Merge pull request #66 from LinkedEarth/queries

proxy queries

pylipd/__init__.py

@@ -1,4 +1,6 @@
-__version__ = "1.3.7"
+from importlib.metadata import version
+__version__ = version('pyleoclim')
+
 
 from .utils import *
 from .classes import *

pylipd/globals/queries.py

@@ -132,6 +132,19 @@
     }
     
 
+"""
+
+QUERY_DISTINCT_PROXY = """
+    PREFIX le: <http://linked.earth/ontology#>
+    
+    SELECT distinct ?proxy 
+    WHERE {
+        OPTIONAL{?uri le:hasProxy ?proxyObj .
+                 ?proxyObj rdfs:label ?proxy .}
+        ?uri le:hasVariableId ?TSID
+    }
+    
+
 """
 
 QUERY_VARIABLE = """
@@ -257,6 +270,18 @@
     }
 """
 
+QUERY_FILTER_VARIABLE_PROXY = """
+    SELECT ?uri ?dsuri ?dsname ?tableuri ?id ?proxy WHERE {
+        ?uri le:hasVariableId ?id .
+        ?uri le:hasProxy ?proxyObj .
+        ?proxyObj rdfs:label ?proxy .
+        FILTER regex(?proxy, "[proxy].*", "i") .
+        ?uri le:foundInDataset ?dsuri .
+        ?uri le:foundInDatasetName ?dataSetName .
+        ?uri le:foundInTable ?tableuri .
+    }
+"""
+
 QUERY_TIMESERIES_ESSENTIALS_PALEO ="""
     PREFIX wgs84: <http://www.w3.org/2003/01/geo/wgs84_pos#>
     SELECT ?dataSetName ?archiveType ?geo_meanLat ?geo_meanLon ?geo_meanElev 

pylipd/lipd_series.py

@@ -1,5 +1,5 @@
 from tqdm import tqdm
-from .globals.queries import QUERY_FILTER_VARIABLE_NAME, QUERY_VARIABLE, QUERY_DISTINCT_VARIABLE, QUERY_VARIABLE_ESSENTIALS
+from .globals.queries import QUERY_FILTER_VARIABLE_NAME, QUERY_VARIABLE, QUERY_DISTINCT_VARIABLE, QUERY_VARIABLE_ESSENTIALS, QUERY_DISTINCT_PROXY, QUERY_FILTER_VARIABLE_PROXY
 
 from .utils.multi_processing import multi_load_lipd_series
 from .utils.rdf_graph import RDFGraph
@@ -95,7 +95,7 @@ def get_all_variables(self):
     def get_all_variable_names(self):
 
         """
-        Get a list of all possible distinct variableNames. Useful for filtering and qeurying. 
+        Get a list of all possible distinct variableNames. Useful for filtering and querying. 
 
         Returns
         -------
@@ -115,6 +115,30 @@ def get_all_variable_names(self):
         """
 
         return self.query(QUERY_DISTINCT_VARIABLE)[1].iloc[:,0].values.tolist()
+
+    def get_all_proxy(self):
+
+        """
+        Get a list of all possible proxy. Useful for filtering and querying. 
+
+        Returns
+        -------
+        list
+            A list of unique proxies
+        
+        Examples
+        --------
+        
+        .. jupyter-execute::
+            
+            from pylipd.utils.dataset import load_dir
+            lipd = load_dir('Pages2k')
+            S = lipd.to_lipd_series()
+            proxyName = S.get_all_proxy()
+            print(proxyName)
+        """
+
+        return self.query(QUERY_DISTINCT_PROXY)[1].iloc[:,0].values.tolist()
 
     def get_timeseries_essentials(self):
         '''This function returns information about each variable: `dataSetName`, `archiveType`, `name`, `values`, `units`, `TSID`, `proxy`.
@@ -167,6 +191,18 @@ def filter_by_name(self, name):
         
         pylipd.lipd_series.LiPDSeries
             A new LiPDSeries object that only contains variables that have the specified name (regex)
+        
+        Examples
+        --------
+        
+        .. jupyter-execute::
+
+            from pylipd.utils.dataset import load_datasets
+            lipd = load_datasets('ODP846.Lawrence.2006.lpd')
+            S = lipd.to_lipd_series()
+            sst = S.filter_by_name('sst')
+            
+            print(sst.get_all_variable_names())
 
