From 5f6b71b421811f9c3b8fc6d1f0bc9361131096fe Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Wed, 25 Mar 2020 22:45:56 +0000
Subject: [PATCH] feat: switch to the new JHU dataset format
---
notebooks/Dashboard.ipynb | 2 +-
notebooks/process/CompileGeoData.ipynb | 10 ++++-----
notebooks/process/ToRates.ipynb | 15 ++++++-------
.../covid_19_dashboard/helper.py | 22 ++++++++-----------
4 files changed, 22 insertions(+), 27 deletions(-)
diff --git a/notebooks/Dashboard.ipynb b/notebooks/Dashboard.ipynb
index 588336ca..17e57941 100644
--- a/notebooks/Dashboard.ipynb
+++ b/notebooks/Dashboard.ipynb
@@ -52,7 +52,7 @@
"# Identify countries with 100 or more cases\n",
"countries_over_thresh = helper.countries_with_number_of_cases(jhu_frames_map, 'confirmed', 100)\n",
"# Filter out some countries with very high case/population ratio\n",
- "countries_over_thresh = [c for c in countries_over_thresh if c not in set(['San Marino', 'Iceland'])]"
+ "countries_over_thresh = [c for c in countries_over_thresh if c not in set(['Andorra', 'Iceland', 'San Marino'])]"
]
},
{
diff --git a/notebooks/process/CompileGeoData.ipynb b/notebooks/process/CompileGeoData.ipynb
index afc2c2b8..3dda43ed 100644
--- a/notebooks/process/CompileGeoData.ipynb
+++ b/notebooks/process/CompileGeoData.ipynb
@@ -25,8 +25,8 @@
"metadata": {},
"outputs": [],
"source": [
- "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
- "worldmap_path = \"../data/worldmap/country_centroids.csv\"\n",
+ "ts_folder = \"../../data/covid-19_jhu-csse/\"\n",
+ "worldmap_path = \"../../data/worldmap/country_centroids.csv\"\n",
"out_folder = None\n",
"PAPERMILL_OUTPUT_PATH = None"
]
@@ -49,7 +49,7 @@
"outputs": [],
"source": [
"def read_jhu_covid_region_df(name):\n",
- " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " filename = os.path.join(ts_folder, f\"time_series_covid19_{name}_global.csv\")\n",
" df = pd.read_csv(filename)\n",
" df = df.set_index(['Country/Region', 'Province/State', 'Lat', 'Long'])\n",
" df.columns = pd.to_datetime(df.columns)\n",
@@ -63,7 +63,7 @@
"metadata": {},
"outputs": [],
"source": [
- "confirmed_df = read_jhu_covid_region_df(\"Confirmed\")"
+ "confirmed_df = read_jhu_covid_region_df(\"confirmed\")"
]
},
{
@@ -183,7 +183,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.6"
+ "version": "3.7.3"
}
},
"nbformat": 4,
diff --git a/notebooks/process/ToRates.ipynb b/notebooks/process/ToRates.ipynb
index cfc1c6bc..9aa7f046 100644
--- a/notebooks/process/ToRates.ipynb
+++ b/notebooks/process/ToRates.ipynb
@@ -27,9 +27,9 @@
},
"outputs": [],
"source": [
- "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
- "wb_path = \"../data/worldbank/SP.POP.TOTL.zip\"\n",
- "geodata_path = \"../data/geodata/geo_data.csv\"\n",
+ "ts_folder = \"../../data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"../../data/worldbank/SP.POP.TOTL.zip\"\n",
+ "geodata_path = \"../../data/geodata/geo_data.csv\"\n",
"out_folder = None\n",
"PAPERMILL_OUTPUT_PATH = None"
]
@@ -54,7 +54,7 @@
"outputs": [],
"source": [
"def read_jhu_covid_region_df(name):\n",
- " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " filename = os.path.join(ts_folder, f\"time_series_covid19_{name}_global.csv\")\n",
" df = pd.read_csv(filename)\n",
" df = df.set_index(['Country/Region', 'Province/State', 'Lat', 'Long'])\n",
" df.columns = pd.to_datetime(df.columns)\n",
