change code name

Author: nmdefries

_delphi_utils_python/data_proc/geomap/geo_data_proc.py

@@ -41,10 +41,10 @@
 FIPS_HRR_OUT_FILENAME = "fips_hrr_table.csv"
 FIPS_ZIP_OUT_FILENAME = "fips_zip_table.csv"
 FIPS_HHS_FILENAME = "fips_hhs_table.csv"
-FIPS_POPSAFEFIPS_OUT_FILENAME = "fips_popsafe-fips_table.csv"
+FIPS_CHNGFIPS_OUT_FILENAME = "fips_chng-fips_table.csv"
 FIPS_POPULATION_OUT_FILENAME = "fips_pop.csv"
 
-POPSAFEFIPS_STATE_OUT_FILENAME = "popsafe-fips_state_table.csv"
+CHNGFIPS_STATE_OUT_FILENAME = "chng-fips_state_table.csv"
 ZIP_HSA_OUT_FILENAME = "zip_hsa_table.csv"
 ZIP_HRR_OUT_FILENAME = "zip_hrr_table.csv"
 ZIP_FIPS_OUT_FILENAME = "zip_fips_table.csv"
@@ -478,8 +478,8 @@ def derive_zip_hhs_crosswalk():
     zip_state.sort_values(["zip", "hhs"]).to_csv(join(OUTPUT_DIR, ZIP_HHS_FILENAME), index=False)
 
 
-def derive_fips_popsafefips_crosswalk():
-    """Build a crosswalk table for FIPS to pop-safe fips."""
+def derive_fips_chngfips_crosswalk():
+    """Build a crosswalk table for FIPS to CHNG FIPS."""
     if not isfile(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME)):
         derive_fips_state_crosswalk()
 
@@ -506,35 +506,35 @@ def derive_fips_popsafefips_crosswalk():
     county_groups["group"] = county_groups["group"].str.zfill(2).astype("string")
     county_groups["fips"] = county_groups["fips"].str.zfill(5).astype("string")
     # Combine state codes and group ids into a single FIPS code.
-    county_groups["popsafe-fips"] = county_groups["state_fips"] + "g" + county_groups["group"]
+    county_groups["chng-fips"] = county_groups["state_fips"] + "g" + county_groups["group"]
 
-    county_groups = county_groups[["fips", "popsafe-fips"]]
+    county_groups = county_groups[["fips", "chng-fips"]]
     fips_to_state = pd.read_csv(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME), dtype="string", index_col=False)
 
     # Get all the fips that aren't included in the low-population groupings.
     extra_fips_list = list(set(fips_to_state.fips) - set(county_groups.fips))
-    # Normal fips codes and pop-safe fips codes are the same for high-population counties.
-    extra_fips_df = pd.DataFrame({"fips" : extra_fips_list, "popsafe-fips" : extra_fips_list}, dtype="string")
+    # Normal fips codes and CHNG fips codes are the same for high-population counties.
+    extra_fips_df = pd.DataFrame({"fips" : extra_fips_list, "chng-fips" : extra_fips_list}, dtype="string")
 
     # Combine high-pop and low-pop counties.
     pd.concat(
         [county_groups, extra_fips_df]
     ).sort_values(
-        ["fips", "popsafe-fips"]
+        ["fips", "chng-fips"]
     ).to_csv(
-        join(OUTPUT_DIR, FIPS_POPSAFEFIPS_OUT_FILENAME), index=False
+        join(OUTPUT_DIR, FIPS_CHNGFIPS_OUT_FILENAME), index=False
     )
 
 
-def derive_popsafefips_state_crosswalk():
-    """Build a crosswalk table for FIPS to pop-safe fips."""
+def derive_chngfips_state_crosswalk():
+    """Build a crosswalk table for FIPS to CHNG FIPS."""
     if not isfile(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME)):
         derive_fips_state_crosswalk()
 
-    if not isfile(join(OUTPUT_DIR, FIPS_POPSAFEFIPS_OUT_FILENAME)):
-        derive_fips_popsafefips_crosswalk()
+    if not isfile(join(OUTPUT_DIR, FIPS_CHNGFIPS_OUT_FILENAME)):
+        derive_fips_chngfips_crosswalk()
 
