def update_graph(DayofWeek, TimeofDay, branch_index, func, pltTitle):
'''
plot barplots of different functions for specific DayofWeek and TimeofDay
Parameters
---
DayofWeek: Str
TimeofDay: Str
func: Str
pltTitle: Str
branch_index: Str
'''
chart = alt.Chart(new_df).mark_bar(color="cornflowerblue").encode(
alt.X('Product line:N'),
alt.Y(func, type='quantitative'),
tooltip=[
alt.Tooltip('Product line', title='Product line'),
alt.Tooltip('Day_of_week', title="Day of Week"),
alt.Tooltip('Time_of_day', title="Time of Day"),
alt.Tooltip(func, title=pltTitle)
]).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=branch_index)).transform_filter(
alt.FieldEqualPredicate(
field='Day_of_week',
equal=DayofWeek)).transform_filter(
alt.FieldEqualPredicate(
field='Time_of_day',
equal=TimeofDay)).properties(width=280,
height=200,
title=pltTitle)
return chart
def make_bar_plot(day_of_week, time_of_day, branch_index, func, plot_title, y_title):
'''Make a bar plot filtered by branch, day of week, and time of day
Parameters
---
day_of_week: Str
time_of_day: Str
func: Str
plot_title: Str
branch_index: Str
'''
bar_plot = (alt
.Chart(df)
.mark_bar(color = 'cornflowerblue')
.encode(alt.X('Product line:N', title=None),
alt.Y(func, type='quantitative', title=y_title),
tooltip=[alt.Tooltip('Product line', title='Product line'),
alt.Tooltip('Day_of_week', title='Day of Week'),
alt.Tooltip('Time_of_day', title='Time of Day'),
alt.Tooltip(func, title=plot_title)])
.transform_filter(alt.FieldEqualPredicate(field='Branch', equal=branch_index))
.transform_filter(alt.FieldEqualPredicate(field='Day_of_week', equal=day_of_week))
.transform_filter(alt.FieldEqualPredicate(field='Time_of_day', equal=time_of_day))
.properties(width=250, height=175, title= plot_title)
)
return bar_plot
def timeseries_chart(data, category):
chartData = (
data[data['chapter'] == category]
.groupby(["cause_of_death_map", "sex", "year"])
.agg({"count": "sum"})
.reset_index()
.sort_values("count", ascending=False)
)
colorScale = alt.Scale(
domain=['Males', 'Females'],
range=['#4A90E2', '#50E3C2']
)
choices = chartData[chartData['cause_of_death_map'] != 'Other']['cause_of_death_map'].unique()
colorScale = alt.Scale(
domain=['Males', 'Females'],
range=['#4A90E2', '#50E3C2']
)
base = alt.Chart(chartData).mark_line(
point=True,
interpolate="cardinal"
).encode(
x=alt.X("year", type="nominal", axis=alt.Axis(labelAngle=330), title="Year"),
y=alt.Y("count", title="Number of Deaths"),
tooltip=chartData.columns.tolist(),
color=alt.Color("sex", scale=colorScale, legend=alt.Legend(title="Gender"))
).properties(
width=350,
height=200
)
one = base.transform_filter(
alt.FieldEqualPredicate(field='cause_of_death_map', equal=choices[0])
).properties(
title=choices[0]
)
two = base.transform_filter(
alt.FieldEqualPredicate(field='cause_of_death_map', equal=choices[1])
).properties(
title=choices[1]
)
three = base.transform_filter(
alt.FieldEqualPredicate(field='cause_of_death_map', equal=choices[2])
).properties(
title=choices[2]
)
chart = alt.hconcat(one, two, three).configure(
axis=alt.Axis(grid=False)
)
return return_vega_spec_json(chart)
def make_heat_map(branch_index, func, plot_title):
'''Make a heat map by day of week and time of day
Parameters
---
branch_index: Str
func: Str
plot_title: Str
'''
days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
times = ['Morning', 'Afternoon', 'Evening']
heat_map = (alt
.Chart(df)
.mark_rect()
.encode(alt.X('Day_of_week:N', title=None, sort=days),
alt.Y('Time_of_day:N', title=None, sort=times),
alt.Color(func, type = 'quantitative' ,title=None, scale=alt.Scale(scheme='greens')),
tooltip=[alt.Tooltip('Day_of_week', title='Day of the week'),
alt.Tooltip('Time_of_day', title='Time of the day'),
alt.Tooltip(func, type='quantitative', title=plot_title, format=',.0f')])
.configure_axisX(labelAngle=45)
.transform_filter(alt.FieldEqualPredicate(field='Branch', equal= branch_index))
.configure_axis(labelFontSize=13, titleFontSize=13)
.configure_title(fontSize=14)
.properties(width=180, height=130, title=plot_title)
)
return heat_map
def make_total_sales(store_id='A'):
# Create total sales heat map (unfiltered by store)
total_sales = (
alt.Chart(df) # make this react to the radio
.mark_rect().encode(
alt.X('Day_of_week:N', title=None, sort=days),
alt.Y('Time_of_day:N', title=None, sort=times),
alt.Color('sum(Total):Q',
title=None,
scale=alt.Scale(scheme='greens')),
tooltip=[
alt.Tooltip('Day_of_week', title='Day of the week'),
alt.Tooltip('Time_of_day', title="Time of the day"),
alt.Tooltip('sum(Total):Q', title='Sales', format='$,.0f')
]).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=store_id)).configure_axis(
labelFontSize=13, titleFontSize=13).configure_title(
fontSize=14).properties(width=180,
height=130,
title='Total sales'))
return total_sales
def update_world_chart(year, stat_type, include_usa, gdp_pct):
map_stat = 'percent_GDP' if gdp_pct else 'USD_Value'
map_legend = '% GDP' if gdp_pct else 'USD Value'
arms_df_tmp = arms_gdp.copy()
if not include_usa:
arms_df_tmp.loc[arms_df_tmp['Country'] == 'USA', map_stat] = 0
print(year, stat_type, include_usa, gdp_pct)
chart = alt.Chart(world_map_skl).mark_geoshape(stroke='white').encode(
color=alt.condition(alt.FieldEqualPredicate(field=map_stat, equal=0),
alt.value('lightgray'), map_stat + ':Q',
scale=alt.Scale(scheme='goldorange'),
legend=alt.Legend(title=map_legend)),
tooltip=['Country:N', map_stat + ':Q']
).transform_lookup(
lookup='id',
from_=alt.LookupData(arms_df_tmp.query("Year == " + str(year)).query("Direction == '%s'" % (stat_type)), 'id',
[map_stat, 'Country'])
).project('equirectangular').properties(
width=720,
height=300,
background='white'
).configure_axis(
grid=False
)
return html.Iframe(
sandbox='allow-scripts',
id='plot',
width='900',
height='350',
style={'border-width': '0'},
srcDoc=chart.to_html()
)
def concat_earnings_rank(year, geo):
ear_rank = alt.Chart(
eco, title="Average weekly earnings by province/territory"
).mark_bar().encode(
x=alt.X('average(All industries):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('$,f')),
title=None),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition(
(alt.datum.Geography == geo) | (alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All industries):Q',
format='$,',
title='Earnings')
]).transform_filter(alt.FieldEqualPredicate(
field='Year',
equal=year)).configure_view(strokeOpacity=0).configure_axis(
domain=False).configure_title(fontSize=30)
w = 300
h = 200
ear_rank = ear_rank.properties(width=w, height=h)
return ear_rank.to_html()
def make_transaction_size(store_id='A'):
