We Keep Coding

In Bokeh, how can I display different information for points and patches?

I want to display different information for different layers (points and patches) using bokeh.
I downloaded the shapefile and the population information of Haitian cities respectively from here and from here and I merged them.
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import geopandas as gpd
import osmnx as ox
from bokeh.layouts import row, column
from bokeh.models import Select
from bokeh.palettes import Spectral5
from bokeh.plotting import curdoc, figure, save
from bokeh.sampledata.autompg import autompg_clean as df
from bokeh.io import show
from bokeh.models import LogColorMapper
from bokeh.palettes import Viridis6 as palette
from bokeh.plotting import figure
from bokeh.models import ColumnDataSource
from bokeh.sampledata.us_counties import data as counties
from bokeh.sampledata.unemployment import data as unemployment
import pandas as pd
import geopandas as gpd
import shapely
color_mapper = LogColorMapper(palette=palette)
Some functions
def getPolyCoords(row, geom, coord_type):
"""Returns the coordinates ('x' or 'y') of edges of a Polygon exterior"""
# Parse the exterior of the coordinate
exterior = row[geom].exterior
if coord_type == 'x':
# Get the x coordinates of the exterior
return list( exterior.coords.xy[0] )
elif coord_type == 'y':
# Get the y coordinates of the exterior
return list( exterior.coords.xy[1] )
def getPointCoords(row, geom, coord_type):
"""Calculates coordinates ('x' or 'y') of a Point geometry"""
if coord_type == 'x':
return row[geom].x
elif coord_type == 'y':
return row[geom].y
Cities data
haiti = gpd.read_file(hti_admbnda_adm2_cnigs_20181129.shp')
haiti = haiti.to_crs({'init': 'epsg:32618'})
haiti = haiti[haiti.index != 98].reset_index(drop=True) ## i=98 is corrupted
pop = pd.read_csv('hti_admnbnda_adm2_cnigs2013c.csv')
level = 2
left = 'adm%dcode'%level
right = 'ADM%d_PCODE'%level
h_geom = pd.merge(pop, haiti, left_on=left, right_on=right)
Then I created a data for bokeh
grid = pd.DataFrame()
grid['x'] = h_geom.apply(getPolyCoords, geom='geometry', coord_type='x', axis=1)
grid['y'] = h_geom.apply(getPolyCoords, geom='geometry', coord_type='y', axis=1)
grid['Name'] = h_geom['adm2_en']
grid['Population'] = h_geom['TOTAL']
data=dict(
x=list(grid['x'].values),
y=list(grid['y'].values),
name=list(grid['Name'].values),
rate=list(grid['Population'].values),
)
From osmnx I get points of schools
selected_amenities = ['school']
place = 'Haiti'
schoolOSM = ox.pois_from_place(place=place, amenities=selected_amenities)
schools = gpd.GeoDataFrame(schoolOSM)
idxok = []
for i in schools.index:
if type(schools['geometry'][i]) == shapely.geometry.point.Point:
idxok.append(i)
schools = schools[schools.index.isin(idxok)]
schools['x'] = schools.apply(getPointCoords, geom='geometry', coord_type='x', axis=1)
schools['y'] = schools.apply(getPointCoords, geom='geometry', coord_type='y', axis=1)
data1=dict(
x=list(schools['x'].values),
y=list(schools['y'].values),
)
Then I want to show the information: I would like to show Name, Population and coordinates for cities while only coordinates for schools.
TOOLS = "pan,wheel_zoom,reset,hover,save"
p = figure(title="Schools Point in Haiti", tools=TOOLS,
x_axis_location=None, y_axis_location=None,
tooltips=[("Name", "#name"), ("Population", "#rate"), ("(Long, Lat)", "($x, $y)")])
p.hover.point_policy = "follow_mouse"
p.patches('x', 'y', source=data,
fill_color={'field': 'rate', 'transform': color_mapper},
fill_alpha=1.0, line_color="black", line_width=1)
# Add points on top (as black points)
p.circle('x', 'y', size=3, source=data1, color="black")
show(p)
In doing so I get the information of Name, Population, Long, Lat for both Schools and Cities. But Schools do not have the info Name and Population, so I get something like

