diff --git a/.gitattributes b/.gitattributes
index d7d532ecd9b5561134ea6debb2e565af16445ebd..9afe52d034d59b89e2bbd51ff6fafb187a426869 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -2,3 +2,4 @@ data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv filter=lfs diff=lfs me
data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv filter=lfs diff=lfs merge=lfs -text
data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv filter=lfs diff=lfs merge=lfs -text
data/worldbank/SP.POP.TOTL.zip filter=lfs diff=lfs merge=lfs -text
+data/covid-19_rates/** filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl b/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..ee8c3ca5ce03d4f3c0ec3a8f6aefcba58f7aa740
--- /dev/null
+++ b/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl
@@ -0,0 +1,115 @@
+arguments: []
+baseCommand:
+- papermill
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+ input_1:
+ default: ts_folder
+ inputBinding:
+ position: 1
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_2:
+ default:
+ class: Directory
+ listing: []
+ path: ../../data/covid-19_jhu-csse
+ inputBinding:
+ position: 2
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: Directory
+ input_3:
+ default: wb_path
+ inputBinding:
+ position: 3
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_4:
+ default:
+ class: File
+ path: ../../data/worldbank/SP.POP.TOTL.zip
+ inputBinding:
+ position: 4
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_5:
+ default: out_folder
+ inputBinding:
+ position: 5
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_6:
+ default: data/covid-19_rates
+ inputBinding:
+ position: 6
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_7:
+ default:
+ class: File
+ path: ../../notebooks/ToRates.ipynb
+ inputBinding:
+ position: 7
+ prefix: --inject-paths
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_8:
+ default: runs/ToRates.run.ipynb
+ inputBinding:
+ position: 8
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+outputs:
+ output_0:
+ outputBinding:
+ glob: $(inputs.input_8)
+ streamable: false
+ type: File
+ output_1:
+ outputBinding:
+ glob: $(inputs.input_6)
+ streamable: false
+ type: Directory
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+ listing:
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: runs
+ writable: true
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: data/covid-19_rates
+ writable: true
+ - entry: $(inputs.input_2)
+ entryname: data/covid-19_jhu-csse
+ writable: false
+ - entry: $(inputs.input_4)
+ entryname: data/worldbank/SP.POP.TOTL.zip
+ writable: false
+ - entry: $(inputs.input_7)
+ entryname: notebooks/ToRates.ipynb
+ writable: false
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/covid-19_rates/ts_rates_19-covid-confirmed.csv b/data/covid-19_rates/ts_rates_19-covid-confirmed.csv
new file mode 100644
index 0000000000000000000000000000000000000000..68469b73899f1a13e5dfc305c01e517f2372300f
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-confirmed.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953941d2e4414e15f0e840d13c806b56d0cfda23f402d2d8daf840ef9e6ba666
+size 55521
diff --git a/data/covid-19_rates/ts_rates_19-covid-deaths.csv b/data/covid-19_rates/ts_rates_19-covid-deaths.csv
new file mode 100644
index 0000000000000000000000000000000000000000..927fd93f7b7d3b87e3dc685bc8e283c4d007d41d
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-deaths.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d07625575b61e275be3ba1b85e04dc96984df348680d2c3f5866a4443144138
+size 28842
diff --git a/data/covid-19_rates/ts_rates_19-covid-recovered.csv b/data/covid-19_rates/ts_rates_19-covid-recovered.csv
new file mode 100644
index 0000000000000000000000000000000000000000..c35fa7b034cd61892a7d26c0bb897288662cf439
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-recovered.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae1d5842d547e04eec2706bb61a5f5c019f244150dbab899c675ad67f166524
+size 38957
diff --git a/runs/ToRates.run.ipynb b/runs/ToRates.run.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..2925f4eefd7a6bff1c917d01551b49198f9d0e50
--- /dev/null
+++ b/runs/ToRates.run.ipynb
@@ -0,0 +1,827 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.019737,
+ "end_time": "2020-03-13T14:54:48.276145",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.256408",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Convert Series to Rates per 100,000"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "papermill": {
+ "duration": 0.327112,
