Merge branch 'develop' into hysplitdev

.codespell-exclude

@@ -0,0 +1,37 @@
+          <th>CAf</th>
+          <td>CAf</td>
+   "SIZ",	"Size distribution"
+   "ALL",	"All of the above retrievals (SIZ to FLUX) in one file"
+    hda = hysplit.combine_dataset([file1,file2], drange=[d1,d2])
+   print(hda)
+    metdata = ish_mod.ISH()
+    df = metdata.add_data(dates, country=None, box=area, resample=False)
+        "CNA",
+        d["CAf"] = add_multiple_lazy(d, newkeys, weights=neww)
+        d["CAf"] = d["CAf"].assign_attrs(
+            {"units": r"$\mu g m^{-3}$", "name": "CAf", "long_name": "Fine Mode particulate CA"}
+        "CAf": ["CAf"],
+    #  value is tuple (filename, metdata)
+        Scrip file path for unstructured grid output
+    if "CAf" in var_list:
+                "PRES": "pres_pa_mid",
+        CMAQ model data including new CAf calculation
+    # allvars = Series(["TEMP", "Q", "PRES"])
+    #         "p": dset["PRES"][:].compute().values
+        var_list.append("pres")
+        if var == "pres":  # Insert special versions.
+        "SIZ",
+                df.loc[con, "variable"] = "Caf"
+                df.loc[con, "variable"] = "Laf"
+            ["AZ", "CO", "ID", "KS", "MT", "NE", "NV", "NM", "ND", "SD", "UT", "WY"], dtype="|S12"
+    r = array(["AZ", "CO", "ID", "KS", "MT", "NE", "NV", "NM", "ND", "SD", "UT", "WY"])
+    ser = array(["Southeast" for i in se])
+    region = concatenate([ser, ner, ncr, scr, rr, pr])
+        "North Dakota": "ND",
+        fo = self.fs.open(f)
+        out = xr.open_dataset(fo, engine="h5netcdf")
+    """Read SNPP OMPS Nadir Mapper Total Column Ozone L2 data from NASA GES DISC
+    a.prod = "SIZ"
+    df = aeronet.add_data(dates, inv_type="ALM15", product="SIZ")
+    df = aeronet.add_data(dates, inv_type="HYB15", product="SIZ")
+    # https://aeronet.gsfc.nasa.gov/cgi-bin/print_web_data_inv_v3?site=Cart_Site&year=2002&month=6&day=1&year2=2003&month2=6&day2=14&product=SIZ&AVG=20&ALM15=1&if_no_html=1

.github/workflows/ci.yml

@@ -11,7 +11,7 @@ on:
 
 jobs:
   test:
-    name: Test
+    name: Test (Py ${{ matrix.python-version }})
     runs-on: ubuntu-latest
     if: github.repository == 'noaa-oar-arl/monetio'
     strategy:
@@ -22,29 +22,35 @@ jobs:
         shell: bash -l {0}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - name: Set up Python (micromamba)
-        uses: mamba-org/provision-with-micromamba@v15
+      - name: Set up Python (micromamba) [>3.6]
+        if: matrix.python-version != '3.6'
+        uses: mamba-org/setup-micromamba@v1
+        with:
+          environment-file: environment-dev.yml
+          cache-environment: true
+          create-args: >-
+            python=${{ matrix.python-version }}
+
+      - name: Set up Python (micromamba) [3.6]
+        if: matrix.python-version == '3.6'
+        uses: mamba-org/setup-micromamba@v1
         with:
           environment-file: environment-dev.yml
-          cache-env: true
-          extra-specs: |
+          cache-environment: true
+          create-args: >-
             python=${{ matrix.python-version }}
+            attrs=22.2.0
 
       - name: Test with pytest
-        run: pytest -n auto -v -k 'not aqs'
+        run: pytest -n auto -v
 
       - name: Test with pytspack installed
         run: |
           pip install https://github.com/noaa-oar-arl/pytspack/archive/master.zip
           pytest -n auto -v -k with_pytspack
 
