Include Notebook for Intermediary CESM Output Diagnostics (NCAR#340)

Include Cecile's spaghetti plot nb, pull utils out of nb, include intermediary outputs example

Author: TeaganKing

cupid_utils/cupid_utils/multi-component/spatial_means.py

@@ -0,0 +1,132 @@
+from __future__ import annotations
+
+import xarray as xr
+import numpy as np
+
+
+def global_mean(variable):
+    """
+    Description: compute the global mean (weigthed) of a variable
+    Argument:
+       ds: variable
+    Return:
+       ds_ann: annual mean
+    """
+    weights = np.cos(np.deg2rad(variable.lat))
+    variable_weighted = variable.weighted(weights)
+    variable_mean = variable_weighted.mean(("lon", "lat"))
+    return variable_mean
+
+
+def compute_ann_mean(filepath, case, var, lat1=None, lat2=None, lon1=None, lon2=None):
+    """
+    Description: Compute the annual mean within a specified latitude (lat1-lat2)
+    and longitude (lon1-lon2) range of the variable "var".
+
+    Arguments:
+        filepath = filepath
+        case = casename
+        var = variable name
+        lat1 = starting latitude
+        lat2 = ending latitude
+        lon1 = starting longitude
+        lon2 = ending longitude
+    """
+    filename = filepath + case + "/" + case + "." + var + ".nc"
+    ds = xr.open_dataset(filename)
+
+    # Select the subset of data within the specified latitude and longitude ranges before calculating the annual mean
+    ds_subset = ds.sel(lat=slice(lat1, lat2), lon=slice(lon1, lon2))
+
+    var_ann = ds_subset[var].groupby("time.year").mean()
+    var_lat_lon_ann = lat_lon_mean(var_ann, lat1, lat2, lon1, lon2)
+
+    return var_lat_lon_ann
+
+
+def compute_var_g_ann(filepath, case, var):
+    """
+    Compute the weighted annual global mean of
+    a given variable.
+    Argument:
+       case = casename
+       var = variable name
+    """
+    filename = filepath + case + "/" + case + "." + var + ".nc"
+    ds = xr.open_dataset(filename)
+    return global_mean(ds[var].groupby("time.year").mean())
+
+
+def lat_lon_mean(variable, lat1, lat2, lon1, lon2):
+    """
+    Description: Compute the mean (weighted by cosine of latitude) of a variable
+    within a specified latitude (lat1-lat2) and longitude (lon1-lon2) range.
+
+    Arguments:
+        variable: xarray DataArray representing the variable to be averaged.
+        lat1: Starting latitude for the range.
+        lat2: Ending latitude for the range.
+        lon1: Starting longitude for the range.
+        lon2: Ending longitude for the range.
+
+    Return:
+        variable_mean: The mean value of the variable within the specified lat/lon range.
+    """
+    # Select the subset of data within the specified latitude and longitude ranges
+    variable_subset = variable.sel(lat=slice(lat1, lat2), lon=slice(lon1, lon2))
+
+    # Compute weights as the cosine of the latitude, adjusted for the selected range
+    weights = np.cos(np.deg2rad(variable_subset.lat))
+
+    # Apply weighted mean over the subset
+    variable_weighted = variable_subset.weighted(weights)
+    variable_mean = variable_weighted.mean(("lon", "lat"))
+
+    return variable_mean
+
+
+def lat_lon_mean_norm(variable, lat1, lat2, lon1, lon2):
+    # TODO: This could be combined with lat_lon_mean by adding a normalize_weights argument
+    """
+    Description: Compute the mean (weighted by cosine of latitude) of a variable
+    within a specified latitude (lat1-lat2) and longitude (lon1-lon2) range.
+
+    Arguments:
+        variable: xarray DataArray representing the variable to be averaged.
+        lat1: Starting latitude for the range.
+        lat2: Ending latitude for the range.
+        lon1: Starting longitude for the range.
+        lon2: Ending longitude for the range.
+
+    Return:
+        variable_mean: The mean value of the variable within the specified lat/lon range.
+    """
+    # Select the data subset within the specified latitude and longitude ranges
+    variable_subset = variable.sel(lat=slice(lat1, lat2), lon=slice(lon1, lon2))
+
+    # Compute weights as the cosine of the latitude, adjusted for the selected range
+    # Ensure weights are normalized (sum to 1) over the selected latitude range for accurate weighting
+    latitudes = variable_subset.lat
+    weights = np.cos(np.deg2rad(latitudes))
+    weights /= weights.sum(dim="lat")
+
+    # Apply weighted mean over the subset
+    variable_weighted = variable_subset.weighted(weights)
+    variable_mean = variable_weighted.mean(("lon", "lat"))
+
+    return variable_mean
+
+
+def compute_var_zonal_ann(filepath, case, var):
+    """
+    Description: compute the annual global mean (weighted) of
+    a variable var
+    Argument:
+       case = casename
+       var = variable name
+    """
+    filename = filepath + case + "/" + case + "." + var + ".nc"
+    ds = xr.open_dataset(filename)
+    ds.mean(["lon"])
+    var_zonal_ann = ds[var].groupby("time.year").mean().mean(["lon"])
+    return var_zonal_ann

