mwhv2.github.io/dat_vis.html at main · mwhv2/mwhv2.github.io · GitHub

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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
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
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
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
<!DOCTYPE html>
<html>
<head>
    <title>MWL - Data Visualizations</title>
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
    <link rel="stylesheet" href="styles.css">
</head>
<body>
<div class="container">
<header>
    <div class="head1">Matt Wentzel-Long</div>
    <hr>
</header>
<nav class="navbar navbar-expand navbar-light bg-white justify-content-between">
  <div class="container-fluid">
      <div class="navbar-nav">
        <a class="nav-link" href="index.html">Home</a>
        <a class="nav-link" href="cv.html">Curriculum Vitae</a>
        <a class="nav-link" href="dis_codes.html"">Dissertation Codes</a>
        <a class="nav-link" href="dat_vis.html"><b>Data Visualizations</b></a>
      </div>
  </div>
</nav>
</div>
<div class="body_sec">
<h2>SunPy TimeSeries Data Summary</h2>
<h3>HTML-based Summary</h3>
<iframe id="igraph" scrolling="no" style="border:none;" seamless="seamless"
src="Images/sunpy.timeseries.GBM.html" height="700" width="100%"></iframe>

<p>Code available on my <a href="https://github.com/mwhv2/sunpy-git/blob/main/sunpy/timeseries/timeseriesbase.py" target="_blank">Github</a>. This data summary is best viewed within a Jupyter notebook. It is created via two functions: _text_summary and _repr_html_.</p>

<h3>Alternate Plotly-based summary</h3>
<iframe id="igraph" scrolling="no" style="border:none;" seamless="seamless"
src="Images/TimeSeries_Plotly.html" height="700" width="100%"></iframe>

<p>This alternate summary can be added to the "timeseriesbase.py" code of the TimeSeries object. It is available <a href="https://github.com/mwhv2/mwhv2.github.io/blob/main/plotly_summary.py" target="_blank">here</a>.</p>


<h2>COVID-19 Data</h2>
<iframe id="igraph" scrolling="no" style="border:none;" seamless="seamless"
src="Images/Covid19_Plotly.html" height="700" width="100%"></iframe>

<button type="button" class="collapsible">Code</button>
<div class="content">
<pre class="prettyprint">
# This notebook uses COVID-19 data from the following Github page which
# is updated daily from the Johns Hopkins Univserity CSSE (specifically,
# the countries-aggregated dataset):
# https://github.com/datasets/covid-19
# It is based on a tutorial at the following URL:
# https://towardsdatascience.com/visualizing-covid-19-data-beautifully-in-python-in-5-minutes-or-less-affc361b2c6a

import pandas as pd
import plotly.graph_objects as go
from plotly.offline import iplot
import plotly.io as pio

# Load the data into a dataframe and select a subset of countries to examine.
# Countries can be added or removed from this list (just be sure to update the
# traces on the plot below).
df = pd.read_csv('https://raw.githubusercontent.com/datasets/covid-19/master/data/countries-aggregated.csv',
                 parse_dates=['Date'])
countries = ['Canada', 'Germany', 'United Kingdom', 'US', 'France', 'South Africa', 'Brazil', 'Korea, South',
             'Ethiopia', 'Japan']
df = df[df['Country'].isin(countries)]

# Restructure the data into separate dataframes for cases and deaths,
# and set the Date column as the index.
df1 = df.pivot(index='Date', columns='Country', values='Confirmed')
df2 = df.pivot(index='Date', columns='Country', values='Deaths')
countries = list(df1.columns)
covid = df1.reset_index('Date')
deaths = df2.reset_index('Date')
covid.set_index(['Date'], inplace=True)
deaths.set_index(['Date'], inplace=True)
covid.columns = countries
deaths.columns = countries

n,b = covid.shape

# Create 7-day rolling average dataframes over the entire cases and deaths dataset.
rav = pd.DataFrame(covid[countries].values[1:]-covid[countries].values[:n-1])
rav.columns = countries
date = pd.DataFrame(covid.index[1:])
date[countries] = rav
date.set_index(['Date'],inplace=True)
rav_cases = date.rolling(window=7)[countries].mean()

rav2 = pd.DataFrame(deaths[countries].values[1:]-deaths[countries].values[:n-1])
rav2.columns = countries
date2 = pd.DataFrame(covid.index[1:])
date2[countries] = rav2
date2.set_index(['Date'],inplace=True)
rav_deaths = date2.rolling(window=7)[countries].mean()

