def make_interactive_chart():
'''
'''
pts = alt.selection(type="single", encodings=['x'])
rect = alt.Chart(data.movies.url).mark_rect().encode(
alt.X('IMDB_Rating:Q', bin=True),
alt.Y('Rotten_Tomatoes_Rating:Q', bin=True),
alt.Color('count()',
scale=alt.Scale(scheme='greenblue'),
legend=alt.Legend(title='Total Records')))
circ = rect.mark_point().encode(
alt.ColorValue('grey'),
alt.Size('count()', legend=alt.Legend(
title='Records in Selection'))).transform_filter(pts)
bar = alt.Chart(data.movies.url).mark_bar().encode(
x='Major_Genre:N',
y='count()',
color=alt.condition(pts, alt.ColorValue("steelblue"),
alt.ColorValue("grey"))).properties(selection=pts,
width=550,
height=200)
return alt.vconcat(rect + circ, bar).resolve_legend(color="independent",
size="independent")
def make_amount_plot(infile):
purchases = infra.pd.read_parquet(infile)
purchases = purchases.assign(count=1)
purchases = purchases[["amount_bytes", "count"
]].groupby(["amount_bytes"]).sum().reset_index()
purchases["amount_mb"] = purchases["amount_bytes"] / 1000**2
alt.Chart(purchases).mark_point().encode(
x=alt.X(
"amount_mb",
title="Session Purchase Amount (MB) (Log Scale)",
scale=alt.Scale(type="log", domain=(10, 2000)),
),
y=alt.Y(
"count",
title="Occurrences (Count) (Log Scale)",
scale=alt.Scale(type="log", ),
),
color=alt.condition(
'datum.count>1000',
alt.ColorValue('red'),
alt.ColorValue('steelblue'),
),
shape=alt.condition(
'datum.count>1000',
alt.ShapeValue('diamond'),
alt.ShapeValue('triangle'),
),
).properties(
width=500,
height=300,
).save("renders/purchase_timing_per_user_clumped_amounts.png",
scale_factor=2.0)
print(purchases)
def pdp_plot(df,
rows,
columns,
values,
variables=None,
vars_filter=None,
clusters=False,
cluster_centers=5,
columns_type='N',
x_title=None,
y_title=None,
width=700,
height=300):
'''
Plots a pdp plot for one variable.
Parameters
----------
df : pandas.DataFrame
Expects the l
Returns
-------
altair.Chart
'''
df = df.copy()
if vars_filter and variables:
df = df[df[variables] == vars_filter].drop(variables, axis=1)
base = alt.Chart(df).properties(width=width, height=height)
if clusters:
df_clusters = utils.pdp_clusters(cluster_centers, df, rows, columns,
values)
background = alt.Chart(df_clusters).mark_line(strokeWidth=2).encode(
alt.X(f'{columns}:{columns_type}', title=x_title),
alt.Y(values, title=y_title), alt.Opacity(rows, legend=None),
alt.ColorValue('#468499')).properties(width=width, height=height)
else:
background = base.mark_line(strokeWidth=1).encode(
alt.X(f'{columns}:{columns_type}', title=x_title),
alt.Y(values, title=y_title), alt.Opacity(rows, legend=None),
alt.ColorValue('#bbbbbb'))
df_avg = df.groupby(columns)[values].mean().reset_index()
avg_base = alt.Chart(df_avg).encode(
alt.X(f'{columns}:{columns_type}', title=x_title),
alt.Y(values, title=y_title),
)
avg = avg_base.mark_line(strokeWidth=5, color='gold')
avg += avg_base.mark_line(strokeWidth=2)
avg += avg_base.mark_point(filled=True, size=55)
return background + avg
def skyview_cmd(subsample, out_file, data_type='kepler'):
brush = alt.selection(
type='interval',
resolve='global',
on="[mousedown[event.shiftKey], window:mouseup] > \
window:mousemove!",
zoom='False',
translate="[mousedown[event.shiftKey], window:mouseup] > \
window:mousemove!")