-    fips_to_group = pd.read_csv(join(OUTPUT_DIR, FIPS_POPSAFEFIPS_OUT_FILENAME), dtype="string", index_col=False)
+    fips_to_group = pd.read_csv(join(OUTPUT_DIR, FIPS_CHNGFIPS_OUT_FILENAME), dtype="string", index_col=False)
     fips_to_state = pd.read_csv(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME), dtype="string", index_col=False)
 
     group_to_state = fips_to_group.join(
@@ -543,9 +543,9 @@ def derive_popsafefips_state_crosswalk():
             columns = "fips"
         ).drop_duplicates(
         ).sort_values(
-            ["popsafe-fips", "state_code"]
+            ["chng-fips", "state_code"]
         )
-    group_to_state.to_csv(join(OUTPUT_DIR, POPSAFEFIPS_STATE_OUT_FILENAME), index=False)
+    group_to_state.to_csv(join(OUTPUT_DIR, CHNGFIPS_STATE_OUT_FILENAME), index=False)
 
 
 def clear_dir(dir_path: str):
@@ -574,5 +574,5 @@ def clear_dir(dir_path: str):
     derive_zip_population_table()
     derive_fips_hhs_crosswalk()
     derive_zip_hhs_crosswalk()
-    derive_fips_popsafefips_crosswalk()
-    derive_popsafefips_state_crosswalk()
+    derive_fips_chngfips_crosswalk()
+    derive_chngfips_state_crosswalk()

_delphi_utils_python/delphi_utils/data/2019/popsafe-fips_state_table.csv renamed to _delphi_utils_python/delphi_utils/data/2019/chng-fips_state_table.csv

@@ -1,4 +1,4 @@
-popsafe-fips,state_code,state_id,state_name
+chng-fips,state_code,state_id,state_name
 01000,01,al,Alabama
 01001,01,al,Alabama
 01003,01,al,Alabama

_delphi_utils_python/delphi_utils/data/2019/fips_popsafe-fips_table.csv renamed to _delphi_utils_python/delphi_utils/data/2019/fips_chng-fips_table.csv

@@ -1,4 +1,4 @@
-fips,popsafe-fips
+fips,chng-fips
 01000,01000
 01001,01001
 01003,01003

_delphi_utils_python/delphi_utils/data/2020/popsafe-fips_state_table.csv renamed to _delphi_utils_python/delphi_utils/data/2020/chng-fips_state_table.csv

@@ -1,4 +1,4 @@
-popsafe-fips,state_code,state_id,state_name
+chng-fips,state_code,state_id,state_name
 01000,01,al,Alabama
 01001,01,al,Alabama
 01003,01,al,Alabama

_delphi_utils_python/delphi_utils/data/2020/fips_popsafe-fips_table.csv renamed to _delphi_utils_python/delphi_utils/data/2020/fips_chng-fips_table.csv

@@ -1,4 +1,4 @@
-fips,popsafe-fips
+fips,chng-fips
 01000,01000
 01001,01001
 01003,01003

_delphi_utils_python/delphi_utils/geomap.py

@@ -41,8 +41,8 @@ class GeoMapper:  # pylint: disable=too-many-public-methods
     - [x] fips -> megacounty
     - [x] fips -> hrr
     - [x] fips -> hhs
-    - [x] fips -> popsafe-fips
-    - [x] popsafe-fips -> state : unweighted
+    - [x] fips -> chng-fips
+    - [x] chng-fips -> state : unweighted
     - [x] nation
     - [ ] zip -> dma (postponed)
 
@@ -82,15 +82,15 @@ class GeoMapper:  # pylint: disable=too-many-public-methods
             "hhs": "zip_hhs_table.csv"
         },
         "fips": {
-            "popsafe-fips": "fips_popsafe-fips_table.csv",
+            "chng-fips": "fips_chng-fips_table.csv",
             "zip": "fips_zip_table.csv",
             "hrr": "fips_hrr_table.csv",
             "msa": "fips_msa_table.csv",
             "pop": "fips_pop.csv",
             "state": "fips_state_table.csv",
             "hhs": "fips_hhs_table.csv",
         },
-        "popsafe-fips": {"state": "popsafe-fips_state_table.csv"},
+        "chng-fips": {"state": "chng-fips_state_table.csv"},
         "state": {"state": "state_codes_table.csv"},
         "state_code": {
             "hhs": "state_code_hhs_table.csv",
@@ -169,7 +169,7 @@ def _load_geo_values(self, geo_type):
 