You need to create two separate data sources and two separate HoverTools.
from bokeh.models import HoverTool
data_cities = dict(x = list(cities['x'].values), y = list(cities['y'].values))
data_schools = dict(x = list(schools['x'].values), y = list(schools['y'].values))
cities = p.circle('x', 'y', size = 3, source = data_cities, color = "green")
schools = p.circle('x', 'y', size = 3, source = data_schools, color = "blue")
hover_cities = HoverTool(renderers = [cities], tooltips = [("Name", "#name"), ("Population", "#rate"), ("(Long, Lat)", "($x, $y)")]))
hover_schools = HoverTool(renderers = [schools], tooltips = [("(Long, Lat)", "($x, $y)")]))
p.add_tools(hover_cities)
p.add_tools(hover_schools)

bokeh hover multiline with datetime axis

I want to create a multiline Bokeh plot with datetime axis and a hover tool that shows the datetime of the data point. This should be supported and I have tried to obtain the intended behaviour in two ways:
Use hover.formatters to format the x-value. This has no effect on the plot.
Add a description variable with the correctly formatted date/time values. This results in a hover tool where all date/time values are displayed in a list for each point.
I have included a smaller example of my code that illustrates my approach and the result. It is used in conjunction with a checkboxgroup that updates the data. This is why a new ColumnDataSource is made from the dataframe.
import pandas as pd
import numpy as np
from bokeh.io import output_file, show
from bokeh.plotting import figure
from bokeh.models import HoverTool, ColumnDataSource
from bokeh.palettes import Spectral4
from bokeh.layouts import column
#output_file("demo.html")
available_quant = ["LACTIC_ACID", "GLUCOSE", "XYLOSE", "FORMIC_ACID"]
quant_legend = ["Lactic acid", "Glucose", "Xylose", "Formic acid"]
Create a dataframe with 4 quantities and the time
datelist = pd.date_range(end = pd.datetime.today(), periods=100).tolist()
desc = datelist
for i, date in enumerate(datelist):
desc[i] = str(date)
RT_x = np.linspace(-5, 5, num=100)
lactic = RT_x**2
data = {'time': datelist, 'desc': desc, 'LACTIC_ACID': RT_x**2 + 2, 'GLUCOSE': RT_x**2, 'XYLOSE': RT_x**2 - 2, 'FORMIC_ACID': RT_x**2 - 4}
df = pd.DataFrame.from_dict(data)
df['time'] = pd.to_datetime(df['time'], format = "%Y-%m-%d %H:%M:%S")
Copy the relevant data to a columndatasource
substance_colors = Spectral4
quant_to_plot = available_quant
xs = []
ys = []
xsprint = []
colors = []
labels = []
for i, substance in enumerate(quant_to_plot):
xs.append(list(df['time']))
ys.append(list(df[substance]))
xsprint.append(list(df['desc']))
index = available_quant.index(substance)
colors.append(substance_colors[index])
labels.append(quant_legend[index])
new_src = ColumnDataSource(data={'x': xs, 'y': ys, 'desc': xsprint, 'color': colors, 'label': labels})
Make the first plot using hover.formatters
p = figure(plot_width=800, plot_height=400, x_axis_type="datetime", title = 'Demo', x_axis_label = 'Time', y_axis_label = 'c [g/mL]')
p.multi_line('x','y', color = 'color', legend = 'label', source = new_src)
hover = HoverTool(tooltips=[('Type','#label'),
('Time','$x'),
('Conc','$y')],
formatters={'Time': 'datetime'},
mode = 'mouse',
line_policy='next')
p.add_tools(hover)
p.legend.location = "top_left"
p.legend.orientation = "horizontal"
Make second plot using description variable
p2 = figure(plot_width=800, plot_height=400, x_axis_type="datetime", title = 'Demo', x_axis_label = 'Time', y_axis_label = 'c [g/mL]')
p2.multi_line('x','y', color = 'color', legend = 'label', source = new_src)
hover = HoverTool(tooltips=[('Type','#label'),
('Time','#desc'),
('Conc','$y')],
mode = 'mouse',
line_policy='nearest')
p2.add_tools(hover)
mylayout = column(p, p2)
show(mylayout)
Am I missing something trivial? I am running Bokeh 0.13.0 and python 3.6.4.

