These resources show how to take data from a single Pandas DataFrame and plot different columns subplots on a Plotly graph. I'm interested in creating figures from separate DataFrames and plotting them to the same graph as subplots. Is this possible with Plotly?
https://plot.ly/python/subplots/
https://plot.ly/pandas/subplots/
I'm creating each figure from a dataframe like this:
import pandas as pd
import cufflinks as cf
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
fig1 = df.iplot(kind='bar',barmode='stack',x='Type',
y=mylist,asFigure=True)
Edit:
Here is an example based on Naren's feedback:
Create the dataframes:
a={'catagory':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'catagory':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
The plot will just show the information for the dogs, not the birds or cats:
fig = tls.make_subplots(rows=2, cols=1)
fig1 = df1.iplot(kind='bar',barmode='stack',x='catagory',
y=['dogs','cats','birds'],asFigure=True)
fig.append_trace(fig1['data'][0], 1, 1)
fig2 = df2.iplot(kind='bar',barmode='stack',x='catagory',
y=['dogs','cats','birds'],asFigure=True)
fig.append_trace(fig2['data'][0], 2, 1)
iplot(fig)
Here's a short function in a working example to save a list of figures all to a single HTML file.
def figures_to_html(figs, filename="dashboard.html"):
with open(filename, 'w') as dashboard:
dashboard.write("<html><head></head><body>" + "\n")
for fig in figs:
inner_html = fig.to_html().split('<body>')[1].split('</body>')[0]
dashboard.write(inner_html)
dashboard.write("</body></html>" + "\n")
# Example figures
import plotly.express as px
gapminder = px.data.gapminder().query("country=='Canada'")
fig1 = px.line(gapminder, x="year", y="lifeExp", title='Life expectancy in Canada')
gapminder = px.data.gapminder().query("continent=='Oceania'")
fig2 = px.line(gapminder, x="year", y="lifeExp", color='country')
gapminder = px.data.gapminder().query("continent != 'Asia'")
fig3 = px.line(gapminder, x="year", y="lifeExp", color="continent",
line_group="country", hover_name="country")
figures_to_html([fig1, fig2, fig3])
You can get a dashboard that contains several charts with legends next to each one:
import plotly
import plotly.offline as py
import plotly.graph_objs as go
fichier_html_graphs=open("DASHBOARD.html",'w')
fichier_html_graphs.write("<html><head></head><body>"+"\n")
i=0
while 1:
if i<=40:
i=i+1
#______________________________--Plotly--______________________________________
color1 = '#00bfff'
color2 = '#ff4000'
trace1 = go.Bar(
x = ['2017-09-25','2017-09-26','2017-09-27','2017-09-28','2017-09-29','2017-09-30','2017-10-01'],
y = [25,100,20,7,38,170,200],
name='Debit',
marker=dict(
color=color1
)
)
trace2 = go.Scatter(
x=['2017-09-25','2017-09-26','2017-09-27','2017-09-28','2017-09-29','2017-09-30','2017-10-01'],
y = [3,50,20,7,38,60,100],
name='Taux',
yaxis='y2'
)
data = [trace1, trace2]
layout = go.Layout(
title= ('Chart Number: '+str(i)),
titlefont=dict(
family='Courier New, monospace',
size=15,
color='#7f7f7f'
),
paper_bgcolor='rgba(0,0,0,0)',
plot_bgcolor='rgba(0,0,0,0)',
yaxis=dict(
title='Bandwidth Mbit/s',
titlefont=dict(
color=color1
),
tickfont=dict(
color=color1
)
),
yaxis2=dict(
title='Ratio %',
overlaying='y',
side='right',
titlefont=dict(
color=color2
),
tickfont=dict(
color=color2
)
)
)
fig = go.Figure(data=data, layout=layout)
plotly.offline.plot(fig, filename='Chart_'+str(i)+'.html',auto_open=False)
fichier_html_graphs.write(" <object data=\""+'Chart_'+str(i)+'.html'+"\" width=\"650\" height=\"500\"></object>"+"\n")
else:
break
fichier_html_graphs.write("</body></html>")
print("CHECK YOUR DASHBOARD.html In the current directory")
Result:
You can also try the following using cufflinks:
cf.subplots([df1.figure(kind='bar',categories='category'),
df2.figure(kind='bar',categories='category')],shape=(2,1)).iplot()
And this should give you:
New Answer:
We need to loop through each of the animals and append a new trace to generate what you need. This will give the desired output I am hoping.
