Fix single-tract census queries

When doing a single-tract census query you want to specify the tract ID in the "for" spec and not the "in" spec.
UDST · Jul 15, 2015 · bcfe7d0 · bcfe7d0
1 parent bbbcb6c
commit bcfe7d0
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 12 deletions.
diff --git a/synthpop/census_helpers.py b/synthpop/census_helpers.py
@@ -57,12 +57,12 @@ def block_group_query(self, census_columns, state, county, tract=None,
                            tract=tract, year=year)
 
     def tract_query(self, census_columns, state, county, tract=None,
-                    year=None, id=None):
-        if id is None:
-            id = "*"
+                    year=None):
+        if tract is None:
+            tract = "*"
         return self._query(census_columns, state, county,
-                           forstr="tract:%s" % id,
-                           tract=tract, year=year)
+                           forstr="tract:%s" % tract,
+                           year=year)
 
     def _query(self, census_columns, state, county, forstr,
                tract=None, year=None):
@@ -165,8 +165,8 @@ def _read_csv(self, loc):
                                                "ST": "object"
                                                })
             pums_df = pums_df.rename(columns = {
-                                                'PUMA10':'puma10', 
-                                                'PUMA00':'puma00', 
+                                                'PUMA10':'puma10',
+                                                'PUMA00':'puma00',
                                                 'SERIALNO':'serialno'
                                                 })
             self.pums_cache[loc] = pums_df
@@ -190,10 +190,10 @@ def download_household_pums(self, state, puma10=None, puma00=None):
         if puma00 is not None:
             pums00 = self._read_csv(self.pums00_household_base_url % (state, puma00))
             pums = pd.concat([pums, pums00], ignore_index = True)
-            
+
         # filter out gq and empty units (non-hh records)
-        pums = pums[(pums.RT == 'H') & (pums.NP > 0) & (pums.TYPE == 1)]  
-        
+        pums = pums[(pums.RT == 'H') & (pums.NP > 0) & (pums.TYPE == 1)]
+
         return pums
 
     def try_fips_lookup(self, state, county=None):

diff --git a/synthpop/test/test_censushelpers.py b/synthpop/test/test_censushelpers.py
@@ -25,7 +25,8 @@ def test_block_group_and_tract_query(c):
                                        tract="030600")
 
     assert len(df) == 3
-    assert_series_equal(df["B11001_001E"], df["B08201_001E"])
+    assert_series_equal(
+      df["B11001_001E"], df["B08201_001E"], check_names=False)
     assert np.all(df.state == "06")
     assert np.all(df.county == "075")
 
@@ -39,7 +40,8 @@ def test_block_group_and_tract_query(c):
 
     # number of block groups in San Francisco
     assert len(df) == 581
-    assert_series_equal(df["B11001_001E"], df["B08201_001E"])
+    assert_series_equal(
+      df["B11001_001E"], df["B08201_001E"], check_names=False)
     assert np.all(df.state == "06")
     assert np.all(df.county == "075")