Merge pull request #397 from knaaptime/lodescodes

expose lodes codebook

docs/api.rst

@@ -32,6 +32,7 @@ available quickly with no configuration by accessing methods on the class.
     DataStore.codebook
     DataStore.counties
     DataStore.ejscreen
+    DataStore.lodes_codebook
     DataStore.ltdb
     DataStore.msa_definitions
     DataStore.msas

geosnap/_data.py

@@ -79,6 +79,7 @@ def __dir__(self):
             "codebook",
             "counties",
             "ejscreen",
+            "lodes_codebook",
             "ltdb",
             "msa_definitions",
             "msas",
@@ -107,6 +108,18 @@ def show_data_dir(self, verbose=True):
             print(self.data_dir)
         return self.data_dir
 
+    def lodes_codebook(self):
+        """_summary_
+
+        Returns
+        -------
+        pandas.DataFrame
+            decription of variables returned with LODES/LEHD data.
+        """
+        return pd.read_csv(
+            os.path.join(os.path.dirname(os.path.abspath(__file__)), "io/lodes.csv")
+        )
+
     def bea_regions(self):
         """Table that maps states to their respective BEA regions
 
@@ -119,7 +132,7 @@ def bea_regions(self):
             os.path.join(
                 os.path.dirname(os.path.abspath(__file__)), "io/bea_regions.csv"
             ),
-            converters={'stfips':str}
+            converters={"stfips": str},
         )
 
     def acs(self, year=2018, level="tract", states=None):
@@ -208,7 +221,7 @@ def seda(
             "gcs",
             "cs",
         ], "`standardize` argument must be either 'cs' for cohort-standardized or 'gcs' for grade-cohort-standardized"
-        if pooling=='poolsub':
+        if pooling == "poolsub":
             fn = f"seda_{level}_{pooling}_{standardize}_4.1_corrected"
         else:
             fn = f"seda_{level}_{pooling}_{standardize}_4.1"

geosnap/tests/test_datastore.py

@@ -1,61 +1,81 @@
 from geosnap import DataStore
-datasets=DataStore()
+
+datasets = DataStore()
 
 
 def test_data_dir():
     loc = datasets.show_data_dir()
     assert len(loc) > 5
 
+
 def test_acs():
     df = datasets.acs(year=2012, states=["11"])
     assert df.shape == (179, 104)
 
+
 def test_tracts90():
     df = datasets.tracts_1990(states=["11"])
     assert df.shape == (192, 164)
 
+
 def test_tracts00():
     df = datasets.tracts_2000(states=["11"])
     assert df.shape == (188, 192)
 
+
 def test_tracts10():
     df = datasets.tracts_2010(states=["11"])
     assert df.shape == (179, 194)
 
+
 def test_tracts20():
     df = datasets.tracts_2020(states=["11"])
     assert df.shape == (206, 15)
 
+
 def test_counties():
     assert datasets.counties().shape == (3233, 2)
 
+
 def test_states():
     assert datasets.states().shape == (51, 3)
 
+
 def test_msas():
     df = datasets.msas()
     assert df.shape == (939, 4)
 
+
 def test_msa_defs():
     df = datasets.msa_definitions()
     assert df.shape == (1916, 13)
 
+
 def test_codebook():
     df = datasets.codebook()
     assert df.shape == (194, 12)
 
+
 def test_bea():
     df = datasets.bea_regions()
     assert df.shape == (51, 4)
 
+
 def test_blocks_2000():
-    df = datasets.blocks_2000(states=['11'])
+    df = datasets.blocks_2000(states=["11"])
     assert df.shape == (5674, 3)
 
+
 def test_blocks_2010():
-    df = datasets.blocks_2010(states=['11'])
+    df = datasets.blocks_2010(states=["11"])
     assert df.shape == (6507, 5)
 
+
 def test_blocks_2020():
-    df = datasets.blocks_2020(states=['11'])
+    df = datasets.blocks_2020(states=["11"])
     assert df.shape == (6012, 7)
+
+
+def test_lodes_codebook():
+    df = datasets.lodes_codebook()
+    assert df.shape == (42, 4)