pan = alt.selection(
type='interval',
bind='scales',
on="[mousedown[!event.shiftKey], window:mouseup] > \
window:mousemove!",
translate="[mousedown[!event.shiftKey], window:mouseup] > \
window:mousemove!")
if data_type == 'kepler':
scale = alt.Scale(domain=['none', 'cand', 'conf'],
range=['#4a69bd', '#e55039', '#f6b93b'])
color = alt.Color('planet?:N', scale=scale)
xscale = alt.Scale(domain=[270, 310])
yscale = alt.Scale(domain=[35, 55])
elif data_type == 'k2':
#scale = alt.Scale(domain=['none', 'cand'],
# range=['#4a69bd', '#e55039'])
#color = alt.Color('k2c_disp:N', scale=scale)
color = 'k2c_disp'
xscale = alt.Scale(domain=[0, 360])
yscale = alt.Scale(domain=[-90, 90])
else:
print("ERROR: data_type not recognized")
return
chart1 = alt.Chart(subsample).mark_point().encode(
alt.X('ra_gaia', scale=xscale, axis=alt.Axis(title='Gaia RA (deg)')),
alt.Y('dec_gaia', scale=yscale, axis=alt.Axis(title='Gaia Dec (deg)')),
color=alt.condition(brush, color, alt.ColorValue('gray'))).properties(
selection=brush + pan,
projection={'type': 'gnomonic'},
width=450,
height=500)
chart2 = alt.Chart(subsample).mark_point().encode(
alt.X('gaiamag_minus_kepmag', axis=alt.Axis(title='G - K (mag)')),
alt.Y('abs_gmag', axis=alt.Axis(title='abs. G')),
color=alt.condition(brush, color, alt.ColorValue('gray'))).properties(
selection=brush, width=450, height=500)
chart = chart1 | chart2
chart.savechart(out_file)
def linking_tree_with_plots_brush(dataFrame, list_of_data, list_of_titles,
color, ToolTip):
"""Creates a linked brushable altair plot with the tree and the charts appended
Parameters
-----------
dataframe: Pandas Dataframe
dataframe including node data and dimensionality reduction data
list_of_data: list
list of all the names of the columns in the dataframe for which you want graphs: goes in the order of [x1,y1,x2,y2,x3,y3] etc.
list_of_titles: list
list of all the TITLES you want for each axis: goes in order of[x1,y1,x2,y2,x3,y3] etc.
color: string
what the data should be colored by (ex. by clade, by region)
ToolTip: list
when hovering over the data, what data should be shown
Returns
---------
A brushable altair plot combining the tree with the plots of columns passed in
"""
list_of_chart = []
if (len(list_of_data) % 2 != 0 or len(list_of_titles) % 2 != 0):
raise Exception(
'The length of list_of_data and the length of list_of_titles should not be odd.'
)
else:
base = alt.Chart(dataFrame)
brush = alt.selection(type='interval', resolve='global')
tree_name = base.mark_circle().encode(
x=alt.X("date:Q",
scale=alt.Scale(domain=(dataFrame["date"].min() - 0.2,
dataFrame["date"].max() + 0.2)),
title="Date"),
y=alt.Y("y:Q", title=""),
color=alt.condition(brush, color, alt.ColorValue('gray')),
tooltip=ToolTip).add_selection(brush).properties(width=400,
height=250)
list_of_chart.append(tree_name)
for i in range(0, len(list_of_data) - 1, 2):
if (i == len(list_of_data)):
break
chart = base.mark_circle(size=60).encode(
x=alt.X(list_of_data[i], title=list_of_titles[i]),
y=alt.X(list_of_data[i + 1], title=list_of_titles[i + 1]),
color=alt.condition(brush, color, alt.ColorValue('gray')),
tooltip=ToolTip).add_selection(brush).properties(width=250,
height=250)
list_of_chart.append(chart)
return list_of_chart
def createChart(data, zipcode):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
#rating_selection = alt.selection_single(name="rating", empty="all", encodings=['y'])
data = data[data['zipcode'] == zipcode].nlargest(20, 'num')
try:
maxCount = int(data['num'].max())
except ValueError:
maxCount = 10
data = pd.DataFrame([{"name": "undefine", "num": 0}])
return alt.Chart(data)\
.mark_bar(stroke="Black")\
