I tried to specify x and y axis ticks on Bokeh plot as [0,25,50,75,100] and try major_label_overrides x as distance {0:'alone(0)',25: 'not close(25)', 50: 'alright close(50)', 75: 'middle close(75)', 100:'very close(100)'}, y axis custom as frequency {0:'never',25: 'once a year', 50: 'once a month', 75: 'once a week', 100:'everyday(100)'}. However, it shows an error. Thank you.
ValueError: expected an instance of type Ticker, got [25, 50, 75, 100]
of type list
I have tried
p.xaxis.ticker = FixedTicker(ticks=[0, 25, 50,75,100])
it fixes the tick problem but I can't customise it to frequency.
Below is my code and github repository.
https://github.com/Lastget/Covid19_Job_risks.git
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from bokeh.io import output_file, show
from bokeh.plotting import figure
from bokeh.models import ColumnDataSource, Select
from bokeh.models import HoverTool, Label, LabelSet
from bokeh.io import curdoc
from bokeh.layouts import row
from bokeh.models.renderers import GlyphRenderer
from math import pi
from bokeh.models import FixedTicker
# Improt files
expose = pd.read_csv(r'Exposed_to_Disease_or_Infections.csv',encoding='gbk')
expose.head() #context, code, occupation
expose.shape #(968,3)
physical = pd.read_csv('Physical_Proximity.csv')
physical.head()
physical.shape #(967,3)
TW_job = pd.read_excel('Small_Chinese.xlsx',encoding='utf-8')
TW_job.shape #(968,3)
TW_job = TW_job.iloc[:,:2]
TW_job.head()
#Merge
temp_df = pd.merge(expose,physical,on=['Code','Occupation'])
temp_df.head()
temp_df.columns=['Expose_frequency','Code','Occupation','Physical_proximity']
temp_df.head()
full_table = temp_df.merge(TW_job,how='left',on='Code')
full_table.shape #967,5
# Delete Expose frequency for Rock splitter, timing deivce
full_table = full_table.iloc[:965,:]
# change expose to int64
full_table['Expose_frequency']=full_table['Expose_frequency'].astype('int64')
full_table.info()
# Start plotting
source = ColumnDataSource(full_table)
p = figure(title="各職業對新型冠狀病毒之風險圖", x_axis_label='工作時與人接近程度', y_axis_label='工作時暴露於疾病頻率',
plot_width=900, plot_height=600)
p.circle('Physical_proximity','Expose_frequency',
name = 'allcircle',
size=10,fill_alpha=0.2, source=source, fill_color='gray', hover_fill_color='firebrick', hover_line_color="firebrick", line_color=None)
hover = HoverTool(tooltips=[('職業','#TW_Occupation'),('Occupation','#Occupation'),('暴露於疾病指數','#Expose_frequency'),('與人接近距離指數','#Physical_proximity')])
p.add_tools(hover)
p.xaxis.ticker = [0, 25, 50,75,100]
p.xaxis.major_label_overrides = {0:'獨自工作(0)',25: '不近(25)', 50: '稍微近(50)', 75: '中等距離(75)', 100:'非常近(100)'}
p.yaxis.ticker = [0, 25, 50,75,100]
p.yaxis.major_label_overrides = {0:'從不(0)',25: '一年一次(25)', 50: '一個月一次(50)', 75: '一週一次(75)', 100:'每天(100)'}
p.yaxis.major_label_orientation = pi/4
# remove tool bar
p.toolbar.logo = None
p.toolbar_location = None
def remove_glyphs(figure, glyph_name_list):
renderers = figure.select(dict(type=GlyphRenderer))
for r in renderers:
if r.name in glyph_name_list:
col = r.glyph.y
r.data_source.data[col] = [np.nan] * len(r.data_source.data[col])
# Define a callback function
def update_plot(attr, old, new):
remove_glyphs(p,['point_select'])
old_choice=full_table[full_table['TW_Occupation']==old]
choice=full_table[full_table['TW_Occupation']==new]
a=choice['Physical_proximity']
b=choice['Expose_frequency']
p.circle(a,b,size=10,fill_alpha=1,fill_color=None,line_color="firebrick", name='point_select')
# Add Select
select = Select(title='請選擇工作', options=sorted(full_table['TW_Occupation'].tolist()), value='')
# Attach the update_plot callback to the 'value' property of select
select.on_change('value', update_plot)
#layout
layout = row(p, select)
# Add the plot to the current document
curdoc().add_root(layout)
Related
I'm trying to make a dropdown menu with Bokeh that highlights the points in clusters I found. I have the dropdown menu working, but now I want to be able to visualize another categorical variable by color: Noun Class with levels of Masc, Fem, and Neuter. The problem is that the legend won't update when I switch which cluster I'm visualizing. Furthermore, if the first cluster I visualize doesn't have all 3 noun classes in it, the code starts treating all the other clusters I try to look at as (incorrectly) having that first cluster's noun class. For example, if Cluster 0 is the default and only has Masc points, all other clusters I look at using the dropdown menu are treated as only having Masc points even if they have Fem or Neuter in the actual DF.
