def make_plot_top(data):
"""
Make the time plot for
San Fransisco crime data.
parameters:
-----------
data : pandas.DataFrame
data frame containing the crime data
returns:
--------
alt.Chart
altair plot
"""
# Create a plot of the Displacement and the Horsepower of the cars dataset
# making the slider
slider = alt.binding_range(min=0, max=23, step=1)
select_hour = alt.selection_single(name='select',
fields=['hour'],
bind=slider,
init={'hour': 19})
chart = alt.Chart(data).mark_bar(size=30).encode(
x=alt.X('Category', type='nominal', title='Category'),
y=alt.Y('count()', title="Count", scale=alt.Scale(domain=(0, 3300))),
tooltip='count()').properties(
title="Hourly crime occurrences for selected crimes",
width=500,
height=250).add_selection(select_hour).transform_filter(
select_hour)
chart.configure_title(fontSize=12)
return chart
def create_visualisation(df_dic: Dict[int, pd.DataFrame], ts: np.ndarray,
colours: List[str]) -> alt.Chart:
time_field = "t"
select_time = alt.selection_single(
name="select",
fields=[time_field],
init={time_field: min(ts)},
bind=alt.binding_range(min=min(ts), max=max(ts), step=ts[1] - ts[0]),
)
chart = (alt.Chart(pd.DataFrame({
"x": [0],
"y": [0]
})).mark_point(opacity=0).encode(x="x", y="y").add_selection(select_time))
for k, df in df_dic.items():
for t in ts:
df_t = df[df["t"] == t]
df_t.sort_index()
base = alt.Chart(df_t).transform_filter(select_time)
chart += base.mark_line(color=colours[k - 1]).encode(
alt.X("x:Q"), alt.Y("y:Q"), alt.OpacityValue(
1)).transform_filter(select_time) + base.mark_point(
color=colours[k - 1]).encode(
alt.X("x:Q"), alt.Y("y:Q"),
alt.OpacityValue(1)).transform_filter(select_time)
return chart.interactive()
def draw_v4():
grade = pd.read_csv("data/grade_by_year.csv")
resource = pd.read_csv("data/resource_by_year.csv")
slider = alt.binding_range(min=2013, max=2018, step=1)
select_year = alt.selection_single(name="Year",
fields=['Post year'],
bind=slider,
init={'Post year': 2018})
g_histo = alt.Chart(grade).mark_bar().encode(
x="Project Grade Level Category:N",
y="Project Cost:Q",
color=alt.Color("Project Grade Level Category:N"),
tooltip=[
"Project Grade Level Category:N", "Project Cost:Q"
]).add_selection(select_year).transform_filter(select_year).properties(
width=500, height=500)
r_histo = alt.Chart(resource).mark_bar().encode(
x="Project Resource Category:N",
y="Project Cost:Q",
color=alt.Color("Project Resource Category:N"),
tooltip=[
"Project Resource Category:N", "Project Cost:Q"
]).add_selection(select_year).transform_filter(select_year).properties(
width=500, height=500)
st.write(g_histo)
st.write(r_histo)
return
def plot_tsne(source, x_col, y_col, category, perplexities, img_name):
cats = list(source[category].unique())
# Base
base = alt.Chart(source).mark_point(filled=True).encode(x=x_col + ':Q',
y=y_col + ':Q',
tooltip=img_name +
':N')
# A slider filter
perp_slider = alt.binding_range(min=10, max=40, step=10)
slider_selection = alt.selection_single(bind=perp_slider,
fields=[perplexities],
name="Change")
# Color changing marks
rating_radio = alt.binding_radio(options=cats)
rating_select = alt.selection_single(fields=[category],
bind=rating_radio,
name="Filter")
rating_color_condition = alt.condition(
rating_select, alt.Color(category + ':N', legend=None),
alt.value('lightgray'))
highlight_ratings = base.add_selection(
rating_select, slider_selection).encode(
color=rating_color_condition).transform_filter(
slider_selection).properties(title="tSNE Scatter Plot")
return highlight_ratings.properties(width=800, height=300)
def histogram(values, title=""):
"""Histogram with percentage on y and a rule at mean
slider for reducing the number of values used.