+ "end_time": "2020-03-13T14:54:48.613995",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.286883",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "papermill": {
+ "duration": 0.025647,
+ "end_time": "2020-03-13T14:54:48.658686",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.633039",
+ "status": "completed"
+ },
+ "tags": [
+ "parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"../data/worldbank/SP.POP.TOTL.zip\"\n",
+ "out_folder = None\n",
+ "PAPERMILL_OUTPUT_PATH = None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "papermill": {
+ "duration": 0.027378,
+ "end_time": "2020-03-13T14:54:48.697099",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.669721",
+ "status": "completed"
+ },
+ "tags": [
+ "injected-parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "# Parameters\n",
+ "PAPERMILL_INPUT_PATH = \"notebooks/ToRates.ipynb\"\n",
+ "PAPERMILL_OUTPUT_PATH = \"runs/ToRates.run.ipynb\"\n",
+ "ts_folder = \"./data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"./data/worldbank/SP.POP.TOTL.zip\"\n",
+ "out_folder = \"./data/covid-19_rates/\"\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009984,
+ "end_time": "2020-03-13T14:54:48.724400",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.714416",
+ "status": "completed"
+ },
+ "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": 4,
+ "metadata": {
+ "papermill": {
+ "duration": 0.044299,
+ "end_time": "2020-03-13T14:54:48.778200",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.733901",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "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": 5,
+ "metadata": {
+ "papermill": {
+ "duration": 0.126546,
+ "end_time": "2020-03-13T14:54:48.922552",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.796006",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "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": "code",
+ "execution_count": 6,
+ "metadata": {
+ "papermill": {
+ "duration": 0.05437,
+ "end_time": "2020-03-13T14:54:48.984940",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.930570",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>2020-01-22</th>\n",
+ " <th>2020-01-23</th>\n",
+ " <th>2020-01-24</th>\n",
+ " <th>2020-01-25</th>\n",
+ " <th>2020-01-26</th>\n",
+ " <th>2020-01-27</th>\n",
+ " <th>2020-01-28</th>\n",
+ " <th>2020-01-29</th>\n",
+ " <th>2020-01-30</th>\n",
+ " <th>2020-01-31</th>\n",
+ " <th>...</th>\n",
+ " <th>2020-03-01</th>\n",
+ " <th>2020-03-02</th>\n",
+ " <th>2020-03-03</th>\n",
+ " <th>2020-03-04</th>\n",
+ " <th>2020-03-05</th>\n",
+ " <th>2020-03-06</th>\n",
+ " <th>2020-03-07</th>\n",
+ " <th>2020-03-08</th>\n",
+ " <th>2020-03-09</th>\n",
+ " <th>2020-03-10</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Country/Region</th>\n",
+ " <th>Long</th>\n",
+ " <th>Lat</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Mainland China</th>\n",
+ " <th>111.542903</th>\n",
+ " <th>33.406936</th>\n",
+ " <td>547</td>\n",
+ " <td>639</td>\n",
+ " <td>916</td>\n",
+ " <td>1399</td>\n",
+ " <td>2062</td>\n",
+ " <td>2863</td>\n",
+ " <td>5494</td>\n",
+ " <td>6070</td>\n",
+ " <td>8124</td>\n",
+ " <td>9783</td>\n",
+ " <td>...</td>\n",
+ " <td>79826</td>\n",
+ " <td>80026</td>\n",
+ " <td>80151</td>\n",
+ " <td>80271</td>\n",
+ " <td>80422</td>\n",
+ " <td>80573</td>\n",
+ " <td>80652</td>\n",
+ " <td>80699</td>\n",
+ " <td>80735</td>\n",
+ " <td>80757</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Italy</th>\n",
+ " <th>12.000000</th>\n",
+ " <th>43.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>...</td>\n",
+ " <td>1694</td>\n",
+ " <td>2036</td>\n",
+ " <td>2502</td>\n",
+ " <td>3089</td>\n",
+ " <td>3858</td>\n",
+ " <td>4636</td>\n",
+ " <td>5883</td>\n",
+ " <td>7375</td>\n",
+ " <td>9172</td>\n",
+ " <td>10149</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Iran (Islamic Republic of)</th>\n",
+ " <th>53.000000</th>\n",
+ " <th>32.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>978</td>\n",
+ " <td>1501</td>\n",
+ " <td>2336</td>\n",
+ " <td>2922</td>\n",
+ " <td>3513</td>\n",
+ " <td>4747</td>\n",
+ " <td>5823</td>\n",
+ " <td>6566</td>\n",
+ " <td>7161</td>\n",
+ " <td>8042</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Republic of Korea</th>\n",
+ " <th>128.000000</th>\n",
+ " <th>36.000000</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>11</td>\n",
+ " <td>...</td>\n",
+ " <td>3736</td>\n",
+ " <td>4335</td>\n",
+ " <td>5186</td>\n",
+ " <td>5621</td>\n",
+ " <td>6088</td>\n",
+ " <td>6593</td>\n",
+ " <td>7041</td>\n",
+ " <td>7314</td>\n",
+ " <td>7478</td>\n",
