info from JSON/text file(s) and sum the them.
     ref_timers = sum_timers(read_gcclassic(ref_files))
     dev_timers = sum_timers(read_gcclassic(dev_files))

gcpy/benchmark/modules/benchmark_scrape_gchp_timers.py

@@ -331,6 +331,10 @@ def make_benchmark_gchp_timing_table(
     # Create the destination folder
     make_directory(dst, overwrite)
 
+    # Replace whitespace in the ref and dev labels
+    ref_label = replace_whitespace(ref_label)
+    dev_label = replace_whitespace(dev_label)
+
     # Strip timing info from JSON/text file(s) and sum the them.
     ref_timers = sum_timers(read_timing_data(ref_files))
     dev_timers = sum_timers(read_timing_data(dev_files))