Related
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.
Update the question:
How to select a certain species in barplot, nonselected bars will change color?
How to show text on top of each bar?
from bokeh.sampledata.iris import flowers
from bokeh.plotting import figure, output_file, show
from bokeh.models import ColumnDataSource, CategoricalColorMapper
from bokeh.layouts import column, row
#color mapper to color data by species
mapper = CategoricalColorMapper(factors = ['setosa','versicolor', 'virginica'],\
palette = ['green', 'blue', 'red'])
output_file("plots.html")
#group by species and plot barplot for count
species = flowers.groupby('species')
source = ColumnDataSource(species)
p = figure(plot_width = 800, plot_height = 400, title = 'Count by Species', \
x_range = source.data['species'], tools = 'box_select')
p.vbar(x = 'species', top = 'petal_length_count', width = 0.8, source = source,\
nonselection_fill_color = 'gray', nonselection_fill_alpha = 0.2,\
color = {'field': 'species', 'transform': mapper})
show(p)
First: please try to ask unrelated questions in separate SO posts.
Hit testing and selection was not implemented for vbar and hbar until recently. Using the recent 0.12.11 release, your code behaves as you are wanting:
Regarding labels for each bar, you want to use the LabelSet annotation, as demonstrated in the User's Guide Something like:
labels = LabelSet(x='species', y='petal_count_length', text='some_column',
x_offset=5, y_offset=5, source=source)
p.add_layout(labels)
The linking question is too vague. I would suggest opening a new SO question with more information and description of what exactly you are trying to accomplish.
There is an example here for how to create a multi-colored text title.
However, I want to apply this to a plot that already has a figure in it.
For example, if I apply it to this (same code as with the example minus a few extras and with another figure)...:
plt.rcdefaults()
import matplotlib.pyplot as plt
%matplotlib inline
from matplotlib import transforms
fig = plt.figure(figsize=(4,3), dpi=300)
def rainbow_text(x,y,ls,lc,**kw):
t = plt.gca().transData
fig = plt.gcf()
plt.show()
#horizontal version
for s,c in zip(ls,lc):
text = plt.text(x,y," "+s+" ",color=c, transform=t, **kw)
text.draw(fig.canvas.get_renderer())
ex = text.get_window_extent()
t = transforms.offset_copy(text._transform, x=ex.width, units='dots')
plt.figure()
rainbow_text(0.5,0.5,"all unicorns poop rainbows ! ! !".split(),
['red', 'orange', 'brown', 'green', 'blue', 'purple', 'black'],
size=40)
...the result is 2 plots with the title enlarged.
This sort of makes sense to me because I'm using plt. two times.
But how do I integrate it so that it only refers to the first instance of plt. in creating the title?
Also, about this line:
t = transforms.offset_copy(text._transform, x=ex.width, units='dots')
I notice it can alter the spacing between words, but when I play with the values of x, results are not predictable (spacing is inconsistent between words).
How can I meaningfully adjust that value?
And finally, where it says "units='dots'", what are the other options? Are 'dots' 1/72nd of an inch (and is that the default for Matplotlib?)?
How can I convert units from dots to inches?
Thanks in advance!
In fact the bounding box of the text comes in units unlike the ones used, for example, in scatterplot. Text is a different kind of object that gets somehow redraw if you resize the window or change the ratio. By having a stabilized window you can ask the coordinates of the bounding box in plot units and build your colored text that way:
a = "all unicorns poop rainbows ! ! !".split()
c = ['red', 'orange', 'brown', 'green', 'blue', 'purple', 'black']
f = plt.figure(figsize=(4,3), dpi=120)
ax = f.add_subplot(111)
r = f.canvas.get_renderer()
space = 0.1
w = 0.5
counter = 0
for i in a:
t = ax.text(w, 1.2, a[counter],color=c[counter],fontsize=12,ha='left')
transf = ax.transData.inverted()
bb = t.get_window_extent(renderer=f.canvas.renderer)
bb = bb.transformed(transf)
w = w + bb.xmax-bb.xmin + space
counter = counter + 1
plt.ylim(0.5,2.5)
plt.xlim(0.6,1.6)
plt.show()
, which results in:
This, however, is still not ideal since you need to keep controlling the size of your plot axis to obtain the correct spaces between words. This is somewhat arbitrary but if you manage to do your program with such a control it's feasible to use plot units to achieve your intended purpose.
ORIGINAL POST:
plt. is just the call to the library. In truth you are creating an instance of plt.figure in the global scope (so it can be seen in locally in the function). Due to this you are overwriting the figure because you use the same name for the variable (so it's just one single instance in the end). To solve this try controlling the names of your figure instances. For example:
import matplotlib.pyplot as plt
#%matplotlib inline
from matplotlib import transforms
fig = plt.figure(figsize=(4,3), dpi=300)
#plt.show(fig)
def rainbow_text(x,y,ls,lc,**kw):
t = plt.gca().transData
figlocal = plt.gcf()
#horizontal version
for s,c in zip(ls,lc):
text = plt.text(x,y," "+s+" ",color=c, transform=t, **kw)
text.draw(figlocal.canvas.get_renderer())
ex = text.get_window_extent()
t = transforms.offset_copy(text._transform, x=ex.width, units='dots')
plt.show(figlocal) #plt.show((figlocal,fig))
#plt.figure()
rainbow_text(0.5,0.5,"all unicorns poop rainbows ! ! !".split(),
['red', 'orange', 'brown', 'green', 'blue', 'purple', 'black'],
size=40,)
I've commented several instructions but notice I give a different name for the figure local to the function (figlocal). Also notice that in my examples of show I control directly which figure should be shown.