-      - name: Downgrade OpenSSL and test AQS
-        run: |
-          micromamba install 'openssl <3'
-          pytest -n auto -v -k aqs
-
   docs:
     name: Check docs build
     runs-on: ubuntu-latest
@@ -54,16 +60,13 @@ jobs:
         shell: bash -l {0}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set up Python (micromamba)
-        uses: mamba-org/provision-with-micromamba@v15
+        uses: mamba-org/setup-micromamba@v1
         with:
           environment-file: docs/environment-docs.yml
-          cache-env: true
-
-      - name: Downgrade OpenSSL (for AQS URL linkcheck)
-        run: micromamba install 'openssl <3'
+          cache-environment: true
 
       - name: linkcheck
         run: sphinx-build -b linkcheck docs docs/_build/linkcheck

.github/workflows/lint.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'noaa-oar-arl/monetio'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: actions/setup-python@v4
         with:
           python-version: "3.9"
@@ -24,7 +24,18 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'noaa-oar-arl/monetio'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: citation-file-format/cffconvert-github-action@2.0.0
         with:
           args: "--validate"
+
+  spell:
+    name: codespell
+    runs-on: ubuntu-latest
+    if: github.repository == 'noaa-oar-arl/monetio'
+    steps:
+      - uses: actions/checkout@v4
+      - uses: codespell-project/actions-codespell@v2
+        with:
+          exclude_file: .codespell-exclude
+          skip: "./monetio/data/aqs_qualifiers.csv,./monetio/data/cemsinfo.csv,./monetio/data/stations.tsv"

.pre-commit-config.yaml

@@ -3,6 +3,7 @@ repos:
     rev: "v4.4.0"
     hooks:
       - id: trailing-whitespace
+        exclude: tdump\.[0-9]*
       - id: end-of-file-fixer
       - id: check-docstring-first
       - id: check-yaml

docs/conf.py

@@ -60,6 +60,7 @@
     "https://doi.org/10.1080/10473289.2005.10464718",
     "https://www.camx.com",
 ]
+user_agent = "Mozilla/5.0 (X11; Linux x86_64; rv:25.0) Gecko/20100101 Firefox/25.0"
 
 # -- Extension configuration -------------------------------------------------
 

docs/environment-docs.yml

@@ -3,7 +3,7 @@ channels:
   - conda-forge
   - nodefaults
 dependencies:
-  - python=3.9
+  - python=3.10
   #
   # core
   - dask

docs/index.rst

@@ -64,8 +64,8 @@ Supported datasets
 * `HYSPLIT <https://www.ready.noaa.gov/HYSPLIT.php/>`_
 * `CMAQ <https://www.epa.gov/cmaq/>`_
 * `CAMx <https://www.camx.com/about/>`_
-* FV3-CHEM (comming soon)
-* WRF-CHEM (comming soon)
+* FV3-CHEM (coming soon)
+* WRF-CHEM (coming soon)
 
 **Supported Observations**
 

docs/models.rst

@@ -242,7 +242,7 @@ The source dimension tags which source term the run used.
     Attributes:
         sample time hours:  1.0
 
-To calcluate mass loading
+To calculate mass loading
 
 .. code-block:: python
 
@@ -260,7 +260,7 @@ To find top heights
    massload =  hypslit.hysp_hysp_heights(hxr, threshold=0, height_mult=1/1000.0, mult=1e10, mass_load=False)
 
 returns xarray DataArray which gives top height of each level which contains mass loading higher
-than the given threshold value. mult is a mutiplicative factor applied before thresholding.
+than the given threshold value. mult is a multiplicative factor applied before thresholding.
 height_mult is a multiplicative factor used to convert heights from meters to some other unit.
 In this example heights are converted to km.
 mass_load is a boolean which indicates whether the height should be determined from the mass loading value (True)

docs/observations.rst

@@ -23,7 +23,7 @@ AirNow is the near realtime dataset for air composition and meteorology measurem
 
