bokeh is not plotting my graphs after giving input - python

After seeing the capabilities of Bokeh I started working with it. Now I am trying to make a Vbar with my dataset.
my dataset (10 rows)
dataset
I have read the tutorial quite a number of times and used the example provided by the official documentation:
https://hub.mybinder.org/user/bokeh-bokeh-notebooks-ate6xt0k/notebooks/tutorial/07%20-%20Bar%20and%20Categorical%20Data%20Plots.ipynb
from bokeh.models import ColumnDataSource
from bokeh.palettes import Spectral6
fruits = ['Apples', 'Pears', 'Nectarines', 'Plums', 'Grapes', 'Strawberries']
counts = [5, 3, 4, 2, 4, 6]
source = ColumnDataSource(data=dict(fruits=fruits, counts=counts, color=Spectral6))
p = figure(x_range=fruits, plot_height=250, y_range=(0, 9), title="Fruit Counts")
p.vbar(x='fruits', top='counts', width=0.9, color='color', legend="fruits", source=source)
p.xgrid.grid_line_color = None
p.legend.orientation = "horizontal"
p.legend.location = "top_center"
show(p)
This I tried to replicate with my own dataset.
from bokeh.models import ColumnDataSource
from bokeh.palettes import Spectral6
source = ColumnDataSource(top_ten_start)
p = figure(x_range='Bank_name', plot_height=250, y_range=(0, 90), title="BAnks")
p.vbar(x='Bank_name', top='Tier_1_ratio', width=0.9, legend="test", source=source)
p.xgrid.grid_line_color = None
p.legend.orientation = "horizontal"
p.legend.location = "top_center"
show(p)
I expected to see a bar chart as shown on the tutorial but nothing is plotting.
I thought by replacing the input of the "x_range", "plot" and "x" it would be enough to work.
Perhaps the following information would help:
These are the dtypes:
Country_code object
Bank_name object
Tier_1_ratio float64
dtype: object

x_range expects a list of categorical values but you supplied a string. This would be okay if it was a glyph and you were using a source, but this is not a glyph. I changed this variable to source.data['Bank_name'] so it uses the bank names in your ColumnDataSource.
from bokeh.models import ColumnDataSource
from bokeh.plotting import figure, show
from bokeh.palettes import Spectral7
import pandas as pd
top_ten_start = pd.read_csv('top_ten_start.csv')
top_ten_start['color'] = Spectral7
source = ColumnDataSource(top_ten_start)
p = figure(x_range=source.data['Bank_name'], plot_height=750, y_range=(0, 90), title="Banks")
p.vbar(x='Bank_name', top='Tier_1_ratio', width=0.9, legend='Bank_name', source=source, color='color')
p.xgrid.grid_line_color = None
p.xaxis.major_label_orientation = 45
show(p)

Related

Creating more than 4 stacked line charts with bokeh interactive legends

I was consulting the bokeh user guide (link) on creating interactive legends (see subsection on "Hiding glyphs").
The code given allows me to create up to 4 stacked line charts. For example, if I try to create a fifth line chart ("AAP"):
p = figure(width=800, height=250, x_axis_type="datetime")
p.title.text = 'Click on legend entries to hide the corresponding lines'
import pandas as pd
from bokeh.palettes import Spectral4
from bokeh.plotting import figure, show
from bokeh.sampledata.stocks import AAPL, GOOG, IBM, MSFT
for data, name, color in zip([AAPL, GOOG, IBM, MSFT, AAPL], ["AAPL", "GOOG", "IBM", "MSFT", "AAP"], Spectral4):
df = pd.DataFrame(data)
df['date'] = pd.to_datetime(df['date'])
p.line(df['date'], df['close'], line_width=2, color=color, alpha=0.8, legend_label=name)
p.legend.location = "top_left"
p.legend.click_policy="hide"
show(p)
it will still only show four.
I was wondering if it is possible to extend this code and create many more line charts (say 20) and if so, how this can be done.
Thank you
Your approach is working fine and would work, if you use Spectral5 instead of Spectral4 as palette. You have to know, that zip iterates over all lists and stops if one list has no more items. That was the case.
Minimal working example:
import pandas as pd
from bokeh.plotting import figure, show, output_notebook
from bokeh.sampledata.stocks import AAPL, GOOG, IBM, MSFT
output_notebook()
p = figure(width=800, height=250, x_axis_type="datetime")
p.title.text = 'Click on legend entries to hide the corresponding lines'
dataset = [AAPL, GOOG, IBM, MSFT, AAPL]
nameset = ["AAPL", "GOOG", "IBM", "MSFT", "AAP"]
colorset = ['blue', 'red', 'green', 'magenta', 'black']
for data, name, color in zip(dataset, nameset, colorset):
df = pd.DataFrame(data)
df['date'] = pd.to_datetime(df['date'])
p.line(df['date'], df['close'], line_width=2, color=color, alpha=0.8, legend_label=name)
p.legend.location = "top_left"
p.legend.click_policy="hide"
show(p)
Output:
Comment
For this I used bokeh 2.4.3 but with bokeh 3.+ this should work, too.

