Related
I am trying to plot a choropleth map with a drop-down menu to select multiple variables and also show each variable with a time slider to display data over time.
import plotly
import numpy as np
plotly.offline.init_notebook_mode()
# Reading sample data using pandas DataFrame
df = pd.read_csv('https://raw.githubusercontent.\
com/plotly/datasets/master/2011_us_ag_exports.csv')
data = [dict(type='choropleth',
locations = df['code'].astype(str),
z=df['total exports'].astype(float),
locationmode='USA-states')]
# let's create some more additional, data
for i in range(5):
data.append(data[0].copy())
data[-1]['z'] = data[0]['z'] * np.random.rand(*data[0]['z'].shape)
# let's now create slider for map
steps = []
for i in range(len(data)):
step = dict(method='restyle',
args=['visible', [False] * len(data)],
label='Year {}'.format(i + 1980))
step['args'][1][i] = True
steps.append(step)
slider = [dict(active=0,
pad={"t": 1},
steps=steps)]
layout = dict(geo=dict(scope='usa',
projection={'type': 'albers usa'}),
sliders=slider)
fig = dict(data=data,
layout=layout)
plotly.offline.iplot(fig)
This example is taken from: here
Any ideas how to add another column as data points?
Here the code I wrote.
I took the data from pandas DF (not pasted here).
The x values are from DF index columns that is a DateTime column.
The issue that I want to resolve is in line:
TOOLTIPS = [("index", "$index"),("(Time,Temperature)", "($x, $y)"),]
when I have to change the $x format to a correct format in order to see the the time format in the hover window on the bokeh plot.
see the python code
import datetime as dt
from bokeh.plotting import figure, output_file, show
from bokeh.layouts import gridplot
from bokeh.models import ColumnDataSource, CDSView, BooleanFilter
from bokeh.models import DatetimeTickFormatter
x=df_bases.index
y0=df_bases["base_1"]
y1=df_bases["base_5"]
y2=df_bases["base_12"]
# output to static HTML file
output_file("temperatures from thermocouples.html")
# add some renderers
output_file("Thermocouples temperature.html", title="Thermocouples temperature")
TOOLTIPS = [("index", "$index"),("(Time,Temperature)", "($x, $y)"),]
# create a new plot with a datetime axis type
p = figure( tooltips=TOOLTIPS , plot_width=1250, plot_height=580, x_axis_type="datetime", x_axis_label='Time',
y_axis_label='Temperature [°C]', title="Thermocouples temperature")
p.line(x, y0, legend="thermocouple 1", line_width=1 , color='navy', alpha=1)
p.line(x, y1, legend="thermocouple 5", color="green")
p.line(x, y2, legend="thermocouple 12", line_width=1 , color='orange', alpha=1)#, line_dash="4 4")
p.border_fill_color = "whitesmoke"
p.xaxis.formatter=DatetimeTickFormatter(
microseconds = ['%Y-%m-%d %H:%M:%S.%f'],
milliseconds = ['%Y-%m-%d %H:%M:%S.%3N'],
seconds = ["%Y-%m-%d %H:%M:%S"],
minsec = ["%Y-%m-%d %H:%M:%S"],
minutes = ["%Y-%m-%d %H:%M:%S"],
hourmin = ["%Y-%m-%d %H:%M:%S"],
hours=["%Y-%m-%d %H:%M:%S"],
days=["%Y-%m-%d %H:%M:%S"],
months=["%Y-%m-%d %H:%M:%S"],
years=["%Y-%m-%d %H:%M:%S"],
)
p.title.align = 'center'
# create a column data source for the plots to share
source = ColumnDataSource(data=dict(x=x, y0=y0, y1=y1, y2=y2))
# create a view of the source for one plot to use
view = CDSView(source=source)
# show the results
show(p)
Currently (as of Bokeh 1.2) the hover tool does not have any "always on" mode It only hovers in response to hit-testing glyphs that are added to the plot. Additionally there is no way to apply formatting to "special vars" like $x (that will be possible starting in Bokeh 2.0). Custom formatters can only be applied to hover tooltips for data columns. Given that, my best suggestion is to switch to using #xinstead (which interrogates the "x" data column, not the x mouse position". If you do that, you can use all the techniques in the Formatting Tooltip Fields section of the docs.
Since you did not provide a complete example (no data to run), I can only provide partial untested suggestions:
# use #x{%F} to specify the %F datetime format (or choose another) for the x column
TOOLTIPS = [("index", "$index"),("(Time,Temperature)", "(#x{%F}, $y)")]
# tell bokeh to use the "datetime" formatter for the x column
p.hover.formatters = {'x': 'datetime'}
# just a suggestion, often useful for timeseries plots
p.hover.mode = 'vline'
I first render the figure in notebook, then I save it in svg form. The figure display in notebook is correct, but the saved svg is missing some markers.