     "The U.S. EPA AirNow program is the national repository of real time air quality data and forecasts for the United States. AirNow is the vehicle for providing timely Air Quality Index (AQI) information to the public, media outlets, other federal agencies and their applications, and to the research community. The system is managed by the U.S. EPA’s Office of Air Quality Planning and Standards Outreach and Information Division, Information Transfer Group in Research Triangle Park (RTP), North Carolina. AirNow is currently hosted and operated at a contractor facility, known as the AirNow Data Management Center (DMC), which currently resides outside of RTP." - https://www.airnow.gov/index.cfm?action=ani.airnowUS
 
-AirNow_ data can be dowloaded from the Amazon S3 server and aggregated using the
+AirNow_ data can be downloaded from the Amazon S3 server and aggregated using the
 monet.obs.airnow class.  For example,lets say that we want to look at data from
 2018-05-01 to 2018-05-05.
 
@@ -46,7 +46,7 @@ This provides a structured :py:class:`~pandas.DataFrame`.
 
     df.head()
 
-Some users may want to keep a local copy of the data and not have to retrive the data
+Some users may want to keep a local copy of the data and not have to retrieve the data
 each time they want to access the data.  There is a simple kwarg that can be used to
 download the data, *download=True*.  By default, *download* is set to False.
 
@@ -93,8 +93,8 @@ MONET is able to use the EPA AQS data that is collected and reported on an hourl
     prepare reports for Congress as mandated by the Clean Air Act." - https://www.epa.gov/aqs
 
 We will begin by loading hourly ozone concentrations from 2018.  The EPA AQS data
-is seperated into yearly files and seperate files for hourly and daily data.  The
-files are also seperated by which variable is measured.  For instance, hourly ozone files
+is separated into yearly files and separate files for hourly and daily data.  The
+files are also separated by which variable is measured.  For instance, hourly ozone files
 for the entire year of 2018 are found in https://aqs.epa.gov/aqsweb/airdata/hourly_44201_2018.zip.
 We will first load a single variable and then add multiple later on.
 
@@ -146,13 +146,13 @@ Let's load variables PM10 and OZONE using hourly data to get an idea of how to g
 
   df = aqs.add_data(dates, param=['OZONE','PM10'])
 
-Loading Specfic Network
-^^^^^^^^^^^^^^^^^^^^^^^
+Loading Specific Network
+^^^^^^^^^^^^^^^^^^^^^^^^
 
 Sometimes you may want to load a specific network that is available in the AQS data
 files.  For instance, lets load data from the Chemical Speciation Network (CSN;
 https://www.epa.gov/amtic/chemical-speciation-network-csn).
-As of writting this tutorial we will load the 2017 data as it is complete.
+As of writing this tutorial we will load the 2017 data as it is complete.
 
 .. code::   python
 
@@ -176,7 +176,7 @@ AERONET
 
     "The AERONET (AErosol RObotic NETwork) project is a federation of ground-based
     remote sensing aerosol networks established by NASA and PHOTONS (PHOtométrie pour le Traitement Opérationnel de Normalisation Satellitaire; Univ. of Lille 1, CNES, and CNRS-INSU)
-    and is greatly expanded by networks (e.g., RIMA, AeroSpan, AEROCAN, and CARSNET) and collaborators from national agencies, institutes, universities, individual scientists, and partners. Fo more than 25 years, the project has provided long-term, continuous and readily accessible public domain database of aerosol optical, microphysical and radiative properties for aerosol research and characterization, validation of satellite retrievals, and synergism with other databases. The network imposes standardization of instruments, calibration, processing and distribution.
+    and is greatly expanded by networks (e.g., RIMA, AeroSpan, AEROCAN, and CARSNET) and collaborators from national agencies, institutes, universities, individual scientists, and partners. For more than 25 years, the project has provided long-term, continuous and readily accessible public domain database of aerosol optical, microphysical and radiative properties for aerosol research and characterization, validation of satellite retrievals, and synergism with other databases. The network imposes standardization of instruments, calibration, processing and distribution.
 