Bokeh: legend with MultiIndex table

I just discovered Bokeh recently, and I try to display a legend for each day of week (represented by 'startdate_dayweek'). The legend should contain the color for each row corresponding to each day.
import pandas as pd
from bokeh.plotting import figure, show
from bokeh.io import output_file
from bokeh.palettes import Set1_7
output_file("conso_daily.html")
treatcriteria_data_global = pd.read_csv(r"treatcriteria_evolution.csv", sep=';')
final_global_data = treatcriteria_data_global.groupby(['startdate_weekyear','startdate_dayweek'],as_index = False).sum().pivot('startdate_weekyear','startdate_dayweek').fillna(0)
numlines = len(final_global_data.columns)
palette = Set1_7[0:numlines]
ts_list_of_list = []
for i in range(0,len(final_global_data.columns)):
ts_list_of_list.append(final_global_data.index)
vals_list_of_list = final_global_data.values.T.tolist()
p = figure(width=500, height=300)
p.left[0].formatter.use_scientific = False
p.multi_line(ts_list_of_list, vals_list_of_list,
legend='startdate_dayweek',
line_color = palette,
line_width=4)
show(p)
But I don't have the expected result in the legend:
How to have the legend for each day? Is the problem due to the fact that I created a MultiIndex table? Thanks.
The multi_line() function can take the parameter legend_field or legend_group. Both are working very well for your usecase, if you use a ColumnDataSource as source. Keep in mind, that a error will come if you use both parameters at the same time.
Minimal Example
from bokeh.plotting import figure, show, output_notebook
from bokeh.models import ColumnDataSource
output_notebook()
source = ColumnDataSource(dict(
xs=[[1,2,3,4,5],[1,2,3,4,5],[1,2,3,4,5]],
ys=[[1,2,3,4,5],[1,1,1,1,5],[5,4,3,2,1]],
legend =['red', 'green', 'blue'],
line_color = ['red', 'green', 'blue']))
p = figure(width=500, height=300)
p.multi_line(xs='xs',
ys='ys',
legend_field ='legend',
line_color = 'line_color',
source=source,
line_width=4)
show(p)
Output

Cannot import name 'Scatter' from 'bokeh.plotting'