My main question is this: how can I update the legend such that it's only attending to the respective noun classes of 'Curr'
Here's some reproducible code:
import pandas as pd
from bokeh.io import output_file, show, output_notebook, save, push_notebook
from bokeh.models import ColumnDataSource, Select, DateRangeSlider, CustomJS
from bokeh.plotting import figure, Figure, show
from bokeh.models import CustomJS
from bokeh.layouts import row,column,layout
import random
import numpy as np
from bokeh.transform import factor_cmap
from bokeh.palettes import Colorblind
import bokeh.io
from bokeh.resources import INLINE
#Generate reproducible DF
noun_class_names = ["Masc","Fem","Neuter"]
x = [random.randint(0,50) for i in range(100)]
y = [random.randint(0,50) for i in range(100)]
rand_clusters = [str(random.randint(0,10)) for i in range(100)]
noun_classes = [random.choice(noun_class_names) for i in range(100)]
df = pd.DataFrame({'x_coord':x, 'y_coord':y,'noun class':noun_classes,'cluster labels':rand_clusters})
df.loc[df['cluster labels'] == '0', 'noun class'] = 'Masc' #ensure that cluster 0 has all same noun class to illustrate error
clusters = [str(i) for i in range(len(df['cluster labels'].unique()))]
cols1 = df#[['cluster labels','x_coord', 'y_coord']]
cols2 = cols1[cols1['cluster labels'] == '0']
Overall = ColumnDataSource(data=cols1)
Curr = ColumnDataSource(data=cols2)
#plot and the menu is linked with each other by this callback function
callback = CustomJS(args=dict(source=Overall, sc=Curr), code="""
var f = cb_obj.value
sc.data['x_coord']=[]
sc.data['y_coord']=[]
for(var i = 0; i <= source.get_length(); i++){
if (source.data['cluster labels'][i] == f){
sc.data['x_coord'].push(source.data['x_coord'][i])
sc.data['y_coord'].push(source.data['y_coord'][i])
sc.data['noun class'].push(source.data['noun class'][i])
sc.data['cluster labels'].push(source.data['cluster labels'][i])
}
}
sc.change.emit();
""")
menu = Select(options=clusters, value='0', title = 'Cluster #') # create drop down menu
bokeh_p=figure(x_axis_label ='X Coord', y_axis_label = 'Y Coord', y_axis_type="linear",x_axis_type="linear") #creating figure object
mapper = factor_cmap(field_name = "noun class", palette = Colorblind[6], factors = df['noun class'].unique()) #color mapper for noun classes
bokeh_p.circle(x='x_coord', y='y_coord', color='gray', alpha = .5, source=Overall) #plot all other points in gray
bokeh_p.circle(x='x_coord', y='y_coord', color=mapper, line_width = 1, source=Curr, legend_group = 'noun class') # plotting the desired cluster using glyph circle and colormapper
bokeh_p.legend.title = "Noun Classes"
menu.js_on_change('value', callback) # calling the function on change of selection
bokeh.io.output_notebook(INLINE)
show(layout(menu,bokeh_p), notebook_handle=True)
Thanks in advance and I hope you have a nice day :)
Imma keep it real with y'all... The code works how I want now and I'm not entirely sure what I did. What I think I did was reset the noun classes in the Curr data source and then update the legend label field after selecting a new cluster to visualize and updating the xy coords. If anyone can confirm or correct me for posterity's sake I would appreciate it :)
Best!
import pandas as pd
import random
import numpy as np
from bokeh.plotting import figure, Figure, show
from bokeh.io import output_notebook, push_notebook, show, output_file, save
from bokeh.transform import factor_cmap
from bokeh.palettes import Colorblind
from bokeh.layouts import layout, gridplot, column, row
from bokeh.models import ColumnDataSource, Slider, CustomJS, Select, DateRangeSlider, Legend, LegendItem
import bokeh.io
from bokeh.resources import INLINE
#Generate reproducible DF
noun_class_names = ["Masc","Fem","Neuter"]
x = [random.randint(0,50) for i in range(100)]
y = [random.randint(0,50) for i in range(100)]
rand_clusters = [str(random.randint(0,10)) for i in range(100)]
noun_classes = [random.choice(noun_class_names) for i in range(100)]
df = pd.DataFrame({'x_coord':x, 'y_coord':y,'noun class':noun_classes,'cluster labels':rand_clusters})
df.loc[df['cluster labels'] == '0', 'noun class'] = 'Masc' #ensure that cluster 0 has all same noun class to illustrate error
clusters = [str(i) for i in range(len(df['cluster labels'].unique()))]
cols1 = df#[['cluster labels','x_coord', 'y_coord']]
cols2 = cols1[cols1['cluster labels'] == '0']
Overall = ColumnDataSource(data=cols1)
Curr = ColumnDataSource(data=cols2)
#plot and the menu is linked with each other by this callback function
callback = CustomJS(args=dict(source=Overall, sc=Curr), code="""
var f = cb_obj.value
sc.data['x_coord']=[]
sc.data['y_coord']=[]
sc.data['noun class'] =[]
for(var i = 0; i <= source.get_length(); i++){
if (source.data['cluster labels'][i] == f){
sc.data['x_coord'].push(source.data['x_coord'][i])
sc.data['y_coord'].push(source.data['y_coord'][i])
sc.data['noun class'].push(source.data['noun class'][i])
sc.data['cluster labels'].push(source.data['cluster labels'][i])
}
}
sc.change.emit();
bokeh_p.legend.label.field = sc.data['noun class'];
""")
menu = Select(options=clusters, value='0', title = 'Cluster #') # create drop down menu
bokeh_p=figure(x_axis_label ='X Coord', y_axis_label = 'Y Coord', y_axis_type="linear",x_axis_type="linear") #creating figure object
mapper = factor_cmap(field_name = "noun class", palette = Colorblind[6], factors = df['noun class'].unique()) #color mapper- sorry this was a thing that carried over from og code (fixed now)
bokeh_p.circle(x='x_coord', y='y_coord', color='gray', alpha = .05, source=Overall)
bokeh_p.circle(x = 'x_coord', y = 'y_coord', fill_color = mapper, line_color = mapper, source = Curr, legend_field = 'noun class')
bokeh_p.legend.title = "Noun Classes"
menu.js_on_change('value', callback) # calling the function on change of selection
bokeh.io.output_notebook(INLINE)
show(layout(menu,bokeh_p), notebook_handle=True)
I have been mainly working in VS code to create a bokeh dashboard and I now need to get it to run within a Jupyter notebook. I know that some transformations in the code are required to push the code to a Jupyter notebook and for it to update interactively with widgets.