+ " <td>7513</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>France</th>\n",
+ " <th>2.000000</th>\n",
+ " <th>47.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>5</td>\n",
+ " <td>5</td>\n",
+ " <td>5</td>\n",
+ " <td>...</td>\n",
+ " <td>130</td>\n",
+ " <td>191</td>\n",
+ " <td>204</td>\n",
+ " <td>285</td>\n",
+ " <td>377</td>\n",
+ " <td>653</td>\n",
+ " <td>949</td>\n",
+ " <td>1126</td>\n",
+ " <td>1209</td>\n",
+ " <td>1784</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>5 rows × 49 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 2020-01-22 2020-01-23 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 547 639 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 1 1 \n",
+ "France 2.000000 47.000000 0 0 \n",
+ "\n",
+ " 2020-01-24 2020-01-25 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 916 1399 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 2 2 \n",
+ "France 2.000000 47.000000 2 3 \n",
+ "\n",
+ " 2020-01-26 2020-01-27 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 2062 2863 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 3 4 \n",
+ "France 2.000000 47.000000 3 3 \n",
+ "\n",
+ " 2020-01-28 2020-01-29 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 5494 6070 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 4 4 \n",
+ "France 2.000000 47.000000 4 5 \n",
+ "\n",
+ " 2020-01-30 2020-01-31 ... \\\n",
+ "Country/Region Long Lat ... \n",
+ "Mainland China 111.542903 33.406936 8124 9783 ... \n",
+ "Italy 12.000000 43.000000 0 2 ... \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 ... \n",
+ "Republic of Korea 128.000000 36.000000 4 11 ... \n",
+ "France 2.000000 47.000000 5 5 ... \n",
+ "\n",
+ " 2020-03-01 2020-03-02 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 79826 80026 \n",
+ "Italy 12.000000 43.000000 1694 2036 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 978 1501 \n",
+ "Republic of Korea 128.000000 36.000000 3736 4335 \n",
+ "France 2.000000 47.000000 130 191 \n",
+ "\n",
+ " 2020-03-03 2020-03-04 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80151 80271 \n",
+ "Italy 12.000000 43.000000 2502 3089 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 2336 2922 \n",
+ "Republic of Korea 128.000000 36.000000 5186 5621 \n",
+ "France 2.000000 47.000000 204 285 \n",
+ "\n",
+ " 2020-03-05 2020-03-06 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80422 80573 \n",
+ "Italy 12.000000 43.000000 3858 4636 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 3513 4747 \n",
+ "Republic of Korea 128.000000 36.000000 6088 6593 \n",
+ "France 2.000000 47.000000 377 653 \n",
+ "\n",
+ " 2020-03-07 2020-03-08 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80652 80699 \n",
+ "Italy 12.000000 43.000000 5883 7375 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 5823 6566 \n",
+ "Republic of Korea 128.000000 36.000000 7041 7314 \n",
+ "France 2.000000 47.000000 949 1126 \n",
+ "\n",
+ " 2020-03-09 2020-03-10 \n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80735 80757 \n",
+ "Italy 12.000000 43.000000 9172 10149 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 7161 8042 \n",
+ "Republic of Korea 128.000000 36.000000 7478 7513 \n",
+ "France 2.000000 47.000000 1209 1784 \n",
+ "\n",
+ "[5 rows x 49 columns]"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "frames_map['confirmed'].sort_values(frames_map['confirmed'].columns[-1], ascending=False).head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.011038,
+ "end_time": "2020-03-13T14:54:49.012475",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.001437",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Read in World Bank data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "papermill": {
+ "duration": 0.043639,
+ "end_time": "2020-03-13T14:54:49.064213",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.020574",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "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": {
+ "papermill": {
+ "duration": 0.010307,
+ "end_time": "2020-03-13T14:54:49.091394",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.081087",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "There is 2018 pop data for all countries/regions except Eritrea"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "papermill": {
+ "duration": 0.055137,
+ "end_time": "2020-03-13T14:54:49.154951",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.099814",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Country Name</th>\n",
+ " <th>Country Code</th>\n",
+ " <th>Indicator Name</th>\n",