# Create average transaction size heat map (unfiltered by store)
transaction_size = (alt.Chart(df).mark_rect().transform_aggregate(
groupby=['Branch', 'Day_of_week', 'Time_of_day'],
total_sales='sum(Total):Q',
total_trxns='count(Invoice ID):Q').transform_calculate(
Avg_trans_size='datum.total_sales / datum.total_trxns').encode(
alt.X('Day_of_week:N', title=None, sort=days),
alt.Y('Time_of_day:N', title=None, sort=times),
alt.Color('Avg_trans_size:Q',
title=None,
scale=alt.Scale(scheme='greens')),
tooltip=[
alt.Tooltip('Day_of_week', title='Day of the week'),
alt.Tooltip('Time_of_day', title="Time of the day"),
alt.Tooltip('Avg_trans_size:Q',
title='Average transaction size',
format='$,.0f')
]).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=store_id)).configure_axis(
labelFontSize=13,
titleFontSize=13).configure_title(
fontSize=14).properties(
width=180,
height=130,
title='Average transaction size'))
return transaction_size
def make_bar_plot(day_of_week, time_of_day, branch_index, func, plot_title,
y_title):
'''
Make a bar plot filtered by branch, day of week, and time of day
Parameters
----------
day_of_week: str
the day of week ranging from Monday to Sunday
time_of_day: str
the time of day (Morning, Afternoon or Evening)
func: str
the variable to be used as y axis
plot_title: str
the name to be used as title
branch_index: str
the character used to represent the supermarket branch
Returns
-------
Altair chart object
a bar plot
'''
bar_plot = (alt.Chart(df).mark_bar(color='cornflowerblue').encode(
alt.X('Product line:N', title=None),
alt.Y(func, type='quantitative', title=y_title),
tooltip=[
alt.Tooltip('Product line', title='Product line'),
alt.Tooltip(func, title=plot_title)
]).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=branch_index)).transform_filter(
alt.FieldEqualPredicate(
field='Day_of_week',
equal=day_of_week)).transform_filter(
alt.FieldEqualPredicate(
field='Time_of_day',
equal=time_of_day)).properties(
width=250, height=175, title=plot_title))
return bar_plot
def concat_gdp_indus_vis(year, geo):
real_gdp_ind_rank = alt.Chart(industry_gdp, title="GDP contribution by industry").mark_bar().encode(
y=alt.Y('sum(Industry GDP):Q', title='CA$ (MM)',
axis=alt.Axis(tickCount=3, titleFontSize=20, grid=False, format=('$,f'))),
x=alt.X('Industry:O', sort='-y', axis=alt.Axis(labelAngle=-90), title=None),
color=alt.Color('sum(Industry GDP)', title='GDP', scale=alt.Scale(scheme='blues'),
legend=alt.Legend(format=('$,f'))),
tooltip=[alt.Tooltip('Geography', title='Province/territory'), alt.Tooltip('Year'), alt.Tooltip('Industry'),
alt.Tooltip('sum(Industry GDP):Q', format=('$,.0f'), title='GDP')]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year)).transform_filter(
alt.FieldEqualPredicate(field='Geography', equal=geo))
real_gdp_ind_gr_rank = alt.Chart(industry_gdp_gr, title="GDP growth rate by industry").mark_bar().encode(
y=alt.Y('sum(Industry GDP):Q', title=None, axis=alt.Axis(tickCount=3, grid=False, format=('%'))),
x=alt.X('Industry:O', sort='-y', title=None, axis=alt.Axis(labelLimit=90, labelAngle=-90)),
color=alt.Color('sum(Industry GDP)', title='GDP growth rate', scale=alt.Scale(scheme='redblue'),
legend=alt.Legend(format=('%'))),
tooltip=[alt.Tooltip('Geography', title='Province/territory'), alt.Tooltip('Year'), alt.Tooltip('Industry'),
alt.Tooltip('sum(Industry GDP):Q', format=('.2%'), title='Growth rate')]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year)).transform_filter(
alt.FieldEqualPredicate(field='Geography', equal=geo))
w = 400
h = 300
real_gdp_ind_rank = real_gdp_ind_rank.properties(
width=w,
height=h
)
real_gdp_ind_gr_rank = real_gdp_ind_gr_rank.properties(
width=w,
height=h
)
vis = (real_gdp_ind_rank | real_gdp_ind_gr_rank).configure_view(strokeOpacity=0).configure_axis(domain=False,
ticks=False).configure_title(fontSize=30)
return vis.to_html()
def make_heat_map(branch_index, func, plot_title):
"""
Make a heat map by day of week and time of day
Parameters
----------
branch_index: str
the character used to represent the supermarket branch
func: str
the variable to be associated with alt.Color()
plot_title: str
the name to be used as title
Returns
-------
Altair chart object
a heat map
"""
days = [
'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday',
'Sunday'
]
times = ['Morning', 'Afternoon', 'Evening']
heat_map = (alt.Chart(df).mark_rect().encode(
alt.X('Day_of_week:N', title=None, sort=days),
alt.Y('Time_of_day:N', title=None, sort=times),
alt.Color(func,
type='quantitative',
title=None,
scale=alt.Scale(scheme='greens')),
tooltip=[
alt.Tooltip(func,
type='quantitative',
title=plot_title,
format=',.0f')
]).configure_axisX(labelAngle=45).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=branch_index)).configure_axis(
labelFontSize=13,
titleFontSize=13).configure_title(fontSize=14).properties(
width=180, height=130, title=plot_title))
return heat_map
def __create_world_timeseries_chart(self, case_type, ntype="New"):
"""create trend chart for global numbers
Args:
case_type (string): "confirmed", "recovered", "death"
ntype (string): "Total" or "New"
Returns:
[type]: [description]
"""
if case_type == "confirmed":
chart_title = "Global Confirmed Cases"
case_type = 1
elif case_type == "death":
chart_title = "Global Deaths"
case_type = 2
elif case_type == "recovered":
chart_title = "Global Recovered Cases"
case_type = 3
if ntype == "Total":
chart_title = chart_title + " Over Time"
else:
chart_title = "New " + chart_title + " Per Day"
data = self.data_reader.get_timeserie_data_by_country("all", case_type)
chart = (
alt.Chart(
data,
title=alt.TitleParams(text=chart_title),
height=200,
)
.mark_line()
.transform_filter(alt.FieldEqualPredicate(field="type", equal=ntype))
.encode(
x=alt.X("date:T", title="", axis=alt.Axis(format=("%b %Y"))),
y=alt.Y("count:Q", title=""),
)
.configure_axis(grid=False)
.configure_title(anchor="start")
.properties(width=735)
)
return chart.to_html()
def __create_timeserie_chart(self, country, case_type=1, ntype="Total"):
data = self.data_reader.get_timeserie_data_by_country(
country, case_type)
if case_type == 1:
chart_title = "Cases over time"
elif case_type == 2:
chart_title = "Deaths over time"
chart = (
alt.Chart(
data,
title=alt.TitleParams(text=chart_title, subtitle=country),
).mark_line().transform_filter(
alt.FieldEqualPredicate(field="type", equal=ntype)).encode(
x=alt.X("date:T", title=""),
y=alt.Y("count:Q", title="")).configure_axis(
grid=False).configure_title(anchor="start").properties(
width=350, height=200)
# .properties(width="container", height="container")
)
return chart.to_html()
def make_customer_traffic(store_id='A'):
