Merge pull request #15 from kthyng/proto

Updates for working prototype!

.gitignore

@@ -1,3 +1,5 @@
+*.png
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

ci/environment-py3.7.yml

@@ -5,8 +5,11 @@ dependencies:
   - python=3.7
   ############## These will have to be adjusted to your specific project
   - cartopy
+  - cf_xarray
+  - extract_model
   - matplotlib
   - numpy
+  - ocean_data_gateway
   - pandas
   - scipy
   - xarray

ci/environment-py3.8.yml

@@ -5,8 +5,11 @@ dependencies:
   - python=3.8
   ############## These will have to be adjusted to your specific project
   - cartopy
+  - cf_xarray
+  - extract_model
   - matplotlib
   - numpy
+  - ocean_data_gateway
   - pandas
   - scipy
   - xarray

docs/index.rst

@@ -9,7 +9,7 @@ Welcome to ocean-model-skill-assessor's documentation!
 .. toctree::
    :maxdepth: 3
 
-   prototype
+   Demo_workflows
    api
 
 

environment.yml

@@ -6,6 +6,7 @@ dependencies:
   - pytest
   # Examples (remove and add as needed)
   - cartopy
+  - cf_xarray
   - extract_model
   - jupyter
   - jupyterlab

notebooks/config_local.yaml

@@ -0,0 +1,44 @@
+---
+approach: "stations"
+loc_model: "https://thredds.cencoos.org/thredds/dodsC/CENCOOS_CA_ROMS_FCST.nc"
+axds:
+bbox:
+criteria:
+  salt:
+    name:
+      "sea_water_practical_salinity$"
+erddap:
+figname_map: "local_cli.png"
+figname_data_prefix: "local_cli_"
+local:
+  filenames:
+    - "edu_humboldt_tdp.csv"
+    - "bodega-bay-bml_wts.nc"
+only_search: false
+only_searchplot: false
+parallel: true
+readers:
+  - "local"
+run_qc: false
+skip_units: true
+stations:
+time_range:
+  - "2021-9-1"
+  - "2021-9-8"
+var_def:
+  salt:
+    units: "psu"
+    fail_span:
+      - -10
+      - 60
+    suspect_span:
+      - -1
+      - 45
+variables:
+  - "salt"
+xarray_kwargs:
+  chunks:
+    time:
+      1
+    depth:
+      1

notebooks/config_nonlocal.yaml

@@ -0,0 +1,45 @@
+---
+approach: "stations"
+loc_model: "https://thredds.cencoos.org/thredds/dodsC/CENCOOS_CA_ROMS_FCST.nc"
+axds:
+bbox:
+criteria:
+  salt:
+    name:
+      "sea_water_practical_salinity$"
+erddap:
+  known_server:
+    "ioos"
+figname_map: "nonlocal_cli.png"
+figname_data_prefix: "nonlocal_cli_"
+local:
+only_search: false
+only_searchplot: false
+parallel: true
+readers:
+  - "erddap"
+run_qc: false
+skip_units: true
+stations:
+  - "edu_humboldt_tdp"
+  - "bodega-bay-bml_wts"
+time_range:
+  - "2021-9-1"
+  - "2021-9-8"
+var_def:
+  salt:
+    units: "psu"
+    fail_span:
+      - -10
+      - 60
+    suspect_span:
+      - -1
+      - 45
+variables:
+  - "salt"
+xarray_kwargs:
+  chunks:
+    time:
+      1
+    depth:
+      1

notebooks/config_nonlocal_region.yaml

@@ -0,0 +1,47 @@
+---
+approach: "region"
+loc_model: "https://thredds.cencoos.org/thredds/dodsC/CENCOOS_CA_ROMS_FCST.nc"
+axds:
+bbox:
+  - -124.5
+  - 40
+  - -123.5
+  - 42
+criteria:
+  salt:
+    name:
+      "sea_water_practical_salinity$"
+erddap:
+  known_server:
+    "ioos"
+figname_map: "nonlocal_cli_region.png"
+figname_data_prefix: "nonlocal_cli__region"
+local:
+only_search: false
+only_searchplot: false
+parallel: true
+readers:
+  - "erddap"
+run_qc: false
+skip_units: true
+stations:
+time_range:
+  - "2021-9-1"
+  - "2021-9-8"
+var_def:
+  salt:
+    units: "psu"
+    fail_span:
+      - -10
+      - 60
+    suspect_span:
+      - -1
+      - 45
+variables:
+  - "salt"
+xarray_kwargs:
+  chunks:
+    time:
+      1
+    depth:
+      1

