Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Convert Series to Rates per 100,000"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": [
"parameters"
]
},
"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",
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
"out_folder = None\n",
"PAPERMILL_OUTPUT_PATH = None"
]
},
{
"cell_type": "markdown",
"metadata": {
"tags": [
"parameters"
]
},
"source": [
"## Read in JHU CSSE data\n",
"\n",
"I will switch to [xarray](http://xarray.pydata.org/en/stable/), but ATM, it's easier like this..."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def read_jhu_covid_region_df(name):\n",
" filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.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",
" region_df = df.groupby(level='Country/Region').sum()\n",
" loc_df = df.reset_index([2,3]).groupby(level='Country/Region').mean()[['Long', 'Lat']]\n",
" return region_df.join(loc_df).set_index(['Long', 'Lat'], append=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"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",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Read in World Bank data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import zipfile\n",
"zf = zipfile.ZipFile(wb_path)\n",
"pop_df = pd.read_csv(zf.open(\"API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv\"), skiprows=4)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"There is 2018 pop data for all countries/regions except Eritrea"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pop_df[pd.isna(pop_df['2018'])]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Fix the country/region names that differ between the World Bank population data and the JHU CSSE data."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"region_wb_jhu_map = {\n",
" 'Brunei Darussalam': 'Brunei',\n",
" 'Czech Republic': 'Czechia',\n",
" 'Egypt, Arab Rep.': 'Egypt',\n",
" 'Hong Kong SAR, China': 'Hong Kong SAR',\n",
" 'Iran, Islamic Rep.': 'Iran',\n",
" 'Korea, Rep.': 'Korea, South',\n",
" 'Macao SAR, China': 'Macao SAR',\n",
" 'Russian Federation': 'Russia',\n",
" 'Slovak Republic': 'Slovakia',\n",
" 'St. Martin (French part)': 'Saint Martin',\n",
" 'United States': 'US'\n",
"}\n",
"current_pop_ser = pop_df[['Country Name', '2018']].copy().replace(region_wb_jhu_map).set_index('Country Name')['2018']\n",
"data_pop_ser = current_pop_ser[current_pop_ser.index.isin(frames_map['confirmed'].index.levels[0])]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Use this to find the name in the series\n",
"# current_pop_ser[current_pop_ser.index.str.contains('Czech')]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"There are some regions that we cannot resolve, but we will just ignore these."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"frames_map['confirmed'].loc[\n",
" frames_map['confirmed'].index.levels[0].isin(data_pop_ser.index) == False\n",
"].iloc[:,-2:]"
]
},
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Read in geodata to get additional population numbers"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"geodata_df = pd.read_csv(geodata_path).drop('Unnamed: 0', axis=1).set_index('name_jhu')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Add in populations for missing countries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"missing_countries = frames_map['confirmed'].loc[\n",
" frames_map['confirmed'].index.levels[0].isin(data_pop_ser.index) == False\n",
"].iloc[:,-2:].reset_index()['Country/Region']\n",
"\n",
"display(geodata_df.loc[geodata_df.index.isin(missing_countries)])\n",
"\n",
"data_pop_ser = data_pop_ser.append(geodata_df.loc[geodata_df.index.isin(missing_countries), 'pop_est'])"
]
},
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Compute rates per 100,000 for regions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def cases_to_rates_df(df):\n",
" per_100000_df = df.reset_index([1, 2], drop=True)\n",
" per_100000_df = per_100000_df.div(data_pop_ser, 'index').mul(100000).dropna()\n",
" per_100000_df.index.name = 'Country/Region'\n",
" return per_100000_df\n",
" \n",
"def frames_to_rates(frames_map):\n",
" return {k: cases_to_rates_df(v) for k,v in frames_map.items()}\n",
"\n",
"\n",
"rates_map = frames_to_rates(frames_map)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if PAPERMILL_OUTPUT_PATH:\n",
" for k, v in rates_map.items():\n",
" out_path = os.path.join(out_folder, f\"ts_rates_19-covid-{k}.csv\")\n",
" v.reset_index().to_csv(out_path)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 4
}