     AERONET collaboration provides globally distributed observations of spectral aerosol optical depth (AOD), inversion products, and precipitable water in diverse aerosol regimes. Version 3 AOD data are computed for three data quality levels: Level 1.0 (unscreened), Level 1.5 (cloud-screened and quality controlled), and Level 2.0 (quality-assured). Inversions, precipitable water, and other AOD-dependent products are derived from these levels and may implement additional quality checks. " -https://aeronet.gsfc.nasa.gov
 
@@ -206,7 +206,7 @@ Available Measurements
    :widths: 20, 20
 
    "SIZ",	"Size distribution"
-   "RIN",	"Refractive indicies (real and imaginary)"
+   "RIN",	"Refractive indices (real and imaginary)"
    "CAD",	"Coincident AOT data with almucantar retrieval"
    "VOL",	"Volume concentration, volume mean radius, effective radius and standard deviation"
    "TAB",	"AOT absorption"
@@ -277,7 +277,7 @@ NTN
     "The NTN is the only network providing a long-term record of precipitation chemistry across the United States.
 
     Sites predominantly are located away from urban areas and point sources of pollution. Each site has a precipitation
-    chemistry collector and gage. The automated collector ensures that the sample is exposed only during precipitation (wet-only-sampling)."
+    chemistry collector and gauge. The automated collector ensures that the sample is exposed only during precipitation (wet-only-sampling)."
     - https://nadp.slh.wisc.edu/NTN/
 
 Available Measurements
@@ -296,14 +296,14 @@ Available Measurements
 MDN
 ^^^
 
-    "The MDN is the only network providing a longterm record of total mercury (Hg) concentration and deposition in precipitation in the United States and Canada. All MDN sites follow standard procedures and have uniform precipitation chemistry collectors and gages. The automated collector has the same basic design as the NTN collector but is modified to preserve mercury. Modifications include a glass funnel, connecting tube, bottle for collecting samples, and an insulated enclosure to house this sampling train. The funnel and connecting tube reduce sample exposure to the open atmosphere and limit loss of dissolved mercury. As an additional sample preservation measure, the collection bottle is charged with 20 mL of a one percent hydrochloric acid solution."
+    "The MDN is the only network providing a longterm record of total mercury (Hg) concentration and deposition in precipitation in the United States and Canada. All MDN sites follow standard procedures and have uniform precipitation chemistry collectors and gauges. The automated collector has the same basic design as the NTN collector but is modified to preserve mercury. Modifications include a glass funnel, connecting tube, bottle for collecting samples, and an insulated enclosure to house this sampling train. The funnel and connecting tube reduce sample exposure to the open atmosphere and limit loss of dissolved mercury. As an additional sample preservation measure, the collection bottle is charged with 20 mL of a one percent hydrochloric acid solution."
     - https://nadp.slh.wisc.edu/MDN/
 
 Available Measurements
 ======================
 
 * net concentration of methyl mercury in ng/L (conc)
-* precipitation amount (in inches) reported by the raingage for the entire sampling period. (raingage)
+* precipitation amount (in inches) reported by the rain gauge for the entire sampling period. (rain gauge)
 * Mg2+ (mg)
 * Na+ (na)
 * K+ (k)
@@ -364,7 +364,7 @@ To see what data is in the DataFrame simply output the column header values
 
 .. code:: python
 
-    print(df.colums.values)
+    print(df.columns.values)
 
 Available Measurements
 ^^^^^^^^^^^^^^^^^^^^^^

docs/tutorial/CMAQ_hi_volcano.rst

@@ -18,7 +18,7 @@ eruption. First, import MONET and several helper functions for later.
 Now the data can be downloaded from the MONET github page in the
 MONET/data directory. We will assume you already have this downloaded
 and will proceed. Open the simulation. As of right now we still require
-that a seperate grdcro2d (grddot2d) file be loaded for the mass points
+that a separate grdcro2d (grddot2d) file be loaded for the mass points
 (dot points) using the ``grid`` kwarg.
 