"""
df = pd.DataFrame({values.name: values, 'num': list(range(1, len(values) + 1))})
slider = alt.binding_range(min=1, max=len(values), step=1, name='Number of samples: ')
selection = alt.selection_single(bind=slider, fields=['num'], name="num",
init={'num': len(values)})
base = alt.Chart(df).transform_filter('datum.num <= num_num')
plot = base.transform_joinaggregate(
total='count(*)'
).transform_calculate(
pct='1 / datum.total'
).mark_bar().encode(
alt.X(f'{values.name}:Q', bin=True),
alt.Y('sum(pct):Q', axis=alt.Axis(format='%'))
).add_selection(
selection
).properties(
title=title
)
rule = base.mark_rule(color='red').encode(
x=f'mean({values.name}):Q',
size=alt.value(5)
)
return plot + rule
def make_plot_top(df_new=df_t4):
# Create a plot of the Displacement and the Horsepower of the cars dataset
# making the slider
slider = alt.binding_range(min = 0, max = 23, step = 1)
select_hour = alt.selection_single(name='select', fields = ['hour'],
bind = slider, init={'hour': 0})
#begin of my code
# typeDict = {'ASSAULT':'quantitative',
# 'VANDALISM':'quantitative',
# 'LARCENY/THEFT':'quantitative',
# 'VEHICLE THEFT':'quantitative'
# }
# end
chart = alt.Chart(df_new).mark_bar(size=30).encode(
x=alt.X('Category',type='nominal', title='Category'),
y=alt.Y('count()', title = "Count" , scale = alt.Scale(domain = (0,3300))),
tooltip='count()'
).properties(
title = "Per hour crime occurrences for the top 4 crimes",
width=500,
height = 315
).add_selection(
select_hour
).transform_filter(
select_hour
)
return chart
def Joint_Prob_plot(df):
year_min = df["cohort"].min()
year_max = df["cohort"].max()
slider = alt.binding_range(min=year_min, max=year_max, step=1)
select = alt.selection_single(name="year",
fields=['cohort'],
bind=slider,
init={'cohort': year_min})
df_new = df.apply(lambda row: gen_plot_df(row), axis=1)
df_new = pd.concat(list(df_new))
base = alt.Chart(df_new)
# chart on Joint Prob
plot_scale = alt.Scale(type="pow",
exponent=0.5,
scheme="greens",
nice=True)
color = alt.Color('MR:Q', scale=plot_scale)
joint_chart = base.mark_rect().encode(
x="p:O",
y=alt.Y('k:O', sort=alt.EncodingSortField('k', order='descending')),
color=color).add_selection(select).transform_filter(select).properties(
height=200, width=200)
color_scale = alt.Scale(
domain=['1', '2', '3', '4', '5'],
range=['#4c78a8', '#f58518', '#e45756', '#72b7b2', '#54a24b'])
p_mag_1 = base.mark_bar().encode(
x=alt.X("p:O"),
y=alt.Y('sum(MR):Q', scale=alt.Scale(domain=(0, 1))),
color=alt.Color('k:O', scale=color_scale, legend=None),
order=alt.Order(aggregate='sum',
type="quantitative",
sort='descending')).add_selection(
select).transform_filter(select).properties(
height=150, width=200)
k_mag_1 = base.mark_bar().encode(
y=alt.Y("k:O", sort=alt.EncodingSortField('k', order='descending')),
x=alt.X('sum(MR):Q', scale=alt.Scale(domain=(0, 1))),
color=alt.Color('p:O',
scale=color_scale,
sort=alt.EncodingSortField('p', order='ascending'),
legend=None),
order=alt.Order(aggregate='sum',
type="quantitative",
sort='descending')).add_selection(
select).transform_filter(select).properties(
height=200, width=150)
people_c = people_plot(df, select).properties(width=300, height=300)
return (p_mag_1 & (joint_chart | k_mag_1)
& people_c).resolve_scale(color='independent')
def world_map(highlight, highlight2):
slider = alt.binding_range(min=1991, max=2011, step=1)
select_year = alt.selection_single(name="Year",
fields=['Year'],
bind=slider,
init={'Year': 2011})
map = alt.Chart(df).mark_geoshape(stroke='#aaa', strokeWidth=0.25).encode(
color=alt.condition(highlight2 | highlight,
'CO2 emissions (kt):Q',
alt.value('lightgrey'),
scale=alt.Scale(scheme='redyellowblue',
reverse=True)),
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita"
]
).transform_lookup(
lookup='Country Name',
from_=alt.LookupData(
"https://raw.githubusercontent.com/KoGor/Map-Icons-Generator/master/data/world-110m-country-names.tsv",
'name', ['id', "name"])).transform_lookup(
lookup='id',
from_=alt.LookupData(
countries,
'id',
fields=["id", "type", "properties", "geometry"])
).project(type="equirectangular").properties(
width=1100,
height=650,
title='worldwide CO2 total emissions and emissions per capita'
).add_selection(highlight, highlight2)
percapita = alt.Chart(df).mark_circle(opacity=0.4, ).encode(
size=alt.Size('CO2 emissions per capita:Q',
scale=alt.Scale(range=[10, 3000])),
color=alt.condition(highlight2 | highlight, alt.value('red'),
alt.value('lightgrey')),
longitude='Longitude (average):Q',
latitude='Latitude (average):Q',
tooltip=[
"Country Name", "CO2 emissions (kt)", "CO2 emissions per capita"
]
).transform_lookup(
lookup='Country Name',
from_=alt.LookupData(
"https://raw.githubusercontent.com/KoGor/Map-Icons-Generator/master/data/world-110m-country-names.tsv",
'name', ['id', "name"])).transform_lookup(
lookup='id',
from_=alt.LookupData(
countries,
'id',
fields=["id", "type", "properties", "geometry"
])).project(type="equirectangular").properties(
width=900,
height=400,
)
return alt.layer(map, percapita) \
.add_selection(select_year) \
.transform_filter(select_year)
def write():
st.title("Nagel-Schereckenberg (NaSch) Model Simulation Page")
st.write(NASCH_explanation_string)
# Set parameters
st.sidebar.subheader("Set Parameters")
bool_periodic_boundary = st.sidebar.checkbox(
"Periodic Boundary Condition?", True)
bool_initrandom = st.sidebar.checkbox("Random initialization?", True)
const_nSteps = st.sidebar.slider("Number of steps to simulate", 10, 2000,
100, 10)
const_L = st.sidebar.slider("Number of slots", 10, 50, 20)
const_vmax = st.sidebar.slider("Maximum speed", 1, 10, 5)
const_density = st.sidebar.slider("Initial Density", 0.0, 0.95, 0.5, 0.05)
const_stepProb = st.sidebar.slider("Step Probability", 0.05, 1.0, 0.5,
0.05)
const_entryProb = st.sidebar.slider("Entry Probability (alpha)", 0.05,
0.95, 0.5, 0.05)
if st.button("Run simulation?"):
df, flux = simulate_nasch(
n_steps=const_nSteps,
n_slots=const_L,
init_random=bool_initrandom,
init_density=const_density,
const_vmax=const_vmax,
const_stepprob=const_stepProb,
periodic_boundary=bool_periodic_boundary,
entry_prob=const_entryProb,
)
df_plot = df.copy()
df_plot["img"] = ["car"] * len(df_plot)
df_plot["car"] = [1] * len(df_plot)
slider = alt.binding_range(min=0, max=const_nSteps - 1, step=1)
select_time = alt.selection_single(name="time",
fields=["time"],
bind=slider,
init={"time": 1})
c = (alt.Chart(df_plot).properties(height=100).mark_text(
size=30, baseline="middle").encode(
alt.X(
"position",
type="quantitative",
scale=alt.Scale(domain=[0, const_L]),
),
alt.Y(field="car", type="ordinal"),
alt.Text("emoji:N"),
).transform_calculate(emoji="{'car':'🚗'}[datum.img]").
add_selection(select_time).transform_filter(select_time))
st.write(
"Now, try and play with the slider representing the timepoint, to see the cars move in time!"