# Create a visualization where Cases and Deaths can be viewed via buttons.
fig = go.Figure()

dates = rav_cases.index

fig.add_trace(go.Scatter(x=dates, y=rav_cases['US'], name='US', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['Brazil'], name='Brazil', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['Japan'], name='Japan', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['Germany'], name='Germany', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['United Kingdom'], name='United Kingdom', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['Korea, South'], name='South Korea', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['Ethiopia'], name='Ethiopia', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_cases['South Africa'], name='South Africa', hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['US'], name='US', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['Brazil'], name='Brazil', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['Japan'], name='Japan', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['Germany'], name='Germany', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['United Kingdom'], name='United Kingdom', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['Korea, South'], name='South Korea', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['Ethiopia'], name='Ethiopia', visible=False, hovertemplate="%{y:.2f}"))
fig.add_trace(go.Scatter(x=dates, y=rav_deaths['South Africa'], name='South Africa', visible=False, hovertemplate="%{y:.2f}"))


fig.update_layout(updatemenus = list([
    dict(type="buttons",direction="left",yanchor="top",y=1.1,x=0.1,
         active=0,
         showactive = True,
         buttons=list([
            dict(label = "Cases",
                 method = "update",
                 args = [{"visible": [True, True,True,True,True,True,True,True,False,False,False,False,False,False,False,False]},
                         {'yaxis':{'title':"7-day Avg. of Cases"}}]),
            dict(label = "Deaths",
                 method = "update",
                 args = [{"visible": [False, False,False,False,False,False,False,False,True,True,True,True,True,True,True,True]},
                         {'yaxis':{'title':"7-day Avg. of Deaths"}}])
            ]))])
                 )

fig.update_layout(dict(title="COVID-19 Data",
              showlegend=True,
              xaxis=dict(title="Date"),
              hovermode="x unified",template="seaborn"
             )
                 )

fig.add_annotation(xref="paper",x="1",yref="paper",y="-0.1",
                   text="""<a href='https://github.com/datasets/covid-19'>Source: JHU CSSE COVID-19 Data </a>""",
                   showarrow=False)

# fig.show()
pio.write_html(fig,file="Covid19_Plotly.html")

</pre>
</div>

<iframe id="igraph" scrolling="no" style="border:none;" seamless="seamless"
src="Images/Covid19_WorldMap_Cases_PerCapita.html" height="600" width="100%"></iframe>

<button type="button" class="collapsible">Code</button>
<div class="content">
<pre class="prettyprint">
# This notebook creates a visual world map that shows the change in the total number
# of Covid cases/deaths per month per capita. It uses the countryinfo Python library
# to retrieve ISO Alpha-3 codes and population information.
import pandas as pd
import plotly.express as px
import plotly.io as pio
from countryinfo import CountryInfo

# Load the countries-aggregated COVID dataset
df = pd.read_csv('https://raw.githubusercontent.com/datasets/covid-19/master/data/countries-aggregated.csv',
                 parse_dates=['Date'])
df = df.drop(labels='Recovered', axis=1)

# Restructure the data into separate dataframes for cases and deaths,
# and set the Date column as the index. Then calculate monthly totals
# of cases and deaths for each country.
df1 = df.pivot(index='Date', columns='Country', values='Confirmed')
df2 = df.pivot(index='Date', columns='Country', values='Deaths')
countries = list(df1.columns)
covid = df1.reset_index('Date')
deaths = df2.reset_index('Date')
covid.set_index(['Date'], inplace=True)
deaths.set_index(['Date'], inplace=True)
covid.columns = countries
deaths.columns = countries
date = covid.index[1:]

n,b = covid.shape
covid = pd.DataFrame(covid[countries].values[1:]-covid[countries].values[:n-1])
covid.columns = countries
covid.insert(0, 'Date', date)
covid.set_index(['Date'], inplace=True)
deaths = pd.DataFrame(deaths[countries].values[1:]-deaths[countries].values[:n-1])
deaths.columns = countries
deaths.insert(0, 'Date', date)
deaths.set_index(['Date'], inplace=True)
covid = covid.groupby(pd.PeriodIndex(covid.index, freq="M")).sum()
deaths = deaths.groupby(pd.PeriodIndex(deaths.index, freq="M")).sum()

