From 8c822570d77adbed08f1260ac07b7395441160bc Mon Sep 17 00:00:00 2001
From: khider <11758571+khider@users.noreply.github.com>
Date: Mon, 29 Jul 2024 10:20:19 -0700
Subject: [PATCH] filter by resolution

---
 pylipd/globals/queries.py       | 13 +++++++
 pylipd/lipd_series.py           | 60 ++++++++++++++++++++++++++++++---
 pylipd/tests/test_LiPDSeries.py |  8 ++++-
 3 files changed, 75 insertions(+), 6 deletions(-)

diff --git a/pylipd/globals/queries.py b/pylipd/globals/queries.py
index a609d3b..9196a49 100644
--- a/pylipd/globals/queries.py
+++ b/pylipd/globals/queries.py
@@ -282,6 +282,19 @@
     }
 """
 
+QUERY_FILTER_VARIABLE_RESOLUTION = """
+    SELECT ?uri ?dsuri ?dsname ?tableuri ?id ?v WHERE {
+        ?uri le:hasVariableId ?id .
+        ?uri le:hasResolution ?res .
+        ?res le:has[stat]Value ?v .
+        FILTER(?v<[value]) .
+        ?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 
diff --git a/pylipd/lipd_series.py b/pylipd/lipd_series.py
index c7e6469..1791935 100644
--- a/pylipd/lipd_series.py
+++ b/pylipd/lipd_series.py
@@ -1,6 +1,5 @@
 from tqdm import tqdm
-from .globals.queries import QUERY_FILTER_VARIABLE_NAME, QUERY_VARIABLE, QUERY_DISTINCT_VARIABLE, QUERY_VARIABLE_ESSENTIALS, QUERY_DISTINCT_PROXY, QUERY_FILTER_VARIABLE_PROXY
-
+from .globals.queries import QUERY_FILTER_VARIABLE_NAME, QUERY_VARIABLE, QUERY_DISTINCT_VARIABLE, QUERY_VARIABLE_ESSENTIALS, QUERY_DISTINCT_PROXY, QUERY_FILTER_VARIABLE_PROXY, QUERY_FILTER_VARIABLE_RESOLUTION
 from .utils.multi_processing import multi_load_lipd_series
 from .utils.rdf_graph import RDFGraph
 
@@ -254,10 +253,61 @@ def filter_by_proxy(self, proxy):
         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
-    
\ No newline at end of file
+    
+    def filter_by_resolution(self, threshold, stats='Mean'):
+        '''
+        Filters series to return a new LiPDSeries that only keeps variables that have a resolution less than the specified threshold. 
+
+        Parameters
+        ----------
+        threshold : float
+            The maximum resolution to keep
+        stats : str, optional
+            Whether to use 'Mean', 'Median', 'Min' or 'Max' resolution. The default is 'Mean'.
+
+        Raises
+        ------
+        ValueError
+            Make sure that the stats is of ['Mean','Median', 'Min', 'Max'].
+
+        Returns
+        -------
+        S : pylipd.lipd_series.LiPDSeries
+            A new LiPDSeries object that only contains the filtered variables
+        
+        Examples
+        --------
+        
+        .. jupyter-execute::
+    
+            from pylipd.utils.dataset import load_dir
+            lipd = load_dir('Pages2k')
+            S = lipd.to_lipd_series()
+            S_filtered = S.filter_by_resolution(10)
+
+        '''
+        
+        stats = stats.capitalize() #make sure that the first letter is capitalized
+        stats_allowed = ['Mean','Median', 'Min', 'Max'] #possible values
+        if stats not in stats_allowed:
+            raise ValueError("Stats must be ['Mean','Median', 'Min', 'Max']")
+        
+        threshold = float(threshold) # make sure this is a float or can be coerced in one
+        
+        query = QUERY_FILTER_VARIABLE_RESOLUTION
+        query = query.replace("[value]", str(threshold))
+        query = query.replace("[stat]", stats)
+
+        qres,q_df = self.query(query)
+        
+        varuris = [str(row.uri) for row in qres]
+        dsuris = [*set([str(row.dsuri) for row in qres])]
+    
+        rdfgraph = self.get(varuris)
+        S = LiPDSeries(rdfgraph.graph)
+        S.lipds = {k: self.lipds[k].copy() for k in dsuris}
+        return S
\ No newline at end of file
diff --git a/pylipd/tests/test_LiPDSeries.py b/pylipd/tests/test_LiPDSeries.py
index 9e28d99..6bfdfb7 100644
--- a/pylipd/tests/test_LiPDSeries.py
+++ b/pylipd/tests/test_LiPDSeries.py
@@ -18,7 +18,7 @@
 4. after `pip install pytest-xdist`, one may execute "pytest -n 4" to test in parallel with number of workers specified by `-n`
 5. for more details, see https://docs.pytest.org/en/stable/usage.html
 """
-
+import pytest
 from pylipd.lipd_series import LiPDSeries
 
 class TestLoad():
@@ -64,6 +64,12 @@ def test_proxy_t0(self,pages2k):
         Sfiltered = S.filter_by_proxy('ring width')
         v = Sfiltered.get_all_proxy()
         assert len(v)==1
+    
+    @pytest.mark.parametrize('stats',['Mean','Median','Min','Max'])
+    def test_resolution_t0(self,stats,pages2k):
+        D=pages2k
+        S = D.to_lipd_series()
+        Sfiltered = S.filter_by_resolution(threshold = 10,stats=stats)
         
 
         
\ No newline at end of file