)
st.altair_chart(c, use_container_width=True)
fig, axes = get_spatiotemporal_plot(df, flux)
st.write("Here is a summary figure as well!")
st.pyplot(fig)
def traceplot(output_dir: str, chains: BEASTPosteriorDirFmt,
params: str = None):
CONTROL_FMT = chains[0].control.format
md5sums = {c.control.view(CONTROL_FMT).md5sum() for c in chains}
if len(md5sums) > 1:
raise ValueError("Chains do not share a posterior distribution as they"
" were generated with different inputs/parameters/"
"priors, so they cannot be visualized together.")
if params is None:
params = []
params = list(reversed(params)) + ['likelihood']
dfs = []
for idx, chain in enumerate(chains, 1):
df = chain.log.view(pd.DataFrame)[['state'] + params]
df['CHAIN'] = 'Chain %d' % idx
dfs.append(df)
data = pd.concat(dfs)
url = 'data.json'
gen_end = data['state'].iloc[-1]
gen_step = gen_end - data['state'].iloc[-2]
slider = alt.binding_range(min=0, max=gen_end, step=gen_step,
name='Burn-in: ')
selector = alt.selection_single(name="BurnIn", fields=['burnin'],
bind=slider, init={'burnin': 0})
traceplots = []
for param in params:
line = alt.Chart(url).mark_line(
interpolate='step-after',
opacity=0.8
).encode(
x=alt.X('state:Q', title='Generation'),
y=alt.Y(param, type='quantitative', scale=alt.Scale(zero=False)),
color='CHAIN:N'
).add_selection(
selector
).transform_filter(
alt.datum.state >= selector.burnin
).properties(width=800).interactive(bind_y=False)
hist = alt.Chart(url).mark_bar().encode(
x=alt.X('count()', title='Frequency'),
y=alt.Y(param, type='quantitative', bin=alt.Bin(), title=None),
color='CHAIN:N'
).transform_filter(
alt.datum.state >= selector.burnin
).properties(width=200)
traceplot = alt.hconcat(line, hist).resolve_scale(y='shared')
traceplots.append(traceplot)
dash = alt.vconcat(*traceplots)
dash.save(os.path.join(output_dir, 'index.html'))
data.to_json(os.path.join(output_dir, url), orient='records')
def get_binding_range(self):
range_max = self.get_range_max()
if '7d' in self.case_a or '7d' in self.case_b:
input_dropdown = alt.binding_range(min=range_max - 7,
max=range_max,
step=1,
name='Date:')
else:
input_dropdown = alt.binding_range(min=0,
max=range_max,
step=1,
name='Date:')
selection = alt.selection_single(fields=['date_transformed'],
bind=input_dropdown,
init={'date_transformed': range_max})
return selection
def get_line_chart(multi=False):
flunet_df = get_df()
countries = flunet_df.columns.tolist()[1:]
transformed_df = pd.melt(
flunet_df,
id_vars=["week"],
value_vars=countries,
var_name="country",
value_name="flu_cases",
)
transformed_df["index"] = transformed_df["week"] % 53
slider1 = alt.binding_range(min=1, max=52, step=1)
slider2 = alt.binding_range(min=1, max=52, step=1)
select_week1 = alt.selection_single(name="week1",
fields=["week"],
bind=slider1)
select_week2 = alt.selection_single(name="week2",
fields=["week"],
bind=slider2)
if multi:
multi_select = alt.selection_multi(fields=["country"])
selection = alt.selection_multi(fields=["country"])
line, color = plot(selection, transformed_df)
make_selector = (alt.Chart(pd.DataFrame({
"country": countries
})).mark_rect().encode(y="country",
color=color).add_selection(selection))
return line | make_selector
selector = alt.selection(
type="single",
fields=["country"],
bind=alt.binding_select(options=countries),
name="Select",
)
line, _ = plot(selector, transformed_df)
return (line.add_selection(select_week2).add_selection(select_week1).