.encode(
alt.X("num:Q", axis=alt.Axis(title="Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y('name:O', axis=alt.Axis(title="cuisine"),
sort=alt.SortField(field="num", op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
def createChart(data, zipcode):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
try:
data = pd.concat([data['cuisine'], data['perZip' + zipcode]],
axis=1).nlargest(20, 'perZip' + zipcode)
maxCount = int(data['perZip' + zipcode].max())
except KeyError:
maxCount = 1
data = pd.DataFrame([{"cuisine": "", 'perZip' + zipcode: 0}])
return alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X('perZip'+zipcode+':Q', axis=alt.Axis(title="Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y('cuisine:O', axis=alt.Axis(title="cuisine"),
sort=alt.SortField(field='perZip'+zipcode, op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
def createChart(data):
color_expression = "highlight._vgsid_==datum._vgsid_"
#color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
rating_selection = alt.selection_single(name="rating",
empty="all",
encodings=['y'])
maxCount = int(data['restaurants'].max())
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("mean(restaurants):Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', axis=alt.Axis(title="Cuisine"),
sort=alt.SortField(field="restaurants", op="mean", order='descending')),
alt.ColorValue("LightGrey"),#, condition=color_condition), # Remove color condition
).properties(
width=200,
height=350,
selection = highlight_selection+rating_selection,
)
return alt.hconcat(barMean, data=data)
def draw_chart(data, zipcode):
# color expression, highlights bar on mouseover
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
#highlight bar when mouse is hovering
highlight_selection = alt.selection_single(name="highlight", empty="all", on="mouseover")
try:
data = pd.concat([data["cuisine"], data["perZip"+zipcode]], axis=1).nlargest(25, "perZip"+zipcode)
maxCount = int(data["perZip"+zipcode].max())
except KeyError:
maxCount = 1
data = pd.DataFrame([{"cuisine":"", "perZip"+zipcode:0}])
return alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("perZip"+zipcode+":Q",
axis=alt.Axis(title="Number of Restaurants"),
scale=alt.Scale(domain=(0,maxCount))),
alt.Y("cuisine:O", axis=alt.Axis(title="Cuisine Type"),
sort=alt.SortField(field="perZip"+zipcode,
op="argmax")),
alt.ColorValue("LightGrey",
condition=color_condition),
).properties(
selection = highlight_selection,
)
def createChart(data, name=''):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
barMean = alt.Chart() \
.mark_bar(stroke="Black") \
.encode(
alt.X("rating:Q", axis=alt.Axis(title="The number of restaurants")),
alt.Y('name:O', axis=alt.Axis(title="Cuisines".format(name)),
sort=alt.SortField(field="rating", op="mean", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection,
)
return alt.hconcat(
barMean,
data=data,
title="The number of restaurants ({} in NYC) - Top 25 cuisines".format(
name))
def get_interactive_proportions_plot(gender_balance):
source = data_frames[gender_balance]
pts = alt.selection(type="multi", encodings=['x'])
lin = alt.Chart(source).mark_line().encode(
alt.X('year:O', title='Year'),
alt.Y('female_prop:Q',
title="Proportion of Women",
axis=alt.Axis(format='%'),
scale=alt.Scale(domain=[0, 1])),
alt.Color('job:N', legend=None)).transform_filter(pts).properties(
width=500, height=375, title="Proportion of Women by Year")
label = alt.selection_single(
encodings=['x'], # limit selection to x-axis value
on='mouseover', # select on mouseover events
nearest=True, # select data point nearest the cursor