# Use countryinfo to retrieve ISO Alpha-3 country codes
# to be used later in the choropleth plot. Print and drop countries
# which the search cannot identify fromm the dataframes.
# Divide the monthly case/death totals by the populations to
# estimate shares of populations with Covid cases or deaths.
print("Converting country names for cases...")
for i in covid.columns:
    try:
        cy = CountryInfo(i)
        iso = cy.iso()['alpha3']
        pop = cy.population()
        covid.rename(columns={i:iso}, inplace=True)
        covid[iso] = covid[iso].div(pop)
        covid[iso] = covid[iso].mul(100)
    except KeyError:
        covid.drop(columns=i, inplace=True)
        countries.remove(i)
        print(f"No record for {i}. Dropping from dataframe.")

print("Converting country names for deaths...")
for i in deaths.columns:
    try:
        cy = CountryInfo(i)
        iso = cy.iso()['alpha3']
        pop = cy.population()
        deaths.rename(columns={i:iso}, inplace=True)
        deaths[iso] = deaths[iso].div(pop)
        deaths[iso] = deaths[iso].mul(100)
    except KeyError:
        deaths.drop(columns=i, inplace=True)
        print(f"No record for {i}. Dropping from dataframe.")
print("Done")

# Restructure the data frames so that both country names and
# ISO Alpha-3 codes are given.
data = covid.values
dates = covid.index
iso_alpha = covid.columns
covid = pd.DataFrame(data=data, columns=[countries, iso_alpha], index=dates)

data2 = deaths.values
dates2 = deaths.index
iso_alpha2 = deaths.columns
deaths = pd.DataFrame(data=data2, columns=[countries, iso_alpha2], index=dates)

# Melt the dataframes into a form which choropleth can use.
covid = covid.melt(var_name=['Country', 'iso_alpha'], value_name='Cases', ignore_index=False)
deaths = deaths.melt(var_name=['Country', 'iso_alpha'], value_name='Deaths', ignore_index=False)

# Convert the dates from PeriodIndex to strings for choropleth
covid.set_index(covid.index, inplace=True)
covid.index = covid.index.strftime('%Y-%m')

deaths.set_index(deaths.index, inplace=True)
deaths.index = deaths.index.strftime('%Y-%m')

# Create the plot for Covid cases
fig = px.choropleth(covid, locations="iso_alpha",
                    color="Cases",
                    color_continuous_scale=px.colors.sequential.Plasma,
                    hover_name="Country",hover_data=["Cases"],
                    animation_frame=covid.index,
                    title="Share of Population with Covid Cases Per Month",
                    template="seaborn")

fig.add_annotation(xref="paper",x="1",yref="paper",y="-0.1",
                   text="""<a href='https://github.com/datasets/covid-19'>Source: JHU CSSE COVID-19 Data </a>""",
                   showarrow=False)

fig.show()
pio.write_html(fig,file="Covid19_WorldMap_Cases_PerCapita.html")

# Create the plot for Covid deaths
fig = px.choropleth(deaths, locations="iso_alpha",
                    color="Deaths",
                    color_continuous_scale=px.colors.sequential.Plasma,
                    hover_name="Country",hover_data=["Deaths",deaths.index],
                    animation_frame=deaths.index,
                    title="Share of Population Covid Deaths Per Month",
                    template="seaborn")

fig.add_annotation(xref="paper",x="1",yref="paper",y="-0.1",
                   text="""<a href='https://github.com/datasets/covid-19'>Source: JHU CSSE COVID-19 Data </a>""",
                   showarrow=False)

fig.show()
pio.write_html(fig,file="Covid19_WorldMap_Deaths_PerCapita.html")

</pre>
</div>

</div>
<footer>Last updated March 2025.</footer>

<script>
var coll = document.getElementsByClassName("collapsible");
var i;
for (i = 0; i < coll.length; i++) {
  coll[i].addEventListener("click", function() {
    this.classList.toggle("active");
    var content = this.nextElementSibling;
    if (content.style.display === "block") {
      content.style.display = "none";
    } else {
      content.style.display = "block";
    }
  });
}
</script>
<script src="https://cdn.jsdelivr.net/gh/google/code-prettify@master/loader/run_prettify.js"></script>
</body>
</html>