The first approach works with the following modification of the hovertool:
hover = HoverTool(tooltips=[('Type','#label'),
('Time','$x{%F}'),
('Conc','$y')],
formatters={'$x': 'datetime'},
mode = 'mouse',
line_policy='nearest')

How to update Pretext in Bokeh with a Select tool

I have a bokeh plot that updates my plot through a select tool. The select tool contains subjects that update the plot where the values are x='Polarity'and y='Subjectivity'.
Here is a dummy data for what I want:
import pandas as pd
import random
list_type = ['All', 'Compliment', 'Sport', 'Remaining', 'Finance', 'Infrastructure', 'Complaint', 'Authority',
'Danger', 'Health', 'English']
df = pd.concat([pd.DataFrame({'Subject' : [list_type[i] for t in range(110)],
'Polarity' : [random.random() for t in range(110)],
'Subjectivity' : [random.random() for t in range(110)]}) for i in range(len(list_type))], axis=0)
My code for updating the plot looks like this:
options = []
options.append('All')
options.extend(df['Subject'].unique().tolist())
source = ColumnDataSource(df)
p = figure()
r = p.circle(x='Polarity', y='Subjectivity', source = source)
select = Select(title="Subject", options=options, value="All")
output_notebook()
def update_plot(attr, old, new):
if select.value=="All":
df_filter = df.copy()
else:
df_filter = df[df['Subject']==select.value]
source1 = ColumnDataSource(df_filter)
r.data_source.data = source1.data
select.on_change('value', update_plot)
layout = column(row(select, width=400), p)
#show(layout)
curdoc().add_root(layout)
I want to add a 'Pretext' that has a df.describe(), that can update with the plot through the select tool. I tried this by adding these codes but it displays nothing:
stats = PreText(text='', width=500)
t1 = select.value
def update_stats(df, t1):
stats.text = str(df[[t1, select.value+'_returns']].describe())
select.on_change('value', update_plot, update_stats)
layout = column(row(select, width=400), p, stats)
curdoc().add_root(layout)
show(layout)
Anyone know a solution? Thanks!

You don't need two separate function for that, you can just change your original function update_plot to add statement to change the text for PreText as stats.text = str(df_filter.describe()). The function will look as below -
def update_plot(attr, old, new):
if select.value=="All":
df_filter = df.copy()
else:
df_filter = df[df['Subject']==select.value]
source1 = ColumnDataSource(df_filter)
r.data_source.data = source1.data
stats.text = str(df_filter.describe())
Entire code
from bokeh.models.widgets import Select, PreText
from bokeh.layouts import column, row
from bokeh.models import ColumnDataSource
from bokeh.plotting import figure, curdoc
from bokeh.plotting import figure, show
import pandas as pd
import random
list_type = ['All', 'Compliment', 'Sport', 'Remaining', 'Finance', 'Infrastructure', 'Complaint', 'Authority',
'Danger', 'Health', 'English']
df = pd.concat([pd.DataFrame({'Subject' : [list_type[i] for t in range(110)],
'Polarity' : [random.random() for t in range(110)],
'Subjectivity' : [random.random() for t in range(110)]}) for i in range(len(list_type))], axis=0)
options = []
options.append('All')
options.extend(df['Subject'].unique().tolist())
source = ColumnDataSource(df)
p = figure()
r = p.circle(x='Polarity', y='Subjectivity', source = source)
select = Select(title="Subject", options=options, value="All")
#output_notebook()
stats = PreText(text=str(df.describe()), width=500)
def update_plot(attr, old, new):
if select.value=="All":
df_filter = df.copy()
else:
df_filter = df[df['Subject']==select.value]
source1 = ColumnDataSource(df_filter)
r.data_source.data = source1.data
stats.text = str(df_filter.describe())
select.on_change('value', update_plot)
layout = column(row(select, width=400), p, stats)
#show(layout)
curdoc().add_root(layout)