empty='none' # empty selection includes no data points
)
lin_w_interaction = alt.layer(
lin, # base line chart
alt.Chart().mark_rule(color='#aaa').encode(
x='year:O').transform_filter(label),
lin.mark_circle().encode(opacity=alt.condition(label, alt.value(
1), alt.value(0))).add_selection(label),
lin.mark_text(
align='left', dx=5, dy=-5, stroke='white',
strokeWidth=2).encode(text=alt.Text(
'female_prop:Q', format='.2%')).transform_filter(label),
lin.mark_text(align='left', dx=5, dy=-5).encode(text=alt.Text(
'female_prop:Q', format='.2%')).transform_filter(label),
data=source)
bar = alt.Chart(source).mark_bar(size=30).encode(
y=alt.Y('job:N',
title='',
sort=alt.EncodingSortField(field="total_prop_female",
op="sum",
order="descending")),
x=alt.X('total_prop_female:Q',
title="Proportion of Women",
axis=alt.Axis(format='%')),
color=alt.condition(pts, alt.Color(
'job:N', legend=None), alt.ColorValue("grey"))).properties(
width=250,
height=375,
title="Jobs by Proportion of Women (For the 10 most " +
gender_balance + " jobs)").add_selection(pts)
interactive_job_chart = alt.hconcat(lin_w_interaction, bar).resolve_legend(
color="independent",
size="independent").configure_axis(labelFontSize=13, titleFontSize=14)
# Save html as a StringIO object in memory
job_gender_proportions_html = io.StringIO()
interactive_job_chart.save(job_gender_proportions_html, 'html')
# Return the html from StringIO object
return job_gender_proportions_html.getvalue()
def _createRules(self,
source,
tooltip=True,
timetext=False,
timetexttop=False,
timetextheightmod=1,
field='value:Q'):
selectors = alt.Chart(source.data).mark_point(opacity=0).encode(
x='dateandtime:T', ).add_selection(self.nearestTime)
rules = alt.Chart(source.data).mark_rule().encode(
x='dateandtime:T',
color=alt.condition('isValid(datum.value)', alt.ColorValue('gray'),
alt.ColorValue('red'))).transform_filter(
self.nearestTime)
if timetext:
if timetexttop:
flip = -1
else:
flip = 1
time_text_dy = flip * (self.def_height * timetextheightmod / 2 +
11)
time_text = rules.mark_text(
align='center',
dx=0,
dy=time_text_dy,
fontSize=self.mark_text_font_size +
1).encode(text=alt.condition(self.nearestTime,
'dateandtime:T',
alt.value(' '),
format='%b %-d, %H:%M'))
rules = rules + time_text
if tooltip:
points = source.mark_point(
size=40, filled=True).encode(opacity=alt.condition(
self.nearestTime, alt.value(0.8), alt.value(0)))
text = source.mark_text(
align='left', dx=5, dy=-10,
fontSize=self.mark_text_font_size).encode(text=alt.condition(
self.nearestTime, field, alt.value(' '), format='.1f'))
return selectors + rules + points + text
return selectors + rules
def _build_slope(df,
values,
time,
bars,
col,
text,
filter_in,
y_pos=10,
width=350,
height=400,
y_title=None):
base = alt.Chart(df)
if time is None:
slope_x_title = ''
slope_filter = {
'or': [f'datum.slope_x == "averages"',
filter_in.ref()]
}
else:
max_time = df[time].max()
slope_x_title = f'{max_time}'
slope_filter = {
'and': [{
'or': [f'datum.slope_x == "averages"',
filter_in.ref()]
}, f'datum.{time} == {max_time}']
}
slope_base = base.encode(
x=alt.X('slope_x:N',
title=slope_x_title,
axis=alt.Axis(labels=False),
scale=alt.Scale(domain=['averages', 'measures', ''])),
y=alt.Y(values,
title=y_title,
scale=alt.Scale(domain=[df[values].min(), df[values].max()])),
color=alt.Color(
col, legend=None)).transform_filter(slope_filter).properties(
width=width, height=height)
slope_points = slope_base.mark_point(filled=True, size=150)
slope_lines = slope_base.mark_line()
slope_text_1 = slope_base.mark_text(dx=-25, dy=5).encode(
text=values).transform_filter('datum.slope_x == "averages"')