# Create customer traffic heat map (unfiltered by store)
customer_traffic = (alt.Chart(df).mark_rect().encode(
alt.X('Day_of_week:N', title=None, sort=days),
alt.Y('Time_of_day:N', title=None, sort=times),
alt.Color('count(Invoice ID):Q',
title=None,
scale=alt.Scale(scheme='greens')),
tooltip=[
alt.Tooltip('Day_of_week', title='Day of the week'),
alt.Tooltip('Time_of_day', title="Time of the day"),
alt.Tooltip('count(Invoice ID):Q', title='No. of transactions')
]).transform_filter(
alt.FieldEqualPredicate(
field='Branch', equal=store_id)).configure_axis(
labelFontSize=13,
titleFontSize=13).configure_title(fontSize=14).properties(
width=180, height=130, title='Customer traffic'))
return customer_traffic
def get_bar_chart(ranks_st: pd.DataFrame, sorted_omic: list,
conditionals_1: str, conditionals_2: str, omic_column: str,
omic: str, omic1: str, omic2: str, x_size: float,
y_size: float, mlt, selector1, selector2):
if omic == omic1:
x = alt.X('%s:N' % omic1, sort=sorted_omic, axis=None)
y = alt.Y('mean(rank):Q', axis=alt.Axis(titleFontSize=8))
width = x_size
height = 50
else:
x = alt.X('mean(rank):Q', axis=alt.Axis(titleFontSize=8, orient='top'))
y = alt.Y('%s:N' % omic2, sort=sorted_omic, axis=None)
width = 50
height = y_size
if omic_column:
color = alt.condition(mlt, omic_column, alt.ColorValue("grey"))
else:
color = alt.condition(mlt, alt.ColorValue("steelblue"),
alt.ColorValue("grey"))
tooltips = [
omic, 'mean(rank)', 'stdev(rank)',
'min(%s)' % conditionals_1,
'min(%s)' % conditionals_2
]
if omic_column:
tooltips.append(omic_column)
bar_omic = alt.Chart(ranks_st).mark_bar(
).encode(x=x, y=y, color=color, tooltip=tooltips).add_selection(
mlt, selector1, selector2).transform_filter(
alt.FieldEqualPredicate(field='conditional', equal='conditionals')
).transform_filter(
alt.datum[conditionals_1] <= selector1.cutoff1).transform_filter(
alt.datum[conditionals_2] <= selector2.cutoff2).properties(
width=width, height=height)
return bar_omic
def concat_cpi_vis(year, geo):
all_cpi_evo = alt.Chart(eco, title="CPI all-items evolution").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='2002=100',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(All-items):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=(',.0f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All-items):Q',
format=('.0f'),
title='CPI')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
all_cpi_gr = alt.Chart(eco_gr, title="Growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('sum(All-items):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(All-items):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
gasoline_cpi_evo = alt.Chart(
eco, title="CPI gasoline evolution").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='2002=100',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Gasoline):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=(',.0f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Gasoline):Q', title='CPI')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
gasoline_cpi_gr = alt.Chart(eco_gr, title="Growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('sum(Gasoline):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(Gasoline):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
cpi_rank = alt.Chart(
eco, title="CPI all-items by province/territory").mark_bar().encode(
x=alt.X('average(All-items):Q',
title='2002=100',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
format=(',.0f'))),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition((alt.datum.Geography == geo) |
(alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All-items):Q', title='CPI')
]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year))
cpi_gr_rank = alt.Chart(
eco_gr, title="Growth rate by province/territory").mark_bar().encode(
x=alt.X('average(All-items):Q',
title=None,
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
format=('%'))),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition((alt.datum.Geography == geo) |
(alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All-items):Q',
format=('.2%'),
title='CPI')
]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year))
w = 300
h = 200
all_cpi_evo = all_cpi_evo.properties(width=w, height=h)
all_cpi_gr = all_cpi_gr.properties(width=w, height=h)
gasoline_cpi_evo = gasoline_cpi_evo.properties(width=w, height=h)
gasoline_cpi_gr = gasoline_cpi_gr.properties(width=w, height=h)
cpi_rank = cpi_rank.properties(width=w, height=h)
cpi_gr_rank = cpi_gr_rank.properties(width=w, height=h)
all_cpi = (all_cpi_evo | all_cpi_gr)
gasoline_cpi = (gasoline_cpi_evo | gasoline_cpi_gr)
rank_cpi = (cpi_rank | cpi_gr_rank)
cpi_plot = ((all_cpi & gasoline_cpi)
& rank_cpi).configure_view(strokeOpacity=0).configure_axis(
domain=False).configure_title(fontSize=30)
return cpi_plot.to_html()
def concat_ngdp_vis(year, geo):
nominal_gdp = alt.Chart(
eco, title="Total GDP").mark_bar().transform_aggregate(
groupby=['Geography', 'Year'], GDP='sum(Nominal GDP)').encode(
x=alt.X('sum(GDP):Q',
title='CA$ (MM)',
axis=alt.Axis(titleFontSize=20,
grid=False,
ticks=False,
labels=False)),
y=alt.Y('Geography:O',
sort='-x',
title=None,
axis=alt.Axis(labelFontSize=20,
ticks=False,
grid=False)),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography', equal=geo)).transform_filter(
alt.FieldEqualPredicate(
field='Year', equal=year)).properties(
height=200, width=400).mark_text(
dx=-175, color='darkblue',
size=40).encode(text=alt.Text(
'sum(GDP):Q', format=('$,')))
nominal_gdp_gr = alt.Chart(
eco_gr, title="Growth rate").mark_bar().transform_aggregate(
groupby=['Geography', 'Year'], GDP='sum(Nominal GDP)').encode(
x=alt.X('sum(GDP):Q',
title='Yearly %',
axis=alt.Axis(titleFontSize=20,
grid=False,
ticks=False,
labels=False)),
y=alt.Y('Geography:O',
sort='-x',
title=None,
axis=alt.Axis(grid=False, ticks=False, labels=False)),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography', equal=geo)).transform_filter(
alt.FieldEqualPredicate(
field='Year', equal=year)).properties(
height=200, width=400).mark_text(
dx=-175, color='darkblue',
size=40).encode(text=alt.Text(
'sum(GDP):Q', format=('.2%')))
nominal_gdp_evo = alt.Chart(eco, title="GDP evolution").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('sum(Nominal GDP):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('$,f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(Nominal GDP):Q', format=('$,'), title='GDP')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
nominal_gdp_rank = alt.Chart(
eco, title="Contribution by province/territory").mark_bar().encode(
x=alt.X('sum(Nominal GDP):Q',
title='CA$ (MM)',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
