From c90274b2e9dfb0168acc904dd1362100618d3a60 Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Wed, 8 Apr 2020 12:48:48 +0000
Subject: [PATCH] feat: use Harvard Worldmap for regions without population
data from Worldbank
---
.../covid_19_dashboard/converters/jhu.py | 31 ++++++++++++++++---
1 file changed, 27 insertions(+), 4 deletions(-)
diff --git a/src/covid-19/covid_19_dashboard/covid_19_dashboard/converters/jhu.py b/src/covid-19/covid_19_dashboard/covid_19_dashboard/converters/jhu.py
index 2236705ca..a6b53cdaf 100644
--- a/src/covid-19/covid_19_dashboard/covid_19_dashboard/converters/jhu.py
+++ b/src/covid-19/covid_19_dashboard/covid_19_dashboard/converters/jhu.py
@@ -28,32 +28,55 @@ class JhuCsseGlobalCaseConverter(CaseConverterImpl):
pop_df = pd.read_csv(
zf.open("API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv"), skiprows=4
)
-
+ pop_df = pop_df[["Country Name", "Country Code", "2018"]]
# Fix the names of countries
region_jhu_wb_map = {
+ "Bahamas": "Bahamas, The",
"Brunei": "Brunei Darussalam",
+ "Burma": "Myanmar",
+ "Congo (Brazzaville)": "Congo, Rep.",
+ "Congo (Kinshasa)": "Congo, Dem. Rep.",
"Czechia": "Czech Republic",
"Egypt": "Egypt, Arab Rep.",
+ "Gambia": "Gambia, The",
"Hong Kong SAR": "Hong Kong SAR, China",
"Iran": "Iran, Islamic Rep.",
"Korea, South": "Korea, Rep.",
+ "Kyrgyzstan": "Kyrgyz Republic",
+ "Laos": "Lao PDR",
"Macao SAR": "Macao SAR, China",
"Russia": "Russian Federation",
+ "Saint Kitts and Nevis": "St. Kitts and Nevis",
+ "Saint Lucia": "St. Lucia",
+ "Saint Vincent and the Grenadines": "St. Vincent and the Grenadines",
"Slovakia": "Slovak Republic",
"Saint Martin": "St. Martin (French part)",
+ "Syria": "Syrian Arab Republic",
+ 'Taiwan*': 'Taiwan',
+ "Venezuela": "Venezuela, RB",
"US": "United States",
}
df = df.replace(region_jhu_wb_map)
+
+ # add in missing data from Harvard worldmap
+ missing_countries = pd.unique(df.loc[df["region_label"].isin(pop_df["Country Name"]) == False, "region_label"])
+ worldmap_df = pd.read_csv(self.atlas_folder / "worldmap" / "country_centroids.csv")
+ worldmap_df = worldmap_df[['name', 'sov_a3', 'pop_est']]
+ worldmap_df = worldmap_df.rename({"name": "Country Name",
+ "sov_a3": "Country Code",
+ "pop_est": "2018"}, axis=1)
+ worldmap_df = worldmap_df.loc[worldmap_df["Country Name"].isin(missing_countries)]
+ pop_df = pop_df.append(worldmap_df)
+
+ pop_ser = pop_df.set_index("Country Code")["2018"]
country_code_map = {
r["Country Name"]: r["Country Code"]
for i, r in pop_df[["Country Name", "Country Code"]].iterrows()
}
df["country"] = df["region_label"].replace(country_code_map)
df['country_label'] = df['region_label']
- pop_ser = pop_df.set_index("Country Code")["2018"]
- merged = df.loc[df["country"].isin(pop_ser.index)].copy()
- # TODO Also consult for worldmap data for countries like Taiwan
+ merged = df.loc[df["country"].isin(pop_ser.index)].copy()
merged["population"] = merged.apply(lambda r: pop_ser.loc[r["country"]], axis=1)
merged['region_iso'] = merged['country']
return self._set_common_columns(merged)
--
GitLab