Merge pull request #1328 from cmu-delphi/release/indicators_v0.2.0_utils_v0.2.0

Release covidcast-indicators 0.2.0

Author: krivard

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.25
+current_version = 0.2.0
 commit = True
 message = chore: bump covidcast-indicators to {new_version}
 tag = False

_delphi_utils_python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.17
+current_version = 0.2.0
 commit = True
 message = chore: bump delphi_utils to {new_version}
 tag = False

_delphi_utils_python/data_proc/geomap/consistency_checks.ipynb

@@ -24,7 +24,7 @@
 FIPS_MSA_URL = "https://www2.census.gov/programs-surveys/metro-micro/geographies/reference-files/2018/delineation-files/list1_Sep_2018.xls"
 JHU_FIPS_URL = "https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/UID_ISO_FIPS_LookUp_Table.csv"
 STATE_CODES_URL = "http://www2.census.gov/geo/docs/reference/state.txt?#"
-FIPS_POPULATION_URL = "https://www2.census.gov/programs-surveys/popest/datasets/2010-2019/counties/totals/co-est2019-alldata.csv"
+FIPS_POPULATION_URL = "https://www2.census.gov/programs-surveys/popest/datasets/2010-2020/counties/totals/co-est2020-alldata.csv"
 FIPS_PUERTO_RICO_POPULATION_URL = (
     "https://www2.census.gov/geo/docs/maps-data/data/rel/zcta_county_rel_10.txt?"
 )
@@ -358,34 +358,31 @@ def create_fips_population_table():
     census_pop["fips"] = census_pop.apply(
         lambda x: f"{x['STATE']:02d}{x['COUNTY']:03d}", axis=1
     )
-    census_pop["pop"] = census_pop["POPESTIMATE2019"]
+    census_pop["pop"] = census_pop["POPESTIMATE2020"]
     census_pop = census_pop[["fips", "pop"]]
+
+    # Set population for Dukes and Nantucket combo county
+    dukes_pop = int(census_pop.loc[census_pop["fips"] == "25007", "pop"])
+    nantu_pop = int(census_pop.loc[census_pop["fips"] == "25019", "pop"])
     census_pop = pd.concat(
         [
             census_pop,
             pd.DataFrame(
                 {
-                    "fips": ["70002", "70003"],
-                    "pop": [0, 0],
+                    "fips": [
+                        "70002",  # Dukes and Nantucket combo county
+                        "70003"   # Kansas City
+                    ],
+                    "pop": [
+                        dukes_pop + nantu_pop,
+                        491918    # via Google
+                    ],
                 }
             ),
         ]
     )
     census_pop = census_pop.reset_index(drop=True)
 
-    # Set population for Dukes and Nantucket
-    dn_fips = "70002"
-    dukes_fips = "25007"
-    nantu_fips = "25019"
-
-    census_pop.loc[census_pop["fips"] == dn_fips, "pop"] = (
-        census_pop.loc[census_pop["fips"] == dukes_fips, "pop"].values
-        + census_pop.loc[census_pop["fips"] == nantu_fips, "pop"].values
-    )
-
-    # Set population for Kansas City
-    census_pop.loc[census_pop["fips"] == "70003", "pop"] = 491918  # via Google
-
     # Get the file with Puerto Rico populations
     df_pr = pd.read_csv(FIPS_PUERTO_RICO_POPULATION_URL)
     df_pr["fips"] = df_pr["STATE"].astype(str).str.zfill(2) + df_pr["COUNTY"].astype(

_delphi_utils_python/data_proc/geomap/geo_data_proc.py

@@ -14,4 +14,4 @@
 from .signal import add_prefix
 from .nancodes import Nans
 
-__version__ = "0.1.17"
+__version__ = "0.2.0"

_delphi_utils_python/data_proc/geomap/source-file-sanity-check.ipynb

@@ -71,6 +71,8 @@ fips,hhs
 02020,10
 02050,10
 02060,10
+02063,10
+02066,10
 02068,10
 02070,10
 02090,10
@@ -91,7 +93,6 @@ fips,hhs
 02220,10
 02230,10
 02240,10
-02261,10
 02275,10
 02282,10
 02290,10
@@ -3234,60 +3235,60 @@ fips,hhs
 69100,9
 69110,9
 69120,9
-78000,2
-33000,1
+27000,5
+40000,6
+70000,9
+31000,7
 09000,1
+48000,6
 32000,9
-04000,9
-30000,8
-15000,9
-69000,9
+50000,1
 25000,1
-19000,7
-01000,4
-51000,3
-41000,10
-66000,9
-22000,6
-06000,9
-39000,5
-38000,8
 53000,10
-12000,4
-46000,8
 17000,5
-48000,6
-34000,2
-08000,8
-36000,2
-40000,6
-47000,4
+28000,4
+02000,10
 49000,8
+54000,3
+20000,7
+08000,8
+34000,2
+35000,6
 45000,4
+29000,7
+66000,9
+05000,6
+41000,10
+37000,4
 55000,5
-11000,3
-02000,10
-72000,2
-23000,1
-16000,10
 44000,1
-54000,3
-10000,3
-21000,4
-28000,4
-18000,5
-05000,6
 56000,8
+36000,2
+19000,7
 24000,3
-50000,1
-37000,4
-20000,7
-31000,7
-29000,7
-27000,5
+46000,8
+38000,8
+72000,2
+23000,1
+78000,2
+16000,10
+47000,4
+22000,6
 13000,4
+30000,8
+39000,5
+18000,5
+11000,3
+15000,9
 42000,3
-35000,6
-60000,9
+01000,4
+12000,4
+10000,3
+04000,9
+69000,9
+06000,9
+33000,1
 26000,5
-70000,9
+21000,4
+60000,9
+51000,3