I am trying to represent the data using the bokeh scatter.
Here is my code:
from bokeh.plotting import Scatter, output_file, show import pandas
df=pandas.Dataframe(colume["X","Y"])
df["X"]=[1,2,3,4,5,6,7]
df["Y"]=[23,43,32,12,34,54,33]
p=Scatter(df,x="X",y="Y", title="Day Temperature measurement", xlabel="Tempetature", ylabel="Day")
output_file("File.html")
show(p)
The Output should look like this:
Expected Output
The error is:
ImportError Traceback (most recent call
> last) <ipython-input-14-1730ac6ad003> in <module>
> ----> 1 from bokeh.plotting import Scatter, output_file, show
> 2 import pandas
> 3
> 4 df=pandas.Dataframe(colume["X","Y"])
> 5
ImportError: cannot import name 'Scatter' from 'bokeh.plotting'
(C:\Users\LENOVO\Anaconda3\lib\site-packages\bokeh\plotting__init__.py)
I had also found that the Scatter is no longer maintained now. Is there is any way to use it?
Also which alternative do I have to represent the data same as the Scatter using any another python libraries?
Using older version of Bokeh will resolve this issue?
Scatter (with a capital S) has never been part of bokeh.plotting. It used to be a part of the old bokeh.charts API that was removed several years ago. However, it is not needed at all to create basic scatter plots, since all the glyph methods in bokeh.plotting (e.g circle, square) are all implicitly scatter-type functions to begin with:
from bokeh.plotting import figure, show
import pandas as pd
df = pd.DataFrame({"X" :[1,2,3,4,5,6,7],
"Y": [23,43,32,12,34,54,33]})
p = figure(x_axis_label="Tempetature", y_axis_label="Day",
title="Day Temperature measurement")
p.circle("X", "Y", size=15, source=df)
show(p)
Which yields:
You can also just pass the data directly to circle as in the other answer.
If you want to do fancier things, like map the marker type based on a column there is also a plot.scatter (lower case s) methods on the figure:
from bokeh.plotting import figure, show
from bokeh.sampledata.iris import flowers
from bokeh.transform import factor_cmap, factor_mark
SPECIES = ['setosa', 'versicolor', 'virginica']
MARKERS = ['hex', 'circle_x', 'triangle']
p = figure(title = "Iris Morphology")
p.xaxis.axis_label = 'Petal Length'
p.yaxis.axis_label = 'Sepal Width'
p.scatter("petal_length", "sepal_width", source=flowers, legend_field="species", fill_alpha=0.4, size=12,
marker=factor_mark('species', MARKERS, SPECIES),
color=factor_cmap('species', 'Category10_3', SPECIES))
show(p)
which yields:
If you look up "scatter" in the docs, you'll find
Scatter Markers
To scatter circle markers on a plot, use the circle() method of Figure:
from bokeh.plotting import figure, output_file, show
# output to static HTML file
output_file("line.html")
p = figure(plot_width=400, plot_height=400)
# add a circle renderer with a size, color, and alpha
p.circle([1, 2, 3, 4, 5], [6, 7, 2, 4, 5], size=20, color="navy", alpha=0.5)
# show the results
show(p)
To work with dataframes, just pass in the columns like df.X and df.Y to the x and y args.
from bokeh.plotting import figure, show, output_file
import pandas as pd
df = pd.DataFrame(columns=["X","Y"])
df["X"] = [1,2,3,4,5,6,7]
df["Y"] = [23,43,32,12,34,54,33]
p = figure()
p.scatter(df.X, df.Y, marker="circle")
#from bokeh.io import output_notebook
#output_notebook()
show(p) # or output to a file...

How to expand limited color palette in Python's Bokeh plot

I have the following code:
from bokeh.plotting import figure, show, output_file
from bokeh.sampledata.iris import flowers
from bokeh.models import LinearColorMapper
from bokeh.models import ColumnDataSource
from bokeh.models import ColorBar
from bokeh.palettes import Reds9
p = figure(title = "Iris Morphology")
p.xaxis.axis_label = "Petal Length"
p.yaxis.axis_label = "Petal Width"
source = ColumnDataSource(flowers)
# Reverse the color and map it
Reds9.reverse()
exp_cmap = LinearColorMapper(palette=Reds9,
low = min(flowers["petal_length"]),
high = max(flowers["petal_length"]))
p.circle("petal_length", "petal_width", source=source, line_color=None,
fill_color={"field":"petal_length", "transform":exp_cmap})
bar = ColorBar(color_mapper=exp_cmap, location=(0,0))
p.add_layout(bar, "left")
show(p)
Which produces the following plot:
Notice that I use Brewer's Red palette which is limited to 9 colors.
from bokeh.palettes import Reds9
How can I expand it to 256?
Bokeh's palettes are simply a list of HTML colors. You can create your own one. For example, picking the list from https://www.w3schools.com/colors/colors_shades.asp:
myReds = [
'#000000',
'#080000',
'#100000',
'#180000',
'#200000',
'#280000',
'#300000',
'#380000',
'#400000',
'#480000',
'#500000',
'#580000',
'#600000',
'#680000',
'#700000',
'#780000',
'#800000',
'#880000',
'#900000',
'#980000',
'#A00000',
'#A80000',
'#B00000',
'#B80000',
'#C00000',
'#C80000',
'#D00000',
'#D80000',
'#E00000',
'#E80000',
'#F00000',
'#F80000',
'#FF0000']
Then replace Reds9 by myReds:
[...]
exp_cmap = LinearColorMapper(palette=myReds,
low = min(flowers["petal_length"]),
high = max(flowers["petal_length"]))
[...]