import pandas as pd
import numpy as np
import cufflinks as cf
import plotly.tools as tls
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
import random
def generate_random_color():
r = lambda: random.randint(0,255)
return '#%02X%02X%02X' % (r(),r(),r())
a={'catagory':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'catagory':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
#shared Xaxis parameter can make this graph look even better
fig = tls.make_subplots(rows=2, cols=1)
for animal in ['dogs','cats','birds']:
animal_color = generate_random_color()
fig1 = df1.iplot(kind='bar',barmode='stack',x='catagory',
y=animal,asFigure=True,showlegend=False, color = animal_color)
fig.append_trace(fig1['data'][0], 1, 1)
fig2 = df2.iplot(kind='bar',barmode='stack',x='catagory',
y=animal,asFigure=True, showlegend=False, color = animal_color)
#if we do not use the below line there will be two legend
fig2['data'][0]['showlegend'] = False
fig.append_trace(fig2['data'][0], 2, 1)
#additional bonus
#use the below command to use the bar chart three mode
# [stack, overlay, group]
#as shown below
#fig['layout']['barmode'] = 'overlay'
iplot(fig)
Output:
Old Answer:
This will be the solution
Explanation:
Plotly tools has a subplot function to create subplots you should read the documentation for more details here. So I first use cufflinks to create a figure of the bar chart. One thing to note is cufflinks create and object with both data and layout. Plotly will only take one layout parameter as input, hence I take only the data parameter from the cufflinks figure and append_trace it to the make_suplots object. so fig.append_trace() the second parameter is row number and third parameter is column number
import pandas as pd
import cufflinks as cf
import numpy as np
import plotly.tools as tls
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
fig = tls.make_subplots(rows=2, cols=1)
df = pd.DataFrame(np.random.randint(0,100,size=(100, 4)), columns=list('ABCD'))
fig1 = df.iplot(kind='bar',barmode='stack',x='A',
y='B',asFigure=True)
fig.append_trace(fig1['data'][0], 1, 1)
df2 = pd.DataFrame(np.random.randint(0,100,size=(100, 4)), columns=list('EFGH'))
fig2 = df2.iplot(kind='bar',barmode='stack',x='E',
y='F',asFigure=True)
fig.append_trace(fig2['data'][0], 2, 1)
iplot(fig)
If you want to add a common layout to the subplot I suggest that you do
fig.append_trace(fig2['data'][0], 2, 1)
fig['layout']['showlegend'] = False
iplot(fig)
or even
fig.append_trace(fig2['data'][0], 2, 1)
fig['layout'].update(fig1['layout'])
iplot(fig)
So in the first example before plotting, I access the individual parameters of the layout object and change them, you need to go through layout object properties for refernce.
In the second example before plotting, I update the layout of the figure with the cufflinks generated layout this will produce the same output as we see in cufflinks.
You've already received a few suggestions that work perfectly well. They do however require a lot of coding. Facet / trellis plots using px.bar() will let you produce the plot below using (almost) only this:
px.bar(df, x="category", y="dogs", facet_row="Source")
The only extra steps you'll have to take is to introduce a variable on which to split your data, and then gather or concatenate your dataframes like this:
df1['Source'] = 1
df2['Source'] = 2
df = pd.concat([df1, df2])
And if you'd like to include the other variables as well, just do:
fig = px.bar(df, x="category", y=["dogs", "cats", "birds"], facet_row="Source")
fig.update_layout(barmode = 'group')
Complete code:
# imports
import plotly.express as px
import pandas as pd
# data building
a={'category':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'category':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
# data processing
df1['Source'] = 1
df2['Source'] = 2
df = pd.concat([df1, df2])
# plotly figure
fig = px.bar(df, x="category", y="dogs", facet_row="Source")
fig.show()
#fig = px.bar(df, x="category", y=["dogs", "cats", "birds"], facet_row="Source")
#fig.update_layout(barmode = 'group')
Related
I made a bar chart with python plotly, and I want to put a marker on a particular bar, example non-smoking females.
