chem.py 文件源码

def get_wqp_results(self, service, **kwargs):
        """Bring data from WQP site into a Pandas DataFrame for analysis"""

        # set data types
        Rdtypes = {"OrganizationIdentifier": np.str_, "OrganizationFormalName": np.str_, "ActivityIdentifier": np.str_,
                   "ActivityStartTime/Time": np.str_,
                   "ActivityTypeCode": np.str_, "ActivityMediaName": np.str_, "ActivityMediaSubdivisionName": np.str_,
                   "ActivityStartDate": np.str_, "ActivityStartTime/TimeZoneCode": np.str_,
                   "ActivityEndDate": np.str_, "ActivityEndTime/Time": np.str_, "ActivityEndTime/TimeZoneCode": np.str_,
                   "ActivityDepthHeightMeasure/MeasureValue": np.float16,
                   "ActivityDepthHeightMeasure/MeasureUnitCode": np.str_,
                   "ActivityDepthAltitudeReferencePointText": np.str_,
                   "ActivityTopDepthHeightMeasure/MeasureValue": np.float16,
                   "ActivityTopDepthHeightMeasure/MeasureUnitCode": np.str_,
                   "ActivityBottomDepthHeightMeasure/MeasureValue": np.float16,
                   "ActivityBottomDepthHeightMeasure/MeasureUnitCode": np.str_,
                   "ProjectIdentifier": np.str_, "ActivityConductingOrganizationText": np.str_,
                   "MonitoringLocationIdentifier": np.str_, "ActivityCommentText": np.str_,
                   "SampleAquifer": np.str_, "HydrologicCondition": np.str_, "HydrologicEvent": np.str_,
                   "SampleCollectionMethod/MethodIdentifier": np.str_,
                   "SampleCollectionMethod/MethodIdentifierContext": np.str_,
                   "SampleCollectionMethod/MethodName": np.str_, "SampleCollectionEquipmentName": np.str_,
                   "ResultDetectionConditionText": np.str_, "CharacteristicName": np.str_,
                   "ResultSampleFractionText": np.str_,
                   "ResultMeasureValue": np.str_, "ResultMeasure/MeasureUnitCode": np.str_,
                   "MeasureQualifierCode": np.str_,
                   "ResultStatusIdentifier": np.str_, "StatisticalBaseCode": np.str_, "ResultValueTypeName": np.str_,
                   "ResultWeightBasisText": np.str_, "ResultTimeBasisText": np.str_,
                   "ResultTemperatureBasisText": np.str_,
                   "ResultParticleSizeBasisText": np.str_, "PrecisionValue": np.str_, "ResultCommentText": np.str_,
                   "USGSPCode": np.str_, "ResultDepthHeightMeasure/MeasureValue": np.float16,
                   "ResultDepthHeightMeasure/MeasureUnitCode": np.str_,
                   "ResultDepthAltitudeReferencePointText": np.str_,
                   "SubjectTaxonomicName": np.str_, "SampleTissueAnatomyName": np.str_,
                   "ResultAnalyticalMethod/MethodIdentifier": np.str_,
                   "ResultAnalyticalMethod/MethodIdentifierContext": np.str_,
                   "ResultAnalyticalMethod/MethodName": np.str_, "MethodDescriptionText": np.str_,
                   "LaboratoryName": np.str_,
                   "AnalysisStartDate": np.str_, "ResultLaboratoryCommentText": np.str_,
                   "DetectionQuantitationLimitTypeName": np.str_,
                   "DetectionQuantitationLimitMeasure/MeasureValue": np.str_,
                   "DetectionQuantitationLimitMeasure/MeasureUnitCode": np.str_, "PreparationStartDate": np.str_,
                   "ProviderName": np.str_}

        # define date field indices
        dt = [6, 56, 61]
        csv = self.get_response(service, **kwargs).url
        print(csv)
        # read csv into DataFrame
        df = pd.read_csv(csv, dtype=Rdtypes, parse_dates=dt)
        return df