 .. code:: python
@@ -138,7 +138,7 @@ aggrigate species in the concentration file.
 
 
 Notice that this looks like the ncdump of the file except that there are
-seperate coordinates including the latitude and longitude and the time
+separate coordinates including the latitude and longitude and the time
 as numpy.datetime64 objects. Also included is the proj4 string, a pyresample area grid
 and default mapping tables to several different observational datasets.
 
@@ -195,7 +195,7 @@ will add a map using the MONETAccessor and use the ``robust=True`` kwarg.
 Better but we can still do much more. There is low concentrations on
 most of this map making it hard to notice the extremely high values and
 the SO2 data is in ppmv and not ppbv as normally viewed as. Also, a
-logscale may be better fo this type of data as it goes from 0-20000 ppbv
+logscale may be better for this type of data as it goes from 0-20000 ppbv
 rather than a linear scale.
 
 .. code:: python
@@ -208,7 +208,7 @@ rather than a linear scale.
 .. image:: CMAQ_hi_volcano_files/CMAQ_hi_volcano_11_3.png
 
 
-Now let’s us view serveral time slices at once. We will average in time
+Now let’s us view several time slices at once. We will average in time
 (every 8 hours) to give us 6 total subplots.
 
 .. code:: python
@@ -246,7 +246,7 @@ It is often useful to be able to pair model data with observational
 data. MONET uses the pyresample library
 (http://pyresample.readthedocs.io/en/latest/) to do a nearest neighbor
 interpolation. First let us get the airnow data for the dates of the
-simulation. We will also rotate it from the raw AirNow long format (stacked variables) to a wide format (each variable is a seperate column)
+simulation. We will also rotate it from the raw AirNow long format (stacked variables) to a wide format (each variable is a separate column)
 
 
 .. code:: python
@@ -288,7 +288,7 @@ new column (model).
 
 
 Let’s look at the distributions to see if the two overlap to get a
-general scence of performance.
+general sense of performance.
 
 .. code:: python
 

docs/tutorial/NESDIS_VIIRS_AOD.rst

@@ -100,7 +100,7 @@ Notice that the dimensions changed from 1800x3600 to 720x1440.
 Open Multiple Days
 ~~~~~~~~~~~~~~~~~~
 
-If you want to open multiple days in a sinlge call you could use the
+If you want to open multiple days in a single call you could use the
 open\_mfdataset. Lets grab the first nine days of July 2018.
 
 .. code-block:: python

docs/tutorial/_models.rst

@@ -103,7 +103,7 @@ distinguish aerosols which these readers do not process well.
 
 fv3grib2nc4.py like nemsio2nc4.py tool is a command line tool created to
 convert the grib2 aerosol data to netcdf files. fv3grib2nc4.py will
-create seperate files for each of the three layer types; '1 hybrid
+create separate files for each of the three layer types; '1 hybrid
 layer', 'entire atmosphere', and 'surface'. These are the three layers
 that currently hold aerosol data. The tool is available at
 https://github.com/bbakernoaa/fv3grib2nc4
@@ -150,7 +150,7 @@ MONETIO and FV3CHEM
 Using MONET with FV3-Chem is much like using MONET with other model
 outputs. It tries to recognize where the files came from (nemsio, grib2,
 etc....) and then processes the data, renaming coordinates (lat lon to
-latitude and longitude) and processing varaibles like geopotential
+latitude and longitude) and processing variables like geopotential
 height and pressure if available. First lets import ``monet`` and
 ``fv3chem`` from MONET
 

docs/tutorial/aqs_pams.rst

@@ -28,7 +28,7 @@ Now we have all the imports we could need lets load some data. Most of
 the PAMS data is on daily data so lets add the kwarg daily=True to the
 call. We will also create this for the year 2015 and 2016. Some
 variables that may be valuable are the VOCS, ozone, NO2, NOX,
-temperature. For all of the measurments available please see
+temperature. For all of the measurements available please see
 https://aqs.epa.gov/aqsweb/airdata/download_files.html
 
 .. code-block:: python