format=('$,f'))),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition((alt.datum.Geography == geo) |
(alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(Nominal GDP):Q', format=('$,'), title='GDP')
]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year))
nominal_gdp_gr_evo = alt.Chart(eco_gr, title="GDP growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('sum(Nominal GDP):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(Nominal GDP):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year]))
nominal_gdp_gr_rank = alt.Chart(
eco_gr, title="By province/territory").mark_bar().encode(
x=alt.X('sum(Nominal GDP):Q',
title=None,
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
format=('%'))),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition((alt.datum.Geography == geo) |
(alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('sum(Nominal GDP):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year))
w = 300
h = 200
nominal_gdp = nominal_gdp.properties(width=w, height=h)
nominal_gdp_gr = nominal_gdp_gr.properties(width=w, height=h)
nominal_gdp_evo = nominal_gdp_evo.properties(width=w, height=h)
nominal_gdp_rank = nominal_gdp_rank.properties(width=w, height=h)
nominal_gdp_gr_evo = nominal_gdp_gr_evo.properties(width=w, height=h)
nominal_gdp_gr_rank = nominal_gdp_gr_rank.properties(width=w, height=h)
ngdp_summary = (nominal_gdp | nominal_gdp_gr)
ngdp_total = (nominal_gdp_evo | nominal_gdp_rank)
ngdp_gr = (nominal_gdp_gr_evo | nominal_gdp_gr_rank)
ngdp_vis = ((ngdp_summary & ngdp_total)
& ngdp_gr).configure_view(strokeOpacity=0).configure_axis(
domain=False).configure_title(fontSize=30)
return ngdp_vis.to_html()
dailyCount = dailyCount.reset_index()
currentMonth = currentMonth.reset_index()
#Create monthly cumulative line chart
monthlyLine = altair.Chart(currentMonth).mark_line(
stroke='#f304d3').encode(
altair.X('date(Date):T',
axis=altair.Axis(title='Day of the Month')),
altair.Y('MonthlyCumSum',
axis=altair.Axis(title='Total Bikes'),
scale=altair.Scale(domain=(0, 100000))),
altair.Color('Date:O',
timeUnit='year',
legend=altair.Legend(title='Year'))).transform_filter(
altair.FieldEqualPredicate(
timeUnit='year',
field='Date',
equal=datetime.date.today().year)).properties(
width=200, height=200)
monthlyLineAvg = altair.Chart(currentMonth).mark_line(
color='grey', strokeDash=[8, 8]).encode(
altair.X('date(Date):T', axis=altair.Axis(title='')),
altair.Y('mean(MonthlyCumSum)', axis=altair.Axis(title='')),
).properties(width=200, height=200)
monthlyLineBand = altair.Chart(currentMonth).mark_errorband(
extent='stdev', color='grey').encode(
altair.X('date(Date):T', axis=altair.Axis(title='')),
altair.Y('MonthlyCumSum', axis=altair.Axis(title='')),
).properties(width=200, height=200)
def plot_lang_chart(job_title_var):
lang_chart = alt.Chart(data=kaggle_langs).mark_bar().encode(
x='prog_lang', y='count()').transform_filter(
alt.FieldEqualPredicate(field='Q5', equal=job_title_var))
return lang_chart.to_html()
def concat_employment_vis(year, geo):
er_evo = alt.Chart(eco, title="Unemployment rate evolution").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Unemployment rate):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('%')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Unemployment rate):Q',
format=('.2%'),
title='Unemployment rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography', equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2000, year])).properties(height=430)
er_rank = alt.Chart(
eco,
title="Unemployment rate by province/territory").mark_bar().encode(
x=alt.X('average(Unemployment rate):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('%')),
title=None),
y=alt.Y('Geography:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.condition((alt.datum.Geography == geo) |
(alt.datum.Geography == 'Canada'),
alt.value('darkblue'), alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Unemployment rate):Q',
format=('.2%'),
title='Unemployment rate')
]).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=year))
er_ind_rank = alt.Chart(
labour, title="Unemployment rate by industry").mark_bar().encode(
x=alt.X('Unemployment rate:Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
y=alt.Y('Industry:O',
sort='-x',
axis=alt.Axis(labelFontSize=18),
title=None),
color=alt.value('lightblue'),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('Industry'),
alt.Tooltip('Unemployment rate:Q',
format=('.2%'),
title='Unemployment rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Year', equal=year)).transform_filter(
alt.FieldEqualPredicate(field='Geography', equal=geo))
w = 300
h = 200
# nominal_gdp = nominal_gdp.properties(
# width=w,
# height=h
# )
#
# nominal_gdp_gr = nominal_gdp_gr.properties(
# width=w,
# height=h
# )
#
# nominal_gdp_evo = nominal_gdp_evo.properties(
# width=w,
# height=h
# )
er_ind_rank = er_ind_rank.properties(width=w, height=h)
er_rank = er_rank.properties(width=w, height=h)
er_evo = er_evo.properties(width=w, height=h)
employment_plot = ((er_evo | er_rank) & er_ind_rank).configure_view(
strokeOpacity=0).configure_axis(domain=False).configure_title(
fontSize=30)
return employment_plot.to_html()
def app():
####### Datasets
control_dataset = 'https://raw.githubusercontent.com/JulioCandela1993/VisualAnalytics/master/data/control_policy.csv'
deaths_dataset = 'https://raw.githubusercontent.com/JulioCandela1993/VisualAnalytics/master/data/deaths.csv'
####### Dataframes
control_df = pd.read_csv(control_dataset)
####### Dashboard
st.title("Tobacco Control")
st.markdown('''
The following analysis is based on the evaluation made by World Health Organization (WHO)
to country policies against Tobacco. A score from 1 to 5 is assigned depending on the intensity
of a country to deal with Tobacco issues being 1 the worst and 5 the best
''')
####### Control Measures given by WHO
control_metrics = ["Monitor",
"Protect from tobacco smoke",
"Offer help to quit tobacco use",
"Warn about the dangers of tobacco",
"Enforce bans on tobacco advertising",
"Raise taxes on tobacco",
#"Anti-tobacco mass media campaigns"
]
# Main Selector of Control Measures
cols = st.selectbox('Select control measure: ', control_metrics)
if cols in control_metrics:
metric_to_show_in_covid_Layer = cols +":Q"
metric_name = cols
years = ['2008', '2010', '2012', '2014', '2016', '2018']
columns_year = [metric_name+" "+str(year) for year in years]
columns = ["d" +str(year) for year in years]
container_map = st.beta_container()
####### Map Visualization
with container_map:
st.header("How are countries controlling Tobacco consumption?")
