From e8d09f632b65608c404ed54785e86865da0e265d Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Wed, 11 Mar 2020 22:29:45 +0000
Subject: [PATCH] feat: notebook for playing with data
---
notebooks/Play.ipynb | 109 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 109 insertions(+)
create mode 100644 notebooks/Play.ipynb
diff --git a/notebooks/Play.ipynb b/notebooks/Play.ipynb
new file mode 100644
index 00000000..fd34756b
--- /dev/null
+++ b/notebooks/Play.ipynb
@@ -0,0 +1,109 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "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": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_df(name):\n",
+ " filename = f\"../data/covid-19_jhu-csse/time_series_19-covid-{name}.csv\"\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Province/State', 'Country/Region', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "confirmed_df = read_jhu_covid_df(\"Confirmed\")\n",
+ "deaths_df = read_jhu_covid_df(\"Deaths\")\n",
+ "recovered_df = read_jhu_covid_df(\"Recovered\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def summarize_df(df, name):\n",
+ " ser = df.groupby(level='Country/Region').sum().iloc[:,-1].sort_values(ascending=False)\n",
+ " ser.name = f\"Total {name}\"\n",
+ " return ser"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "confirmed_ser = summarize_df(confirmed_df, \"Confirmed\")\n",
+ "deaths_ser = summarize_df(deaths_df, \"Deaths\")\n",
+ "recovered_ser = summarize_df(recovered_df, \"Recovered\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Read in World Bank data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import zipfile\n",
+ "zf = zipfile.ZipFile(\"../data/worldbank/SP.POP.TOTL.zip\")\n",
+ "pop_df = pd.read_csv(zf.open(\"API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv\"), skiprows=4)"
+ ]
+ }
+ ],
+ "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
+}
--
GitLab