examples/intermediary_outputs/config.yml

@@ -0,0 +1,169 @@
+################## SETUP ##################
+
+################
+# Data Sources #
+################
+data_sources:
+    # run_dir is the path to the folder you want
+    ### all the files associated with this configuration
+    ### to be created in
+    run_dir: .
+
+    # nb_path_root is the path to the folder that cupid will
+    ### look for your template notebooks in. It doesn't have to
+    ### be inside run_dir, or be specific to this project, as
+    ### long as the notebooks are there
+    nb_path_root: ../../nblibrary
+
+######################
+# Computation Config #
+######################
+
+computation_config:
+
+    # default_kernel_name is the name of the environment that
+    ### the notebooks in this configuration will be run in by default.
+    ### It must already be installed on your machine. You can also
+    ### specify a different environment than the default for any
+    ### notebook in NOTEBOOK CONFIG
+    default_kernel_name: cupid-analysis
+
+    # log level sets the level of how verbose logging will be.
+    # options include: debug, info, warning, error
+    log_level: 'info'
+
+############# NOTEBOOK CONFIG #############
+
+############################
+# Notebooks and Parameters #
+############################
+
+# All parameters under global_params get passed to all the notebooks
+
+global_params: # TODO: a lot of these params may be irrelevant/misleading for this notebook
+  case_name: 'b.e30_alpha07c_cesm.B1850C_LTso.ne30_t232_wgx3.232'
+  base_case_name: 'b.e30_alpha07c_cesm.B1850C_LTso.ne30_t232_wgx3.228'
+  case_nickname: 'BLT1850_232'
+  base_case_nickname: 'BLT1850_228'
+  CESM_output_dir: /glade/campaign/cesm/development/cross-wg/diagnostic_framework/CESM_output_for_testing
+  ts_dir: null # If this is set to null, it will default to CESM_output_dir; if you don't have permissions to write to CESM_output_dir, you can specify a directory such as your scratch arcive directory
+  lc_kwargs:
+    threads_per_worker: 1
+
+timeseries: # TODO: will need to update timeseries portion of this in next PR
+  num_procs: 8
+  ts_done: [False, False]
+  overwrite_ts: [False, False]
+  case_name: ['b.e30_alpha07c_cesm.B1850C_LTso.ne30_t232_wgx3.232', 'b.e30_alpha07c_cesm.B1850C_LTso.ne30_t232_wgx3.228']
+
+  atm:
+    vars: ['RESTOM','TS']
+    derive_vars: []
+    hist_str: 'cam.h0a'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+    mapping_file: [Null, '/glade/campaign/cesm/cesmdata/inputdata/cpl/gridmaps/ne30pg3/map_ne30pg3_TO_fv0.9x1.25_blin.240826.nc']
+
+
+  lnd:
+    vars: []
+    derive_vars: []
+    hist_str: 'clm2.h0a'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+
+  ocn:
+    vars: []
+    derive_vars: []
+    hist_str: 'h.z'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+
+  ice:
+    vars: ['ICEFRAC']
+    derive_vars: []
+    hist_str: 'cice.h'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+
+  glc:
+    vars: []
+    derive_vars: []
+    hist_str: 'initial_hist'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+
+  rof:
+    vars: []
+    derive_vars: []
+    hist_str: 'h0'
+    start_years: [1,1]
+    end_years: [21,45]
+    level: 'lev'
+
+compute_notebooks:
+
+  # This is where all the notebooks you want run and their
+  # parameters are specified. Several examples of different
+  # types of notebooks are provided.
+
+  # The first key (here infrastructure) is the name of the
+  # notebook from nb_path_root, minus the .ipynb
+
+    infrastructure:
+      index:
+        parameter_groups:
+          none: {}
+
+    atm:
+      Global_TS_RESTOM_tseries:
+        parameter_groups:
+          none:
+            vars:
+              {'TS':'Global',
+               'RESTOM':'Global'}
+    ice:
+      Lab_Sea_ICEFRAC_tseries:
+        parameter_groups:
+          none:
+            vars:
+              {'ICEFRAC': 'Lab Sea'}
+
+########### JUPYTER BOOK CONFIG ###########
+
+##################################
+# Jupyter Book Table of Contents #
+##################################
+book_toc:
+
+  # See https://jupyterbook.org/en/stable/structure/configure.html for
+  # complete documentation of Jupyter book construction options
+
+  format: jb-book
+
+  # All filenames are notebook filename without the .ipynb, similar to above
+
+  root: infrastructure/index # root is the notebook that will be the homepage for the book
+  parts:
+
+    # Parts group notebooks into different sections in the Jupyter book
+    # table of contents, so you can organize different parts of your project.
+    # Each chapter is the name of one of the notebooks that you executed
+    # in compute_notebooks above, also without .ipynb
+
+    - caption: Diagnostic Output from Multiple Components
+      chapters:
+        - file: atm/Global_TS_ICEFRAC_RESTOM_tseries
+
+
+#####################################
+# Keys for Jupyter Book _config.yml #
+#####################################
+book_config_keys:
+
+  title: CESM Intermediate Diagnostic Output   # Title of your jupyter book