     @staticmethod
     def convert_fips_to_mega(data, fips_col="fips", mega_col="megafips"):
-        """Convert fips or popsafe-fips string to a megafips string."""
+        """Convert fips or chng-fips string to a megafips string."""
         data = data.copy()
         data[mega_col] = data[fips_col].astype(str).str.zfill(5)
         data[mega_col] = data[mega_col].str.slice_replace(start=2, stop=5, repl="000")
@@ -234,8 +234,8 @@ def add_geocode(
         """Add a new geocode column to a dataframe.
 
         Currently supported conversions:
-        - fips -> state_code, state_id, state_name, zip, msa, hrr, nation, hhs, popsafe-fips
-        - popsafe-fips -> state_code, state_id, state_name
+        - fips -> state_code, state_id, state_name, zip, msa, hrr, nation, hhs, chng-fips
+        - chng-fips -> state_code, state_id, state_name
         - zip -> state_code, state_id, state_name, fips, msa, hrr, nation, hhs
         - jhu_uid -> fips
         - state_x -> state_y (where x and y are in {code, id, name}), nation
@@ -245,10 +245,10 @@ def add_geocode(
         ---------
         df: pd.DataFrame
             Input dataframe.
-        from_code: {'fips', 'popsafe-fips', 'zip', 'jhu_uid', 'state_code',
+        from_code: {'fips', 'chng-fips', 'zip', 'jhu_uid', 'state_code',
                     'state_id', 'state_name'}
             Specifies the geocode type of the data in from_col.
-        new_code: {'fips', 'popsafe-fips', 'zip', 'state_code', 'state_id',
+        new_code: {'fips', 'chng-fips', 'zip', 'state_code', 'state_id',
                    'state_name', 'hrr', 'msa', 'hhs'}
             Specifies the geocode type in new_col.
         from_col: str, default None
@@ -276,7 +276,7 @@ def add_geocode(
         state_codes = ["state_code", "state_id", "state_name"]
 
         if not is_string_dtype(df[from_col]):
-            if from_code in ["fips", "zip", "popsafe-fips"]:
+            if from_code in ["fips", "zip", "chng-fips"]:
                 df[from_col] = df[from_col].astype(str).str.zfill(5)
             else:
                 df[from_col] = df[from_col].astype(str)
@@ -348,8 +348,8 @@ def replace_geocode(
         """Replace a geocode column in a dataframe.
 
         Currently supported conversions:
-        - fips -> popsafe-fips, state_code, state_id, state_name, zip, msa, hrr, nation
-        - popsafe-fips -> state_code, state_id, state_name
+        - fips -> chng-fips, state_code, state_id, state_name, zip, msa, hrr, nation
+        - chng-fips -> state_code, state_id, state_name
         - zip -> state_code, state_id, state_name, fips, msa, hrr, nation
         - jhu_uid -> fips
         - state_x -> state_y (where x and y are in {code, id, name}), nation
@@ -463,7 +463,7 @@ def fips_to_megacounty(
         mega_col="megafips",
         count_cols=None,
     ):
-        """Convert and aggregate from FIPS or popsafe-fips to megaFIPS.
+        """Convert and aggregate from FIPS or chng-fips to megaFIPS.
 
