Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
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
{
"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
}