slope_text_2 = slope_base.mark_text(align='left', dx=8, dy=5).encode(
text='slope_text:N').transform_filter('datum.slope_x == "measures"')
slope_title = slope_base.mark_text(size=14, dy=-15).encode(
y=alt.value(y_pos), text=bars, color=alt.ColorValue('black'))
return slope_points + slope_lines + slope_text_1 + slope_text_2 + slope_title
def time_window_selector(base: alt.Chart, interpolate: bool) -> alt.LayerChart:
if interpolate is True:
tws = base.mark_area(interpolate="monotone")
else:
tws = base.mark_bar().encode(x2=alt.X2("event_end:T"))
tws = tws.encode(
x=alt.X("event_start", title=""),
y=alt.Y(
"reference_value",
title="",
axis=alt.Axis(values=[], domain=False, ticks=False),
),
color=alt.ColorValue(idle_color),
tooltip=alt.TooltipValue("Click and drag to select time window"),
).properties(height=30, title="Select time window")
tws = tws.add_selection(time_selection_brush) + tws.transform_filter(
time_selection_brush).encode(
color=alt.condition(time_selection_brush, alt.ColorValue(
"#c21431"), alt.ColorValue(idle_color)))
return tws
def plotZip(data, zip_filter):
try:
data_perzip = pd.concat([data[['cuisine', 'perZip']], data.perZip.apply(pd.Series)], axis=1)[['cuisine', str(zip_filter)]]\
.dropna().rename(index=str, columns={str(zip_filter): "total"}).sort_values(by=['total'], ascending=False)
except:
data_perzip = pd.DataFrame({'cuisine': [np.nan], 'total': [np.nan]})
return alt.Chart(data_perzip).mark_bar(stroke="Black").encode(
alt.X("total:Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', sort=alt.SortField(field="total", op="argmax")),
alt.ColorValue("LightGrey"),
).properties(width=200)
def showCuisines(data, zipCode):
data = data[data['zipCode'] == zipCode]
barRest = alt.Chart(data) \
.mark_bar(stroke="Black")\
.encode(alt.X("perZip:Q", axis=alt.Axis(title="Restaurant Count")),\
alt.Y("cuisine:O", axis=alt.Axis(title="Cuisine"),\
sort=alt.SortField(field="perZip", op="sum", order='descending')),\
alt.ColorValue("LightGrey"))
return barRest
def single_scatter(y, x):
brush = alt.selection(type='interval', resolve='global')
return alt.Chart(underlying_display).mark_point().encode(
y= y + ':Q',
x = x + ':Q',
color=alt.condition(brush, 'Sector:N', alt.ColorValue('gray'), legend=None),
tooltip=[ 'Ticker', 'Company:O', 'Sector:N']
).add_selection(
brush
).properties(
width=500
)
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 createChart(data):
maxCount = int(data[0]["count"])
barCount = alt.Chart(pd.DataFrame.from_records(data)) \
.mark_bar(stroke="Black") \
.encode(
alt.X("count:Q",
axis=alt.Axis(title="Number of Restaurants")),
alt.Y("cuisine:O", axis=alt.Axis(title="cuisine"),
sort=alt.SortField(field="count", order="descending",
op="mean")),
alt.ColorValue("LightGrey")
)
return barCount
def grafico_scatter_doble(data):
source = data
brush = alt.selection(type='interval', resolve='global')
base = alt.Chart(source).mark_point().encode(
y='profitableness_MUS$',
color=alt.condition(brush, 'Predominant_genre', alt.ColorValue('gray')),
).add_selection(
brush
).properties(
width=250,
height=250
)
base.encode(x='budget') | base.encode(x='revenue')
return base.encode(x='budget') | base.encode(x='revenue')
def generate_plot(element="Production", compared_year=1995):
stacked = None
stacked2 = None
prod = df_sum[df_sum["Element"] == element].reset_index(drop=True)
count = 0
items = [
"Cereals", "Citrus Fruit", "Fibre Crops", "Fruit", "Pulses",
"Roots and Tubers", "Sugar Crops", "Treenuts", "Vegetables", "Oilcrops"
]
areas = ["World", "Africa", "Asia", "Americas", "Europe", "Oceania"]
for area in areas:
df = prod[prod["Area"] == area]
for item in items:
year_df = df[df["Year"] == compared_year]
year_value = year_df[year_df["Item"] == item]["Value"].reset_index(
drop=True)[0]
df.loc[df['Item'] == item,
'Value'] = ((df[df["Item"] == item]["Value"] - year_value) /
year_value) * 100
base = alt.Chart(df).mark_line().encode(
x=alt.X('Year', scale=alt.Scale(domain=[1960, 2020])),
y=alt.Y('Value', title=f"{element} % vs {compared_year}"),
color=alt.condition(highlight, 'Item',
alt.ColorValue('lightgray')),
tooltip=['Domain', 'Item', 'Year',
'Value']).properties(title=f"{area} {element}")
points = base.mark_circle().encode(
opacity=alt.value(0)).add_selection(highlight)
lines = base.mark_line().encode(
size=alt.condition(~highlight, alt.value(1), alt.value(3)))
current = lines + points
if count < 3:
if stacked is None:
stacked = current
else:
stacked = stacked | current
else:
if stacked2 is None:
stacked2 = current
else:
stacked2 = stacked2 | current
count += 1
final_plot = stacked & stacked2
final_plot.save(f"../html/cashdrop_{element}.html",
embed_options={'renderer': 'svg'})
def fixed_viewpoint_selector(
base: alt.Chart,
active_fixed_viewpoint_selector: bool = False) -> alt.Chart:
"""Transparent selectors across the chart (visible on hover).
This is what tells us the belief time for a given x-value of the cursor.
:param active_fixed_viewpoint_selector: if False, return an idle colored version without tooltip
"""
selector = base.mark_rule().encode(
x=alt.X("belief_time:T", scale={"domain": time_selection_brush.ref()}),
color=alt.ColorValue(idle_color)
if not active_fixed_viewpoint_selector else alt.ColorValue("#c21431"),
opacity=alt.condition(nearest_x_hover_brush, alt.value(1),
alt.value(0)),
tooltip=[
alt.Tooltip(
"belief_time:T",
timeUnit="yearmonthdatehoursminutes",
title="Click to select belief time",
)
] if active_fixed_viewpoint_selector is True else None,
)
return selector.add_selection(nearest_x_select_brush).add_selection(
nearest_x_hover_brush)
def make_plot(data):
pts = alt.selection(type="multi", encodings=['x'])
rect = alt.Chart(data).mark_rect().encode(
alt.X('series number:N'),
alt.Y('grams of sugar', bin=True),
alt.Color('count()',
scale=alt.Scale(scheme='greenblue'),
legend=alt.Legend(title='Recipes')
),
tooltip='ingredient'
)
bar = alt.Chart(data).mark_bar().encode(
x='baker',
y='count(recipe)',
color=alt.condition(pts, alt.ColorValue("steelblue"), alt.ColorValue("grey"))
).properties(
width=550,
height=200
).add_selection(pts)
st.altair_chart(rect)
st.altair_chart(bar)
def plotWords(dfWords):
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
highlight_selection = alt.selection_single(name="highlight", empty="all", on="mouseover")
return alt.Chart(dfWords) \
.mark_bar(stroke="Black") \
.encode(
alt.X("freq", axis=alt.Axis(title="Count")),
alt.Y('word:O', axis=alt.Axis(title="Keyword"),
sort=alt.SortField(field="freq", op="max", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection
)
def get_lines(data, stroke_w, color, selection=None, **kwargs):
lines = alt.Chart(data).mark_line(
strokeWidth=stroke_w, **kwargs).encode(
alt.X(f'{columns}:{columns_type}',
title=x_title,
axis=alt.Axis(minExtent=30)), alt.Y(values,
title=y_title),
alt.Opacity(rows, legend=None),
alt.ColorValue(color)).transform_filter(filter_in).properties(
width=width, height=height)
if selection:
lines = lines.encode(size=alt.condition(
selection, alt.value(stroke_w *
2), alt.value(stroke_w))).properties(
selection=selection)
return lines
def rank_bar(y):
temp = underlying_display[['Ticker', 'Company',y]]
brush3 = alt.selection(type='interval', resolve='global',encodings=['x'])
bar = alt.Chart(temp).mark_bar().encode(
x=alt.X('Ticker:O',sort='-y'),