         Parameters
         ---------
@@ -565,15 +565,15 @@ def get_geos_within(self, container_geocode, contained_geocode_type, container_g
         Supports these 4 combinations:
             - all states within a nation
             - all counties within a state
-            - all popsafe counties within a state
+            - all CHNG counties+county groups within a state
             - all states within an hhs region
 
         Parameters
         ----------
         container_geocode: str
             Instance of nation/state/hhs to find the sub-regions of
         contained_geocode_type: str
-            The subregion type to retrieve. One of "state", "county", "fips", "popsafe-fips"
+            The subregion type to retrieve. One of "state", "county", "fips", "chng-fips"
         container_geocode_type: str
             The parent region type. One of "state", "nation", "hhs"
 
@@ -590,7 +590,7 @@ def get_geos_within(self, container_geocode, contained_geocode_type, container_g
                 crosswalk_state = self._crosswalks["fips"]["state"]
                 fips_hhs = crosswalk_hhs[crosswalk_hhs["hhs"] == container_geocode]["fips"]
                 return set(crosswalk_state[crosswalk_state["fips"].isin(fips_hhs)]["state_id"])
-        elif (contained_geocode_type in ("county", "fips", "popsafe-fips") and
+        elif (contained_geocode_type in ("county", "fips", "chng-fips") and
                 container_geocode_type == "state"):
             contained_geocode_type = self.as_mapper_name(contained_geocode_type)
             crosswalk = self._crosswalks[contained_geocode_type]["state"]
@@ -600,4 +600,4 @@ def get_geos_within(self, container_geocode, contained_geocode_type, container_g
         raise ValueError("(contained_geocode_type, container_geocode_type) was "
                          f"({contained_geocode_type}, {container_geocode_type}), but "
                          "must be one of (state, nation), (state, hhs), (county, state)"
-                         ", (fips, state), (popsafe-fips, state)")
+                         ", (fips, state), (chng-fips, state)")

_delphi_utils_python/tests/test_geomap.py

@@ -190,9 +190,9 @@ def test_load_fips_msa_table(self, geomapper):
         msa_data = geomapper.get_crosswalk(from_code="fips", to_code="msa")
         assert tuple(msa_data.columns) == ("fips", "msa")
 
-    def test_load_fips_popsafefips_table(self, geomapper):
-        popsafe_data = geomapper.get_crosswalk(from_code="fips", to_code="popsafe-fips")
-        assert tuple(popsafe_data.columns) == ("fips", "popsafe-fips")
+    def test_load_fips_chngfips_table(self, geomapper):
+        chngfips_data = geomapper.get_crosswalk(from_code="fips", to_code="chng-fips")
+        assert tuple(chngfips_data.columns) == ("fips", "chng-fips")
 
     def test_load_jhu_uid_fips_table(self, geomapper):
         jhu_data = geomapper.get_crosswalk(from_code="jhu_uid", to_code="fips")
@@ -230,7 +230,7 @@ def test_megacounty(self, geomapper):
             }
         )
         pd.testing.assert_frame_equal(new_data.set_index("megafips").sort_index(axis=1), expected_df.set_index("megafips").sort_index(axis=1))
-        # popsafe-county should have the same behavior when converting to megacounties.
+        # chng-fips should have the same behavior when converting to megacounties.
         mega_county_groups = self.mega_data_3.copy()
         mega_county_groups.fips.replace({1125:"01g01"}, inplace = True)
         new_data = geomapper.fips_to_megacounty(self.mega_data_3, 4, 1)
@@ -246,7 +246,7 @@ def test_megacounty(self, geomapper):
             }
         )
         pd.testing.assert_frame_equal(new_data.set_index("megafips").sort_index(axis=1), expected_df.set_index("megafips").sort_index(axis=1))
-        # popsafe-county should have the same behavior when converting to megacounties.
+        # chng-fips should have the same behavior when converting to megacounties.
         mega_county_groups = self.mega_data_3.copy()
         mega_county_groups.fips.replace({1123:"01g01"}, inplace = True)
         new_data = geomapper.fips_to_megacounty(self.mega_data_3, 4, 1, thr_col="count")
@@ -260,7 +260,7 @@ def test_add_population_column(self, geomapper):
         with pytest.raises(ValueError):
             new_data = geomapper.add_population_column(self.zip_data, "hrr")
         with pytest.raises(ValueError):
-            new_data = geomapper.add_population_column(self.zip_data, "popsafe-fips")
+            new_data = geomapper.add_population_column(self.zip_data, "chng-fips")
         new_data = geomapper.add_population_column(self.fips_data_5, "fips")
         assert new_data.shape == (4, 5)
         new_data = geomapper.add_population_column(self.state_data, "state_code")
@@ -302,22 +302,22 @@ def test_add_geocode(self, geomapper):
             )
         )
 