#st.header('"'A global view of the implementation of the policy """ around the world'"')
st.markdown('''
In the folling map, we can identify the intensity of a specific control policy for each country.
We can also see the evolution of these policies from 2008 to 2018
''')
# Year Selector
select_year_list = st.selectbox('Select year: ', years)#st.slider('Select year: ', 2008, 2018, 2008, step = 2)
select_year = int(select_year_list)
# Map Topology
url_topojson = 'https://raw.githubusercontent.com/JulioCandela1993/VisualAnalytics/master/world-countries.json'
data_topojson_remote = alt.topo_feature(url=url_topojson, feature='countries1')
### Map Chart
map_geojson = alt.Chart(data_topojson_remote).mark_geoshape(
stroke="black",
strokeWidth=1,
#fill='lightgray'
).encode(
color=alt.Color(metric_to_show_in_covid_Layer),
).transform_lookup(
lookup="properties.name",
from_=alt.LookupData(control_dataset, "Country", [metric_name,"Year"])
).properties(
width=700,
height=500
)
choro = alt.Chart(data_topojson_remote, title = 'Implementation of the policy "' +metric_name+'" around the world').mark_geoshape(
stroke='black'
).encode(
color=alt.Color(metric_to_show_in_covid_Layer,
scale=alt.Scale(range=['#ffe8dd','#ef4f4f']),
legend=None),
tooltip=[
alt.Tooltip("properties.name:O", title="Country"),
alt.Tooltip(metric_to_show_in_covid_Layer, title=metric_name),
alt.Tooltip("year:Q", title="Year"),
],
).transform_calculate(
d2008 = "1",
d2010 = "1",
d2012 = "1",
d2014 = "1",
d2016 = "1",
d2018 = "1"
).transform_fold(
columns, as_=['year', 'metric']
).transform_calculate(
yearQ = 'replace(datum.year,"d","")'
).transform_calculate(
key_val = 'datum.properties.name + datum.yearQ'
).transform_lookup(
lookup="key_val",
from_=alt.LookupData(control_dataset, "ID", [metric_name,"Year"])
).transform_calculate(
year='parseInt(datum.Year)',
).transform_filter(
alt.FieldEqualPredicate(field='year', equal=select_year)
)
st.altair_chart(map_geojson + choro)
## Qualification array
qualifications = pd.DataFrame.from_dict({
"keys": [1,2,3,4,5],
"category":["1.Very Bad", "2.Bad", "3.Medium", "4.Good", "5.Perfect"]
})
## Legend Chart
##### Data Transformations
legend_info = alt.Chart(control_dataset).transform_joinaggregate(
num_countries='count(*)',
).transform_filter(
alt.FieldEqualPredicate(field='Year', equal=select_year)
).transform_lookup(
lookup=metric_name,
from_=alt.LookupData(qualifications, "keys", ["category"])
).transform_aggregate(
count='count()',
groupby=[metric_name,"category"]
).transform_joinaggregate(
total='sum(count)'
).transform_calculate(
pct='datum.count / datum.total'
)
legend_bar = legend_info.mark_bar().encode(
x=alt.X('pct:Q', stack="normalize", sort=alt.SortField(metric_to_show_in_covid_Layer), title = None, axis = None),
color=alt.Color(metric_to_show_in_covid_Layer,
scale=alt.Scale(range=['#ffe8dd','#ef4f4f'])
,legend = None),
tooltip=[
alt.Tooltip(metric_to_show_in_covid_Layer, title=metric_name)
],
)
legend_value = legend_info.mark_text(dx = -11, align='center', baseline='middle', color='black', fontWeight = "bold").encode(
x=alt.X('pct:Q', sort=alt.SortField(metric_to_show_in_covid_Layer), stack='normalize', axis = None),
#detail = metric_to_show_in_covid_Layer,
color=alt.Color(metric_name +":O",
scale=alt.Scale(range=['#000000','#000000'])
,legend = None),
text=alt.Text('pct:Q',format='.0%')
)
legend_category = legend_info.mark_text(dx = 10, dy = 10, align='left', baseline='middle', color='black', angle = 90, fontWeight = "bold").encode(
x=alt.X('pct:Q', sort=alt.SortField(metric_to_show_in_covid_Layer), stack='normalize', axis = None),
#detail = metric_to_show_in_covid_Layer,
color=alt.Color(metric_name +":O",
scale=alt.Scale(range=['#000000','#000000'])
,legend = None),
#text=alt.Text(metric_to_show_in_covid_Layer)
text=alt.Text("category:N")
)
legend_chart = (legend_bar + legend_value + legend_category).properties(
width=700,
height=100,
title = metric_name
).configure_title(align = "left"
).configure_view(
strokeWidth=0
)
st.altair_chart(legend_chart)
##### Evolution of policy per selected countries
container_policycountry = st.beta_container()
with container_policycountry:
st.header("Evolution of the policy per country")
st.markdown('''
In addition, we can evaluate and compare the evolution of the selected policy among different countries of our interest:
''')
## Selector of countries
countries = st.multiselect('Select countries to plot',
control_df.groupby('Country').count().reset_index()['Country'].tolist(),
default=['China', 'India', 'France'])
st.markdown('''
''')
xscale_barchart = alt.Scale(domain=(0, 5))
## Comparisson Chart of Policies per country
barchart_country = alt.Chart(control_dataset,width=90,height=20,
title = 'Evolution of Policy "' + metric_name + '" per selected countries'
).mark_bar( size = 20
).encode(
alt.X('value:Q', scale = xscale_barchart, title = "", axis = alt.Axis(grid = False)),
alt.Row('Country:N', title = "", spacing = 5, header = alt.Header(labelAngle = 0, labelAlign = "left",labelLimit = 100)),
alt.Column("Year:O", title = "", spacing = 10),
color=alt.Color("value:Q",
scale=alt.Scale(domain=[1,4], range=['#ffe8dd','#ef4f4f']),
legend=None),
tooltip=[
alt.Tooltip("Country:N", title="Country"),
alt.Tooltip(metric_to_show_in_covid_Layer, title=metric_name),
alt.Tooltip("Year:O", title="Year"),
]
).transform_fold(
[metric_name],
as_ = ['Measurement_type', 'value']
).transform_filter(
alt.FieldOneOfPredicate(field="Country", oneOf=countries)
).transform_filter(
{'field': 'Year', 'range': [2008,2018]}
).configure_title(align = "center", anchor = "middle", dy = -10)
st.altair_chart(barchart_country)
st.altair_chart(legend_chart)
####### Scatterplot control policy vs deaths
def render_latex(formula, fontsize=10, dpi=100):
"""Renders LaTeX formula into Streamlit."""