I have referred to this documentation:-
https://docs.bokeh.org/en/latest/docs/user_guide/jupyter.html#userguide-jupyter-notebook
But it is either too simplistic for my code, or that I have not used the push_notebook commands properly (or both).
Here is the code that I am trying to run in the notebook:-
################################### Code chunk 1##########################
from ipywidgets import interact
import pandas as pd
import numpy as np
import math
from bokeh.models import HoverTool
from bokeh.io import curdoc, output_notebook, push_notebook
from bokeh.plotting import figure, ColumnDataSource
from bokeh.layouts import layout, row, column, gridplot
from bokeh.models.widgets import RangeSlider
#https://discourse.bokeh.org/t/interactive-histograms-not-updating-with-sliders/3779/25
#clustering packages
from operator import index
from bokeh.models.widgets.markups import Div
import numpy as np
from numpy.lib import source
import pandas as pd
from bokeh.io import curdoc
from bokeh.layouts import column, row, gridplot, Column, Row
from bokeh.models import ColumnDataSource, Select, Slider, BoxSelectTool, LassoSelectTool, Tabs, Panel, LinearColorMapper, ColorBar, BasicTicker, PrintfTickFormatter, MultiSelect, DataTable, TableColumn
from bokeh.plotting import figure, curdoc, show
from bokeh.palettes import viridis, gray, cividis, Category20
from bokeh.transform import factor_cmap
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import classification_report, confusion_matrix, mean_squared_error, r2_score, recall_score, f1_score
from sklearn.preprocessing import StandardScaler, PolynomialFeatures
from sklearn.cluster import KMeans
from sklearn.svm import SVC
from sklearn.decomposition import PCA
#tables
from time import time
output_notebook()
################################# Code chunk 2 ###########################################
#define the categorical variable
category_a = ['A','B','C']
category_b = ['X','Y','Z']
print("step 2")
df = pd.DataFrame({
'id': np.arange(0, 100),
'date': pd.date_range(start='1/1/2021', periods=100, freq='D'),
'month':np.random.randint(1, 12, 100),
'sensor_1': np.random.uniform(0, 1,100),
'sensor_2': np.random.uniform(10, 150, 100),
'sensor_3': np.random.randint(0, 90, 100),
'sensor_4': np.random.randint(0, 450, 100),
'sensor_5': np.random.randint(0, 352, 100),
'categorya': np.random.choice(category_a, 100, p=[0.2, 0.4, 0.4]),
'categoryb': np.random.choice(category_b, 100, p=[0.6, 0.2, 0.2]),
})
source = ColumnDataSource(data=df)
################################### Code chunk 3##############################
class hist_data:
def __init__(self, df, col, n_bins, bin_range):
self.sensor1_lwr = min(df['sensor_1'])#duration millisecond
self.sensor1_upr = max(df['sensor_1'])#duration millisecond
self.sensor2_lwr = min(df['sensor_2'])#count watch
self.sensor2_upr = max(df['sensor_2'])#count_watch
self.sensor3_lwr = min(df['sensor_3'])#count idle
self.sensor3_upr = max(df['sensor_3'])#count idle
self.sensor4_lwr = min(df['sensor_4'])#count inter and watch
self.sensor4_upr = max(df['sensor_4'])#count inter and watch
self.sensor5_lwr = min(df['sensor_5'])#count inter
self.sensor5_upr = max(df['sensor_5'])#count inter
self.col = col
self.n_bins = n_bins
self.bin_range = bin_range
self.original_df = df
self.source = ColumnDataSource(self.create_hist_data(df))
def filt_df(self):
filt = (pd.DataFrame(self.original_df[(self.original_df.sensor_1 >=self.sensor1_lwr) &
(self.original_df.sensor_1 <= self.sensor1_upr) &
(self.original_df.sensor_2 >= self.sensor2_lwr) &
(self.original_df.sensor_2 <= self.sensor2_upr) &
(self.original_df.sensor_3 >= self.sensor3_lwr) &
(self.original_df.sensor_3 <= self.sensor3_upr) &
(self.original_df.sensor_4 >= self.sensor4_lwr) &
(self.original_df.sensor_4 <= self.sensor4_upr) &
(self.original_df.sensor_5 >= self.sensor5_lwr) &
(self.original_df.sensor_5 <= self.sensor5_upr)]))
print(f'{self.sensor1_lwr} {self.sensor1_upr} {self.sensor2_lwr} {self.sensor2_upr} {self.sensor3_lwr} {self.sensor3_upr} {self.sensor4_lwr} {self.sensor4_upr} {self.sensor5_lwr} {self.sensor5_upr}')
filt.shape
return ColumnDataSource(self.create_hist_data(filt))
def create_hist_data(self,df):
arr_hist, edges = np.histogram(df[self.col],bins=self.n_bins, range=self.bin_range)
arr_df = pd.DataFrame({'count': arr_hist, 'left': edges[:-1], 'right': edges[1:]})
arr_df['f_count'] = ['%d' % count for count in arr_df['count']]