#!/usr/bin/python3
import pandas as pd
import numpy as np
import math
from bokeh.plotting import figure, show, ColumnDataSource, save, output_file, reset_output
from bokeh.models import HoverTool, Legend
from bokeh.layouts import gridplot
import colorsys # needed for generating N equally extinguishable colors
from itertools import cycle
d = {'Sex': ['male', 'male','male','male', 'male','male','female','female','female','female','female','female'], 'age': [20, 20,20, 25,25,25,20, 20,20,25,25,25], 'working_hours': [20,30,40,20,30,40,20,30,40,20,30,40],'income': [1000, 2000,3000,1500, 2500,3500,1100, 2100,3100,1300, 2300,3300] }
values = pd.DataFrame(data=d)
x_var = 'working_hours'
x_var_dimension = 'H'
y_var = 'income'
y_var_dimension = 'Dollars'
hover = HoverTool(tooltips=[("data (x,y)", "(#x, #y)")])
TOOLS=[hover]
p= figure(width=1200, height=600,tools=TOOLS, x_axis_type='linear', x_axis_label='%s [%s]'%(x_var, x_var_dimension),y_axis_label='%s [%s]'%(y_var, y_var_dimension))
nr_expressions_row_col=9
figs_array_row_col = []
figs_row_row_col=[]
legend_its_row_col = []
legend_its_row_col_renderer = []
loop_count = 0;
markers = ['circle', 'square', 'triangle', 'asterisk', 'circle_x', 'square_x', 'inverted_triangle', 'x', 'circle_cross', 'square_cross', 'diamond', 'cross']
pool = cycle(markers)
for key, group in values.groupby(['Sex']):
for key_sub1, group_sub1 in group.groupby(['age']):
loop_count+=1
x_data = group_sub1[x_var].values;
y_data = group_sub1[y_var].values
(color_r,color_g,color_b) = colorsys.hsv_to_rgb(loop_count*1.0/nr_expressions_row_col, 1, 1)
plot_row_col_line = p.line(x_data, y_data,line_color=(int(255*color_r),int(255*color_g),int(255*color_b)))
plot_row_col_glyph = p.scatter(x_data, y_data, color=(int(255*color_r),int(255*color_g),int(255*color_b)), size=10, marker=next(pool))
legend_its_row_col.append(("%s %s"%(key,key_sub1), [plot_row_col_line, plot_row_col_glyph]))
legend_row_col = Legend(items = legend_its_row_col, location=(0,0))
legend_row_col.click_policy = 'hide'
legend_row_col.background_fill_alpha = 0
p.add_layout(legend_row_col, 'left')
figs_row_row_col.append(p)
figs_array_row_col.append(figs_row_row_col)
grid_row_col = gridplot(figs_array_row_col)
reset_output()
output_notebook()
show(grid_row_col)
p.output_backend = "svg"
export_svgs(grid_row_col, filename="%s/"%'.' + "_" +"stackoverflow.svg")
Here is what I see in notebook, which is what I expected:
And here is what I see when opening '_stackoverflow.svg'
The legend color for 'female 25' and 'male 20' is partially black. (the marker part) and 'female 20' is missing both marker and its legend.
The reason you are seeing different colors in the notebook and the exported image is that they use two different backends. You set the backend to SVG just before exporting it in the last line. Therefore, though the exported image uses SVG backend, the image on the notebook uses the default backend, which is canvas.
The backend can be set with two options: one you used and one where you add output_backend="svg" argument when you call figure. That is, replacing
p= figure(width=1200, height=600,tools=TOOLS, x_axis_type='linear', x_axis_label='%s [%s]'%(x_var, x_var_dimension),y_axis_label='%s [%s]'%(y_var, y_var_dimension))
with
p= figure(width=1200, height=600,tools=TOOLS, x_axis_type='linear', x_axis_label='%s [%s]'%(x_var, x_var_dimension),y_axis_label='%s [%s]'%(y_var, y_var_dimension), output_backend="svg").
Now you will see the same issue you see in the exported image on you notebook image. It seems like this is a bug in the SVG backend, and most likely they are working on that. Unfortunately there is no expected date for the bug fix.
I'm attempting to create a BoxPlot using Bokeh. When I get to the section where I need to identify outliers, it fails if a given category has no outliers.
If I remove the "problem" category, the BoxPlot executes properly. it's only when I attempt to create this BoxPlot with a category that has no outliers it fails.
