cdc_covidnet: change states to lowercase to align with geo_util default

cdc_covidnet/delphi_cdc_covidnet/update_sensor.py

@@ -92,7 +92,7 @@ def update_sensor(
                                new_code="state_id",
                                dropna=False)
     # To use the original column name, reassign original column and drop new one
-    hosp_df[APIConfig.STATE_COL] = hosp_df["state_id"].str.upper()
+    hosp_df[APIConfig.STATE_COL] = hosp_df["state_id"]
     hosp_df.drop("state_id", axis=1, inplace=True)
     assert not hosp_df.duplicated(["date", "geo_id"]).any(), "Non-unique (date, geo_id) pairs"
     hosp_df.set_index(["date", "geo_id"], inplace=True)
@@ -105,7 +105,6 @@ def update_sensor(
     signals = add_prefix(SIGNALS, wip_signal=read_params()["wip_signal"], prefix="wip_")
     for signal in signals:
         write_to_csv(hosp_df, signal, output_path)
-
     return hosp_df
 
 

cdc_covidnet/tests/receiving_test/202010_state_wip_covidnet.csv

@@ -1,15 +1,15 @@
 geo_id,val,se,sample_size
-CA,0.2,NA,NA
-CO,0.1,NA,NA
-CT,0.1,NA,NA
-GA,0.5,NA,NA
-MD,0.1,NA,NA
-MN,0.0,NA,NA
-NM,0.0,NA,NA
-NY,0.1,NA,NA
-OR,0.1,NA,NA
-TN,0.1,NA,NA
-IA,0.0,NA,NA
-MI,0.1,NA,NA
-OH,0.0,NA,NA
-UT,0.0,NA,NA
+ca,0.2,NA,NA
+co,0.1,NA,NA
+ct,0.1,NA,NA
+ga,0.5,NA,NA
+md,0.1,NA,NA
+mn,0.0,NA,NA
+nm,0.0,NA,NA
+ny,0.1,NA,NA
+or,0.1,NA,NA
+tn,0.1,NA,NA
+ia,0.0,NA,NA
+mi,0.1,NA,NA
+oh,0.0,NA,NA
+ut,0.0,NA,NA

cdc_covidnet/tests/receiving_test/202011_state_wip_covidnet.csv

@@ -1,15 +1,15 @@
 geo_id,val,se,sample_size
-CA,1.0,NA,NA
-CO,0.8,NA,NA
-CT,1.0,NA,NA
-GA,2.7,NA,NA
-MD,0.4,NA,NA
-MN,0.1,NA,NA
-NM,0.2,NA,NA
-NY,0.7,NA,NA
-OR,0.5,NA,NA
-TN,0.7,NA,NA
-IA,0.0,NA,NA
-MI,0.2,NA,NA
-OH,0.3,NA,NA
-UT,0.2,NA,NA
+ca,1.0,NA,NA
+co,0.8,NA,NA
+ct,1.0,NA,NA
+ga,2.7,NA,NA
+md,0.4,NA,NA
+mn,0.1,NA,NA
+nm,0.2,NA,NA
+ny,0.7,NA,NA
+or,0.5,NA,NA
+tn,0.7,NA,NA
+ia,0.0,NA,NA
+mi,0.2,NA,NA
+oh,0.3,NA,NA
+ut,0.2,NA,NA

cdc_covidnet/tests/test_update_sensor.py

@@ -76,17 +76,16 @@ def test_syn_update_sensor(self):
 
             # Generate the csvs
             hosp_df = update_sensor(state_files, mmwr_info, temp_dir, start_date, end_date)
-
             # Check dataframe returned
             assert hosp_df.index.nlevels == 2
             assert set(hosp_df.index.names) == {"date", "geo_id"}
-            assert set(hosp_df.index.get_level_values("geo_id")) == {"CA", "PA"}
+            assert set(hosp_df.index.get_level_values("geo_id")) == {"ca", "pa"}
             assert set(hosp_df.index.get_level_values("date")) == \
                     {datetime(2020, 3, 7), datetime(2020, 3, 14)}
             assert set(hosp_df["epiweek"].unique()) == {10, 11}
             geo_index = hosp_df.index.get_level_values("geo_id")
-            assert np.allclose(hosp_df.loc[geo_index == "CA", "val"], [2.5, 3.5])
-            assert np.allclose(hosp_df.loc[geo_index == "PA", "val"], [10.3, 11.2])
+            assert np.allclose(hosp_df.loc[geo_index == "ca", "val"], [2.5, 3.5])
+            assert np.allclose(hosp_df.loc[geo_index == "pa", "val"], [10.3, 11.2])
             assert pd.isna(hosp_df["se"]).all()
             assert pd.isna(hosp_df["sample_size"]).all()
 
@@ -108,7 +107,7 @@ def test_syn_update_sensor(self):
                 assert pd.isna(data["sample_size"]).all()
 
                 # Check values are right
-                assert set(data["geo_id"].unique()) == {"CA", "PA"}
+                assert set(data["geo_id"].unique()) == {"ca", "pa"}
                 assert np.allclose(
                     data["val"], [
                         state_1["datadownload"][i]["cumulative-rate"],