arr_df['f_interval'] = ['%d to %d ' % (left, right) for left, right in zip(arr_df['left'], arr_df['right'])]
return (arr_df)
df = df
########################histograms
hist_data_A = hist_data(df,'sensor_1',math.floor(math.sqrt(df['sensor_1'].nunique())),[min(df['sensor_1']),max(df['sensor_1'])])
hist_data_B = hist_data(df,'sensor_2',math.floor(math.sqrt(df['sensor_2'].nunique())),[min(df['sensor_2']),max(df['sensor_2'])])
hist_data_C = hist_data(df,'sensor_3',math.floor(math.sqrt(df['sensor_3'].nunique())),[min(df['sensor_3']),max(df['sensor_3'])])
hist_data_D = hist_data(df,'sensor_4',math.floor(math.sqrt(df['sensor_4'].nunique())),[min(df['sensor_4']),max(df['sensor_4'])])
hist_data_E = hist_data(df,'sensor_5',math.floor(math.sqrt(df['sensor_5'].nunique())),[min(df['sensor_5']),max(df['sensor_5'])])
############################slider
A_Slider= RangeSlider(start=min(df['sensor_1']), end=max(df['sensor_1']), value=(min(df['sensor_1']),max(df['sensor_1'])), step=1, title='sensor_1')
B_Slider = RangeSlider(start=min(df['sensor_2']), end=max(df['sensor_2']), value=(min(df['sensor_2']),max(df['sensor_2'])), step=1, title='sensor_2')
C_Slider = RangeSlider(start=min(df['sensor_3']), end=max(df['sensor_3']), value=(min(df['sensor_3']),max(df['sensor_3'])), step=1, title='sensor_3')
D_Slider = RangeSlider(start=min(df['sensor_4']), end=max(df['sensor_4']), value=(min(df['sensor_4']),max(df['sensor_4'])), step=1, title='sensor_4')
E_Slider = RangeSlider(start=min(df['sensor_5']), end=max(df['sensor_5']), value=(min(df['sensor_5']),max(df['sensor_5'])), step=1, title='sensor_5')
def callback_A(attr,new,old):
hist_data_A.sensor1_lwr = new[0]
hist_data_A.sensor1_upr = new[1]
hist_data_A.source = hist_data_A.filt_df()
Graphs1.children[0] = plot_data_A()
push_notebook(handle=grid)
def callback_B(attr,new,old):
hist_data_B.sensor2_lwr = new[0]
hist_data_B.sensor2_upr = new[1]
hist_data_B.source = hist_data_B.filt_df()
Graphs1.children[1] = plot_data_B()
push_notebook(handle=grid)
def callback_C(attr,new,old):
hist_data_C.sensor3_lwr = new[0]
hist_data_C.sensor3_upr = new[1]
hist_data_C.source = hist_data_C.filt_df()
Graphs1.children[2] = plot_data_C()
push_notebook(handle=grid)
def callback_D(attr,new,old):
hist_data_D.sensor4_lwr = new[0]
hist_data_D.sensor4_upr = new[1]
hist_data_D.source = hist_data_D.filt_df()
Graphs2.children[0] = plot_data_D()
push_notebook(handle=grid)
def callback_E(attr,new,old):
hist_data_E.sensor5_lwr = new[0]
hist_data_E.sensor5_upr = new[1]
hist_data_E.source = hist_data_E.filt_df()
Graphs2.children[1] = plot_data_E()
push_notebook(handle=grid)
A_Slider.on_change("value",callback_A)
B_Slider.on_change("value",callback_B)
C_Slider.on_change("value",callback_C)
D_Slider.on_change("value",callback_D)
E_Slider.on_change("value",callback_E)
(df,'sensor_1',df['sensor_1'].nunique(),[min(df['sensor_1']),max(df['sensor_1'])])
(df,'sensor_2',df['sensor_2'].nunique(),[min(df['sensor_2']),max(df['sensor_2'])])
(df,'sensor_3',df['sensor_3'].nunique(),[min(df['sensor_3']),max(df['sensor_3'])])
(df,'sensor_4',df['sensor_4'].nunique(),[min(df['sensor_4']),max(df['sensor_4'])])
(df,'sensor_5',df['sensor_5'].nunique(),[min(df['sensor_5']),max(df['sensor_5'])])
# Histogram
def interactive_histogram( hist_data, title,x_axis_label,x_tooltip):
source = hist_data
# Set up the figure same as before
toollist = ['lasso_select', 'tap', 'reset', 'save','crosshair','wheel_zoom','pan','hover','box_select']
p = figure(plot_width = 400,
plot_height = 400,
title = title,
x_axis_label = x_axis_label,
y_axis_label = 'Count',tools=toollist)
# Add a quad glyph with source this time
p.quad(bottom=0,
top='count',
left='left',
right='right',
source=source,
fill_color='red',
hover_fill_alpha=0.7,
hover_fill_color='blue',
line_color='black')
# Add style to the plot
p.title.align = 'center'
p.title.text_font_size = '18pt'
p.xaxis.axis_label_text_font_size = '12pt'
p.xaxis.major_label_text_font_size = '12pt'
p.yaxis.axis_label_text_font_size = '12pt'
p.yaxis.major_label_text_font_size = '12pt'
# Add a hover tool referring to the formatted columns
hover = HoverTool(tooltips = [(x_tooltip, '#f_interval'),
('Count', '#f_count')])
# Add the hover tool to the graph
p.add_tools(hover)
return p
push_notebook(handle=grid)
#binsize = 10
binzise = 100
def plot_data_A():
A_hist = interactive_histogram(hist_data_A.source, 'sensor_1','sensor_1','sensor_1')
return A_hist
def plot_data_B():