Changing colors on bokeh patches plot real time

I'm trying to create a bokeh plot of the US States, and color each of the state according to some data. Now using this tutorial I managed to create this, but I also want to enhance it, and add a slider to it, to change the values displayed. For example like displaying separate years.
With the help of this tutorial, I managed to add the slider, and the underlying data does change, according to the hover text, but the colors aren't recalculated, and so the visual representation does not match the values.
This is the code I've used, from a Jupyter notebook, so anybody who wants to try can reproduce
from bokeh.io import show, output_notebook
from bokeh.models import (
ColumnDataSource,
HoverTool,
LogColorMapper,
Range1d, CustomJS, Slider
)
from bokeh.palettes import Inferno256 as palette
from bokeh.plotting import figure
from bokeh.layouts import row, widgetbox
from bokeh.sampledata.us_counties import data as counties
from bokeh.sampledata.us_states import data as states
from bokeh.sampledata.unemployment import data as unemployment
import pandas as pd
import random
output_notebook()
palette.reverse()
states_accumulated ={}
available_state_codes = states.keys()
for key, value in counties.items():
state_name = value["state"].upper()
if state_name in states.keys() and "number" not in states[state_name]:
states[state_name]["number"] = key[0]
for key,state in states.items():
state["code"] = key
state_list = []
for key,state in states.items():
state_list.append(state)
unemployment_transf = []
for key,value in unemployment.items():
unemployment_transf.append({
"State":key[0],
"County":key[1],
"Value":value
})
unemp_df = pd.DataFrame(unemployment_transf)
unemp_sum = unemp_df.groupby("State").mean()["Value"]
unemp_sum = unemp_sum.sort_index()
unemp_sum_flat = {key:value for key, value in unemp_sum.items()}
for state in state_list:
state["value"] = unemp_sum_flat[state["number"]]
state_df = pd.DataFrame(state_list)
color_mapper = LogColorMapper(palette=palette)
state_xy = (list(state_df["lons"].values),list(state_df["lats"].values))
max_x = max([max(l) for l in state_xy[0]])
max_y = max([max(l) for l in state_xy[1]])
min_x = min([min(l) for l in state_xy[0]])
min_y = min([min(l) for l in state_xy[1]])
data=dict(
x=state_xy[0],
y=state_xy[1],
name=list(state_df["name"].values),
used = list(state_df["value"].values)
)
data['1999'] = list(state_df["value"].values)
data['2000'] = [random.randrange(0,10) for i in range(len(state_xy[0]))]
source = ColumnDataSource(data)
TOOLS = "pan,wheel_zoom,reset,hover,save"
p = figure(
title="States", tools=TOOLS,
x_axis_location=None, y_axis_location=None
)
p.width=450
p.height = 450
p.x_range= Range1d(-170,-60)
p.y_range = Range1d(min_y-10,max_y+10)
p.grid.grid_line_color = None
renderer = p.patches('x', 'y', source=source,
fill_color={'field': 'used', 'transform': color_mapper},
fill_alpha=0.7, line_color="white", line_width=0.5)
hover = p.select_one(HoverTool)
hover.point_policy = "follow_mouse"
hover.tooltips = [
("Name", "#name"),
("Unemployment rate)", "#used%"),
("(Long, Lat)", "($x, $y)"),
]
callback = CustomJS(args=dict(source=source,plot=p,color_mapper = color_mapper,renderer = renderer), code="""
var data = source.data;
var year = year.value;
used = data['used']
should_be = data[String(year)]
for (i = 0; i < should_be.length; i++) {
used[i] = should_be[i];
}
""")
year_slider = Slider(start=1999, end=2000, value=1999, step=1,
title="year", callback=callback)
callback.args["year"] = year_slider
layout = row(
p,
widgetbox(year_slider),
)
show(layout)
Sample images of the plot:
What I would like to accomplish, is that when I change the slider, the colors on the plot should change. Now I think the JS callback should call some kind of redraw or recalculate, but I haven't found any documentation about it. Is there a way to do this?

append source.change.emit() to the Javascipt code to trigger the change event.