fig = plt.figure()
text = fig.text(0, 0, '$%s$' % formula, fontsize=fontsize)
fig.savefig(BytesIO(), dpi=dpi) # triggers rendering
bbox = text.get_window_extent()
width, height = bbox.size / float(dpi) + 0.05
fig.set_size_inches((width, height))
dy = (bbox.ymin / float(dpi)) / height
text.set_position((0, -dy))
buffer = BytesIO()
fig.savefig(buffer, dpi=dpi, format='jpg')
plt.close(fig)
st.image(buffer)
container_correlation = st.beta_container()
with container_correlation:
st.header("Are the policies having an impact in the deaths by Smoking?")
st.markdown('''
Countries have implemented different control policies against Tobacco which have been measured by WHO from 2008 until 2018.
During this period, some countries have strengthen their policies; however, we don't know the real impact of them.
As a consequence, the following visualization measures the correlation of the change in control policies with
respect to the change in deaths by Smoking. The definitions of % of change are the following:
''')
render_latex(r'\%\ change\ in\ '+metric_name+r'\ =\ \frac{'+metric_name+r'\ in\ 2016}{'+metric_name+r'\ in\ 2008}')
render_latex(r'\%\ change\ in\ Deaths\ by\ Smoking\ =\ \frac{Deaths\ by\ Smoking\ in\ 2016}{Deaths\ by\ Smoking\ in\ 2008}')
st.markdown('''
The user can also select brush the histograms in order to filter the points and
evaluate the slope of the regression in more detail (with groups that increased more or less in control policies, for example)
''')
brush = alt.selection_interval()
## Data Transformations
base_scatter = alt.Chart(control_dataset).transform_lookup(
lookup="ID",
from_=alt.LookupData(deaths_dataset, "ID", ["deaths","Year"])
).transform_calculate(
deaths='parseFloat(datum.deaths)',
year='parseInt(datum.Year)',
metric = alt.datum[metric_name]
).transform_calculate(
deaths_2016='datum.year==2016?datum.deaths:0',
deaths_2008='datum.year==2008?datum.deaths:0',
metric_2016='datum.year==2016?datum.metric:0',
metric_2008='datum.year==2008?datum.metric:0',
year='parseInt(datum.Year)',
sizepoint = '2'
).transform_aggregate(
deaths_2016='sum(deaths_2016)',
metric_2016='sum(metric_2016)',
deaths_2008='sum(deaths_2008)',
metric_2008='sum(metric_2008)',
groupby=["Country"]
).transform_calculate(
incr_ratio_deaths='((datum.deaths_2016/datum.deaths_2008)-1)*100',
incr_ratio_metric='((datum.metric_2016/datum.metric_2008)-1)*100',
)
xscale = alt.Scale(domain=(-100, 300))
yscale = alt.Scale(domain=(-100, 200))
## Scatterplot of changes in Policy and changes in deaths
points_scatter = base_scatter.mark_point(size=50, stroke="#ef4f4f").encode(
alt.X('incr_ratio_metric:Q', scale = xscale, title = '% change of efforts in ' + metric_name + ' from 2008 to 2016'),
alt.Y('incr_ratio_deaths:Q', scale=yscale, title = '% change in deaths from 2008 to 2016'),
#color=alt.condition(brush, alt.value('blue'), alt.value('lightgray')),
#opacity=alt.condition(brush, alt.value(0.75), alt.value(0.05)),
tooltip=[
alt.Tooltip("deaths_2016:Q", title="Deaths in 2016"),
alt.Tooltip("deaths_2008:Q", title="Deaths in 2008"),
alt.Tooltip("Country:N", title="Country"),
],
).properties(
width=450,
height=450
).transform_filter(brush)
regression_scatter = points_scatter.transform_regression(
on='incr_ratio_metric', regression='incr_ratio_deaths', method = 'linear'
).mark_line(color='#19456b')
scatter_final = (points_scatter + regression_scatter)
# Histogram of changes in policy
top_hist = base_scatter.mark_area(line=True, opacity=0.3).encode(
alt.X("incr_ratio_metric:Q",
bin=alt.Bin(maxbins=30, extent=xscale.domain),
title=''
),
alt.Y('count()', title=''),
color=alt.value("#ef4f4f")
).add_selection(
brush
).properties(width=450 , height=100, title = "Distribution of % change in policy")
# Histogram of changes in deaths
right_hist = base_scatter.mark_area(line=True, opacity=0.3).encode(
alt.Y('incr_ratio_deaths:Q',
bin=alt.Bin(maxbins=20, extent=yscale.domain),
title='',
),
alt.X('count()', title=''),
color=alt.value("#ef4f4f")
).add_selection(
brush
).properties(width=110, height=450,
title=alt.TitleParams(text="Distribution of % change in deaths", align="center", angle = 90, orient = 'right')
)
st.altair_chart((top_hist & (scatter_final |right_hist )
).properties(title = "Correlation between % change in policy and % change in deaths"
).configure_title(align = "center", anchor = "middle", dy = -10))
def make_individual_metric_chart(metric, name):
"""
Makes a chart for a single metric and a single provider.
Assumes: dataframe 'df' that has all the data from CSVs
Assumes: dataframes 'names' and 'metrics' for lookups
"""
providerdf = df[(df["Metric"] == metric) & (df["Type"] == "Individual") &
(df["Name"] == name)]