-        # fips -> popsafe-fips
-        new_data = geomapper.add_geocode(self.fips_data_5, "fips", "popsafe-fips")
-        assert sorted(list(new_data["popsafe-fips"])) == ['01123', '18181', '48g19', '72003']
-        assert new_data["popsafe-fips"].size == self.fips_data_5.fips.size
-        new_data = geomapper.replace_geocode(self.fips_data_5, "fips", "popsafe-fips")
-        assert sorted(list(new_data["popsafe-fips"])) == ['01123', '18181', '48g19', '72003']
-        assert new_data["popsafe-fips"].size == self.fips_data_5.fips.size
-
-        # popsafe-fips -> state_id
-        new_data = geomapper.replace_geocode(self.fips_data_5, "fips", "popsafe-fips")
-        new_data2 = geomapper.add_geocode(new_data, "popsafe-fips", "state_id")
+        # fips -> chng-fips
+        new_data = geomapper.add_geocode(self.fips_data_5, "fips", "chng-fips")
+        assert sorted(list(new_data["chng-fips"])) == ['01123', '18181', '48g19', '72003']
+        assert new_data["chng-fips"].size == self.fips_data_5.fips.size
+        new_data = geomapper.replace_geocode(self.fips_data_5, "fips", "chng-fips")
+        assert sorted(list(new_data["chng-fips"])) == ['01123', '18181', '48g19', '72003']
+        assert new_data["chng-fips"].size == self.fips_data_5.fips.size
+
+        # chng-fips -> state_id
+        new_data = geomapper.replace_geocode(self.fips_data_5, "fips", "chng-fips")
+        new_data2 = geomapper.add_geocode(new_data, "chng-fips", "state_id")
         assert new_data2["state_id"].unique().size == 4
         assert new_data2["state_id"].size == self.fips_data_5.fips.size
         assert sorted(list(new_data2["state_id"])) == ['al', 'in', 'pr', 'tx']
 
-        new_data2 = geomapper.replace_geocode(new_data, "popsafe-fips", "state_id")
+        new_data2 = geomapper.replace_geocode(new_data, "chng-fips", "state_id")
         assert new_data2["state_id"].unique().size == 4
         assert new_data2["state_id"].size == 4
         assert sorted(list(new_data2["state_id"])) == ['al', 'in', 'pr', 'tx']
@@ -395,20 +395,20 @@ def test_get_geos(self, geomapper):
         assert geomapper.get_geo_values("nation") == {"us"}
         assert geomapper.get_geo_values("hhs") == set(str(i) for i in range(1, 11))
         assert len(geomapper.get_geo_values("fips")) == 3236
-        assert len(geomapper.get_geo_values("popsafe-fips")) == 2711
+        assert len(geomapper.get_geo_values("chng-fips")) == 2711
         assert len(geomapper.get_geo_values("state_id")) == 60
         assert len(geomapper.get_geo_values("zip")) == 32976
 
     def test_get_geos_2019(self, geomapper_2019):
         assert len(geomapper_2019.get_geo_values("fips")) == 3235
-        assert len(geomapper_2019.get_geo_values("popsafe-fips")) == 2710
+        assert len(geomapper_2019.get_geo_values("chng-fips")) == 2710
 
     def test_get_geos_within(self, geomapper):
         assert len(geomapper.get_geos_within("us","state","nation")) == 60
         assert len(geomapper.get_geos_within("al","county","state")) == 68
         assert len(geomapper.get_geos_within("al","fips","state")) == 68
         assert geomapper.get_geos_within("al","fips","state") == geomapper.get_geos_within("al","county","state")
-        assert len(geomapper.get_geos_within("al","popsafe-fips","state")) == 66
+        assert len(geomapper.get_geos_within("al","chng-fips","state")) == 66
         assert len(geomapper.get_geos_within("4","state","hhs")) == 8
         assert geomapper.get_geos_within("4","state","hhs") == {'al', 'fl', 'ga', 'ky', 'ms', 'nc', "tn", "sc"}