transform_filter("datum.week > week1_week").transform_filter(
"datum.week < week2_week"))
def plot_altair_3(xcol, ycol):
select_quality = alt.selection_single(name='Select',
fields=['quality'],
init={'quality': 3.0},
bind=alt.binding_range(min=3.0,
max=9.0,
step=1.0))
chart = alt.Chart(
wine, title=ycol + " VS " + xcol).mark_circle(opacity=0.5).encode(
alt.X(xcol), alt.Y(ycol), alt.Size('chlorides in g/dm3'),
alt.OpacityValue(0.5)).add_selection(
select_quality).transform_filter(select_quality)
return chart.to_html()
def getjson2():
data1_df = pd.read_csv('./data/vis2_hr_weather.csv')
alt.data_transformers.enable('default', max_rows=None)
interval = alt.selection_multi(fields=['weather_desc'])
# interval1 = alt.selection_multi(fields = ['hr:N'])
scatter = alt.Chart(data1_df).mark_circle(size=45).encode(
y=alt.Y('count:Q', title='Count'),
x=alt.X('temp_bin:N', title='Temperature Bucket (Farenheit)'),
color=alt.condition(
interval,
alt.Color('weather_desc:N', scale=alt.Scale(scheme='category20')),
alt.value('lightgray')),
tooltip=[
alt.Tooltip(shorthand='hr:N', title=("Average Count")),
alt.Tooltip(shorthand='weather_desc:N', title=("Weather"))
]).properties(selection=interval,
width=400,
title='Weather and Time popularity Info Plot')
hour_slider = alt.binding_range(min=1, max=24, step=1)
slider_selection = alt.selection_single(bind=hour_slider,
fields=['hr'],
name="Hour")
# percent_slider = alt.binding_range(min=10, max=100, step=5)
# slider_selection = alt.selection_single(bind=percent_slider, fields=['percentile'], name = "percentile")
scatter2 = alt.Chart(data1_df).mark_point().encode(
x=alt.X('wind_bin:N', title='Wind Speed Bucket (Km/h)'),
size=alt.Size('count:Q', title='Average Count'),
y=alt.Y('duration_mean:Q', title='Average Duration in Minutes'),
shape='is_member:N',
tooltip=[
alt.Tooltip(shorthand='duration_mean:Q',
title=("Average Duration")),
alt.Tooltip(shorthand='temp_bin:N',
title=("Temperature Bucket (Farenheit)")),
alt.Tooltip(shorthand='weather_desc', title=("Weather")),
alt.Tooltip(shorthand='count:Q', title=("Average Count"))
]).properties(selection=interval,
title='Counts Based on Temperature Hour and Wind Speed',
width=200,
height=500).transform_filter(interval).add_selection(
slider_selection).transform_filter(
slider_selection).interactive()
data = (scatter | scatter2).to_dict()
return jsonify(data)
def step4_related_factors():
# next_block()
st.header("Step4: Factors that may affect CO2 emissions")
st.write("Tips:")
st.write("1. Add indicators you want to compare with CO2 emissions!")
st.write("2. Put your mouse on a country and compare across indicators!")
st.write("3. Remember to play with the year slide bar :)")
slider = alt.binding_range(min=1991, max=2011, step=1)
select_year = alt.selection_single(name="Year",
fields=['Year'],
bind=slider,
init={'Year': 2011})
highlight = alt.selection_single(
on='mouseover', fields=['Country Name'],
empty='all') # init={"Country Name": "United States"})
dataset2 = st.multiselect("Choose factors to compare!", [
"CO2 emissions per GDP", "CO2 emissions (kt)",
"CO2 emissions per capita", "Urban population (% of total)",
"Renewable energy consumption (% of total final energy consumption)",
"Forest area (% of land area)",
"Marine protected areas (% of territorial waters)",
"Population growth (annual %)",
"Renewable electricity output % of total",
"Terrestrial protected areas % of total",
"Total greenhouse gas emissions (kt of CO2 equivalent)"
], [
"CO2 emissions (kt)", "CO2 emissions per GDP",
"Renewable electricity output % of total"
])
st.write(
alt.hconcat(
world_map_for_factors(highlight, dataset2, select_year),
alt.Chart(df).mark_point().encode(
alt.X(alt.repeat("column"), type='quantitative'),
alt.Y(alt.repeat("row"), type='quantitative'),
color='Country Name:N',
).properties(
width=160,
height=160,
).repeat(
row=dataset2,
column=dataset2,
).transform_filter(select_year).interactive()))
def display_the_conplot():
slider = alt.binding_range(min=2006, max=2013, step=1)
select_year = alt.selection_single(name='Select',
fields=['Year'],
bind=slider,
init={'Year': 2006})
base = alt.Chart(tidy_df).add_selection(select_year).transform_filter(
select_year).transform_calculate(types=alt.expr.if_(
alt.datum.Half == 1.0, '1st Half', '2nd Half')).properties(
width=250, )
color_scale = alt.Scale(domain=['1st Half', '2nd Half'],
range=['green', 'orange'])
left = base.transform_filter(alt.datum.types == '1st Half').encode(
y=alt.Y('County Councils:O', axis=None),
x=alt.X('sum(esb):Q',
title='ESB Count',
sort=alt.SortOrder('descending')),
color=alt.Color('types:N', scale=color_scale, legend=None),
tooltip=('sum(esb):Q')).mark_bar().properties(
title='First Half of Year')
middle = base.encode(
y=alt.Y('County Councils:O', axis=None),
text=alt.Text('County Councils:O'),
).mark_text(color='steelblue', size=15).properties(width=105)
right = base.transform_filter(alt.datum.types == '2nd Half').encode(
y=alt.Y('County Councils:O', axis=None),
x=alt.X('sum(esb):Q', title='ESB Count'),
color=alt.Color('types:N', scale=color_scale, legend=None),
tooltip=('sum(esb):Q')).mark_bar().properties(