Appending source.trigger("change"); to the CustomJS seems to solve the problem, now as the slider changes, the colors change.

Slicing data in Bokeh callback to produce dashboard-like interactions

I am trying to produce a dashboard like interactions for my bar chart using callback function without using bokeh serve functionality. Ultimately, I would like to be able to change the plot if any of the two drop-down menus is changed. So far this only works when threshold value is hard-coded. I only know how to extract cb_obj value but not from dropdown that is not actually called. I have looked at this and this answer to formulate first attempt.
Here is my code:
from bokeh.io import show, output_notebook, output_file
from bokeh.models import ColumnDataSource, Whisker
from bokeh.plotting import figure
from bokeh.transform import factor_cmap
from bokeh.models import CustomJS, ColumnDataSource, Slider, Select
from bokeh.layouts import column
import numpy as np
import pandas as pd
def generate_data(factor=10):
rawdata = pd.DataFrame(np.random.rand(10,4)*factor, columns = ["A","B","C","D"])
idx = pd.MultiIndex.from_product([["Exp "+str(i) for i in range(5)],
[20,999]],names=["Experiment","Threshold"])
rawdata.index = idx
return rawdata.reset_index()
# Generate data
output_notebook()
count_data = generate_data()
error_data = generate_data(factor=2)
groups = ["A","B","C","D"]
initial_counts = count_data[(count_data.Experiment == "Exp 0")
& (count_data.Threshold == 20)][["A","B","C","D"]].values[0]
initial_errors = error_data[(error_data.Experiment == "Exp 0")
& (error_data.Threshold == 20)][["A","B","C","D"]].values[0]
# Create primary sources of data
count_source = ColumnDataSource(data=count_data)
error_source = ColumnDataSource(data=error_data)
# Create plotting source of data
source = ColumnDataSource(data=dict(groups=groups, counts=initial_counts,
upper=initial_counts+initial_errors,
lower=initial_counts-initial_errors))
# Bar chart and figure
p = figure(x_range=groups, plot_height=350, toolbar_location=None, title="Values", y_range=(0,20))
p.vbar(x='groups', top='counts', width=0.9, source=source, legend="groups",
line_color='white', fill_color=factor_cmap('groups', palette=["#962980","#295f96","#29966c","#968529"],
factors=groups))
# Error bars
p.add_layout(
Whisker(source=source, base="groups", upper="upper", lower="lower", level="overlay")
)
def callback(source=source, count_source = count_source, error_source=error_source, window=None):
def slicer(data_source, experiment, threshold, dummy_col, columns):
""" Helper function to enable lookup of data."""
count = 0
for row in data_source[dummy_col]:
if (data_source["Experiment"][count] == experiment) & (data_source["Threshold"][count] == threshold):
result = [data_source[col][count] for col in columns]
count+=1
return result
# Initialise data sources
data = source.data
count_data = count_source.data
error_data = error_source.data
# Initialise values
experiment = cb_obj.value
threshold = 20
counts, upper, lower = data["counts"], data["upper"], data["lower"]
tempdata = slicer(count_data, experiment, threshold,"Experiment", ["A","B","C","D"])
temperror = slicer(error_data, experiment, threshold,"Experiment", ["A","B","C","D"])
# Select values and emit changes
for i in range(len(counts)):
counts[i] = tempdata[i]
for i in range(len(counts)):
upper[i] = counts[i]+temperror[i]
lower[i] = counts[i]-temperror[i]
source.change.emit()
exp_dropdown = Select(title="Select:", value="Exp 0", options=list(count_data.Experiment.unique()))
thr_dropdown = Select(title="Select:", value="12", options=list(count_data.Threshold.astype(str).unique()))
exp_dropdown.callback = CustomJS.from_py_func(callback)
p.xgrid.grid_line_color = None
p.legend.orientation = "horizontal"
p.legend.location = "top_center"
layout = column(exp_dropdown,thr_dropdown, p)
show(layout)