         '''
         query = QUERY_FILTER_VARIABLE_NAME
@@ -176,9 +212,52 @@ def filter_by_name(self, name):
         varuris = [str(row.uri) for row in qres]
         dsuris = [*set([str(row.dsuri) for row in qres])]
 
-        print(len(dsuris))
+        #print(len(dsuris))
+
+        rdfgraph = self.get(varuris)
+        S = LiPDSeries(rdfgraph.graph)
+        S.lipds = {k: self.lipds[k].copy() for k in dsuris}
+        return S
 
+    def filter_by_proxy(self, proxy):
+        '''
+        Filters series to return a new LiPDSeries that only keeps variables that have the specified proxy (regex)
+    
+        Parameters
+        ----------
+    
+        proxy : str
+            The name of the proxy to filter by
+    
+        Returns
+        -------
+        
+        pylipd.lipd_series.LiPDSeries
+            A new LiPDSeries object that only contains variables that have the specified name (regex)
+        
+        Examples
+        --------
+        
+        .. jupyter-execute::
+    
+            from pylipd.utils.dataset import load_dir
+            lipd = load_dir('Pages2k')
+            S = lipd.to_lipd_series()
+            S_filtered = S.filter_by_proxy('ring width')
+            print(S_filtered.get_all_proxy())
+    
+        '''
+        query = QUERY_FILTER_VARIABLE_PROXY
+        query = query.replace("[proxy]", proxy)
+
+        qres, qres_df = self.query(query)
+        varuris = [str(row.uri) for row in qres]
+        dsuris = [*set([str(row.dsuri) for row in qres])]
+
+        #print(len(dsuris))
+
         rdfgraph = self.get(varuris)
         S = LiPDSeries(rdfgraph.graph)
         S.lipds = {k: self.lipds[k].copy() for k in dsuris}
-        return S
+        return S
+

pylipd/tests/test_LiPD.py

@@ -24,6 +24,8 @@
 from pylipd.lipd import LiPD
 import urllib as urllib
 
+
+
 class TestLiPDLoad():
 
     def test_load_t0(self, odp846):
@@ -181,7 +183,10 @@ class TestRdf():
 
     def test_convert_to_rdf_t0(self):
         lipd = LiPD()
-        lipd.convert_lipd_dir_to_rdf("./examples/data/Pages2k", "all-lipd.nq")
+        try:
+            lipd.convert_lipd_dir_to_rdf("../data/Pages2k", "all-lipd.nq")
+        except:
+            lipd.convert_lipd_dir_to_rdf("./examples/data/Pages2k", "all-lipd.nq")
 
 
 

pylipd/tests/test_LiPDSeries.py

@@ -43,7 +43,12 @@ def test_timeseries_essentials_t0(self, pages2k):
         D=pages2k
         S = D.to_lipd_series()
         names = S.get_timeseries_essentials()
-
+
+    def test_proxy_t0(self, pages2k):
+        D=pages2k
+        S = D.to_lipd_series()
+        names = S.get_all_proxy()
+
 class TestFiler():
 
     def test_name_t0(self,pages2k):
@@ -52,5 +57,13 @@ def test_name_t0(self,pages2k):
         Sfiltered = S.filter_by_name('temperature')
         df=Sfiltered.get_timeseries_essentials()
         assert len(df.index)==11
+
+    def test_proxy_t0(self,pages2k):
+        D=pages2k
+        S = D.to_lipd_series()
+        Sfiltered = S.filter_by_proxy('ring width')
+        v = Sfiltered.get_all_proxy()
+        assert len(v)==1
+