Does anyone know how to specify this?
I took an example from the plotly documentation, if I try to put the marker it just takes the center of the main category.
import plotly.express as px
df = px.data.tips()
fig = px.histogram(df, x="sex", y="total_bill",
color='smoker', barmode='group',
height=400)
#trying to set the marker
fig.add_trace(
go.Scatter(x=["Female"],
y=[1100]
))
fig.show()
inspired by this: https://community.plotly.com/t/grouped-bar-charts-with-corresponding-line-chart/19562/4
use xaxis2, work out position, have hardcoded it, but 0.15 has relationship to number of traces in bargoup and x value
import plotly.express as px
import plotly.graph_objects as go
import numpy as np
df = px.data.tips()
fig = px.histogram(
df, x="sex", y="total_bill", color="smoker", barmode="group", height=400
)
# trying to set the marker
fig.add_trace(
go.Scatter(
x=[0.15],
y=[1100],
customdata=[["No", "Female"]],
xaxis="x2",
hovertemplate="smoker=%{customdata[0]}<br>sex=%{customdata[1]}<br>sum of total_bill=%{y}<extra></extra>",
)
)
fig.update_layout(xaxis2={"overlaying": "x", "range": [0, 1], "showticklabels": False})
fig
How do I utilize plotly.express to plot multiple lines on two yaxis out of one Pandas dataframe?
I find this very useful to plot all columns containing a specific substring:
fig = px.line(df, y=df.filter(regex="Linear").columns, render_mode="webgl")
as I don't want to loop over all my filtered columns and use something like:
fig.add_trace(go.Scattergl(x=df["Time"], y=df["Linear-"]))
in each iteration.
It took me some time to fiddle this out, but I feel this could be useful to some people.
# import some stuff
import plotly.express as px
from plotly.subplots import make_subplots
import pandas as pd
import numpy as np
# create some data
df = pd.DataFrame()
n = 50
df["Time"] = np.arange(n)
df["Linear-"] = np.arange(n)+np.random.rand(n)
df["Linear+"] = np.arange(n)+np.random.rand(n)
df["Log-"] = np.arange(n)+np.random.rand(n)
df["Log+"] = np.arange(n)+np.random.rand(n)
df.set_index("Time", inplace=True)
subfig = make_subplots(specs=[[{"secondary_y": True}]])
# create two independent figures with px.line each containing data from multiple columns
fig = px.line(df, y=df.filter(regex="Linear").columns, render_mode="webgl",)
fig2 = px.line(df, y=df.filter(regex="Log").columns, render_mode="webgl",)
fig2.update_traces(yaxis="y2")
subfig.add_traces(fig.data + fig2.data)
subfig.layout.xaxis.title="Time"
subfig.layout.yaxis.title="Linear Y"
subfig.layout.yaxis2.type="log"
subfig.layout.yaxis2.title="Log Y"
# recoloring is necessary otherwise lines from fig und fig2 would share each color
# e.g. Linear-, Log- = blue; Linear+, Log+ = red... we don't want this
subfig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
subfig.show()
The trick with
subfig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
I got from nicolaskruchten here: https://stackoverflow.com/a/60031260
Thank you derflo and vestland! I really wanted to use Plotly Express as opposed to Graph Objects with dual axis to more easily handle DataFrames with lots of columns. I dropped this into a function. Data1/2 works well as a DataFrame or Series.
import plotly.express as px
from plotly.subplots import make_subplots
import pandas as pd
def plotly_dual_axis(data1,data2, title="", y1="", y2=""):
# Create subplot with secondary axis
subplot_fig = make_subplots(specs=[[{"secondary_y": True}]])
#Put Dataframe in fig1 and fig2
fig1 = px.line(data1)
fig2 = px.line(data2)
#Change the axis for fig2
fig2.update_traces(yaxis="y2")
#Add the figs to the subplot figure
subplot_fig.add_traces(fig1.data + fig2.data)
#FORMAT subplot figure
subplot_fig.update_layout(title=title, yaxis=dict(title=y1), yaxis2=dict(title=y2))
#RECOLOR so as not to have overlapping colors
subplot_fig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
return subplot_fig
I am trying to draw a bar chart from the CSV data I transform using pivot_table. The bar chart should have the count on the y-axis and companystatus along the x-axis.