Any instruction on how to remedy this?
The failure occurs at the commented section "Prepare outlier data for plotting [...]"
import numpy as np
import pandas as pd
import datetime
import math
from bokeh.plotting import figure, show, output_file
from bokeh.models import NumeralTickFormatter
# Create time stamps to allow for figure to display span in title
today = datetime.date.today()
delta1 = datetime.timedelta(days=7)
delta2 = datetime.timedelta(days=1)
start = str(today - delta1)
end = str(today - delta2)
#Identify location of prices
itemloc = 'Everywhere'
df = pd.read_excel(r'C:\Users\me\prices.xlsx')
# Create a list from the dataframe that identifies distinct categories for the separate box plots
cats = df['subcategory_desc'].unique().tolist()
# Find the quartiles and IQR for each category
groups = df.groupby('subcategory_desc', sort=False)
q1 = groups.quantile(q=0.25)
q2 = groups.quantile(q=0.5)
q3 = groups.quantile(q=0.75)
iqr = q3 - q1
upper = q3 + 1.5*iqr
lower = q1 - 1.5*iqr
# Find the outliers for each category
def outliers(group):
cat = group.name
return group[(group.price > upper.loc[cat][0]) | (group.price < lower.loc[cat][0])]['price']
out = groups.apply(outliers).dropna()
# Prepare outlier data for plotting, we need coordinates for every outlier.
outx = []
outy = []
for cat in cats:
# only add outliers if they exist
if not out.loc[cat].empty:
for value in out[cat]:
outx.append(cat)
outy.append(value)
I expect that the Box-and-whisker portion of categories with no outliers merely show up without the outlier dots.
Have you tried the code from official documentation, https://docs.bokeh.org/en/latest/docs/gallery/boxplot.html?
# prepare outlier data for plotting, we need coordinates for every outlier.
if not out.empty:
outx = []
outy = []
for keys in out.index:
outx.append(keys[0])
outy.append(out.loc[keys[0]].loc[keys[1]])
Is it possible to add Tooltips to a Timeseries chart?
In the simplified code example below, I want to see a single column name ('a','b' or 'c') when the mouse hovers over the relevant line.
Instead, a "???" is displayed and ALL three lines get a tool tip (rather than just the one im hovering over)
Per the documentation (
http://docs.bokeh.org/en/latest/docs/user_guide/tools.html#hovertool), field names starting with “#” are interpreted as columns on the data source.
How can I display the 'columns' from a pandas DataFrame in the tooltip?
Or, if the high level TimeSeries interface doesn't support this, any clues for using the lower level interfaces to do the same thing? (line? multi_line?) or convert the DataFrame into a different format (ColumnDataSource?)
For bonus credit, how should the "$x" be formatted to display the date as a date?
thanks in advance
import pandas as pd
import numpy as np
from bokeh.charts import TimeSeries
from bokeh.models import HoverTool
from bokeh.plotting import show
toy_df = pd.DataFrame(data=np.random.rand(5,3), columns = ('a', 'b' ,'c'), index = pd.DatetimeIndex(start='01-01-2015',periods=5, freq='d'))
p = TimeSeries(toy_df, tools='hover')
hover = p.select(dict(type=HoverTool))
hover.tooltips = [
("Series", "#columns"),
("Date", "$x"),
("Value", "$y"),
]
show(p)
Below is what I came up with.
Its not pretty but it works.
Im still new to Bokeh (& Python for that matter) so if anyone wants to suggest a better way to do this, please feel free.
import pandas as pd
import numpy as np
from bokeh.charts import TimeSeries
from bokeh.models import HoverTool
from bokeh.plotting import show
toy_df = pd.DataFrame(data=np.random.rand(5,3), columns = ('a', 'b' ,'c'), index = pd.DatetimeIndex(start='01-01-2015',periods=5, freq='d'))
_tools_to_show = 'box_zoom,pan,save,hover,resize,reset,tap,wheel_zoom'
p = figure(width=1200, height=900, x_axis_type="datetime", tools=_tools_to_show)
# FIRST plot ALL lines (This is a hack to get it working, why can't i pass in a dataframe to multi_line?)
# It's not pretty but it works.
# what I want to do!: p.multi_line(df)
ts_list_of_list = []
for i in range(0,len(toy_df.columns)):
ts_list_of_list.append(toy_df.index.T)
vals_list_of_list = toy_df.values.T.tolist()
# Define colors because otherwise multi_line will use blue for all lines...
cols_to_use = ['Black', 'Red', 'Lime']
p.multi_line(ts_list_of_list, vals_list_of_list, line_color=cols_to_use)
# THEN put scatter one at a time on top of each one to get tool tips (HACK! lines with tooltips not yet supported by Bokeh?)