# Lookup clinic from the provider name in the names dataframe.
# Make a comparison dataframe.
clinic_name = names[names.Name == name].iloc[0].Clinic
clinicdf = df[(df["Metric"] == metric) & (df["Name"] == clinic_name)]
# Lookup the metric target -- not all metrics have a target.
metric_target = metrics[metrics.Metric == metric].iloc[0].Target
# If there's a target value, we'll make a rule on graph.
if metric_target:
metricdf = pd.DataFrame([{
"TargetValue": metric_target,
"Title": "Target"
}])
# Make a Current dataframe to use for Strip Chart.
current_date = max(providerdf["Date"])
current_metric = df[(df["Metric"] == metric)
& (df["Type"] == "Individual")
& (df["Date"] == current_date)]
# Altair Graphs to combine.
provider_progress_line = (alt.Chart(providerdf).mark_line(
strokeWidth=4).encode(
alt.X("Date:T", title=""),
alt.Y(
"Percentage:Q",
axis=alt.Axis(format="%", title=""),
scale=alt.Scale(domain=(0, 1)),
),
color=alt.Color("Name:N", legend=None),
).properties(width=200, height=200))
# 1f77b4 -- blue, #ff7f0e -- orange. Currently hardcoded but eventually
# will look up a clinic color. Also will be used in the HTML generation.
clinic_progress_line = (alt.Chart(clinicdf).mark_line(
strokeWidth=2).encode(
alt.X("Date:T", title=""),
alt.Y(
"Percentage:Q",
axis=alt.Axis(format="%", title=""),
scale=alt.Scale(domain=(0, 1)),
),
color=alt.ColorValue("#ff7f0e"),
))
if metric_target:
metric_target_rule = (alt.Chart(metricdf).mark_rule(
strokeWidth=1, strokeDash=[4, 2]).encode(y="TargetValue:Q",
color=alt.value("green"),
opacity=alt.value("0.5")))
fcn_current_strip_chart = (alt.Chart(current_metric).mark_tick(
color="#eee").encode(
alt.Y(
"Percentage:Q",
axis=alt.Axis(format="%", title="", labels=False),
scale=alt.Scale(domain=(0, 1)),
)).properties(height=200))
provider_highlight_strip = (alt.Chart(current_metric).mark_tick().encode(
alt.Y("Percentage:Q"), opacity=alt.value("1.0")).transform_filter(
alt.FieldEqualPredicate(field="Name", equal=name)))
provider_percent = (provider_highlight_strip.mark_text(
align="left", baseline="middle", dx=15, size=20).encode(
text=alt.Text("Percentage:Q", format=".2%")).transform_filter(
alt.FieldEqualPredicate(field="Name", equal=name)))
if metric_target:
chart = provider_progress_line + clinic_progress_line + metric_target_rule | (
fcn_current_strip_chart + provider_highlight_strip +
provider_percent)
return chart
else:
chart = provider_progress_line + clinic_progress_line | (
fcn_current_strip_chart + provider_highlight_strip +
provider_percent)
return chart
def concat_earnings_vis(year, geo):
all_ear_evo = alt.Chart(eco, title="All industries").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='CA$',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(All industries):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('$,f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All industries):Q',
format=('$,'),
title='Earnings')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
all_ear_gr_evo = alt.Chart(eco_gr, title="Growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(All industries):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(All industries):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
goods_ear_evo = alt.Chart(eco, title="Goods-producing sector").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='CA$',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Goods-producing sector):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('$,f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Goods-producing sector):Q',
format=('$,'),
title='Earnings')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
goods_ear_gr_evo = alt.Chart(eco_gr, title="Growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Goods-producing sector):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Goods-producing sector):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
serv_ear_evo = alt.Chart(eco, title="Service-producing").mark_area(
point=alt.OverlayMarkDef(filled=False, fill='darkblue')).encode(
x=alt.X('Year',
title='CA$',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Service-producing sector):Q',
axis=alt.Axis(tickCount=3,
titleFontSize=20,
grid=False,
ticks=False,
format=('$,f')),
title=None),
tooltip=[
alt.Tooltip('Geography', title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Service-producing sector):Q',
format=('$,'),
title='Earnings')
]).transform_filter(
alt.FieldEqualPredicate(field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
serv_ear_gr_evo = alt.Chart(eco_gr, title="Growth rates").mark_bar(
point=alt.OverlayMarkDef(filled=False, fill='darkblue'),
size=16).encode(x=alt.X('Year',
title='Year',
axis=alt.Axis(tickCount=5,
titleFontSize=20,
grid=False,
ticks=False,
format='Y')),
y=alt.Y('average(Service-producing sector):Q',
axis=alt.Axis(tickCount=3,
grid=False,
ticks=False,
format=('%')),
title=None),
color=alt.condition((alt.datum.Year == year),
alt.value('darkblue'),
alt.value('lightblue')),
tooltip=[
alt.Tooltip('Geography',
title='Province/territory'),
alt.Tooltip('Year'),
alt.Tooltip('average(Service-producing sector):Q',
format=('.2%'),
title='Growth rate')
]).transform_filter(
alt.FieldEqualPredicate(
field='Geography',
equal=geo)).transform_filter(
alt.FieldRangePredicate(
'Year', [2002, year]))
w = 300
h = 200
serv_ear_gr_evo = serv_ear_gr_evo.properties(width=w, height=h)
serv_ear_evo = serv_ear_evo.properties(width=w, height=h)
goods_ear_gr_evo = goods_ear_gr_evo.properties(width=w, height=h)
goods_ear_evo = goods_ear_evo.properties(width=w, height=h)
all_ear_gr_evo = all_ear_gr_evo.properties(width=w, height=h)
all_ear_evo = all_ear_evo.properties(width=w, height=h)
all_ear = (all_ear_evo | all_ear_gr_evo)
goods_ear = (goods_ear_evo | goods_ear_gr_evo)
serv_ear = (serv_ear_evo | serv_ear_gr_evo)
earnings_plot = ((all_ear & serv_ear) & goods_ear).configure_view(
strokeOpacity=0).configure_axis(domain=False).configure_title(
fontSize=30)
return earnings_plot.to_html()
alt.Tooltip(metric_to_show_in_covid_Layer, title=metric_name),
alt.Tooltip("year:Q", title="Year"),
],
).transform_calculate(
d2008="1", d2010="1", d2012="1", d2014="1", d2016="1",
d2018="1").transform_fold(columns, as_=[
'year', 'metric'
]).transform_calculate(
yearQ='replace(datum.year,"d","")').transform_calculate(
key_val='datum.properties.name + datum.yearQ').transform_lookup(
lookup="key_val",
from_=alt.LookupData(
control_dataset, "ID",
[metric_name, "Year"])).transform_calculate(
year='parseInt(datum.Year)', ).transform_filter(
alt.FieldEqualPredicate(field='year',
equal=select_year))
with container_map:
st.altair_chart(map_geojson + choro)
####### Scatterplot control policy vs deaths
st.header("Are control policies effective?")
'''
Countries have implemented different control policies against Tobacco which have been measured by WHO from 2008 until 2018.
During this period, some countries have strengthen their policies; however, we don't know the real impact of them in the quality
of citizen's life.