title='Second Half of Year')
conplot = alt.concat(left, middle, right, spacing=5)
conplot.save("templates/conplot.html")
return render_template("conplot.html")
def draw_v3():
df = pd.read_csv("data/state_donate_avg_sum.csv")
slider = alt.binding_range(min=2013, max=2018, step=1)
select_year = alt.selection_single(name="Year",
fields=['Year'],
bind=slider,
init={'Year': 2013})
mean_ = alt.Chart(df).mark_bar().encode(
x=alt.X('Donor State:N'),
y=alt.Y('Mean:Q'),
tooltip=['Donor State:N', 'Mean:Q'
]).add_selection(select_year).transform_filter(select_year)
sum_ = alt.Chart(df).mark_bar().encode(
x=alt.X('Donor State:N'),
y=alt.Y('Sum:Q'),
tooltip=['Donor State:N', 'Sum:Q'],
).add_selection(select_year).transform_filter(select_year)
st.write(mean_)
st.write(sum_)
return
def getjson1():
# import altair as alt
data1_df = pd.read_csv('./data/vis1_hr.csv')
alt.data_transformers.enable('default', max_rows=None)
interval = alt.selection_single(fields=["start_date_hr"])
scatter = alt.Chart(data1_df).mark_point(color='red', size=30).encode(
x=alt.X('start_date_hr:Q', title='Hour'),
y=alt.Y('start_station_count:Q', title='Average Start Station Count'),
color=alt.condition(interval, alt.value('steelblue'),
alt.value('lightgray')),
tooltip='name').properties(selection=interval,
width=800,
title='Start Station Vs Count Plot')
percent_slider = alt.binding_range(min=10, max=100, step=10)
slider_selection = alt.selection_single(bind=percent_slider,
fields=['percentile'],
name="percentile")
scatter1 = alt.Chart(data1_df).mark_circle().encode(
x='vacancy:Q',
y=alt.Y('duration_mean:Q', title='Average Duration in Minutes'),
size=alt.Size('start_station_count:Q'),
color='is_member:N',
tooltip=[
alt.Tooltip(shorthand='name:N', title=("Start Station Name")),
alt.Tooltip(shorthand='start_station_count:Q',
title=("Average No. of Bikes Taken"))
]).properties(selection=interval,
title='Hour and Percentile wise Start Station Analysis',
width=600).transform_filter(interval).add_selection(
slider_selection).transform_filter(
slider_selection).interactive()
# scatter & scatter1
data = (scatter & scatter1).to_dict()
return jsonify(data)
bin_labels_9 = ['Under 15,000', '15,000 to 24,999', '25,000 to 34,999',
'35,000 to 49,999', '50,000 to 74,999', '75,000 to 99,999',
'100,000 to 149,999', '150,000 to 199,999', '200,000 and over']
newDATA['Income Range'] =
for i in range(DATA):
if DATA.
# In[62]:
alt.data_transformers.disable_max_rows()
slider = alt.binding_range(min=1, max=31, step=1)
select_date = alt.selection_single(name="January", fields=['Date'], bind=slider, init={'Date':1})
state_selector = alt.selection_multi(fields=['statename'], init=[{'statename':'Alabama'}])
table = alt.Chart(DATA).mark_bar().encode(
x=alt.X('value:Q', title="% of Visits to Doctor about COVID", aggregate="mean", scale=alt.Scale(domain=[0, 25])),
y=alt.Y('statename:N', title="State")
).add_selection(
state_selector
).add_selection(
select_date
).transform_filter(
select_date)
secondTable = alt.Chart(DATA).mark_bar().encode(
# Delete these row indexes from dataFrame, rows with '<5' value
js.drop(indexNames, inplace=True)
js['JobSeeker Payment'] = js['JobSeeker Payment'].str.split(',').str.join(
'').astype(int)
js
import altair as alt
alt.data_transformers.disable_max_rows()
select_month = alt.selection_single(name='Select',
fields=['Month'],
init={'Month': 3},
bind=alt.binding_range(min=1,
max=12,
step=1))
chart = alt.Chart(js).mark_bar().encode(
x=alt.X('Number of JobSeeker Payment'),
y=alt.Y('SA2 Name', sort='-x'),
tooltip=['SA2 Name', 'JobSeeker Payment']).properties(
title='SA2 with Top10 Number of JobSeeker Payment each Month'
).add_selection(select_month).transform_filter(
select_month).transform_window(rank='rank(JobSeeker Payment)',
sort=[
alt.SortField('JobSeeker Payment',
order='descending')
]).transform_filter(alt.datum.rank < 10)
chart
bind=DROPDOWN_OBJ_AGE,
name='Age',
init={'Group':'Total'}
)
SELECT_OBJ_SEX = alt.selection_single(
fields=['Group'],
bind=DROPDOWN_OBJ_SEX,
name='Demographics',
init={'Group':'Total'}
)
# slider for year and accompanying selection options
SLIDER = alt.binding_range(
min=START_YEAR,
max=END_YEAR,
step=2,
name='Election Year'
)
SELECT_OBJ_YR = alt.selection_single(
name='SelectorName',
fields=['Year'],
bind=SLIDER,
init={'Year':START_YEAR}
)
def generate_map(df_in, map_title, map_type):
'''
Generate US map for given voting or registration data.
+ " There are also some songs that have been played for more than their duration, likely because the user rewound the song."
+ " You can use the slider to explore the relationship between the number of seconds, the proportion of the song that was"
+ " listened to, and the distribution of the proportions in the data. The tooltip provides the exact count of songs in the"
+ " bar being hovered over. To improve the quality of the data analyzed, in allowing following charts we filter out songs"
+ " that were listened to for less than 20 seconds.")
df = df.copy()
df['percent_listened'] = df['msPlayed'] / df['duration_ms']
df['percent_listened'] = df['percent_listened'].clip(0, 1.1) * 100.