how use bokeh vbar chart parameter with groupby object?

Question
Below code is grouped vbar chart example from bokeh documentation.
There are something i can't understand on this example.
Where 'cyl_mfr' is come from in factor_cmap() and vbar()?
'mpg_mean' , is it calculating the mean of 'mpg' column? if then,
why 'mpg_sum' doesn't work?
I want to make my own vbar chart like this example.
Code
from bokeh.io import show, output_file
from bokeh.models import ColumnDataSource, HoverTool
from bokeh.plotting import figure
from bokeh.palettes import Spectral5
from bokeh.sampledata.autompg import autompg_clean as df
from bokeh.transform import factor_cmap
output_file("bars.html")
df.cyl = df.cyl.astype(str)
df.yr = df.yr.astype(str)
group = df.groupby(('cyl', 'mfr'))
source = ColumnDataSource(group)
index_cmap = factor_cmap('cyl_mfr', palette=Spectral5,
factors=sorted(df.cyl.unique()), end=1)
p = figure(plot_width=800, plot_height=300, title="Mean MPG by # Cylinders
and Manufacturer",
x_range=group, toolbar_location=None, tools="")
p.vbar(x='cyl_mfr', top='mpg_mean', width=1, source=source,
line_color="white", fill_color=index_cmap, )
p.y_range.start = 0
p.x_range.range_padding = 0.05
p.xgrid.grid_line_color = None
p.xaxis.axis_label = "Manufacturer grouped by # Cylinders"
p.xaxis.major_label_orientation = 1.2
p.outline_line_color = None
p.add_tools(HoverTool(tooltips=[("MPG", "#mpg_mean"), ("Cyl, Mfr",
"#cyl_mfr")]))
show(p)
The group = df.groupby(('cyl', 'mfr')) makes a <pandas.core.groupby.DataFrameGroupBy object at 0x0xxx>. If you pass this to a ColumnDataSource, bokeh does a lot of magic, and calculates a lot of statistics already
df.columns
Index(['mpg', 'cyl', 'displ', 'hp', 'weight', 'accel', 'yr', 'origin', 'name', 'mfr'],
source.column_names
['accel_count', 'accel_mean', 'accel_std', 'accel_min',
'accel_25%', 'accel_50%', 'accel_75%', 'accel_max', 'displ_count',
'displ_mean', 'displ_std', 'displ_min', 'displ_25%', 'displ_50%',
'displ_75%', 'displ_max', 'hp_count', 'hp_mean', 'hp_std',
'hp_min', 'hp_25%', 'hp_50%', 'hp_75%', 'hp_max', 'mpg_count',
'mpg_mean', 'mpg_std', 'mpg_min', 'mpg_25%', 'mpg_50%',
'mpg_75%', 'mpg_max', 'weight_count', 'weight_mean', 'weight_std',
'weight_min', 'weight_25%', 'weight_50%', 'weight_75%',
'weight_max', 'yr_count', 'yr_mean', 'yr_std', 'yr_min',
'yr_25%', 'yr_50%', 'yr_75%', 'yr_max', 'cyl_mfr']
the cyl_mfr is the labels of the 2 columns on which you grouped by concatenated. In source this has become a column of tuples
mpg_sum is not calculated. If you cant the sum, you will need to calculate that yourself.

Categories

Resources