As for your other questions notice you can use other units as can be seen in the function documentation:
Return a new transform with an added offset.
args:
trans is any transform
kwargs:
fig is the current figure; it can be None if units are 'dots'
x, y give the offset
units is 'inches', 'points' or 'dots'
EDIT: Apparently there's some kind of problem with the extents of the bounding box for text that does not give the correct width of the word and thus the space between words is not stable. My advise is to use the latex functionality of Matplotlib to write the colors in the same string (so only one call of plt.text). You can do it like this:
import matplotlib
import matplotlib.pyplot as plt
matplotlib.use('pgf')
from matplotlib import rc
rc('text',usetex=True)
rc('text.latex', preamble=r'\usepackage{color}')
a = "all unicorns poop rainbows ! ! !".split()
c = ['red', 'orange', 'brown', 'green', 'blue', 'purple', 'black']
st = ''
for i in range(len(a)):
st = st + r'\textcolor{'+c[i]+'}{'+a[i]+'}'
plt.text(0.5,0.5,st)
plt.show()
This however is not an ideal solution. The reason is that you need to have Latex installed, including the necessary packages (notice I'm using the color package). Take a look at Yann answer in this question: Partial coloring of text in matplotlib
#armatita: I think your answer actually does what I need. I thought I needed display coordinates instead, but it looks like I can just use axis 1 coordinates, if that's what this is (I'm planning on using multiple axes via subplot2grid). Here's an example:
import matplotlib.pyplot as plt
%matplotlib inline
dpi=300
f_width=4
f_height=3
f = plt.figure(figsize=(f_width,f_height), dpi=dpi)
ax1 = plt.subplot2grid((100,115), (0,0), rowspan=95, colspan=25)
ax2 = plt.subplot2grid((100,115), (0,30), rowspan=95, colspan=20)
ax3 = plt.subplot2grid((100,115), (0,55), rowspan=95, colspan=35)
ax4 = plt.subplot2grid((100,115), (0,95), rowspan=95, colspan=20)
r = f.canvas.get_renderer()
t = ax1.text(.5, 1.1, 'a lot of text here',fontsize=12,ha='left')
space=0.1
w=.5
transf = ax1.transData.inverted()
bb = t.get_window_extent(renderer=f.canvas.renderer)
bb = bb.transformed(transf)
e = ax1.text(.5+bb.width+space, 1.1, 'text',fontsize=12,ha='left')
print(bb)
plt.show()
I'm not sure what you mean about controlling the axis size, though. Are you referring to using the code in different environments or exporting the image in different sizes? I plan on having the image used in the same environment and in the same size (per instance of using this approach), so I think it will be okay. Does my logic make sense? I have a weak grasp on what's really going on, so I hope so. I would use it with a function (via splitting the text) like you did, but there are cases where I need to split on other characters (i.e. when a word in parentheses should be colored, but not the parentheses). Maybe I can just put a delimiter in there like ','? I think I need a different form of .split() because it didn't work when I tried it.
At any rate, if I can implement this across all of my charts, it will save me countless hours. Thank you so much!
Here is an example where there are 2 plots and 2 instances of using the function for posterity:
import matplotlib.pyplot as plt
%matplotlib inline
dpi=300
f_width=4
f_height=3
f = plt.figure(figsize=(f_width,f_height), dpi=dpi)
ax1 = plt.subplot2grid((100,60), (0,0), rowspan=95, colspan=30)
ax2 = plt.subplot2grid((100,60), (0,30), rowspan=95, colspan=30)
f=f #Name for figure
string = str("Group 1 ,vs. ,Group 2 (,sub1,) and (,sub2,)").split(',')
color = ['black','red','black','green','black','blue','black']
xpos = .5
ypos = 1.2
axis=ax1
#No need to include space if incuded between delimiters above
#space = 0.1
def colortext(f,string,color,xpos,ypos,axis):
#f=figure object name (i.e. fig, f, figure)
r = f.canvas.get_renderer()
counter = 0
for i in string:
t = axis.text(xpos, ypos, string[counter],color=color[counter],fontsize=12,ha='left')
transf = axis.transData.inverted()
bb = t.get_window_extent(renderer=f.canvas.renderer)
bb = bb.transformed(transf)
xpos = xpos + bb.xmax-bb.xmin
counter = counter + 1
colortext(f,string,color,xpos,ypos,axis)
string2 = str("Group 1 part 2 ,vs. ,Group 2 (,sub1,) and (,sub2,)").split(',')
ypos2=1.1
colortext(f,string2,color,xpos,ypos2,axis)
plt.show()
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'
}
))