# unit conversions
ms_per_second = 1000
seconds_per_minute = 60
minutes_per_hour = 60
# make a slider that goes from 0 to 6 minutes played with a step size of 0.5 seconds
seconds_slider = alt.binding_range(min=0, max=8*seconds_per_minute, step = 0.5, name="Cutoff (seconds):")
# make the selection that is based off of the slider and can be used by the chart, initialized to 20 seconds
seconds_selector = alt.selection_single(name="SelectorName", fields=["cutoff"],
bind=seconds_slider, init={"cutoff": 20})
# make the chart whose x-axis in the ratio of milliseconds played to duration of the song (binned over steps of 0.1, meaning 10%)
# and whose y-axis is the count of the number of rows that fall into the ratio bin
# the selector (above) is used to color in the records whose milliseconds played are less than the specified selection
# the width and height of the chart are specified to try to provide better visibility
played_vs_duration = alt.Chart(df).mark_bar().encode(
alt.X("percent_listened:Q", bin=alt.Bin(step=10), title="Percent of Song"),
alt.Y("count():Q", title="Count of Songs"),
alt.Color("played_less_than_cutoff_seconds:N", title="Songs Played for Less than Cutoff",
scale=alt.Scale(domain=['true', 'false'], range=['#d8b365', '#5ab4ac']),
legend=alt.Legend(orient="bottom")),
tooltip = [alt.Tooltip("count():Q", title="Count of Songs")]
).transform_calculate(
def map_state_slider(state_txt, state_counties, confirmed, confirmed_min,
confirmed_max, deaths, deaths_min, deaths_max,
state_fips):
# Pivot confirmed data by day_num
confirmed_pv = confirmed[['fips', 'day_num', 'confirmed']].copy()
confirmed_pv['fips'] = confirmed_pv['fips'].astype(str)
confirmed_pv['day_num'] = confirmed_pv['day_num'].astype(str)
confirmed_pv['confirmed'] = confirmed_pv['confirmed'].astype('int64')
confirmed_pv = confirmed_pv.pivot_table(index='fips',
columns='day_num',
values='confirmed',
fill_value=0).reset_index()
# Pivot deaths data by day_num
deaths_pv = deaths[['lat', 'long_', 'day_num', 'deaths']].copy()
deaths_pv['day_num'] = deaths_pv['day_num'].astype(str)
deaths_pv['deaths'] = deaths_pv['deaths'].astype('int64')
deaths_pv = deaths_pv.pivot_table(index=['lat', 'long_'],
columns='day_num',
values='deaths',
fill_value=0).reset_index()
# Extract column names for slider
column_names = confirmed_pv_wa.columns.tolist()
# Remove first element (`fips`)
column_names.pop(0)
# Convert to int
column_values = [None] * len(column_names)
for i in range(0, len(column_names)):
column_values[i] = int(column_names[i])
# Disable max_rows to see more data
alt.data_transformers.disable_max_rows()
# Topographic information
us_states = alt.topo_feature(topo_usa, 'states')
us_counties = alt.topo_feature(topo_usa, 'counties')
# state county boundaries
base_state = alt.Chart(state_counties).mark_geoshape(
fill='white',
stroke='lightgray',
).properties(
width=800,
height=600,
).project(type='mercator')
# Slider choices
min_day_num = column_values[0]
max_day_num = column_values[len(column_values) - 1]
slider = alt.binding_range(min=min_day_num, max=max_day_num, step=1)
slider_selection = alt.selection_single(fields=['day_num'],
bind=slider,
name="day_num",
init={'day_num': min_day_num})
# Confirmed cases by county
base_state_counties = alt.Chart(us_counties).mark_geoshape(
stroke='black', strokeWidth=0.05).transform_lookup(
lookup='id',
from_=alt.LookupData(confirmed_pv, 'fips', column_names)
).transform_fold(column_names, as_=[
'day_num', 'confirmed'
]).transform_calculate(
state_id="(datum.id / 1000)|0",
day_num='parseInt(datum.day_num)',
confirmed='isValid(datum.confirmed) ? datum.confirmed : -1'
).encode(color=alt.condition(
'datum.confirmed > 0',
alt.Color('confirmed:Q',
scale=alt.Scale(domain=(confirmed_min, confirmed_max),
type='symlog')), alt.value('white')
)).properties(
# update figure title
title=f'COVID-19 WA State Confirmed Cases by County'
).transform_filter((alt.datum.state_id
) == state_fips).transform_filter(slider_selection)
# deaths by long, latitude
points = alt.Chart(deaths_pv).mark_point(
opacity=0.75, filled=True).transform_fold(
column_names, as_=['day_num', 'deaths']).transform_calculate(
day_num='parseInt(datum.day_num)',
deaths='isValid(datum.deaths) ? datum.deaths : -1').encode(
longitude='long_:Q',
latitude='lat:Q',
size=alt.Size('deaths:Q',
scale=alt.Scale(domain=(deaths_min,
deaths_max),
type='symlog'),
title='deaths'),
color=alt.value('#BD595D'),
stroke=alt.value('brown'),
).add_selection(slider_selection).transform_filter(
slider_selection)
# confirmed cases (base_counties) and deaths (points)
return (base_state + base_state_counties + points)
def make_plot():
def mds_special():
font = "Arial"
axisColor = "#000000"
gridColor = "#DEDDDD"
return {
"config": {
"title": {
"fontSize": 24,
"font": font,
"anchor": "start", # equivalent of left-aligned.
"fontColor": "#000000"
},
'view': {
"height": 300,
"width": 400
},
"axisX": {
"domain": True,
#"domainColor": axisColor,
"gridColor": gridColor,
"domainWidth": 1,
"grid": False,
"labelFont": font,
"labelFontSize": 12,
"labelAngle": 0,
"tickColor": axisColor,
"tickSize":
5, # default, including it just to show you can change it
"titleFont": font,
"titleFontSize": 16,
"titlePadding":
10, # guessing, not specified in styleguide
"title": "X Axis Title (units)",
},
"axisY": {
"domain": False,
"grid": True,
"gridColor": gridColor,
"gridWidth": 1,
"labelFont": font,
"labelFontSize": 14,
"labelAngle": 0,
#"ticks": False, # even if you don't have a "domain" you need to turn these off.