+ " <th>Indicator Code</th>\n",
+ " <th>1960</th>\n",
+ " <th>1961</th>\n",
+ " <th>1962</th>\n",
+ " <th>1963</th>\n",
+ " <th>1964</th>\n",
+ " <th>1965</th>\n",
+ " <th>...</th>\n",
+ " <th>2011</th>\n",
+ " <th>2012</th>\n",
+ " <th>2013</th>\n",
+ " <th>2014</th>\n",
+ " <th>2015</th>\n",
+ " <th>2016</th>\n",
+ " <th>2017</th>\n",
+ " <th>2018</th>\n",
+ " <th>2019</th>\n",
+ " <th>Unnamed: 64</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>67</th>\n",
+ " <td>Eritrea</td>\n",
+ " <td>ERI</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>1007590.0</td>\n",
+ " <td>1033328.0</td>\n",
+ " <td>1060486.0</td>\n",
+ " <td>1088854.0</td>\n",
+ " <td>1118159.0</td>\n",
+ " <td>1148189.0</td>\n",
+ " <td>...</td>\n",
+ " <td>3213972.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>108</th>\n",
+ " <td>Not classified</td>\n",
+ " <td>INX</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2 rows × 65 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Country Name Country Code Indicator Name Indicator Code 1960 \\\n",
+ "67 Eritrea ERI Population, total SP.POP.TOTL 1007590.0 \n",
+ "108 Not classified INX Population, total SP.POP.TOTL NaN \n",
+ "\n",
+ " 1961 1962 1963 1964 1965 ... 2011 \\\n",
+ "67 1033328.0 1060486.0 1088854.0 1118159.0 1148189.0 ... 3213972.0 \n",
+ "108 NaN NaN NaN NaN NaN ... NaN \n",
+ "\n",
+ " 2012 2013 2014 2015 2016 2017 2018 2019 Unnamed: 64 \n",
+ "67 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "108 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "\n",
+ "[2 rows x 65 columns]"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pop_df[pd.isna(pop_df['2018'])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009197,
+ "end_time": "2020-03-13T14:54:49.179422",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.170225",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "Fix the country/region names that differ between the World Bank population data and the JHU CSSE data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "papermill": {
+ "duration": 0.048983,
+ "end_time": "2020-03-13T14:54:49.237289",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.188306",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "region_wb_jhu_map = {\n",
+ " 'China': 'Mainland China',\n",
+ " 'Iran, Islamic Rep.': 'Iran (Islamic Republic of)',\n",
+ " 'Korea, Rep.': 'Republic of Korea',\n",
+ " 'United States': 'US',\n",
+ " 'United Kingdom': 'UK',\n",
+ " 'Hong Kong SAR, China': 'Hong Kong SAR',\n",
+ " 'Egypt, Arab Rep.': 'Egypt',\n",
+ " 'Vietnam': 'Viet Nam',\n",
+ " 'Macao SAR, China': 'Macao SAR',\n",
+ " 'Slovak Republic': 'Slovakia',\n",
+ " 'Moldova': 'Republic of Moldova',\n",
+ " 'St. Martin (French part)': 'Saint Martin',\n",
+ " 'Brunei Darussalam': 'Brunei'\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": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.010552,
+ "end_time": "2020-03-13T14:54:49.263442",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.252890",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "There are some regions that we cannot resolve, but we will just ignore these."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.008224,
+ "end_time": "2020-03-13T14:54:49.280239",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.272015",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Compute rates per 100,000 for regions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "papermill": {
+ "duration": 0.081057,
+ "end_time": "2020-03-13T14:54:49.370031",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.288974",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "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": 11,
+ "metadata": {
+ "papermill": {
+ "duration": 0.065887,
+ "end_time": "2020-03-13T14:54:49.458887",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.393000",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "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"
+ },
+ "papermill": {
+ "duration": 2.37776,
+ "end_time": "2020-03-13T14:54:49.786899",
+ "environment_variables": {},
+ "exception": null,
+ "input_path": "notebooks/ToRates.ipynb",
+ "output_path": "runs/ToRates.run.ipynb",
+ "parameters": {
+ "PAPERMILL_INPUT_PATH": "notebooks/ToRates.ipynb",
+ "PAPERMILL_OUTPUT_PATH": "runs/ToRates.run.ipynb",
+ "out_folder": "./data/covid-19_rates/",
+ "ts_folder": "./data/covid-19_jhu-csse/",
+ "wb_path": "./data/worldbank/SP.POP.TOTL.zip"
+ },
+ "start_time": "2020-03-13T14:54:47.409139",
+ "version": "1.1.0"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file