for (name, series) in toy_df.iteritems():
# need to repmat the name to be same dimension as index
name_for_display = np.tile(name, [len(toy_df.index),1])
source = ColumnDataSource({'x': toy_df.index, 'y': series.values, 'series_name': name_for_display, 'Date': toy_df.index.format()})
# trouble formating x as datestring, so pre-formating and using an extra column. It's not pretty but it works.
p.scatter('x', 'y', source = source, fill_alpha=0, line_alpha=0.3, line_color="grey")
hover = p.select(dict(type=HoverTool))
hover.tooltips = [("Series", "#series_name"), ("Date", "#Date"), ("Value", "#y{0.00%}"),]
hover.mode = 'mouse'
show(p)
I’m not familiar with Pandas，I just use python list to show the very example of how to add tooltips to muti_lines, show series names ,and properly display date/time。Below is the result.
Thanks to #bs123's answer and #tterry's answer in Bokeh Plotting: Enable tooltips for only some glyphs
my result
# -*- coding: utf-8 -*-
from bokeh.plotting import figure, output_file, show, ColumnDataSource
from bokeh.models import HoverTool
from datetime import datetime
dateX_str = ['2016-11-14','2016-11-15','2016-11-16']
#conver the string of datetime to python datetime object
dateX = [datetime.strptime(i, "%Y-%m-%d") for i in dateX_str]
v1= [10,13,5]
v2 = [8,4,14]
v3= [14,9,6]
v = [v1,v2,v3]
names = ['v1','v2','v3']
colors = ['red','blue','yellow']
output_file('example.html',title = 'example of add tooltips to multi_timeseries')
tools_to_show = 'hover,box_zoom,pan,save,resize,reset,wheel_zoom'
p = figure(x_axis_type="datetime", tools=tools_to_show)
#to show the tooltip for multi_lines,you need use the ColumnDataSource which define the data source of glyph
#the key is to use the same column name for each data source of the glyph
#so you don't have to add tooltip for each glyph,the tooltip is added to the figure
#plot each timeseries line glyph
for i in xrange(3):
# bokeh can't show datetime object in tooltip properly,so we use string instead
source = ColumnDataSource(data={
'dateX': dateX, # python datetime object as X axis
'v': v[i],
'dateX_str': dateX_str, #string of datetime for display in tooltip
'name': [names[i] for n in xrange(3)]
})
p.line('dateX', 'v',source=source,legend=names[i],color = colors[i])
circle = p.circle('dateX', 'v',source=source, fill_color="white", size=8, legend=names[i],color = colors[i])
#to avoid some strange behavior(as shown in the picture at the end), only add the circle glyph to the renders of hover tool
#so tooltip only takes effect on circle glyph
p.tools[0].renderers.append(circle)
# show the tooltip
hover = p.select(dict(type=HoverTool))
hover.tooltips = [("value", "#v"), ("name", "#name"), ("date", "#dateX_str")]
hover.mode = 'mouse'
show(p)
tooltips with some strange behavior,two tips displayed at the same time
Here is my solution. I inspected the glyph render data source to see what are the names on it. Then I use those names on the hoover tooltips. You can see the resulting plot here.
import numpy as np
from bokeh.charts import TimeSeries
from bokeh.models import HoverTool
from bokeh.plotting import show
toy_df = pd.DataFrame(data=np.random.rand(5,3), columns = ('a', 'b' ,'c'), index = pd.DatetimeIndex(start='01-01-2015',periods=5, freq='d'))
#Bockeh display dates as numbers so convert to string tu show correctly
toy_df.index = toy_df.index.astype(str)
p = TimeSeries(toy_df, tools='hover')
#Next 3 lines are to inspect how are names on gliph to call them with #name on hover
#glyph_renderers = p.select(dict(type=GlyphRenderer))
#bar_source = glyph_renderers[0].data_source
#print(bar_source.data) #Here we can inspect names to call on hover
hover = p.select(dict(type=HoverTool))
hover.tooltips = [
("Series", "#series"),
("Date", "#x_values"),
("Value", "#y_values"),
]
show(p)
The original poster's code doesn't work with the latest pandas (DatetimeIndex constructor has changed), but Hovertool now supports a formatters attribute that lets you specify a format as a strftime string. Something like
fig.add_tool(HoverTool(
tooltip=[
('time', '#index{%Y-%m-%d}')
],
formatters={
'#index': 'datetime'
}
))