ocean_model_skill_assessor/CLI.py

@@ -0,0 +1,78 @@
+"""
+Command Line Interface.
+"""
+
+import argparse
+
+import ocean_data_gateway as odg
+import yaml
+
+import ocean_model_skill_assessor as omsa
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    "config_file", help="Give path to configuration file. Should be yaml."
+)
+
+args = parser.parse_args()
+config_file = args.config_file
+
+with open(config_file, "r") as ymlfile:
+    cfg = yaml.load(ymlfile)
+
+approach = cfg["approach"]
+loc_model = cfg["loc_model"]
+axds = cfg["axds"]
+bbox = cfg["bbox"]
+criteria = cfg["criteria"]
+erddap = cfg["erddap"]
+figname_map = cfg["figname_map"]
+figname_data_prefix = cfg["figname_data_prefix"]
+local = cfg["local"]
+only_search = cfg["only_search"]
+only_searchplot = cfg["only_searchplot"]
+parallel = cfg["parallel"]
+readers = cfg["readers"]
+run_qc = cfg["run_qc"]
+skip_units = cfg["skip_units"]
+stations = cfg["stations"]
+time_range = cfg["time_range"]
+var_def = cfg["var_def"]
+variables = cfg["variables"]
+xarray_kwargs = cfg["xarray_kwargs"]
+
+omsa.set_criteria(criteria)
+
+if readers is not None:
+    input_readers = readers
+    readers = []
+    if "local" in input_readers:
+        readers.append(odg.local)
+    if "erddap" in input_readers:
+        readers.append(odg.erddap)
+    if "axds" in input_readers:
+        readers.append(odg.axds)
+
+search = omsa.run(
+    approach=approach,
+    loc_model=loc_model,
+    axds=axds,
+    bbox=bbox,
+    criteria=criteria,
+    erddap=erddap,
+    figname_map=figname_map,
+    figname_data_prefix=figname_data_prefix,
+    local=local,
+    only_search=only_search,
+    only_searchplot=only_searchplot,
+    parallel=parallel,
+    readers=readers,
+    run_qc=run_qc,
+    skip_units=skip_units,
+    time_range=time_range,
+    stations=stations,
+    var_def=var_def,
+    variables=variables,
+    xarray_kwargs=xarray_kwargs,
+)

ocean_model_skill_assessor/__init__.py

@@ -6,6 +6,7 @@
 
 import ocean_model_skill_assessor.accessor  # noqa: F401
 
+from .main import run
 from .plot import map, time_series  # noqa: F401
 from .stats import (  # noqa: F401
     compute_bias,
@@ -17,6 +18,7 @@
     compute_root_mean_square_error,
     compute_stats,
 )
+from .utils import set_criteria
 
 
 try:

ocean_model_skill_assessor/accessor.py

@@ -2,11 +2,29 @@
 Class to facilitate some functions directly on DataFrames.
 """
 
+import re
+
 import pandas as pd
 
 import ocean_model_skill_assessor
 
 
+regex = {
+    "time": {"name": re.compile("\\bt\\b|(time|min|hour|day|week|month|year)[0-9]*")},
+    "Z": {
+        "name": re.compile(
+            "(z|nav_lev|gdep|lv_|[o]*lev|bottom_top|sigma|h(ei)?ght|altitude|depth|"
+            "isobaric|pres|isotherm)[a-z_]*[0-9]*"
+        )
+    },
+    "Y": {"name": re.compile("y|j|nlat|nj")},
+    "latitude": {"name": re.compile("y?(nav_lat|lat|gphi)[a-z0-9]*")},
+    "X": {"name": re.compile("x|i|nlon|ni")},
+    "longitude": {"name": re.compile("x?(nav_lon|lon|glam)[a-z0-9]*")},
+}
+regex["T"] = regex["time"]
+
+
 @pd.api.extensions.register_dataframe_accessor("omsa")
 class SkillAssessorAccessor:
     """Class to facilitate some functions directly on DataFrames."""
@@ -42,3 +60,31 @@ def plot(self, **kwargs):
         ocean_model_skill_assessor.time_series.plot(
             self.df["obs"], self.df["model"], **kwargs
         )
+
+
+@pd.api.extensions.register_dataframe_accessor("cf")
+class cf_pandas:
+    """Bring cf-xarray variable and coord/axis identification to pandas!"""
+
+    def __init__(self, obj):
+        """Initialize with pandas DataFrame."""
+        self.df = obj
+
+    def __getitem__(self, key):
+        """This allows for df.cf[varname], etc."""
+
+        # combine with regex from cf-xarray just for pandas cf
+        criteria = ocean_model_skill_assessor.criteria
+        criteria.update(regex)
+
+        results = []
+        if key in criteria:
+            for criterion, patterns in criteria[key].items():
+                results.extend(
+                    list(
+                        set([var for var in self.df.columns if re.match(patterns, var)])
+                    )
+                )
+
+        key = list(set(results))[0]
+        return self.df[key]