B_hist = interactive_histogram(hist_data_B.source, 'sensor_2','sensor_2','sensor_2')
return B_hist
#
def plot_data_C():
C_hist = interactive_histogram(hist_data_C.source, 'sensor_3','sensor_3','sensor_3')
return C_hist
#
def plot_data_D():
D_hist = interactive_histogram(hist_data_D.source, 'sensor_4','sensor_4','sensor_4')
return D_hist
#
def plot_data_E():
E_hist = interactive_histogram(hist_data_E.source, 'sensor_5','sensor_5','sensor_5')
return E_hist
#
Graphs1 = row([plot_data_A(), plot_data_B(), plot_data_C()])
Graphs2 = row([plot_data_D(), plot_data_E()])
Controls1= column([A_Slider,B_Slider,C_Slider,D_Slider,E_Slider])
#grid = gridplot([[Graphs1],
# [Controls1]])
grid = gridplot([[Controls1,Graphs1],[None,Graphs2]])
show(grid)
Now, it brings up the plots:-
But the widgets do not update the plots. Can someone kindly show me what I am missing?
This sample is altered from the bokeh example, sliders can control the bars in the figure. (sliders.py)
This sample is altered from the bokeh example, sliders can control the bars in the figure. (sliders.py)
In my situation, there are more than 30 sliders on the left. It seems a little messy, so I am trying to use bokeh select element to connect sliders. The aim is the slider area will show only one slider when I select.
I read the document, and there are two ways to use:
One is disabled. If True, the widget will be greyed-out and not responsive to UI events. But it would not hide. Another is visible, but I got an attribute error:
AttributeError("unexpected attribute 'visible' to Slider, similar attributes are disabled")
Is it possible to make bokeh sliders hide or invisible? Or is there any other way to make sliders (more than 30) distinguish more clearly?
Here is the code which can run in Jupyter notebook
import bokeh.plotting.figure as bk_figure
from bokeh.io import curdoc, show
from bokeh.layouts import row, widgetbox
from bokeh.models import ColumnDataSource, Select
from bokeh.models.widgets import Slider, TextInput
from bokeh.io import output_notebook # enables plot interface in J notebook
import numpy as np
# init bokeh
from bokeh.application import Application
from bokeh.application.handlers import FunctionHandler
output_notebook()
# Set up data
data = {
'line_x' : [1,2,3,4],
'line_y' : [4,3,2,1],
'bar_x':[1, 2, 3, 4],
'bar_bottom':[1,1,1,1],
'bar_top':[0.2, 2.5, 3.7, 4],
}
#bar_color
determine_top = data['bar_top']
determine_bottom = data['bar_bottom']
determine_color = []
for i in range(0,4):
if (determine_top[i] > determine_bottom[i]):
determine_color.append('#B3DE69') #green
else:
determine_color.append('firebrick')
i+=1
data['determine_colors'] = determine_color
source = ColumnDataSource(data=data)
# Set up plot
plot = bk_figure(plot_height=400, plot_width=400, title="test",
tools="crosshair,pan,reset,save,wheel_zoom",
x_range=[0, 10], y_range=[-5, 5])
plot.vbar(x='bar_x', width=0.5, top='bar_top',bottom='bar_bottom',
source=source, color='determine_colors')
# Set up widgets
select = Select(title="days_select:",
options=["d1_select", "d2_select", "d3_select", "d4_select"])
d1 = Slider(title="d1", value=0.0, start=-5.0, end=5.0, step=0.1)
d2 = Slider(title="d2", value=1.0, start=-5.0, end=5.0, step=0.1)
d3 = Slider(title="d3", value=0.0, start=0.0, end=2*np.pi)
d4 = Slider(title="d4", value=1.0, start=0.1, end=5.1, step=0.1)
# Set up callbacks
def update_data(attrname, old, new):
# Get the current slider values
d1_value = d1.value
d2_value = d2.value
d3_value = d3.value
d4_value = d4.value
##select
#if select.value == "d2_select":
# d3.disabled = True
# d4.visible = False
# Generate the new curve
new_data = {
'line_x' : [1,2,3,4],
'line_y' : [4,3,2,1],
'bar_x': [1, 2, 3, 4],
'bar_bottom':[d1_value, d2_value, d3_value, d4_value],
'bar_top':[0.2, d1_value, d2_value, d3_value],
}
#bar_color
determine_top = new_data['bar_top']
determine_bottom = new_data['bar_bottom']
determine_color = []
for i in range(0,4):
if (determine_top[i] > determine_bottom[i]):
determine_color.append('green') #green
else:
determine_color.append('red')
i+=1
new_data['determine_colors'] = determine_color
source.data = new_data
for w in [select, d1, d2, d3, d4]:
w.on_change('value', update_data)
# Set up layouts and add to document
layout = row(widgetbox(select, d1, d2, d3, d4), plot)
def modify_doc(doc):
doc.add_root(row(layout, width=800))
doc.title = "Sliders"
handler = FunctionHandler(modify_doc)
app = Application(handler)
show(app)
Thanks for any suggestions.