@@ -70,9 +70,8 @@
"outputs": [],
"source": [
"frames_map = {\n",
- " \"confirmed\": read_jhu_covid_region_df(\"Confirmed\"),\n",
- " \"deaths\": read_jhu_covid_region_df(\"Deaths\"),\n",
- " \"recovered\": read_jhu_covid_region_df(\"Recovered\")\n",
+ " \"confirmed\": read_jhu_covid_region_df(\"confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_region_df(\"deaths\"),\n",
"}"
]
},
@@ -261,7 +260,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.6"
+ "version": "3.7.3"
}
},
"nbformat": 4,
diff --git a/src/covid-19/covid_19_dashboard/covid_19_dashboard/helper.py b/src/covid-19/covid_19_dashboard/covid_19_dashboard/helper.py
index fc71c372..879186f7 100644
--- a/src/covid-19/covid_19_dashboard/covid_19_dashboard/helper.py
+++ b/src/covid-19/covid_19_dashboard/covid_19_dashboard/helper.py
@@ -8,7 +8,7 @@ import os
def read_jhu_covid_df(ts_folder, name):
- filename = os.path.join(ts_folder, f"time_series_19-covid-{name}.csv")
+ filename = os.path.join(ts_folder, f"time_series_covid19_{name}_global.csv")
df = pd.read_csv(filename)
df = df.set_index(['Province/State', 'Country/Region', 'Lat', 'Long'])
df.columns = pd.to_datetime(df.columns)
@@ -18,9 +18,8 @@ def read_jhu_covid_df(ts_folder, name):
def read_jhu_frames_map(ts_folder):
jhu_frames_map = {
- "confirmed": read_jhu_covid_df(ts_folder, "Confirmed"),
- "deaths": read_jhu_covid_df(ts_folder, "Deaths"),
- "recovered": read_jhu_covid_df(ts_folder, "Recovered")
+ "confirmed": read_jhu_covid_df(ts_folder, "confirmed"),
+ "deaths": read_jhu_covid_df(ts_folder, "deaths"),
}
return jhu_frames_map
@@ -37,7 +36,6 @@ def read_rates_frames_map(rates_folder):
rates_frames_map = {
"confirmed": read_rates_covid_df(rates_folder, "confirmed"),
"deaths": read_rates_covid_df(rates_folder, "deaths"),
- "recovered": read_rates_covid_df(rates_folder, "recovered")
}
return rates_frames_map
@@ -67,19 +65,17 @@ def latest_rates_ser(rates_frames_map, name):
def compute_map_df(rates_frames_map, jhu_frames_map, geodata_df, countries_over_thresh):
map_df = pd.concat([
latest_rates_ser(rates_frames_map, 'confirmed'),
- latest_rates_ser(rates_frames_map, 'deaths'),
- latest_rates_ser(rates_frames_map, 'recovered')], axis=1)
+ latest_rates_ser(rates_frames_map, 'deaths')], axis=1)
nominal_df = pd.concat([
latest_jhu_country_ser(jhu_frames_map, 'confirmed'),
- latest_jhu_country_ser(jhu_frames_map, 'deaths'),
- latest_jhu_country_ser(jhu_frames_map, 'recovered')], axis=1)
+ latest_jhu_country_ser(jhu_frames_map, 'deaths')], axis=1)
map_df = pd.concat([map_df, nominal_df, geodata_df[['Longitude', 'Latitude']]], axis=1)
# Restrict to countries with 100 or more cases
map_df = map_df.loc[countries_over_thresh].dropna()
map_df = map_df.reset_index()
map_df.columns = ['Country/Region',
- 'Confirmed/100k', 'Deaths/100k', 'Recovered/100k',
- 'Confirmed', 'Deaths', 'Recovered',
+ 'Confirmed/100k', 'Deaths/100k',
+ 'Confirmed', 'Deaths',
'Long', 'Lat']
return map_df
@@ -103,8 +99,8 @@ def map_of_variable(map_df, variable, title):
size=alt.Size(f'{variable}:Q', title="Cases"),
color=alt.value('steelblue'),
tooltip=["Country/Region:N",
- "Confirmed:Q", "Deaths:Q", "Recovered:Q",
- "Confirmed/100k:Q", "Deaths/100k:Q", "Recovered/100k:Q"]
+ "Confirmed:Q", "Deaths:Q",
+ "Confirmed/100k:Q", "Deaths/100k:Q"]
)
).project(
'naturalEarth1'
--
GitLab