y=y+':Q',
color = alt.condition(brush3, 'Ticker:N', alt.ColorValue('grey'), legend=None)
)
rule = alt.Chart(temp).mark_rule(color='yellow').encode(
y='mean('+y+'):Q'
)
return (bar.add_selection(
brush3
).properties(
width=500
))
def createchart(data):
#color_expression = "(indexof(lower(datum.cuisine)) || (highlight._vgsid_==datum._vgsid_)"
#color_condition = alt.ConditionalPredicateValueDef(color_expression, "SteelBlue")
#highlight_selection = alt.selection_single(name="highlight", on="mouseover", empty="none")
#search_selection = alt.selection_single(name="search", on="mouseover", empty="none", fields=["term"],
#bind=alt.VgGenericBinding('input'))
chart = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("total:Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', sort=alt.SortField(field="total", op="argmax")),
alt.ColorValue("LightGrey"),
)
return chart
def pair_scatter(legend_flag):
brush = alt.selection(type='interval', resolve='global')
base = alt.Chart(underlying_display).mark_point().encode(
y=val_c0+':Q',
color=alt.condition(brush, 'Sector:N', alt.ColorValue('gray'), legend=legend_flag),
size = 'Size:N',
tooltip=[ 'Ticker', 'Company:O', 'Sector:N']
).add_selection(
brush
).properties(width='container')
base1 = base.encode(x=val_c1+':Q')
base2 = base.encode(x=val_c2+':Q')
base3 = base.encode(x=val_c3+':Q')
return (base1 , base2 , base3)
def showRatingDistribution(df, name=''):
zips = name
try:
data = df.sort_values(by=zips, ascending=False).head(15)
except KeyError:
return alt.Chart(pd.DataFrame()).mark_bar()
else:
color_expression = "highlight._vgsid_==datum._vgsid_"
color_condition = alt.ConditionalPredicateValueDef(
color_expression, "SteelBlue")
## There are two types of selection in our chart:
## (1) A selection for highlighting a bar when the mouse is hovering over
highlight_selection = alt.selection_single(name="highlight",
empty="all",
on="mouseover")
## (2) A selection for updating the rating distribution when the mouse is clicked
## Note the encodings=['y'] parameter is needed to specify that once a selection
## is triggered, it will propagate the encoding channel 'y' as a condition for
## any subsequent filter done on this selection. In short, it means use the data
## field associated with the 'y' axis as a potential filter condition.
# rating_selection = alt.selection_single(name="rating", empty="all", encodings=['y'])
## We need to compute the max count to scale our distribution appropriately
# maxCount = int(data[zips].max())
## Our visualization consists of two bar charts placed side by side. The first one
## sorts the apps by their average ratings as below. Note the compound selection
## that is constructed by adding the two selections together.
barMean = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X(zips+":Q", axis=alt.Axis(title="Restuarants")),
alt.Y('cuisine:O', axis=alt.Axis(title="Cuisine".format(name)),
sort=alt.SortField(field=zips, op="max", order='descending')),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection = highlight_selection
)
return barMean
def createChart(data, zip):
color_expression = "(highlight._vgsid_==datum._vgsid_)"
color_condition = alt.ConditionalPredicateValueDef(color_expression,
"SteelBlue")
highlight_selection = alt.selection_single(name="highlight",
on="mouseover",
empty="none")
vis2 = alt.Chart(data) \
.mark_bar(stroke="Black") \
.encode(
alt.X("total:Q", axis=alt.Axis(title="Restaurants")),
alt.Y('cuisine:O', sort=alt.SortField(field="total", op="argmax")),
alt.ColorValue("LightGrey", condition=color_condition),
).properties(
selection=(highlight_selection),
)
return vis2