I am creating a bokeh plot with a slider to refresh plot accordingly. There are 2 issues with the code posted.
1. The plot is not refreshed as per the slider. Please help in providing a fix for this issue.
2. Plot is not displayed with curdoc() when bokeh serve --show fn.ipynb is used
I'm trying to visualise this CSV file.
import pandas as pd
import numpy as np
from bokeh.models import ColumnDataSource, CategoricalColorMapper, HoverTool, Slider
from bokeh.plotting import figure, curdoc
from bokeh.palettes import viridis
from bokeh.layouts import row, widgetbox
#Importing and processing data file
crop = pd.read_csv('crop_production.csv')
#Cleaning Data
crop.fillna(np.NaN)
crop['Season'] = crop.Season.str.strip()
#Removing Whitespace #Filtering the dataset by Season
crop_season = crop[crop.Season == 'Whole Year']
crop_dt = crop_season.groupby(['State_Name', 'District_Name', 'Crop_Year']).mean().round(1)
#Creating Column Data Source
source = ColumnDataSource({
'x' : crop_dt[crop_dt.index.get_level_values('Year')==2001].loc[(['ABC']), :].Area,
'y' : crop_dt[crop_dt.index.get_level_values('Year')==2001].loc[(['ABC']), :].Production,
'state' : crop_dt[crop_dt.index.get_level_values('Year')==2001].loc[(['ABC']), :].index.get_level_values('State_Name'),
'district' : crop_dt[crop_dt.index.get_level_values('Year')==2001].loc[(['ABC']), :].index.get_level_values('District_Name')
})
#Creating color palette for plot
district_list = crop_dt.loc[(['Tamil Nadu']), :].index.get_level_values('District_Name').unique().tolist()
call_colors = viridis(len(district_list))
color_mapper = CategoricalColorMapper(factors=district_list, palette=call_colors)
# Creating the figure
#xmin, xmax = min(data.Crop_Year), max(data.Crop_Year)
#ymin, ymax = min(data.Production), max(data.Production)
p = figure(
title = 'Crop Area vs Production',
x_axis_label = 'Area',
y_axis_label = 'Production',
plot_height=900,
plot_width=1200,
tools = [HoverTool(tooltips='#district')]
)
p.circle(x='x', y='y', source=source, size=12, alpha=0.7,
color=dict(field='district', transform=color_mapper),
legend='district')
p.legend.location = 'top_right'
def update_plot(attr, old, new):
yr = slider.value
new_data = {
'x' : crop_dt[crop_dt.index.get_level_values('Year')==yr].loc[(['ABC']), :].Area,
'y' : crop_dt[crop_dt.index.get_level_values('Year')==yr].loc[(['ABC']), :].Production,
'state' : crop_dt[crop_dt.index.get_level_values('Year')==yr].loc[(['ABC']), :].index.get_level_values('State_Name'),
'district' : crop_dt[crop_dt.index.get_level_values('Year')==yr].loc[(['ABC']), :].index.get_level_values('District_Name')
}
source.data = new_data
#Creating Slider for Year
start_yr = min(crop_dt.index.get_level_values('Crop_Year'))
end_yr = max(crop_dt.index.get_level_values('Crop_Year'))
slider = Slider(start=start_yr, end=end_yr, step=1, value=start_yr, title='Year')
slider.on_change('value',update_plot)
layout = row(widgetbox(slider), p)
curdoc().add_root(layout)
show(layout)
Also tried a different option using CustomJS as below, but still no luck.
callback = CustomJS(args=dict(source=source), code="""
var data = source.data;
var yr = slider.value;
var x = data['x']
var y = data['y']
'x' = crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['ABC']), :].Area;
'y' = crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['ABC']), :].Production;
p.circle(x='x', y='y', source=source, size=12, alpha=0.7,
color=dict(field='district', transform=color_mapper),
legend='district');
}
source.change.emit();
""")
#Creating Slider for Year
start_yr = min(crop_dt.index.get_level_values('Crop_Year'))
end_yr = max(crop_dt.index.get_level_values('Crop_Year'))
yr_slider = Slider(start=start_yr, end=end_yr, step=1, value=start_yr, title='Year', callback=callback)
callback.args["slider"] = yr_slider
Had a lot of issues trying to execute your code and I have changed some things, so feel free to correct me if did something wrong.