As a consequence, we have developed the next visualization to measure the efficiency of each change in control policies with
respect to the change in deaths because of Smoking. We consider "change" as the percentage of variation
between 2008 and 2016. The user can also select brush the histograms in order to filter the points and
def idca_statistics(
var,
bw_method="scott",
choice=None,
avail=None,
wgt=None,
scale_ch=True,
bins=10,
resolution=100,
):
stats, plot_data = idca_statistics_data(
var,
bw_method=bw_method,
choice=choice,
avail=avail,
wgt=wgt,
scale_ch=scale_ch,
bins=bins,
resolution=resolution,
)
name = var.name or "Variable"
selection = alt.selection_single(fields=["Alternative"], bind="legend", empty="all")
selection2 = alt.selection_single(
fields=["Alternative"], bind="legend", empty="none"
)
ax = alt.Chart(plot_data)
alt_names = list(str(i.data) for i in var["alt_names"])
# A dropdown filter
# options = [None] + list(str(i.data) for i in var['alt_names'])
# options_dropdown = alt.binding_select(options=options)
# options_select = alt.selection_single(fields=['Alternative'], bind=options_dropdown, name="Alternative", empty="all")
frequency = (
ax.mark_line(interpolate="step",)
.transform_filter(
{"not": alt.FieldEqualPredicate(field="Alternative", equal=_GENERIC)}
)
.encode(
x=name,
y="Frequency",
color=alt.Color(
"Alternative",
sort=alt_names,
legend=alt.Legend(title="Alternative", orient="left"),
),
# strokeDash="Alternative",
# tooltip="Alternative",
opacity=alt.condition(selection, alt.value(1), alt.value(0.0)),
)
.add_selection(selection)
)
density = (
ax.mark_line()
.encode(
x=name,
y=alt.Y("Density", title="Density"),
color=alt.Color("Alternative", legend=None, sort=alt_names),
# strokeDash=alt.Color("Alternative", legend=None),
# tooltip="Alternative",
opacity=alt.condition(selection2, alt.value(1), alt.value(0.0)),
)
.add_selection(selection2)
.transform_filter(selection2)
)
generic_density = (
ax.mark_line()
.encode(
x=name, y=alt.Y("Density", title="Density"), color=alt.ColorValue("black"),
)
.transform_filter(
{
"and": [
alt.FieldEqualPredicate(field="Alternative", equal=_GENERIC),
selection,
]
}
)
)
density = density + generic_density
annotation = (
ax.mark_text(
align="right",
baseline="top",
# fontSize=20,
# dx=7
)
.encode(
text="Alternative",
x=alt.X(field=name, aggregate="max", type="quantitative", title=name),
y=alt.Y(field="Density", aggregate="max", type="quantitative"),
)
.transform_filter(
{
"and": [
alt.FieldEqualPredicate(field="Alternative", equal=_GENERIC),
selection,
]
}
)
)
density = density + annotation
if choice is not None:
f_areas = (
ax.mark_area(interpolate="step",)
.encode(
x=name,
y=alt.Y("FrequencyChosen", title="Frequency"),
color=alt.Color("Alternative", legend=None, sort=alt_names),
# strokeDash="Alternative",
# tooltip="Alternative",
opacity=alt.condition(selection2, alt.value(0.5), alt.value(0.0)),
)
.transform_filter(selection2)
)
frequency = frequency + f_areas
d_areas = (
ax.mark_area()
.encode(
x=name,
y=alt.Y("DensityChosen", title="Density"),
color=alt.Color("Alternative", legend=None, sort=alt_names),
# strokeDash="Alternative",
# tooltip="Alternative",
opacity=alt.condition(
selection2, alt.value(1 if scale_ch else 0.5), alt.value(0.0)
),
)
.transform_filter(selection2)
)
density = density + d_areas
generic_d_area = (
ax.mark_area()
.encode(
x=name,
y=alt.Y("DensityChosen", title="Density"),
opacity=alt.value(0.5),
color=alt.ColorValue("black"),
)
.transform_filter(
{
"and": [
alt.FieldEqualPredicate(field="Alternative", equal=_GENERIC),
selection,
]
}
)
)
density = density + generic_d_area
chart = frequency.properties(height=160, width=400) & density.properties(
height=90, width=400
)
table_data = stats.to_dataframe().reset_index().reset_index()
table_data["mean"] = table_data["mean"].apply(lambda x: f"{x:.4g}")
table_data["std"] = table_data["std"].apply(lambda x: f"{x:.4g}")
tab = alt.Chart(table_data)
def make_col(colname, title):
return (
tab.mark_text()
.encode(y=alt.Y("index:O", axis=None), text=colname, size=alt.value(10),)
.properties(title=alt.TitleParams(text=title, align="center", fontSize=10),)
)
col1 = make_col("alt_names", "Alternative")
col2 = make_col("mean", "Mean")
col3 = make_col("std", "Std Dev")
return (chart & (col1 | col2 | col3)).configure_view(strokeWidth=0), stats
def plot_psychometric(subject_protocols):
"""
Plot psychometric curves for selected subjects, steps, and variables
Typically called by :meth:`.Terminal.plot_psychometric`.
Args:
subject_protocols (list): A list of tuples, each with
* subject_id (str)
* step_name (str)
* variable (str)
Returns:
:class:`altair.Chart`
"""
for subject, step, var, n_trials in subject_protocols:
# load subject dataframe and subset
asub = Subject(subject)
sub_df = asub.get_trial_data(step)
if n_trials > 0:
sub_df = sub_df[-n_trials:]
# pdb.set_trace()
sub_df = coerce_discrete(sub_df, 'response')
logit = calc_psychometric(sub_df, var)
# generate points to plot regression fit
logit_x = np.linspace(sub_df[var].min(), sub_df[var].max(),
100).reshape(-1, 1)
logit_y = logit.predict_proba(logit_x)
# pdb.set_trace()
this_logit_df = pd.DataFrame({'x': logit_x[:, 0], 'y': logit_y[:, 1]})
this_logit_df['subject'] = subject
this_logit_df['type'] = 'log_regression'
try:
logit_df = pd.concat([logit_df, this_logit_df])
except NameError:
logit_df = this_logit_df
# and also mean accuracy by var
sub_df_sum = sub_df.groupby(var).mean().reset_index()[[
var, 'response'
]]
sub_df_sum['subject'] = subject
sub_df_sum['type'] = 'responses'
sub_df_sum.rename(columns={var: 'x', 'response': 'y'}, inplace=True)
try:
sum_df = pd.concat([sum_df, sub_df_sum])
except NameError:
sum_df = sub_df_sum
# combine dataframes
combo_df = pd.concat([sum_df, logit_df])
acc_points = alt.Chart().encode(
alt.X('x:Q', scale=alt.Scale(type='sqrt'), title=var),
y=alt.Y('y:Q', title="mean response")).transform_filter(
alt.FieldEqualPredicate('responses', 'type')).mark_point()
log_curves = alt.Chart().encode(
alt.X('x:Q', scale=alt.Scale(type='sqrt'), title=var),
y=alt.Y('y:Q', title="mean response")).transform_filter(
alt.FieldEqualPredicate('log_regression', 'type')).mark_line()
combo = alt.layer(acc_points + log_curves,
data=combo_df).facet(row='subject:N')
#combo.sav
return combo