"titleFont": font,
"titleFontSize": 16,
"titlePadding":
10, # guessing, not specified in styleguide
"title": "Y Axis Title (units)",
# titles are by default vertical left of axis so we need to hack this
#"titleAngle": 0, # horizontal
#"titleY": -10, # move it up
#"titleX": 18, # move it to the right so it aligns with the labels
},
}
}
# register the custom theme under a chosen name
alt.themes.register('mds_special', mds_special)
# enable the newly registered theme
alt.themes.enable('mds_special')
#alt.themes.enable('none') # to return to default
# Create a plot of the Displacement and the Horsepower of the cars dataset
# making the slider
slider = alt.binding_range(min=0, max=23, step=1)
select_hour = alt.selection_single(name='hour',
fields=['hour'],
bind=slider,
init={'hour': 0})
chart = alt.Chart(df_t4).mark_bar().encode(
x=alt.X('Category:N',
title="Crime category",
axis=alt.Axis(labelAngle=0)),
y=alt.Y('count()', title="Count", scale=alt.Scale(domain=(0, 3300))),
tooltip='count()').properties(
title="Per hour crime occurrences for the top 4 crimes",
width=600,
height=400).add_selection(select_hour).transform_filter(
select_hour)
return chart
def gen_map_interactive(log_prob_fn, points):
'''Generates choropleth map'''
geojsonfile = 'https://raw.githubusercontent.com/seattleio/seattle-boundaries-data/master/data/neighborhoods.geojson'
# First get the map
geojson = download_json(geojsonfile)
gdf = gpd.GeoDataFrame.from_features(geojson)
gdf['centroid_lat'] = [pt.centroid.x for pt in gdf['geometry']]
gdf['centroid_long'] = [pt.centroid.y for pt in gdf['geometry']]
# Only keep some neighborhoods (adhoc zoom in)
nhood_names_to_keep = ['Belltown', 'Central Business District', 'Minor', 'Broadway',
'Stevens', 'South Lake Union', 'Laurelhurst', 'Eastlake',
'First Hill', 'International District', 'Pioneer Square',
'Westlake', 'Lower Queen Anne', 'University District',
'Pike-Market', 'Stevens', 'Wallingford', 'Fremont',
'West Woodland', 'Adams', 'Lawton Park', 'Interbay', 'Lawton Park',
'Briarcliff', 'Southeast Magnolia', 'North Queen Anne',
'West Queen Anne', 'East Queen Anne', 'Portage Bay', 'Montlake',
'Madison Park', 'Harrison - Denny-Blaine', 'Ravenna', 'Bryant',
'Windermere', 'Roosevelt', 'Green Lake', 'Phinney Ridge',
'Sunset Hill', 'Loyal Heights', 'Whittier Heights', 'Mann',
'Madrona', 'Yesler Terrace', 'Atlantic', 'International District',
'Leschi', 'Industrial District', 'North Beacon Hill',
'Mount Baker', 'Harbor Island']
# Get a reduced gdf with just the above neighborhoods
gdf = gdf.copy().loc[gdf['name'].isin(nhood_names_to_keep)]
# Get densities from KDE for centroids
centroids = np.stack([gdf['centroid_long'], gdf['centroid_lat']]).T
centroids = torch.from_numpy(centroids)
density = torch.exp(log_prob_fn(centroids))
density = density / torch.max(density)
gdf['density'] = density
slider = alt.binding_range(min=1, max=x_svgd_df['iteration'].max() - 1, step=1,
name='Move stations with slider')
select_iter = alt.selection_single(name='iteration',
bind=slider, init={'iteration': 0}
)
# Add Base Layer
base = alt.Chart(gdf).mark_geoshape(
stroke='black',
strokeWidth=1
).encode(
).properties(
width=400,
height=400
)
# Add Choropleth Layer
chloro = alt.Chart(gdf).mark_geoshape(
stroke='black'
).encode(
alt.Color('density',
type='quantitative',
scale=alt.Scale(scheme='cividis', domain=(0, 1))
)
)
# Add points on top of the chart
scatter = alt.Chart(points).mark_circle(color='purple', opacity=0.7, stroke='gray').encode(
latitude='lat:Q',
longitude='long:Q',
).add_selection(
select_iter
).transform_filter(
select_iter
)
return base + chloro + scatter
"""
US Population Over Time
=======================
This chart visualizes the age distribution of the US population over time.
It uses a slider widget that is bound to the year to visualize the age
distribution over time.
"""
# category: case studies
import altair as alt
from vega_datasets import data
source = data.population.url
pink_blue = alt.Scale(domain=('Male', 'Female'), range=["steelblue", "salmon"])
slider = alt.binding_range(min=1900, max=2000, step=10)
select_year = alt.selection_single(name="year", fields=['year'], bind=slider)
alt.Chart(source).mark_bar().encode(
x=alt.X('sex:N', axis=alt.Axis(title=None)),
y=alt.Y('people:Q', scale=alt.Scale(domain=(0, 12000000))),
color=alt.Color('sex:N', scale=pink_blue),
column='age:O').properties(
width=20).add_selection(select_year).transform_calculate(
"sex", alt.expr.if_(alt.datum.sex == 1, "Male",
"Female")).transform_filter(select_year)
Rounded_IMDB_Rating="floor(datum.IMDB_Rating)",
Hundred_Million_Production=
"datum.Production_Budget > 100000000.0 ? 100 : 10",
Release_Year="year(datum.Release_Date)").transform_filter(
alt.datum.IMDB_Rating > 0).transform_filter(
alt.FieldOneOfPredicate(
field='MPAA_Rating',
oneOf=ratings)).encode(x=alt.X(
'Worldwide_Gross:Q',
scale=alt.Scale(domain=(100000, 10**9),
clamp=True)),
y='IMDB_Rating:Q',
tooltip="Title:N")
# A slider filter
year_slider = alt.binding_range(min=1969, max=2018, step=1)
slider_selection = alt.selection_single(bind=year_slider,
fields=['Release_Year'],
name="Release Year_")
filter_year = base.add_selection(slider_selection).transform_filter(
slider_selection).properties(title="Slider Filtering")
# A dropdown filter
genre_dropdown = alt.binding_select(options=genres)
genre_select = alt.selection_single(fields=['Major_Genre'],
bind=genre_dropdown,
name="Genre")
filter_genres = base.add_selection(genre_select).transform_filter(
genre_select).properties(title="Dropdown Filtering")
US Population Over Time
=======================
This chart visualizes the age distribution of the US population over time.