The error was caused by the creation of the ColumnDataSource, I had to change the level value to Crop_Year instead of Year. The loc 'ABC' also caused an error so I removed that too (And I had to add source = ColumnDataSource({, you probably forgot to copy that)
I also added a dropdown menu so it's possible to only show the data from one district.
Also, I'm not quite sure if it's possible to start a bokeh server by supplying a .ipynb file to --serve. But don't pin me down on that, I never use notebooks. I've tested this with a .py file.
#!/usr/bin/python3
import pandas as pd
import numpy as np
from bokeh.models import ColumnDataSource, CategoricalColorMapper, HoverTool
from bokeh.plotting import figure, curdoc
from bokeh.palettes import viridis
from bokeh.layouts import row, widgetbox
from bokeh.models.widgets import Select, Slider
#Importing and processing data file
crop = pd.read_csv('crop_production.csv')
#Cleaning Data
crop.fillna(np.NaN)
crop['Season'] = crop.Season.str.strip()
#Removing Whitespace #Filtering the dataset by Season
crop_season = crop[crop.Season == 'Whole Year']
crop_dt = crop_season.groupby(['State_Name', 'District_Name', 'Crop_Year']).mean().round(1)
crop_dt_year = crop_dt[crop_dt.index.get_level_values('Crop_Year')==2001]
crop_dt_year_state = crop_dt_year[crop_dt_year.index.get_level_values('State_Name')=='Tamil Nadu']
#Creating Column Data Source
source = ColumnDataSource({
'x': crop_dt_year_state.Area.tolist(),
'y': crop_dt_year_state.Production.tolist(),
'state': crop_dt_year_state.index.get_level_values('State_Name').tolist(),
'district': crop_dt_year_state.index.get_level_values('District_Name').tolist()
})
#Creating color palette for plot
district_list = crop_dt.loc[(['Tamil Nadu']), :].index.get_level_values('District_Name').unique().tolist()
call_colors = viridis(len(district_list))
color_mapper = CategoricalColorMapper(factors=district_list, palette=call_colors)
# Creating the figure
p = figure(
title = 'Crop Area vs Production',
x_axis_label = 'Area',
y_axis_label = 'Production',
plot_height=900,
plot_width=1200,
tools = [HoverTool(tooltips='#district')]
)
glyphs = p.circle(x='x', y='y', source=source, size=12, alpha=0.7,
color=dict(field='district', transform=color_mapper),
legend='district')
p.legend.location = 'top_right'
def update_plot(attr, old, new):
#Update glyph locations
yr = slider.value
state = select.value
crop_dt_year = crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr]
crop_dt_year_state = crop_dt_year[crop_dt_year.index.get_level_values('State_Name')==state]
new_data = {
'x': crop_dt_year_state.Area.tolist(),
'y': crop_dt_year_state.Production.tolist(),
'state': crop_dt_year_state.index.get_level_values('State_Name').tolist(),
'district': crop_dt_year_state.index.get_level_values('District_Name').tolist()
}
source.data = new_data
#Update colors
district_list = crop_dt.loc[([state]), :].index.get_level_values('District_Name').unique().tolist()
call_colors = viridis(len(district_list))
color_mapper = CategoricalColorMapper(factors=district_list, palette=call_colors)
glyphs.glyph.fill_color = dict(field='district', transform=color_mapper)
glyphs.glyph.line_color = dict(field='district', transform=color_mapper)
#Creating Slider for Year
start_yr = min(crop_dt.index.get_level_values('Crop_Year'))
end_yr = max(crop_dt.index.get_level_values('Crop_Year'))
slider = Slider(start=start_yr, end=end_yr, step=1, value=start_yr, title='Year')
slider.on_change('value',update_plot)
#Creating drop down for state
options = list(set(crop_dt.index.get_level_values('State_Name').tolist()))
options.sort()
select = Select(title="State:", value="Tamil Nadu", options=options)
select.on_change('value', update_plot)
layout = row(widgetbox(slider, select), p)
curdoc().add_root(layout)
#Jasper Thanks a lot. This works, however it doesnt work with .loc[(['Tamil Nadu']), :]. Reason for having this is to filter the data by adding a bokeh dropdown or radio button object and refresh the plot based on the filters. The below code works only if .loc[(['Tamil Nadu']), :] is removed. Is there any other way to fix this please?
