EPA WQX domain values service

heigeo · Apr 20, 2017 · e926c92 · e926c92
1 parent ebd841a
commit e926c92
Show file tree

Hide file tree

Showing 4 changed files with 134 additions and 0 deletions.
diff --git a/README.rst b/README.rst
@@ -59,6 +59,7 @@ Available Services
  Module             Classes                                                          Data Source     Agency/Org.
 =================== ================================================================ ============== ============
 climata.acis_       ``StationMetaIO``, ``StationDataIO``                             ACIS_           NOAA RCCs
+climata.epa_        ``WqxDomainIO``                                                  WQX_            EPA
 climata.cocorahs_   ``CocorahsIO``                                                   CoCoRaHS_       CoCoRaHS
 climata.hydromet_   ``DailyDataIO``, ``InstantDataIO``, ``AgrimetRecentIO``          Hydromet_       USBR
 climata.nws_        ``HydroForecastIO``, ``EnsembleForecastIO``, ``EnsembleSiteIO``  CNRFC_          NWS
@@ -104,12 +105,14 @@ More Python code examples are available via the `climata-viewer website`_.
 
 .. _ACIS: http://data.rcc-acis.org/
 .. _CoCoRaHS: http://data.cocorahs.org/cocorahs/export/exportmanager.aspx
+.. _WQX: https://www3.epa.gov/storet/wqx/wqx_getdomainvalueswebservice.html
 .. _Hydromet: http://www.usbr.gov/pn/hydromet/arcread.html
 .. _CNRFC: http://www.cnrfc.noaa.gov/
 .. _SNOTEL AWDB: http://www.wcc.nrcs.usda.gov/web_service/awdb_web_service_landing.htm
 .. _NWIS: http://waterdata.usgs.gov/nwis
 .. _climata.acis: https://github.com/heigeo/climata/blob/master/climata/acis/__init__.py
 .. _climata.cocorahs: https://github.com/heigeo/climata/blob/master/climata/cocorahs/__init__.py
+.. _climata.epa: https://github.com/heigeo/climata/blob/master/climata/epa/__init__.py
 .. _climata.hydromet: https://github.com/heigeo/climata/blob/master/climata/hydromet/__init__.py
 .. _climata.nws: https://github.com/heigeo/climata/blob/master/climata/nws/__init__.py
 .. _climata.snotel: https://github.com/heigeo/climata/blob/master/climata/snotel/__init__.py

diff --git a/climata/epa/__init__.py b/climata/epa/__init__.py
@@ -0,0 +1,55 @@
+from wq.io import BaseIO, TimeSeriesMapper, XmlParser
+from climata.base import ZipWebserviceLoader, FilterOpt, DateOpt, ChoiceOpt
+from .constants import DOMAINS
+
+
+class WqxDomainIO(ZipWebserviceLoader, XmlParser, TimeSeriesMapper, BaseIO):
+    """
+    Load WQX / STORET domain values from EPA web services.
+
+    Usage:
+
+        chars = WqxDomainIO(domain='Characteristic')
+        for char in chars:
+            print char.picklist, char.name
+    """
+
+    # Override Default WebserviceLoader options
+    start_date = DateOpt(ignored=True)
+    end_date = DateOpt(ignored=True)
+    state = FilterOpt(ignored=True)
+    basin = FilterOpt(ignored=True)
+    county = FilterOpt(ignored=True)
+    station = FilterOpt(ignored=True)
+    parameter = FilterOpt(ignored=True)
+
+    # Custom Loader options
+    domain = ChoiceOpt(choices=DOMAINS, required=True)
+    base_url = 'http://cdx.epa.gov/wqx/download/DomainValues/'
+
+    @property
+    def url(self):
+        domain = self.getvalue('domain')
+        if domain == 'CharacteristicWithPickList':
+            domain = 'ResultMeasureValuePickList'
+        return self.base_url + domain + '.zip'
+
+    @property
+    def params(self):
+        return {}
+
+    # Custom Parser options
+    ns = '{http://www.exchangenetwork.net/schema/wqx/2}'
+    root_tag = ns + 'WQXElement'
+    item_tag = ns + 'WQXElementRow'
+
+    def parse_item(self, el):
+        return {
+            e.attrib['colname']: e.attrib['value']
+            for e in el.findall(self.ns + 'WQXElementRowColumn')
+        }
+
+    # Custom Mapper options
+    date_formats = ['iso8601']
+    map_floats = False
+    scan_fields = True
diff --git a/climata/epa/constants.py b/climata/epa/constants.py
@@ -0,0 +1,60 @@
+DOMAINS = (
+    'ActivityGroupType',
+    'ActivityMedia',
+    'ActivityMediaSubdivision',
+    'ActivityRelativeDepth',
+    'ActivityType',
+    'AddressType',
+    'AnalyticalMethod',
+    'AnalyticalMethodContext',
+    'Assemblage',
+    'BiologicalIntent',
+    'CellForm',
+    'CellShape',
+    'Characteristic',
+    'CharacteristicWithPickList',
+    'Country',
+    'County',
+    'DetectionQuantitationLimitType',
+    'ElectronicAddressType',
+    'FrequencyClassDescriptor',
+    'Habit',
+    'HorizontalCollectionMethod',
+    'HorizontalCoordinateReferenceSystemDatum',
+    'MeasureUnit',
+    'MethodSpeciation',
+    'MetricType',
+    'MetricTypeContext',
+    'MonitoringLocationType',
+    'NetType',
+    'Organization',
+    'ReferenceLocationType',
+    'ResultDetectionCondition',
+    'ResultLaboratoryComment',
+    'ResultMeasureQualifier',
+    'ResultMeasureValuePickList',
+    'ResultSampleFraction',
+    'ResultStatus',
+    'ResultTemperatureBasis',
+    'ResultTimeBasis',
+    'ResultValueType',
+    'ResultWeightBasis',
+    'SampleCollectionEquipment',
+    'SampleContainerColor',
+    'SampleContainerType',
+    'SampleTissueAnatomy',
+    'SamplingDesignType',
+    'State',
+    'StatisticalBase',
+    'Taxon',
+    'TelephoneNumberType',
+    'TimeZone',
+    'ThermalPreservativeUsed',
+    'ToxicityTestType',
+    'Tribe',
+    'VerticalCollectionMethod',
+    'VerticalCoordinateReferenceSystemDatum',
+    'Voltinism',
+    'WellFormationType',
+    'WellType',
+)
diff --git a/tests/test_epa.py b/tests/test_epa.py
@@ -0,0 +1,16 @@
+from .base import ClimataTestCase
+from climata.epa import WqxDomainIO
+
+
+class EpaTestCase(ClimataTestCase):
+    module = "epa"
+
+    def test_domain(self):
+        data = WqxDomainIO(
+            domain='Characteristic',
+        )
+        self.assertGreater(len(data), 0)
+        item = data[0]
+        self.assertHasFields(item, (
+            "name", "picklist", "samplefractionrequired", "lastchangedate"
+        ))