It uses a slider widget that is bound to the year to visualize the age
distribution over time.
"""
# category: case studies
import altair as alt
from vega_datasets import data
source = data.population.url
pink_blue = alt.Scale(domain=('Male', 'Female'),
range=["steelblue", "salmon"])
slider = alt.binding_range(min=1900, max=2000, step=10)
select_year = alt.selection_single(name="year", fields=['year'], bind=slider)
alt.Chart(source).mark_bar().encode(
x=alt.X('sex:N', axis=alt.Axis(title=None)),
y=alt.Y('people:Q', scale=alt.Scale(domain=(0, 12000000))),
color=alt.Color('sex:N', scale=pink_blue),
column='age:O'
).properties(
width=20
).add_selection(
select_year
).transform_calculate(
"sex", alt.expr.if_(alt.datum.sex == 1, "Male", "Female")
).transform_filter(
select_year
alt.Y('life_expect:Q', scale=alt.Scale(domain=[0,90])),
alt.Size('pop:Q', scale=alt.Scale(domain=[0, 1200000000], range=[0,1000])),
alt.Color('cluster:N', legend=None),
alt.OpacityValue(0.5),
alt.Tooltip('country:N'),
alt.Order('pop:Q', sort='descending')
).add_selection(select_year).transform_filter(select_year)
st.altair_chart(chart)
Drag the slider back and forth to see how the data values change over time!
'''
select_year = alt.selection_single(
name='select', fields=['year'], init={'year': 1955},
bind=alt.binding_range(min=1955, max=2005, step=5)
)
chart = alt.Chart(data).mark_point(filled=True).encode(
alt.X('fertility:Q', scale=alt.Scale(domain=[0,9])),
alt.Y('life_expect:Q', scale=alt.Scale(domain=[0,90])),
alt.Size('pop:Q', scale=alt.Scale(domain=[0, 1200000000], range=[0,1000])),
alt.Color('cluster:N', legend=None),
alt.OpacityValue(0.5),
alt.Tooltip('country:N'),
alt.Order('pop:Q', sort='descending')
).add_selection(select_year).transform_filter(select_year)
st.altair_chart(chart)
st.header("Graphical Marks")
# Topographic information
us_states = alt.topo_feature(topo_usa, 'states')
us_counties = alt.topo_feature(topo_usa, 'counties')
# state borders
base_states = alt.Chart(us_states).mark_geoshape().encode(
stroke=alt.value('lightgray'), fill=alt.value('white')).properties(
width=1200,
height=960,
).project(type='albersUsa', )
# Slider choices
min_day_num = column_values[0]
max_day_num = column_values[len(column_values) - 1]
slider = alt.binding_range(min=min_day_num, max=max_day_num, step=1)
slider_selection = alt.selection_single(fields=['day_num'],
bind=slider,
name="day_num",
init={'day_num': max_day_num})
# Confirmed cases by county
base_counties = alt.Chart(us_counties).mark_geoshape(
stroke='black',
strokeWidth=0.05).project(type='albersUsa').transform_lookup(
lookup='id', from_=alt.LookupData(pdf_usa_conf, 'fips', column_names)
).transform_fold(
column_names,
as_=['day_num', 'confirmed_per100K']).transform_calculate(
day_num='parseInt(datum.day_num)',
confirmed_per100K=
from altair import datum
pn.extension('vega')
#alt.renderers.enable('altair_viewer')
alt.data_transformers.disable_max_rows()
hv.extension("bokeh")
medal_count_year_withCate = pd.read_csv("medal_count_year_withCate.csv")
medal_count_year_top10 = medal_count_year_withCate.loc[medal_count_year_withCate["Order"]<=10]
year_unique = medal_count_year_top10["Year"].unique().tolist()
name_unique = medal_count_year_top10["name"].unique().tolist()
heatmap = hv.HeatMap(medal_count_year_top10, ["Year", "name"],["Medal"])
heatmap.opts(opts.HeatMap(radial=True,colorbar=True, start_angle=np.pi/2, width=500, height=500,
yticks=None,xticks=year_unique,tools=['hover'],toolbar='above'))
slider_year = alt.binding_range(min=1896, max=2016, step=4, name='Year:')
selector_year = alt.selection_single(fields=['Year'],bind=slider_year, init={'Year': 2016})
select_country = alt.selection(type="single", fields=['Year'])
olympic_bar = alt.Chart(medal_count_year_withCate).mark_bar(opacity=0.8).encode(
x=alt.X(field="name", type='nominal', title="country",sort = '-y',
axis=alt.Axis(labelFontSize=10,titleFontSize=15,labelAngle=-45)),
y=alt.Y(field="MedalByCate",type="quantitative",aggregate='sum',stack='zero',title="Total Medals",
axis=alt.Axis(labelFontSize=10,titleFontSize=15)),
color=alt.Color(field = 'MedalCate', type = 'nominal',
scale = alt.Scale(domain = ["Gold","Silver","Bronze"],range=['gold', 'silver','sienna']),
legend=alt.Legend(title="Medal Category",labelFontSize = 15,symbolSize = 30,titleFontSize=10)),
order=alt.Order('MedalCateOrder',sort='ascending')
)
# text