def update_plot(attr, old, new):
yr = slider.value
new_data = {
'x' : crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['Tamil Nadu']), :].Area.tolist(),
'y' : crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['Tamil Nadu']), :].Production.tolist(),
'state' : crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['Tamil Nadu']), :].index.get_level_values('State_Name').tolist(),
'district' : crop_dt[crop_dt.index.get_level_values('Crop_Year')==yr].loc[(['Tamil Nadu']), :].index.get_level_values('District_Name').tolist()
}
source.data = new_data
Given the following bokeh chart (this code must be run in a jupyter notebook):
from bokeh.io import output_notebook, show
from bokeh.plotting import figure
from bokeh.palettes import Dark2_5 as palette
from bokeh.layouts import widgetbox, row, column
from bokeh.models.widgets import CheckboxButtonGroup
import itertools
import numpy as np
output_notebook()
# create a new plot (with a title) using figure
p = figure(plot_width=800, plot_height=400, title="My Line Plot")
start = 10.0
x = range(20)
colors = itertools.cycle(palette)
nseries = 50
# add a line renderer
for n in range(nseries):
y = np.cumsum(np.random.randn(1,20))
p.line(x, y, line_width=1, legend=str(n), color=next(colors))
p.legend.location = "top_left"
p.legend.click_policy="hide"
checkbox_button_group = CheckboxButtonGroup(
labels=[str(n) for n in range(nseries)], active=[0, 1])
show(column([p, checkbox_button_group])) # show the results
Which produces a chart like this:
How can I connect up the checkbox buttons so that they show/hide the relevant series on the plot?
Note:
I know that I can click the legend to achieve this effect. However, I want to plot more series than the legend can show (e.g. it only shows 13 series in the screenshot). Obviously, people will only have maybe 10 series shown at any one time otherwise it becomes hard to see information.
Here is my attempt. It feels clunky though, is there a better solution? Also, how can I call my callback automatically when the plot has loaded, so that series [0,1,2,3] only are made active?
from bokeh.io import output_notebook, show
from bokeh.plotting import figure
from bokeh.palettes import Dark2_5 as palette
from bokeh.layouts import widgetbox, row, column
from bokeh.models.widgets import CheckboxButtonGroup
import itertools
import numpy as np
output_notebook()
# create a new plot (with a title) using figure
p = figure(plot_width=800, plot_height=400, title="My Line Plot")
start = 10.0
x = range(20)
colors = itertools.cycle(palette)
nseries = 50
series = []
# add a line renderer
for n in range(nseries):
y = np.cumsum(np.random.randn(1,20))
series.append(p.line(x, y, line_width=1, legend=str(n), color=next(colors)))
p.legend.location = "top_left"
p.legend.click_policy="hide"
js = ""
for n in range(nseries):
js_ = """
if (checkbox.active.indexOf({n}) >-1) {{
l{n}.visible = true
}} else {{
l{n}.visible = false
}} """
js += js_.format(n=n)
callback = CustomJS(code=js, args={})
checkbox_button_group = CheckboxButtonGroup(labels=[str(n) for n in range(nseries)], active=[0,1,2,3], callback=callback)
callback.args = dict([('l{}'.format(n), series[n]) for n in range(nseries)])
callback.args['checkbox'] = checkbox_button_group
show(column([p, checkbox_button_group])) # show the results
Your solution is fine.
Here is a more compact js callback that relies on the line being numbered with their "name" attribute
from bokeh.io import output_notebook, show
from bokeh.plotting import figure
from bokeh.palettes import Dark2_5 as palette
from bokeh.layouts import widgetbox, row, column
from bokeh.models import CheckboxButtonGroup, CustomJS
import itertools
import numpy as np
# create a new plot (with a title) using figure
p = figure(plot_width=800, plot_height=400, title="My Line Plot")
start = 10.0
x = range(20)
colors = itertools.cycle(palette)
nseries = 50
# add a line renderer
for n in range(nseries):
y = np.cumsum(np.random.randn(1,20))
p.line(x, y, line_width=1, legend=str(n), color=next(colors), name=str(n))
p.legend.location = "top_left"
p.legend.click_policy="hide"
checkbox_button_group = CheckboxButtonGroup(
labels=[str(n) for n in range(nseries)], active=[])
code = """
active = cb_obj.active;
rend_list = fig.renderers;
for (rend of rend_list) {
if (rend.name!==null) {
rend.visible = !active.includes(Number(rend.name));
}
}
"""
checkbox_button_group.callback = CustomJS(args={'fig':p},code=code)
show(column([p, checkbox_button_group])) # show the results
It's also useful if you want to hide groups of lines via keywords by having them share those in their "name" attribute
And here is how you can do it with the bokeh server:
from bokeh.io import curdoc
from bokeh.plotting import figure
from bokeh.palettes import Dark2_5 as palette
from bokeh.layouts import column
from bokeh.models import CheckboxButtonGroup, CustomJS
import itertools
import numpy as np
# create a new plot (with a title) using figure
p = figure(plot_width=800, plot_height=400, title="My Line Plot")
start = 10.0
x = range(20)
colors = itertools.cycle(palette)
nseries = 50
# add a line renderer
line_list = []
for n in range(nseries):
y = np.cumsum(np.random.randn(1,20))
line_list += [p.line(x, y, line_width=1, legend=str(n), color=next(colors))]
p.legend.location = "top_left"
p.legend.click_policy="hide"
checkbox_button_group = CheckboxButtonGroup(labels=[str(n) for n in range(nseries)], active=[])
def update(attr,old,new):
for lineID,line in enumerate(line_list):
line.visible = lineID in new
checkbox_button_group.on_change('active',update)
curdoc().add_root(column([p, checkbox_button_group]))
def init_active():
checkbox_button_group.active = range(3)
curdoc().add_timeout_callback(init_active,1000)