The solution to the question is that Select menu needs to be defined before callback function. This code works:
from bokeh.io import show, output_notebook, output_file
from bokeh.models import ColumnDataSource, Whisker
from bokeh.plotting import figure
from bokeh.transform import factor_cmap
from bokeh.models import CustomJS, ColumnDataSource, Slider, Select
from bokeh.layouts import column
import numpy as np
import pandas as pd
def generate_data(factor=10):
rawdata = pd.DataFrame(np.random.rand(10,4)*factor, columns = ["A","B","C","D"])
idx = pd.MultiIndex.from_product([["Exp "+str(i) for i in range(5)],
[20,999]],names=["Experiment","Threshold"])
rawdata.index = idx
return rawdata.reset_index()
# Generate data
output_notebook()
count_data = generate_data()
error_data = generate_data(factor=2)
groups = ["A","B","C","D"]
initial_counts = count_data[(count_data.Experiment == "Exp 0")
& (count_data.Threshold == 20)][["A","B","C","D"]].values[0]
initial_errors = error_data[(error_data.Experiment == "Exp 0")
& (error_data.Threshold == 20)][["A","B","C","D"]].values[0]
# Create primary sources of data
count_source = ColumnDataSource(data=count_data)
error_source = ColumnDataSource(data=error_data)
# Create plotting source of data
source = ColumnDataSource(data=dict(groups=groups, counts=initial_counts,
upper=initial_counts+initial_errors,
lower=initial_counts-initial_errors))
# Bar chart and figure
p = figure(x_range=groups, plot_height=350, toolbar_location=None, title="Values", y_range=(0,20))
p.vbar(x='groups', top='counts', width=0.9, source=source, legend="groups",
line_color='white', fill_color=factor_cmap('groups', palette=["#962980","#295f96","#29966c","#968529"],
factors=groups))
# Error bars
p.add_layout(
Whisker(source=source, base="groups", upper="upper", lower="lower", level="overlay")
)
exp_dropdown = Select(title="Select:", value="Exp 0", options=list(count_data.Experiment.unique()))
thr_dropdown = Select(title="Select:", value="20", options=list(count_data.Threshold.astype(str).unique()))
def callback(source=source, count_source = count_source, error_source=error_source, exp_dropdown = exp_dropdown,
thr_dropdown=thr_dropdown,window=None):
def slicer(data_source, experiment, threshold, dummy_col, columns):
""" Helper function to enable lookup of data."""
count = 0
for row in data_source[dummy_col]:
if (data_source["Experiment"][count] == experiment) & (data_source["Threshold"][count] == threshold):
result = [data_source[col][count] for col in columns]
count+=1
return result
# Initialise data sources
data = source.data
count_data = count_source.data
error_data = error_source.data
# Initialise values
experiment = exp_dropdown.value
threshold = thr_dropdown.value
counts, upper, lower = data["counts"], data["upper"], data["lower"]
tempdata = slicer(count_data, experiment, threshold,"Experiment", ["A","B","C","D"])
temperror = slicer(error_data, experiment, threshold,"Experiment", ["A","B","C","D"])
# Select values and emit changes
for i in range(len(counts)):
counts[i] = tempdata[i]
for i in range(len(counts)):
upper[i] = counts[i]+temperror[i]
lower[i] = counts[i]-temperror[i]
source.change.emit()
exp_dropdown.callback = CustomJS.from_py_func(callback)
thr_dropdown.callback = CustomJS.from_py_func(callback)
p.xgrid.grid_line_color = None
p.legend.orientation = "horizontal"
p.legend.location = "top_center"
layout = column(exp_dropdown,thr_dropdown, p)
show(layout)