I am getting this instead:
Ultimately, I want to stack the bar by CompanySizeId.
I have been following this video.
import plotly.graph_objects as go
import plotly.offline as pyo
import pandas as pd
countcompany = pd.read_csv(
'https://raw.githubusercontent.com/redbeardcr/Plotly/master/Data/countcompany.csv')
df = pd.pivot_table(countcompany, index='CompanyStatusLabel',
values='n', aggfunc=sum)
print(df)
data = [go.Bar(
x=df.index,
y=df.values,
)]
layout = go.Layout(title='Title')
fig = go.Figure(data=data, layout=layout)
pyo.plot(fig)
Code can be found here
Thanks for any help
If you flatten the array with the y values, i.e. if you replace y=df.values with y=df.values.flatten(), your code will work as expected.
import plotly.graph_objects as go
import plotly.offline as pyo
import pandas as pd
countcompany = pd.read_csv('https://raw.githubusercontent.com/redbeardcr/Plotly/master/Data/countcompany.csv')
df = pd.pivot_table(countcompany, index='CompanyStatusLabel', values='n', aggfunc=sum)
data = [go.Bar(
x=df.index,
y=df.values.flatten(),
)]
layout = go.Layout(title='Title')
fig = go.Figure(data=data, layout=layout)
pyo.plot(fig)
import plotly.express as px
df = px.data.iris()
fig = px.scatter(df, x=“sepal_width”, y=“sepal_length”, color=“species”)
fig.show()
If I want to write the same code in plotly.graph_objects , than how I can include the color argument without using for loop. Basically I want to use bar and line chart in same axis with bar having a color code based on a different variable and pass that as a return in Dash.
bars =
for label, label_df in df.groupby(‘label’):
bars.append(go.Bar(x=label_df.x, y=label_df.y, name=label, marker={‘color’: colors[label]}))
trace1 = bars
trace2 = go.Scatter(x=label_df.x, y=label_df.y, name=‘Nifty 50’, mode=‘lines+markers’)
fig = go.Figure(data=[trace1])
fig.show()
You can use list comprehension:
Update:
df = px.data.iris()
trace1 = [go.Scatter(x=label_df.sepal_width,
y=label_df.sepal_length,
name=label,
mode='markers')
for label, label_df in df.groupby('species')]
fig = go.Figure(data=trace1)
I want to plot this data to evaluate data availability. I used the following plotting code in Plotly.
import datetime
import plotly.express as px
fig = px.bar(df, x=df.index, y="variable", color='value', orientation="h",
hover_data=[df.index],
height=350,
color_continuous_scale=['firebrick', '#2ca02c'],
title='',
template='plotly_white',
)
The result is just like what I want below.
But, the x-index show numbers. I want a timestamp (month+year) on the x-axis, instead.
Edit
Adding the fllowing
fig.update_layout(yaxis=dict(title=''),
xaxis=dict(
title='Timestamp',
tickformat = '%Y-%b',
)
)
Gives
which seems that the x-axis is not read from the data index.
If you want to use bars it seems to me that you need to find a nice workaround. Have you considered to use Heatmap?
import pandas as pd
import plotly.graph_objs as go
df = pd.read_csv("availability3.txt",
parse_dates=["Timestamp"])\
.drop("Unnamed: 0", axis=1)
# you want to have variable as columns
df = pd.pivot_table(df,
index="Timestamp",
columns="variable",
values="value")
fig = go.Figure()
fig.add_trace(
go.Heatmap(
z=df.values.T,
x=df.index,
y=df.columns,
colorscale='RdYlGn',
xgap=1,
ygap=2)
)
fig.show()